Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm into next

Pull KVM updates from Paolo Bonzini:
"At over 200 commits, covering almost all supported architectures, this
was a pretty active cycle for KVM. Changes include:

- a lot of s390 changes: optimizations, support for migration, GDB
support and more

- ARM changes are pretty small: support for the PSCI 0.2 hypercall
interface on both the guest and the host (the latter acked by
Catalin)

- initial POWER8 and little-endian host support

- support for running u-boot on embedded POWER targets

- pretty large changes to MIPS too, completing the userspace
interface and improving the handling of virtualized timer hardware

- for x86, a larger set of changes is scheduled for 3.17. Still, we
have a few emulator bugfixes and support for running nested
fully-virtualized Xen guests (para-virtualized Xen guests have
always worked). And some optimizations too.

The only missing architecture here is ia64. It's not a coincidence
that support for KVM on ia64 is scheduled for removal in 3.17"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (203 commits)
KVM: add missing cleanup_srcu_struct
KVM: PPC: Book3S PR: Rework SLB switching code
KVM: PPC: Book3S PR: Use SLB entry 0
KVM: PPC: Book3S HV: Fix machine check delivery to guest
KVM: PPC: Book3S HV: Work around POWER8 performance monitor bugs
KVM: PPC: Book3S HV: Make sure we don't miss dirty pages
KVM: PPC: Book3S HV: Fix dirty map for hugepages
KVM: PPC: Book3S HV: Put huge-page HPTEs in rmap chain for base address
KVM: PPC: Book3S HV: Fix check for running inside guest in global_invalidates()
KVM: PPC: Book3S: Move KVM_REG_PPC_WORT to an unused register number
KVM: PPC: Book3S: Add ONE_REG register names that were missed
KVM: PPC: Add CAP to indicate hcall fixes
KVM: PPC: MPIC: Reset IRQ source private members
KVM: PPC: Graciously fail broken LE hypercalls
PPC: ePAPR: Fix hypercall on LE guest
KVM: PPC: BOOK3S: Remove open coded make_dsisr in alignment handler
KVM: PPC: BOOK3S: Always use the saved DAR value
PPC: KVM: Make NX bit available with magic page
KVM: PPC: Disable NX for old magic page using guests
KVM: PPC: BOOK3S: HV: Add mixed page-size support for guest
...

Documentation/devicetree/bindings/arm/psci.txt

···
 
 Main node required properties:
 
- - compatible    : Must be "arm,psci"
+ - compatible    : should contain at least one of:
+
+				 * "arm,psci" : for implementations complying to PSCI versions prior to
+					0.2. For these cases function IDs must be provided.
+
+				 * "arm,psci-0.2" : for implementations complying to PSCI 0.2. Function
+					IDs are not required and should be ignored by an OS with PSCI 0.2
+					support, but are permitted to be present for compatibility with
+					existing software when "arm,psci" is later in the compatible list.
 
  - method        : The method of calling the PSCI firmware. Permitted
                    values are:
···
 
 Example:
 
+Case 1: PSCI v0.1 only.
+
 	psci {
 		compatible	= "arm,psci";
 		method		= "smc";
···
 		cpu_off		= <0x95c10001>;
 		cpu_on		= <0x95c10002>;
 		migrate		= <0x95c10003>;
+	};
+
+
+Case 2: PSCI v0.2 only
+
+	psci {
+		compatible	= "arm,psci-0.2";
+		method		= "smc";
+	};
+
+Case 3: PSCI v0.2 and PSCI v0.1.
+
+	A DTB may provide IDs for use by kernels without PSCI 0.2 support,
+	enabling firmware and hypervisors to support existing and new kernels.
+	These IDs will be ignored by kernels with PSCI 0.2 support, which will
+	use the standard PSCI 0.2 IDs exclusively.
+
+	psci {
+		compatible = "arm,psci-0.2", "arm,psci";
+		method = "hvc";
+
+		cpu_on = < arbitrary value >;
+		cpu_off = < arbitrary value >;
+
+		...
 	};

Documentation/virtual/kvm/api.txt

···
   PPC   | KVM_REG_PPC_MMCR0     | 64
   PPC   | KVM_REG_PPC_MMCR1     | 64
   PPC   | KVM_REG_PPC_MMCRA     | 64
+  PPC   | KVM_REG_PPC_MMCR2     | 64
+  PPC   | KVM_REG_PPC_MMCRS     | 64
+  PPC   | KVM_REG_PPC_SIAR      | 64
+  PPC   | KVM_REG_PPC_SDAR      | 64
+  PPC   | KVM_REG_PPC_SIER      | 64
   PPC   | KVM_REG_PPC_PMC1      | 32
   PPC   | KVM_REG_PPC_PMC2      | 32
   PPC   | KVM_REG_PPC_PMC3      | 32
···
   PPC   | KVM_REG_PPC_PPR	| 64
   PPC   | KVM_REG_PPC_ARCH_COMPAT 32
   PPC   | KVM_REG_PPC_DABRX     | 32
+  PPC   | KVM_REG_PPC_WORT      | 64
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
···
 KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
 KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
 KVM_S390_RESTART (vcpu) - restart
+KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
+KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
 KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
 			   parameters in parm and parm64
 KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
···
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
···
 
 4.81 KVM_HAS_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL
-Type: device ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
+Type: device ioctl, vm ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
···
 	  Depends on KVM_CAP_ARM_PSCI.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
+	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
+	  Depends on KVM_CAP_ARM_PSCI_0_2.
 
 
 4.83 KVM_ARM_PREFERRED_TARGET
···
 It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
 external interrupt has just been delivered into the guest. User space
 should put the acknowledged interrupt vector into the 'epr' field.
+
+		/* KVM_EXIT_SYSTEM_EVENT */
+		struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+			__u32 type;
+			__u64 flags;
+		} system_event;
+
+If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
+a system-level event using some architecture specific mechanism (hypercall
+or some special instruction). In case of ARM/ARM64, this is triggered using
+HVC instruction based PSCI call from the vcpu. The 'type' field describes
+the system-level event type. The 'flags' field describes architecture
+specific flags for the system-level event.
 
 		/* Fix the size of the union. */
 		char padding[256];

Documentation/virtual/kvm/devices/vm.txt

···
+Generic vm interface
+====================================
+
+The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
+struct kvm_device_attr as other devices, but targets VM-wide settings
+and controls.
+
+The groups and attributes per virtual machine, if any, are architecture
+specific.
+
+1. GROUP: KVM_S390_VM_MEM_CTRL
+Architectures: s390
+
+1.1. ATTRIBUTE: KVM_S390_VM_MEM_CTRL
+Parameters: none
+Returns: -EBUSY if already a vcpus is defined, otherwise 0
+
+Enables CMMA for the virtual machine
+
+1.2. ATTRIBUTE: KVM_S390_VM_CLR_CMMA
+Parameteres: none
+Returns: 0
+
+Clear the CMMA status for all guest pages, so any pages the guest marked
+as unused are again used any may not be reclaimed by the host.

Documentation/virtual/kvm/ppc-pv.txt

···
 The following enhancements to the magic page are currently available:
 
   KVM_MAGIC_FEAT_SR		Maps SR registers r/w in the magic page
+  KVM_MAGIC_FEAT_MAS0_TO_SPRG7	Maps MASn, ESR, PIR and high SPRGs
 
 For enhanced features in the magic page, please check for the existence of the
 feature before using them!
+
+Magic page flags
+================
+
+In addition to features that indicate whether a host is capable of a particular
+feature we also have a channel for a guest to tell the guest whether it's capable
+of something. This is what we call "flags".
+
+Flags are passed to the host in the low 12 bits of the Effective Address.
+
+The following flags are currently available for a guest to expose:
+
+  MAGIC_PAGE_FLAG_NOT_MAPPED_NX Guest handles NX bits correclty wrt magic page
 
 MSR bits
 ========

Documentation/virtual/kvm/s390-diag.txt

···
 
 If the function code specifies 0x501, breakpoint functions may be performed.
 This function code is handled by userspace.
+
+This diagnose function code has no subfunctions and uses no parameters.

arch/arm/include/asm/kvm_host.h

···
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 
-#define KVM_VCPU_MAX_FEATURES 1
+#define KVM_VCPU_MAX_FEATURES 2
 
 #include <kvm/arm_vgic.h>
 

arch/arm/include/asm/kvm_psci.h

···
 #ifndef __ARM_KVM_PSCI_H__
 #define __ARM_KVM_PSCI_H__
 
-bool kvm_psci_call(struct kvm_vcpu *vcpu);
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 #endif /* __ARM_KVM_PSCI_H__ */

arch/arm/include/asm/psci.h

···
 	int (*cpu_off)(struct psci_power_state state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
 	int (*migrate)(unsigned long cpuid);
+	int (*affinity_info)(unsigned long target_affinity,
+			unsigned long lowest_affinity_level);
+	int (*migrate_info_type)(void);
 };
 
 extern struct psci_operations psci_ops;
 extern struct smp_operations psci_smp_ops;
 
 #ifdef CONFIG_ARM_PSCI
-void psci_init(void);
+int psci_init(void);
 bool psci_smp_available(void);
 #else
-static inline void psci_init(void) { }
+static inline int psci_init(void) { return 0; }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 

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

···
 #define __ARM_KVM_H__
 
 #include <linux/types.h>
+#include <linux/psci.h>
 #include <asm/ptrace.h>
 
 #define __KVM_HAVE_GUEST_DEBUG
···
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */
 
 struct kvm_vcpu_init {
 	__u32 target;
···
 #define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
 #define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
 
-#define KVM_PSCI_RET_SUCCESS		0
-#define KVM_PSCI_RET_NI			((unsigned long)-1)
-#define KVM_PSCI_RET_INVAL		((unsigned long)-2)
-#define KVM_PSCI_RET_DENIED		((unsigned long)-3)
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
 #endif /* __ARM_KVM_H__ */

arch/arm/kernel/psci.c

···
 
 #include <linux/init.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
+#include <linux/pm.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
 #include <asm/errno.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/psci.h>
+#include <asm/system_misc.h>
 
 struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u32, u32, u32, u32);
+typedef int (*psci_initcall_t)(const struct device_node *);
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
+	PSCI_FN_AFFINITY_INFO,
+	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
 static u32 psci_function_id[PSCI_FN_MAX];
-
-#define PSCI_RET_SUCCESS		0
-#define PSCI_RET_EOPNOTSUPP		-1
-#define PSCI_RET_EINVAL			-2
-#define PSCI_RET_EPERM			-3
 
 static int psci_to_linux_errno(int errno)
 {
 	switch (errno) {
 	case PSCI_RET_SUCCESS:
 		return 0;
-	case PSCI_RET_EOPNOTSUPP:
+	case PSCI_RET_NOT_SUPPORTED:
 		return -EOPNOTSUPP;
-	case PSCI_RET_EINVAL:
+	case PSCI_RET_INVALID_PARAMS:
 		return -EINVAL;
-	case PSCI_RET_EPERM:
+	case PSCI_RET_DENIED:
 		return -EPERM;
 	};
 
 	return -EINVAL;
 }
 
-#define PSCI_POWER_STATE_ID_MASK	0xffff
-#define PSCI_POWER_STATE_ID_SHIFT	0
-#define PSCI_POWER_STATE_TYPE_MASK	0x1
-#define PSCI_POWER_STATE_TYPE_SHIFT	16
-#define PSCI_POWER_STATE_AFFL_MASK	0x3
-#define PSCI_POWER_STATE_AFFL_SHIFT	24
-
 static u32 psci_power_state_pack(struct psci_power_state state)
 {
-	return	((state.id & PSCI_POWER_STATE_ID_MASK)
-			<< PSCI_POWER_STATE_ID_SHIFT)	|
-		((state.type & PSCI_POWER_STATE_TYPE_MASK)
-			<< PSCI_POWER_STATE_TYPE_SHIFT)	|
-		((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
-			<< PSCI_POWER_STATE_AFFL_SHIFT);
+	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
+			& PSCI_0_2_POWER_STATE_ID_MASK) |
+		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
+		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
 /*
···
 		: "r" (arg0), "r" (arg1), "r" (arg2));
 
 	return function_id;
+}
+
+static int psci_get_version(void)
+{
+	int err;
+
+	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+	return err;
 }
 
 static int psci_cpu_suspend(struct psci_power_state state,
···
 	return psci_to_linux_errno(err);
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci",	},
-	{},
-};
-
-void __init psci_init(void)
+static int psci_affinity_info(unsigned long target_affinity,
+		unsigned long lowest_affinity_level)
 {
-	struct device_node *np;
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
+	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
+	return err;
+}
+
+static int psci_migrate_info_type(void)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
+	err = invoke_psci_fn(fn, 0, 0, 0);
+	return err;
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
 	const char *method;
-	u32 id;
 
-	np = of_find_matching_node(NULL, psci_of_match);
-	if (!np)
-		return;
-
-	pr_info("probing function IDs from device-tree\n");
+	pr_info("probing for conduit method from DT.\n");
 
 	if (of_property_read_string(np, "method", &method)) {
-		pr_warning("missing \"method\" property\n");
-		goto out_put_node;
+		pr_warn("missing \"method\" property\n");
+		return -ENXIO;
 	}
 
 	if (!strcmp("hvc", method)) {
···
 	} else if (!strcmp("smc", method)) {
 		invoke_psci_fn = __invoke_psci_fn_smc;
 	} else {
-		pr_warning("invalid \"method\" property: %s\n", method);
-		goto out_put_node;
+		pr_warn("invalid \"method\" property: %s\n", method);
+		return -EINVAL;
 	}
+	return 0;
+}
+
+static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+}
+
+static void psci_sys_poweroff(void)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+/*
+ * PSCI Function IDs for v0.2+ are well defined so use
+ * standard values.
+ */
+static int psci_0_2_init(struct device_node *np)
+{
+	int err, ver;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	ver = psci_get_version();
+
+	if (ver == PSCI_RET_NOT_SUPPORTED) {
+		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
+		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
+		err = -EOPNOTSUPP;
+		goto out_put_node;
+	} else {
+		pr_info("PSCIv%d.%d detected in firmware.\n",
+				PSCI_VERSION_MAJOR(ver),
+				PSCI_VERSION_MINOR(ver));
+
+		if (PSCI_VERSION_MAJOR(ver) == 0 &&
+				PSCI_VERSION_MINOR(ver) < 2) {
+			err = -EINVAL;
+			pr_err("Conflicting PSCI version detected.\n");
+			goto out_put_node;
+		}
+	}
+
+	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
+	psci_ops.cpu_suspend = psci_cpu_suspend;
+
+	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+	psci_ops.cpu_off = psci_cpu_off;
+
+	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
+	psci_ops.cpu_on = psci_cpu_on;
+
+	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
+	psci_ops.migrate = psci_migrate;
+
+	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
+	psci_ops.affinity_info = psci_affinity_info;
+
+	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
+		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
+	psci_ops.migrate_info_type = psci_migrate_info_type;
+
+	arm_pm_restart = psci_sys_reset;
+
+	pm_power_off = psci_sys_poweroff;
+
+out_put_node:
+	of_node_put(np);
+	return err;
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int psci_0_1_init(struct device_node *np)
+{
+	u32 id;
+	int err;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	pr_info("Using PSCI v0.1 Function IDs from DT\n");
 
 	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
 		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
···
 
 out_put_node:
 	of_node_put(np);
-	return;
+	return err;
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci", .data = psci_0_1_init},
+	{ .compatible = "arm,psci-0.2", .data = psci_0_2_init},
+	{},
+};
+
+int __init psci_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *matched_np;
+	psci_initcall_t init_fn;
+
+	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+	if (!np)
+		return -ENODEV;
+
+	init_fn = (psci_initcall_t)matched_np->data;
+	return init_fn(np);
 }

arch/arm/kernel/psci_smp.c

···
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/of.h>
+#include <linux/delay.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
···
        /* We should never return */
        panic("psci: cpu %d failed to shutdown\n", cpu);
 }
+
+int __ref psci_cpu_kill(unsigned int cpu)
+{
+	int err, i;
+
+	if (!psci_ops.affinity_info)
+		return 1;
+	/*
+	 * cpu_kill could race with cpu_die and we can
+	 * potentially end up declaring this cpu undead
+	 * while it is dying. So, try again a few times.
+	 */
+
+	for (i = 0; i < 10; i++) {
+		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
+		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
+			pr_info("CPU%d killed.\n", cpu);
+			return 1;
+		}
+
+		msleep(10);
+		pr_info("Retrying again to check for CPU kill\n");
+	}
+
+	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
+			cpu, err);
+	/* Make platform_cpu_kill() fail. */
+	return 0;
+}
+
 #endif
 
 bool __init psci_smp_available(void)
···
 	.smp_boot_secondary	= psci_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= psci_cpu_die,
+	.cpu_kill		= psci_cpu_kill,
 #endif
 };

arch/arm/kvm/arm.c

···
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ARM_PSCI:
+	case KVM_CAP_ARM_PSCI_0_2:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

arch/arm/kvm/handle_exit.c

···
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
+	int ret;
+
 	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
 		      kvm_vcpu_hvc_get_imm(vcpu));
 
-	if (kvm_psci_call(vcpu))
+	ret = kvm_psci_call(vcpu);
+	if (ret < 0) {
+		kvm_inject_undefined(vcpu);
 		return 1;
+	}
 
-	kvm_inject_undefined(vcpu);
-	return 1;
+	return ret;
 }
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)

arch/arm/kvm/psci.c

···
  * as described in ARM document number ARM DEN 0022A.
  */
 
+#define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+
+static unsigned long psci_affinity_mask(unsigned long affinity_level)
+{
+	if (affinity_level <= 3)
+		return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
+
+	return 0;
+}
+
+static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * NOTE: For simplicity, we make VCPU suspend emulation to be
+	 * same-as WFI (Wait-for-interrupt) emulation.
+	 *
+	 * This means for KVM the wakeup events are interrupts and
+	 * this is consistent with intended use of StateID as described
+	 * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
+	 *
+	 * Further, we also treat power-down request to be same as
+	 * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
+	 * specification (ARM DEN 0022A). This means all suspend states
+	 * for KVM will preserve the register state.
+	 */
+	kvm_vcpu_block(vcpu);
+
+	return PSCI_RET_SUCCESS;
+}
+
 static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pause = true;
···
 	struct kvm_vcpu *vcpu = NULL, *tmp;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
+	unsigned long context_id;
 	unsigned long mpidr;
 	phys_addr_t target_pc;
 	int i;
···
 	 * Make sure the caller requested a valid CPU and that the CPU is
 	 * turned off.
 	 */
-	if (!vcpu || !vcpu->arch.pause)
-		return KVM_PSCI_RET_INVAL;
+	if (!vcpu)
+		return PSCI_RET_INVALID_PARAMS;
+	if (!vcpu->arch.pause) {
+		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+			return PSCI_RET_ALREADY_ON;
+		else
+			return PSCI_RET_INVALID_PARAMS;
+	}
 
 	target_pc = *vcpu_reg(source_vcpu, 2);
+	context_id = *vcpu_reg(source_vcpu, 3);
 
 	kvm_reset_vcpu(vcpu);
 
···
 		kvm_vcpu_set_be(vcpu);
 
 	*vcpu_pc(vcpu) = target_pc;
+	/*
+	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
+	 * the general puspose registers are undefined upon CPU_ON.
+	 */
+	*vcpu_reg(vcpu, 0) = context_id;
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
 	wake_up_interruptible(wq);
 
-	return KVM_PSCI_RET_SUCCESS;
+	return PSCI_RET_SUCCESS;
 }
 
-/**
- * kvm_psci_call - handle PSCI call if r0 value is in range
- * @vcpu: Pointer to the VCPU struct
- *
- * Handle PSCI calls from guests through traps from HVC instructions.
- * The calling convention is similar to SMC calls to the secure world where
- * the function number is placed in r0 and this function returns true if the
- * function number specified in r0 is withing the PSCI range, and false
- * otherwise.
- */
-bool kvm_psci_call(struct kvm_vcpu *vcpu)
+static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
+{
+	int i;
+	unsigned long mpidr;
+	unsigned long target_affinity;
+	unsigned long target_affinity_mask;
+	unsigned long lowest_affinity_level;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tmp;
+
+	target_affinity = *vcpu_reg(vcpu, 1);
+	lowest_affinity_level = *vcpu_reg(vcpu, 2);
+
+	/* Determine target affinity mask */
+	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+	if (!target_affinity_mask)
+		return PSCI_RET_INVALID_PARAMS;
+
+	/* Ignore other bits of target affinity */
+	target_affinity &= target_affinity_mask;
+
+	/*
+	 * If one or more VCPU matching target affinity are running
+	 * then ON else OFF
+	 */
+	kvm_for_each_vcpu(i, tmp, kvm) {
+		mpidr = kvm_vcpu_get_mpidr(tmp);
+		if (((mpidr & target_affinity_mask) == target_affinity) &&
+		    !tmp->arch.pause) {
+			return PSCI_0_2_AFFINITY_LEVEL_ON;
+		}
+	}
+
+	return PSCI_0_2_AFFINITY_LEVEL_OFF;
+}
+
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+{
+	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+	vcpu->run->system_event.type = type;
+	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+}
+
+static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+}
+
+int kvm_psci_version(struct kvm_vcpu *vcpu)
+{
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+		return KVM_ARM_PSCI_0_2;
+
+	return KVM_ARM_PSCI_0_1;
+}
+
+static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
+{
+	int ret = 1;
+	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long val;
+
+	switch (psci_fn) {
+	case PSCI_0_2_FN_PSCI_VERSION:
+		/*
+		 * Bits[31:16] = Major Version = 0
+		 * Bits[15:0] = Minor Version = 2
+		 */
+		val = 2;
+		break;
+	case PSCI_0_2_FN_CPU_SUSPEND:
+	case PSCI_0_2_FN64_CPU_SUSPEND:
+		val = kvm_psci_vcpu_suspend(vcpu);
+		break;
+	case PSCI_0_2_FN_CPU_OFF:
+		kvm_psci_vcpu_off(vcpu);
+		val = PSCI_RET_SUCCESS;
+		break;
+	case PSCI_0_2_FN_CPU_ON:
+	case PSCI_0_2_FN64_CPU_ON:
+		val = kvm_psci_vcpu_on(vcpu);
+		break;
+	case PSCI_0_2_FN_AFFINITY_INFO:
+	case PSCI_0_2_FN64_AFFINITY_INFO:
+		val = kvm_psci_vcpu_affinity_info(vcpu);
+		break;
+	case PSCI_0_2_FN_MIGRATE:
+	case PSCI_0_2_FN64_MIGRATE:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+		/*
+		 * Trusted OS is MP hence does not require migration
+	         * or
+		 * Trusted OS is not present
+		 */
+		val = PSCI_0_2_TOS_MP;
+		break;
+	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
+	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	case PSCI_0_2_FN_SYSTEM_OFF:
+		kvm_psci_system_off(vcpu);
+		/*
+		 * We should'nt be going back to guest VCPU after
+		 * receiving SYSTEM_OFF request.
+		 *
+		 * If user space accidently/deliberately resumes
+		 * guest VCPU after SYSTEM_OFF request then guest
+		 * VCPU should see internal failure from PSCI return
+		 * value. To achieve this, we preload r0 (or x0) with
+		 * PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	case PSCI_0_2_FN_SYSTEM_RESET:
+		kvm_psci_system_reset(vcpu);
+		/*
+		 * Same reason as SYSTEM_OFF for preloading r0 (or x0)
+		 * with PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vcpu_reg(vcpu, 0) = val;
+	return ret;
+}
+
+static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
 	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
···
 	switch (psci_fn) {
 	case KVM_PSCI_FN_CPU_OFF:
 		kvm_psci_vcpu_off(vcpu);
-		val = KVM_PSCI_RET_SUCCESS;
+		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
 	case KVM_PSCI_FN_CPU_SUSPEND:
 	case KVM_PSCI_FN_MIGRATE:
-		val = KVM_PSCI_RET_NI;
+		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-
 	default:
-		return false;
+		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
-	return true;
+	return 1;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC instructions.
+ * The calling convention is similar to SMC calls to the secure world
+ * where the function number is placed in r0.
+ *
+ * This function returns: > 0 (success), 0 (success but exit to user
+ * space), and < 0 (errors)
+ *
+ * Errors:
+ * -EINVAL: Unrecognized PSCI function
+ */
+int kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+	switch (kvm_psci_version(vcpu)) {
+	case KVM_ARM_PSCI_0_2:
+		return kvm_psci_0_2_call(vcpu);
+	case KVM_ARM_PSCI_0_1:
+		return kvm_psci_0_1_call(vcpu);
+	default:
+		return -EINVAL;
+	};
 }

arch/arm64/include/asm/cpu_ops.h

···
  * 		from the cpu to be killed.
  * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
  *		cpu being killed.
+ * @cpu_kill:  Ensures a cpu has left the kernel. Called from another cpu.
  * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
  *               to wrong parameters or error conditions. Called from the
  *               CPU being suspended. Must be called with IRQs disabled.
···
 #ifdef CONFIG_HOTPLUG_CPU
 	int		(*cpu_disable)(unsigned int cpu);
 	void		(*cpu_die)(unsigned int cpu);
+	int		(*cpu_kill)(unsigned int cpu);
 #endif
 #ifdef CONFIG_ARM64_CPU_SUSPEND
 	int		(*cpu_suspend)(unsigned long);

arch/arm64/include/asm/cputype.h

···
 
 #define ARM_CPU_PART_AEM_V8	0xD0F0
 #define ARM_CPU_PART_FOUNDATION	0xD000
+#define ARM_CPU_PART_CORTEX_A53	0xD030
 #define ARM_CPU_PART_CORTEX_A57	0xD070
 
 #define APM_CPU_PART_POTENZA	0x0000

arch/arm64/include/asm/kvm_host.h

···
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
 
-#define KVM_VCPU_MAX_FEATURES 2
+#define KVM_VCPU_MAX_FEATURES 3
 
 struct kvm_vcpu;
 int kvm_target_cpu(void);

arch/arm64/include/asm/kvm_psci.h

···
 #ifndef __ARM64_KVM_PSCI_H__
 #define __ARM64_KVM_PSCI_H__
 
-bool kvm_psci_call(struct kvm_vcpu *vcpu);
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 #endif /* __ARM64_KVM_PSCI_H__ */

arch/arm64/include/asm/psci.h

···
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-void psci_init(void);
+int psci_init(void);
 
 #endif /* __ASM_PSCI_H */

arch/arm64/include/uapi/asm/kvm.h

···
 #define KVM_NR_SPSR	5
 
 #ifndef __ASSEMBLY__
+#include <linux/psci.h>
 #include <asm/types.h>
 #include <asm/ptrace.h>
 
···
 #define KVM_ARM_TARGET_FOUNDATION_V8	1
 #define KVM_ARM_TARGET_CORTEX_A57	2
 #define KVM_ARM_TARGET_XGENE_POTENZA	3
+#define KVM_ARM_TARGET_CORTEX_A53	4
 
-#define KVM_ARM_NUM_TARGETS		4
+#define KVM_ARM_NUM_TARGETS		5
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
···
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
 
 struct kvm_vcpu_init {
 	__u32 target;
···
 #define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
 #define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
 
-#define KVM_PSCI_RET_SUCCESS		0
-#define KVM_PSCI_RET_NI			((unsigned long)-1)
-#define KVM_PSCI_RET_INVAL		((unsigned long)-2)
-#define KVM_PSCI_RET_DENIED		((unsigned long)-3)
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
 #endif
 

arch/arm64/kernel/psci.c

···
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
+#include <linux/reboot.h>
+#include <linux/pm.h>
+#include <linux/delay.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
 #include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
+#include <asm/system_misc.h>
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
···
 	int (*cpu_off)(struct psci_power_state state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
 	int (*migrate)(unsigned long cpuid);
+	int (*affinity_info)(unsigned long target_affinity,
+			unsigned long lowest_affinity_level);
+	int (*migrate_info_type)(void);
 };
 
 static struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u64, u64, u64, u64);
+typedef int (*psci_initcall_t)(const struct device_node *);
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
+	PSCI_FN_AFFINITY_INFO,
+	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
 static u32 psci_function_id[PSCI_FN_MAX];
-
-#define PSCI_RET_SUCCESS		0
-#define PSCI_RET_EOPNOTSUPP		-1
-#define PSCI_RET_EINVAL			-2
-#define PSCI_RET_EPERM			-3
 
 static int psci_to_linux_errno(int errno)
 {
 	switch (errno) {
 	case PSCI_RET_SUCCESS:
 		return 0;
-	case PSCI_RET_EOPNOTSUPP:
+	case PSCI_RET_NOT_SUPPORTED:
 		return -EOPNOTSUPP;
-	case PSCI_RET_EINVAL:
+	case PSCI_RET_INVALID_PARAMS:
 		return -EINVAL;
-	case PSCI_RET_EPERM:
+	case PSCI_RET_DENIED:
 		return -EPERM;
 	};
 
 	return -EINVAL;
 }
 
-#define PSCI_POWER_STATE_ID_MASK	0xffff
-#define PSCI_POWER_STATE_ID_SHIFT	0
-#define PSCI_POWER_STATE_TYPE_MASK	0x1
-#define PSCI_POWER_STATE_TYPE_SHIFT	16
-#define PSCI_POWER_STATE_AFFL_MASK	0x3
-#define PSCI_POWER_STATE_AFFL_SHIFT	24
-
 static u32 psci_power_state_pack(struct psci_power_state state)
 {
-	return	((state.id & PSCI_POWER_STATE_ID_MASK)
-			<< PSCI_POWER_STATE_ID_SHIFT)	|
-		((state.type & PSCI_POWER_STATE_TYPE_MASK)
-			<< PSCI_POWER_STATE_TYPE_SHIFT)	|
-		((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
-			<< PSCI_POWER_STATE_AFFL_SHIFT);
+	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
+			& PSCI_0_2_POWER_STATE_ID_MASK) |
+		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
+		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
 /*
···
 		: "r" (arg0), "r" (arg1), "r" (arg2));
 
 	return function_id;
+}
+
+static int psci_get_version(void)
+{
+	int err;
+
+	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+	return err;
 }
 
 static int psci_cpu_suspend(struct psci_power_state state,
···
 	return psci_to_linux_errno(err);
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci",	},
-	{},
-};
-
-void __init psci_init(void)
+static int psci_affinity_info(unsigned long target_affinity,
+		unsigned long lowest_affinity_level)
 {
-	struct device_node *np;
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
+	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
+	return err;
+}
+
+static int psci_migrate_info_type(void)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
+	err = invoke_psci_fn(fn, 0, 0, 0);
+	return err;
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
 	const char *method;
-	u32 id;
 
-	np = of_find_matching_node(NULL, psci_of_match);
-	if (!np)
-		return;
-
-	pr_info("probing function IDs from device-tree\n");
+	pr_info("probing for conduit method from DT.\n");
 
 	if (of_property_read_string(np, "method", &method)) {
-		pr_warning("missing \"method\" property\n");
-		goto out_put_node;
+		pr_warn("missing \"method\" property\n");
+		return -ENXIO;
 	}
 
 	if (!strcmp("hvc", method)) {
···
 	} else if (!strcmp("smc", method)) {
 		invoke_psci_fn = __invoke_psci_fn_smc;
 	} else {
-		pr_warning("invalid \"method\" property: %s\n", method);
-		goto out_put_node;
+		pr_warn("invalid \"method\" property: %s\n", method);
+		return -EINVAL;
 	}
+	return 0;
+}
+
+static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+}
+
+static void psci_sys_poweroff(void)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+/*
+ * PSCI Function IDs for v0.2+ are well defined so use
+ * standard values.
+ */
+static int psci_0_2_init(struct device_node *np)
+{
+	int err, ver;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	ver = psci_get_version();
+
+	if (ver == PSCI_RET_NOT_SUPPORTED) {
+		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
+		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
+		err = -EOPNOTSUPP;
+		goto out_put_node;
+	} else {
+		pr_info("PSCIv%d.%d detected in firmware.\n",
+				PSCI_VERSION_MAJOR(ver),
+				PSCI_VERSION_MINOR(ver));
+
+		if (PSCI_VERSION_MAJOR(ver) == 0 &&
+				PSCI_VERSION_MINOR(ver) < 2) {
+			err = -EINVAL;
+			pr_err("Conflicting PSCI version detected.\n");
+			goto out_put_node;
+		}
+	}
+
+	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN64_CPU_SUSPEND;
+	psci_ops.cpu_suspend = psci_cpu_suspend;
+
+	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+	psci_ops.cpu_off = psci_cpu_off;
+
+	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN64_CPU_ON;
+	psci_ops.cpu_on = psci_cpu_on;
+
+	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
+	psci_ops.migrate = psci_migrate;
+
+	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO;
+	psci_ops.affinity_info = psci_affinity_info;
+
+	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
+		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
+	psci_ops.migrate_info_type = psci_migrate_info_type;
+
+	arm_pm_restart = psci_sys_reset;
+
+	pm_power_off = psci_sys_poweroff;
+
+out_put_node:
+	of_node_put(np);
+	return err;
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int psci_0_1_init(struct device_node *np)
+{
+	u32 id;
+	int err;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	pr_info("Using PSCI v0.1 Function IDs from DT\n");
 
 	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
 		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
···
 
 out_put_node:
 	of_node_put(np);
-	return;
+	return err;
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci",	.data = psci_0_1_init},
+	{ .compatible = "arm,psci-0.2",	.data = psci_0_2_init},
+	{},
+};
+
+int __init psci_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *matched_np;
+	psci_initcall_t init_fn;
+
+	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+
+	if (!np)
+		return -ENODEV;
+
+	init_fn = (psci_initcall_t)matched_np->data;
+	return init_fn(np);
 }
 
 #ifdef CONFIG_SMP
···
 
 	pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
 }
+
+static int cpu_psci_cpu_kill(unsigned int cpu)
+{
+	int err, i;
+
+	if (!psci_ops.affinity_info)
+		return 1;
+	/*
+	 * cpu_kill could race with cpu_die and we can
+	 * potentially end up declaring this cpu undead
+	 * while it is dying. So, try again a few times.
+	 */
+
+	for (i = 0; i < 10; i++) {
+		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
+		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
+			pr_info("CPU%d killed.\n", cpu);
+			return 1;
+		}
+
+		msleep(10);
+		pr_info("Retrying again to check for CPU kill\n");
+	}
+
+	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
+			cpu, err);
+	/* Make op_cpu_kill() fail. */
+	return 0;
+}
 #endif
 
 const struct cpu_operations cpu_psci_ops = {
···
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable	= cpu_psci_cpu_disable,
 	.cpu_die	= cpu_psci_cpu_die,
+	.cpu_kill	= cpu_psci_cpu_kill,
 #endif
 };
 

arch/arm64/kernel/smp.c

···
 	return 0;
 }
 
+static int op_cpu_kill(unsigned int cpu)
+{
+	/*
+	 * If we have no means of synchronising with the dying CPU, then assume
+	 * that it is really dead. We can only wait for an arbitrary length of
+	 * time and hope that it's dead, so let's skip the wait and just hope.
+	 */
+	if (!cpu_ops[cpu]->cpu_kill)
+		return 1;
+
+	return cpu_ops[cpu]->cpu_kill(cpu);
+}
+
 static DECLARE_COMPLETION(cpu_died);
 
 /*
···
 		return;
 	}
 	pr_notice("CPU%u: shutdown\n", cpu);
+
+	/*
+	 * Now that the dying CPU is beyond the point of no return w.r.t.
+	 * in-kernel synchronisation, try to get the firwmare to help us to
+	 * verify that it has really left the kernel before we consider
+	 * clobbering anything it might still be using.
+	 */
+	if (!op_cpu_kill(cpu))
+		pr_warn("CPU%d may not have shut down cleanly\n", cpu);
 }
 
 /*

arch/arm64/kvm/guest.c

···
 			return KVM_ARM_TARGET_AEM_V8;
 		case ARM_CPU_PART_FOUNDATION:
 			return KVM_ARM_TARGET_FOUNDATION_V8;
+		case ARM_CPU_PART_CORTEX_A53:
+			return KVM_ARM_TARGET_CORTEX_A53;
 		case ARM_CPU_PART_CORTEX_A57:
 			return KVM_ARM_TARGET_CORTEX_A57;
 		};

arch/arm64/kvm/handle_exit.c

···
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_psci_call(vcpu))
-		return 1;
+	int ret;
 
-	kvm_inject_undefined(vcpu);
-	return 1;
+	ret = kvm_psci_call(vcpu);
+	if (ret < 0) {
+		kvm_inject_undefined(vcpu);
+		return 1;
+	}
+
+	return ret;
 }
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)

arch/arm64/kvm/sys_regs_generic_v8.c

···
 					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
 					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
+					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
 					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,

arch/mips/Kconfig

···
 	help
 	  Select this option if building a guest kernel for KVM (Trap & Emulate) mode
 
-config KVM_HOST_FREQ
-	int "KVM Host Processor Frequency (MHz)"
+config KVM_GUEST_TIMER_FREQ
+	int "Count/Compare Timer Frequency (MHz)"
 	depends on KVM_GUEST
-	default 500
+	default 100
 	help
-	  Select this option if building a guest kernel for KVM to skip
-	  RTC emulation when determining guest CPU Frequency.  Instead, the guest
-	  processor frequency is automatically derived from the host frequency.
+	  Set this to non-zero if building a guest kernel for KVM to skip RTC
+	  emulation when determining guest CPU Frequency. Instead, the guest's
+	  timer frequency is specified directly.
 
 choice
 	prompt "Kernel page size"

arch/mips/include/asm/kvm_host.h

···
 #include <linux/threads.h>
 #include <linux/spinlock.h>
 
+/* MIPS KVM register ids */
+#define MIPS_CP0_32(_R, _S)					\
+	(KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S)))
+
+#define MIPS_CP0_64(_R, _S)					\
+	(KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S)))
+
+#define KVM_REG_MIPS_CP0_INDEX		MIPS_CP0_32(0, 0)
+#define KVM_REG_MIPS_CP0_ENTRYLO0	MIPS_CP0_64(2, 0)
+#define KVM_REG_MIPS_CP0_ENTRYLO1	MIPS_CP0_64(3, 0)
+#define KVM_REG_MIPS_CP0_CONTEXT	MIPS_CP0_64(4, 0)
+#define KVM_REG_MIPS_CP0_USERLOCAL	MIPS_CP0_64(4, 2)
+#define KVM_REG_MIPS_CP0_PAGEMASK	MIPS_CP0_32(5, 0)
+#define KVM_REG_MIPS_CP0_PAGEGRAIN	MIPS_CP0_32(5, 1)
+#define KVM_REG_MIPS_CP0_WIRED		MIPS_CP0_32(6, 0)
+#define KVM_REG_MIPS_CP0_HWRENA		MIPS_CP0_32(7, 0)
+#define KVM_REG_MIPS_CP0_BADVADDR	MIPS_CP0_64(8, 0)
+#define KVM_REG_MIPS_CP0_COUNT		MIPS_CP0_32(9, 0)
+#define KVM_REG_MIPS_CP0_ENTRYHI	MIPS_CP0_64(10, 0)
+#define KVM_REG_MIPS_CP0_COMPARE	MIPS_CP0_32(11, 0)
+#define KVM_REG_MIPS_CP0_STATUS		MIPS_CP0_32(12, 0)
+#define KVM_REG_MIPS_CP0_CAUSE		MIPS_CP0_32(13, 0)
+#define KVM_REG_MIPS_CP0_EPC		MIPS_CP0_64(14, 0)
+#define KVM_REG_MIPS_CP0_EBASE		MIPS_CP0_64(15, 1)
+#define KVM_REG_MIPS_CP0_CONFIG		MIPS_CP0_32(16, 0)
+#define KVM_REG_MIPS_CP0_CONFIG1	MIPS_CP0_32(16, 1)
+#define KVM_REG_MIPS_CP0_CONFIG2	MIPS_CP0_32(16, 2)
+#define KVM_REG_MIPS_CP0_CONFIG3	MIPS_CP0_32(16, 3)
+#define KVM_REG_MIPS_CP0_CONFIG7	MIPS_CP0_32(16, 7)
+#define KVM_REG_MIPS_CP0_XCONTEXT	MIPS_CP0_64(20, 0)
+#define KVM_REG_MIPS_CP0_ERROREPC	MIPS_CP0_64(30, 0)
+
 
 #define KVM_MAX_VCPUS		1
 #define KVM_USER_MEM_SLOTS	8
···
 
 	u32 io_gpr;		/* GPR used as IO source/target */
 
-	/* Used to calibrate the virutal count register for the guest */
-	int32_t host_cp0_count;
+	struct hrtimer comparecount_timer;
+	/* Count timer control KVM register */
+	uint32_t count_ctl;
+	/* Count bias from the raw time */
+	uint32_t count_bias;
+	/* Frequency of timer in Hz */
+	uint32_t count_hz;
+	/* Dynamic nanosecond bias (multiple of count_period) to avoid overflow */
+	s64 count_dyn_bias;
+	/* Resume time */
+	ktime_t count_resume;
+	/* Period of timer tick in ns */
+	u64 count_period;
 
 	/* Bitmask of exceptions that are pending */
 	unsigned long pending_exceptions;
···
 	uint32_t guest_kernel_asid[NR_CPUS];
 	struct mm_struct guest_kernel_mm, guest_user_mm;
 
-	struct hrtimer comparecount_timer;
-
 	int last_sched_cpu;
 
 	/* WAIT executed */
···
 #define kvm_read_c0_guest_context(cop0)		(cop0->reg[MIPS_CP0_TLB_CONTEXT][0])
 #define kvm_write_c0_guest_context(cop0, val)	(cop0->reg[MIPS_CP0_TLB_CONTEXT][0] = (val))
 #define kvm_read_c0_guest_userlocal(cop0)	(cop0->reg[MIPS_CP0_TLB_CONTEXT][2])
+#define kvm_write_c0_guest_userlocal(cop0, val)	(cop0->reg[MIPS_CP0_TLB_CONTEXT][2] = (val))
 #define kvm_read_c0_guest_pagemask(cop0)	(cop0->reg[MIPS_CP0_TLB_PG_MASK][0])
 #define kvm_write_c0_guest_pagemask(cop0, val)	(cop0->reg[MIPS_CP0_TLB_PG_MASK][0] = (val))
 #define kvm_read_c0_guest_wired(cop0)		(cop0->reg[MIPS_CP0_TLB_WIRED][0])
···
 #define kvm_read_c0_guest_errorepc(cop0)	(cop0->reg[MIPS_CP0_ERROR_PC][0])
 #define kvm_write_c0_guest_errorepc(cop0, val)	(cop0->reg[MIPS_CP0_ERROR_PC][0] = (val))
 
+/*
+ * Some of the guest registers may be modified asynchronously (e.g. from a
+ * hrtimer callback in hard irq context) and therefore need stronger atomicity
+ * guarantees than other registers.
+ */
+
+static inline void _kvm_atomic_set_c0_guest_reg(unsigned long *reg,
+						unsigned long val)
+{
+	unsigned long temp;
+	do {
+		__asm__ __volatile__(
+		"	.set	mips3				\n"
+		"	" __LL "%0, %1				\n"
+		"	or	%0, %2				\n"
+		"	" __SC	"%0, %1				\n"
+		"	.set	mips0				\n"
+		: "=&r" (temp), "+m" (*reg)
+		: "r" (val));
+	} while (unlikely(!temp));
+}
+
+static inline void _kvm_atomic_clear_c0_guest_reg(unsigned long *reg,
+						  unsigned long val)
+{
+	unsigned long temp;
+	do {
+		__asm__ __volatile__(
+		"	.set	mips3				\n"
+		"	" __LL "%0, %1				\n"
+		"	and	%0, %2				\n"
+		"	" __SC	"%0, %1				\n"
+		"	.set	mips0				\n"
+		: "=&r" (temp), "+m" (*reg)
+		: "r" (~val));
+	} while (unlikely(!temp));
+}
+
+static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg,
+						   unsigned long change,
+						   unsigned long val)
+{
+	unsigned long temp;
+	do {
+		__asm__ __volatile__(
+		"	.set	mips3				\n"
+		"	" __LL "%0, %1				\n"
+		"	and	%0, %2				\n"
+		"	or	%0, %3				\n"
+		"	" __SC	"%0, %1				\n"
+		"	.set	mips0				\n"
+		: "=&r" (temp), "+m" (*reg)
+		: "r" (~change), "r" (val & change));
+	} while (unlikely(!temp));
+}
+
 #define kvm_set_c0_guest_status(cop0, val)	(cop0->reg[MIPS_CP0_STATUS][0] |= (val))
 #define kvm_clear_c0_guest_status(cop0, val)	(cop0->reg[MIPS_CP0_STATUS][0] &= ~(val))
-#define kvm_set_c0_guest_cause(cop0, val)	(cop0->reg[MIPS_CP0_CAUSE][0] |= (val))
-#define kvm_clear_c0_guest_cause(cop0, val)	(cop0->reg[MIPS_CP0_CAUSE][0] &= ~(val))
+
+/* Cause can be modified asynchronously from hardirq hrtimer callback */
+#define kvm_set_c0_guest_cause(cop0, val)				\
+	_kvm_atomic_set_c0_guest_reg(&cop0->reg[MIPS_CP0_CAUSE][0], val)
+#define kvm_clear_c0_guest_cause(cop0, val)				\
+	_kvm_atomic_clear_c0_guest_reg(&cop0->reg[MIPS_CP0_CAUSE][0], val)
 #define kvm_change_c0_guest_cause(cop0, change, val)			\
-{									\
-	kvm_clear_c0_guest_cause(cop0, change);				\
-	kvm_set_c0_guest_cause(cop0, ((val) & (change)));		\
-}
+	_kvm_atomic_change_c0_guest_reg(&cop0->reg[MIPS_CP0_CAUSE][0],	\
+					change, val)
+
 #define kvm_set_c0_guest_ebase(cop0, val)	(cop0->reg[MIPS_CP0_PRID][1] |= (val))
 #define kvm_clear_c0_guest_ebase(cop0, val)	(cop0->reg[MIPS_CP0_PRID][1] &= ~(val))
 #define kvm_change_c0_guest_ebase(cop0, change, val)			\
···
 
 
 struct kvm_mips_callbacks {
-	int (*handle_cop_unusable) (struct kvm_vcpu *vcpu);
-	int (*handle_tlb_mod) (struct kvm_vcpu *vcpu);
-	int (*handle_tlb_ld_miss) (struct kvm_vcpu *vcpu);
-	int (*handle_tlb_st_miss) (struct kvm_vcpu *vcpu);
-	int (*handle_addr_err_st) (struct kvm_vcpu *vcpu);
-	int (*handle_addr_err_ld) (struct kvm_vcpu *vcpu);
-	int (*handle_syscall) (struct kvm_vcpu *vcpu);
-	int (*handle_res_inst) (struct kvm_vcpu *vcpu);
-	int (*handle_break) (struct kvm_vcpu *vcpu);
-	int (*vm_init) (struct kvm *kvm);
-	int (*vcpu_init) (struct kvm_vcpu *vcpu);
-	int (*vcpu_setup) (struct kvm_vcpu *vcpu);
-	 gpa_t(*gva_to_gpa) (gva_t gva);
-	void (*queue_timer_int) (struct kvm_vcpu *vcpu);
-	void (*dequeue_timer_int) (struct kvm_vcpu *vcpu);
-	void (*queue_io_int) (struct kvm_vcpu *vcpu,
-			      struct kvm_mips_interrupt *irq);
-	void (*dequeue_io_int) (struct kvm_vcpu *vcpu,
-				struct kvm_mips_interrupt *irq);
-	int (*irq_deliver) (struct kvm_vcpu *vcpu, unsigned int priority,
-			    uint32_t cause);
-	int (*irq_clear) (struct kvm_vcpu *vcpu, unsigned int priority,
-			  uint32_t cause);
+	int (*handle_cop_unusable)(struct kvm_vcpu *vcpu);
+	int (*handle_tlb_mod)(struct kvm_vcpu *vcpu);
+	int (*handle_tlb_ld_miss)(struct kvm_vcpu *vcpu);
+	int (*handle_tlb_st_miss)(struct kvm_vcpu *vcpu);
+	int (*handle_addr_err_st)(struct kvm_vcpu *vcpu);
+	int (*handle_addr_err_ld)(struct kvm_vcpu *vcpu);
+	int (*handle_syscall)(struct kvm_vcpu *vcpu);
+	int (*handle_res_inst)(struct kvm_vcpu *vcpu);
+	int (*handle_break)(struct kvm_vcpu *vcpu);
+	int (*vm_init)(struct kvm *kvm);
+	int (*vcpu_init)(struct kvm_vcpu *vcpu);
+	int (*vcpu_setup)(struct kvm_vcpu *vcpu);
+	gpa_t (*gva_to_gpa)(gva_t gva);
+	void (*queue_timer_int)(struct kvm_vcpu *vcpu);
+	void (*dequeue_timer_int)(struct kvm_vcpu *vcpu);
+	void (*queue_io_int)(struct kvm_vcpu *vcpu,
+			     struct kvm_mips_interrupt *irq);
+	void (*dequeue_io_int)(struct kvm_vcpu *vcpu,
+			       struct kvm_mips_interrupt *irq);
+	int (*irq_deliver)(struct kvm_vcpu *vcpu, unsigned int priority,
+			   uint32_t cause);
+	int (*irq_clear)(struct kvm_vcpu *vcpu, unsigned int priority,
+			 uint32_t cause);
+	int (*get_one_reg)(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg, s64 *v);
+	int (*set_one_reg)(struct kvm_vcpu *vcpu,
+			   const struct kvm_one_reg *reg, s64 v);
 };
 extern struct kvm_mips_callbacks *kvm_mips_callbacks;
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);
···
 extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 							 struct kvm_run *run);
 
-enum emulation_result kvm_mips_emulate_count(struct kvm_vcpu *vcpu);
+uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
+void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare);
+void kvm_mips_init_count(struct kvm_vcpu *vcpu);
+int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
+int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
+int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz);
+void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu);
+void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu);
+enum hrtimer_restart kvm_mips_count_timeout(struct kvm_vcpu *vcpu);
 
 enum emulation_result kvm_mips_check_privilege(unsigned long cause,
 					       uint32_t *opc,
···
 			       struct kvm_vcpu *vcpu);
 
 /* Misc */
-extern void mips32_SyncICache(unsigned long addr, unsigned long size);
 extern int kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
 extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 

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

···
 #define KVM_REG_MIPS_LO (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 33)
 #define KVM_REG_MIPS_PC (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 34)
 
+/* KVM specific control registers */
+
+/*
+ * CP0_Count control
+ * DC:    Set 0: Master disable CP0_Count and set COUNT_RESUME to now
+ *        Set 1: Master re-enable CP0_Count with unchanged bias, handling timer
+ *               interrupts since COUNT_RESUME
+ *        This can be used to freeze the timer to get a consistent snapshot of
+ *        the CP0_Count and timer interrupt pending state, while also resuming
+ *        safely without losing time or guest timer interrupts.
+ * Other: Reserved, do not change.
+ */
+#define KVM_REG_MIPS_COUNT_CTL		(KVM_REG_MIPS | KVM_REG_SIZE_U64 | \
+					 0x20000 | 0)
+#define KVM_REG_MIPS_COUNT_CTL_DC	0x00000001
+
+/*
+ * CP0_Count resume monotonic nanoseconds
+ * The monotonic nanosecond time of the last set of COUNT_CTL.DC (master
+ * disable). Any reads and writes of Count related registers while
+ * COUNT_CTL.DC=1 will appear to occur at this time. When COUNT_CTL.DC is
+ * cleared again (master enable) any timer interrupts since this time will be
+ * emulated.
+ * Modifications to times in the future are rejected.
+ */
+#define KVM_REG_MIPS_COUNT_RESUME	(KVM_REG_MIPS | KVM_REG_SIZE_U64 | \
+					 0x20000 | 1)
+/*
+ * CP0_Count rate in Hz
+ * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without
+ * discontinuities in CP0_Count.
+ */
+#define KVM_REG_MIPS_COUNT_HZ		(KVM_REG_MIPS | KVM_REG_SIZE_U64 | \
+					 0x20000 | 2)
+
 /*
  * KVM MIPS specific structures and definitions
  *

arch/mips/kvm/kvm_locore.S

···
 	.word _C_LABEL(MIPSX(GuestException))	# 29
 	.word _C_LABEL(MIPSX(GuestException))	# 30
 	.word _C_LABEL(MIPSX(GuestException))	# 31
-
-
-/* This routine makes changes to the instruction stream effective to the hardware.
- * It should be called after the instruction stream is written.
- * On return, the new instructions are effective.
- * Inputs:
- * a0 = Start address of new instruction stream
- * a1 = Size, in bytes, of new instruction stream
- */
-
-#define HW_SYNCI_Step       $1
-LEAF(MIPSX(SyncICache))
-	.set	push
-	.set	mips32r2
-	beq	a1, zero, 20f
-	 nop
-	REG_ADDU a1, a0, a1
-	rdhwr	v0, HW_SYNCI_Step
-	beq	v0, zero, 20f
-	 nop
-10:
-	synci	0(a0)
-	REG_ADDU a0, a0, v0
-	sltu	v1, a0, a1
-	bne	v1, zero, 10b
-	 nop
-	sync
-20:
-	jr.hb	ra
-	 nop
-	.set	pop
-END(MIPSX(SyncICache))

arch/mips/kvm/kvm_mips.c

···
 	return 0;
 }
 
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	return gfn;
-}
-
 /* XXXKYMA: We are simulatoring a processor that has the WII bit set in Config7, so we
  * are "runnable" if interrupts are pending
  */
···
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	if (atomic_inc_return(&kvm_mips_instance) == 1) {
-		kvm_info("%s: 1st KVM instance, setup host TLB parameters\n",
-			 __func__);
+		kvm_debug("%s: 1st KVM instance, setup host TLB parameters\n",
+			  __func__);
 		on_each_cpu(kvm_mips_init_vm_percpu, kvm, 1);
 	}
 
···
 		if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE)
 			kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]);
 	}
-
-	if (kvm->arch.guest_pmap)
-		kfree(kvm->arch.guest_pmap);
+	kfree(kvm->arch.guest_pmap);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		kvm_arch_vcpu_free(vcpu);
···
 
 	/* If this is the last instance, restore wired count */
 	if (atomic_dec_return(&kvm_mips_instance) == 0) {
-		kvm_info("%s: last KVM instance, restoring TLB parameters\n",
-			 __func__);
+		kvm_debug("%s: last KVM instance, restoring TLB parameters\n",
+			  __func__);
 		on_each_cpu(kvm_mips_uninit_tlbs, NULL, 1);
 	}
 }
···
 				goto out;
 			}
 
-			kvm_info
-			    ("Allocated space for Guest PMAP Table (%ld pages) @ %p\n",
-			     npages, kvm->arch.guest_pmap);
+			kvm_debug("Allocated space for Guest PMAP Table (%ld pages) @ %p\n",
+				  npages, kvm->arch.guest_pmap);
 
 			/* Now setup the page table */
 			for (i = 0; i < npages; i++) {
···
 	if (err)
 		goto out_free_cpu;
 
-	kvm_info("kvm @ %p: create cpu %d at %p\n", kvm, id, vcpu);
+	kvm_debug("kvm @ %p: create cpu %d at %p\n", kvm, id, vcpu);
 
 	/* Allocate space for host mode exception handlers that handle
 	 * guest mode exits
···
 	if (cpu_has_veic || cpu_has_vint) {
 		size = 0x200 + VECTORSPACING * 64;
 	} else {
-		size = 0x200;
+		size = 0x4000;
 	}
 
 	/* Save Linux EBASE */
···
 		err = -ENOMEM;
 		goto out_free_cpu;
 	}
-	kvm_info("Allocated %d bytes for KVM Exception Handlers @ %p\n",
-		 ALIGN(size, PAGE_SIZE), gebase);
+	kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
+		  ALIGN(size, PAGE_SIZE), gebase);
 
 	/* Save new ebase */
 	vcpu->arch.guest_ebase = gebase;
···
 
 	/* General handler, relocate to unmapped space for sanity's sake */
 	offset = 0x2000;
-	kvm_info("Installing KVM Exception handlers @ %p, %#x bytes\n",
-		 gebase + offset,
-		 mips32_GuestExceptionEnd - mips32_GuestException);
+	kvm_debug("Installing KVM Exception handlers @ %p, %#x bytes\n",
+		  gebase + offset,
+		  mips32_GuestExceptionEnd - mips32_GuestException);
 
 	memcpy(gebase + offset, mips32_GuestException,
 	       mips32_GuestExceptionEnd - mips32_GuestException);
 
 	/* Invalidate the icache for these ranges */
-	mips32_SyncICache((unsigned long) gebase, ALIGN(size, PAGE_SIZE));
+	local_flush_icache_range((unsigned long)gebase,
+				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
 
 	/* Allocate comm page for guest kernel, a TLB will be reserved for mapping GVA @ 0xFFFF8000 to this page */
 	vcpu->arch.kseg0_commpage = kzalloc(PAGE_SIZE << 1, GFP_KERNEL);
···
 		goto out_free_gebase;
 	}
 
-	kvm_info("Allocated COMM page @ %p\n", vcpu->arch.kseg0_commpage);
+	kvm_debug("Allocated COMM page @ %p\n", vcpu->arch.kseg0_commpage);
 	kvm_mips_commpage_init(vcpu);
 
 	/* Init */
 	vcpu->arch.last_sched_cpu = -1;
 
 	/* Start off the timer */
-	kvm_mips_emulate_count(vcpu);
+	kvm_mips_init_count(vcpu);
 
 	return vcpu;
 
···
 
 	kvm_mips_dump_stats(vcpu);
 
-	if (vcpu->arch.guest_ebase)
-		kfree(vcpu->arch.guest_ebase);
-
-	if (vcpu->arch.kseg0_commpage)
-		kfree(vcpu->arch.kseg0_commpage);
-
+	kfree(vcpu->arch.guest_ebase);
+	kfree(vcpu->arch.kseg0_commpage);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
···
 		vcpu->mmio_needed = 0;
 	}
 
+	local_irq_disable();
 	/* Check if we have any exceptions/interrupts pending */
 	kvm_mips_deliver_interrupts(vcpu,
 				    kvm_read_c0_guest_cause(vcpu->arch.cop0));
 
-	local_irq_disable();
 	kvm_guest_enter();
 
 	r = __kvm_mips_vcpu_run(run, vcpu);
···
 	return -ENOIOCTLCMD;
 }
 
-#define MIPS_CP0_32(_R, _S)					\
-	(KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S)))
-
-#define MIPS_CP0_64(_R, _S)					\
-	(KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S)))
-
-#define KVM_REG_MIPS_CP0_INDEX		MIPS_CP0_32(0, 0)
-#define KVM_REG_MIPS_CP0_ENTRYLO0	MIPS_CP0_64(2, 0)
-#define KVM_REG_MIPS_CP0_ENTRYLO1	MIPS_CP0_64(3, 0)
-#define KVM_REG_MIPS_CP0_CONTEXT	MIPS_CP0_64(4, 0)
-#define KVM_REG_MIPS_CP0_USERLOCAL	MIPS_CP0_64(4, 2)
-#define KVM_REG_MIPS_CP0_PAGEMASK	MIPS_CP0_32(5, 0)
-#define KVM_REG_MIPS_CP0_PAGEGRAIN	MIPS_CP0_32(5, 1)
-#define KVM_REG_MIPS_CP0_WIRED		MIPS_CP0_32(6, 0)
-#define KVM_REG_MIPS_CP0_HWRENA		MIPS_CP0_32(7, 0)
-#define KVM_REG_MIPS_CP0_BADVADDR	MIPS_CP0_64(8, 0)
-#define KVM_REG_MIPS_CP0_COUNT		MIPS_CP0_32(9, 0)
-#define KVM_REG_MIPS_CP0_ENTRYHI	MIPS_CP0_64(10, 0)
-#define KVM_REG_MIPS_CP0_COMPARE	MIPS_CP0_32(11, 0)
-#define KVM_REG_MIPS_CP0_STATUS		MIPS_CP0_32(12, 0)
-#define KVM_REG_MIPS_CP0_CAUSE		MIPS_CP0_32(13, 0)
-#define KVM_REG_MIPS_CP0_EBASE		MIPS_CP0_64(15, 1)
-#define KVM_REG_MIPS_CP0_CONFIG		MIPS_CP0_32(16, 0)
-#define KVM_REG_MIPS_CP0_CONFIG1	MIPS_CP0_32(16, 1)
-#define KVM_REG_MIPS_CP0_CONFIG2	MIPS_CP0_32(16, 2)
-#define KVM_REG_MIPS_CP0_CONFIG3	MIPS_CP0_32(16, 3)
-#define KVM_REG_MIPS_CP0_CONFIG7	MIPS_CP0_32(16, 7)
-#define KVM_REG_MIPS_CP0_XCONTEXT	MIPS_CP0_64(20, 0)
-#define KVM_REG_MIPS_CP0_ERROREPC	MIPS_CP0_64(30, 0)
-
 static u64 kvm_mips_get_one_regs[] = {
 	KVM_REG_MIPS_R0,
 	KVM_REG_MIPS_R1,
···
 
 	KVM_REG_MIPS_CP0_INDEX,
 	KVM_REG_MIPS_CP0_CONTEXT,
+	KVM_REG_MIPS_CP0_USERLOCAL,
 	KVM_REG_MIPS_CP0_PAGEMASK,
 	KVM_REG_MIPS_CP0_WIRED,
+	KVM_REG_MIPS_CP0_HWRENA,
 	KVM_REG_MIPS_CP0_BADVADDR,
+	KVM_REG_MIPS_CP0_COUNT,
 	KVM_REG_MIPS_CP0_ENTRYHI,
+	KVM_REG_MIPS_CP0_COMPARE,
 	KVM_REG_MIPS_CP0_STATUS,
 	KVM_REG_MIPS_CP0_CAUSE,
-	/* EPC set via kvm_regs, et al. */
+	KVM_REG_MIPS_CP0_EPC,
 	KVM_REG_MIPS_CP0_CONFIG,
 	KVM_REG_MIPS_CP0_CONFIG1,
 	KVM_REG_MIPS_CP0_CONFIG2,
 	KVM_REG_MIPS_CP0_CONFIG3,
 	KVM_REG_MIPS_CP0_CONFIG7,
-	KVM_REG_MIPS_CP0_ERROREPC
+	KVM_REG_MIPS_CP0_ERROREPC,
+
+	KVM_REG_MIPS_COUNT_CTL,
+	KVM_REG_MIPS_COUNT_RESUME,
+	KVM_REG_MIPS_COUNT_HZ,
 };
 
 static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 			    const struct kvm_one_reg *reg)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int ret;
 	s64 v;
 
 	switch (reg->id) {
···
 	case KVM_REG_MIPS_CP0_CONTEXT:
 		v = (long)kvm_read_c0_guest_context(cop0);
 		break;
+	case KVM_REG_MIPS_CP0_USERLOCAL:
+		v = (long)kvm_read_c0_guest_userlocal(cop0);
+		break;
 	case KVM_REG_MIPS_CP0_PAGEMASK:
 		v = (long)kvm_read_c0_guest_pagemask(cop0);
 		break;
 	case KVM_REG_MIPS_CP0_WIRED:
 		v = (long)kvm_read_c0_guest_wired(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_HWRENA:
+		v = (long)kvm_read_c0_guest_hwrena(cop0);
 		break;
 	case KVM_REG_MIPS_CP0_BADVADDR:
 		v = (long)kvm_read_c0_guest_badvaddr(cop0);
···
 	case KVM_REG_MIPS_CP0_ENTRYHI:
 		v = (long)kvm_read_c0_guest_entryhi(cop0);
 		break;
+	case KVM_REG_MIPS_CP0_COMPARE:
+		v = (long)kvm_read_c0_guest_compare(cop0);
+		break;
 	case KVM_REG_MIPS_CP0_STATUS:
 		v = (long)kvm_read_c0_guest_status(cop0);
 		break;
 	case KVM_REG_MIPS_CP0_CAUSE:
 		v = (long)kvm_read_c0_guest_cause(cop0);
+		break;
+	case KVM_REG_MIPS_CP0_EPC:
+		v = (long)kvm_read_c0_guest_epc(cop0);
 		break;
 	case KVM_REG_MIPS_CP0_ERROREPC:
 		v = (long)kvm_read_c0_guest_errorepc(cop0);
···
 		break;
 	case KVM_REG_MIPS_CP0_CONFIG7:
 		v = (long)kvm_read_c0_guest_config7(cop0);
+		break;
+	/* registers to be handled specially */
+	case KVM_REG_MIPS_CP0_COUNT:
+	case KVM_REG_MIPS_COUNT_CTL:
+	case KVM_REG_MIPS_COUNT_RESUME:
+	case KVM_REG_MIPS_COUNT_HZ:
+		ret = kvm_mips_callbacks->get_one_reg(vcpu, reg, &v);
+		if (ret)
+			return ret;
 		break;
 	default:
 		return -EINVAL;
···
 	case KVM_REG_MIPS_CP0_CONTEXT:
 		kvm_write_c0_guest_context(cop0, v);
 		break;
+	case KVM_REG_MIPS_CP0_USERLOCAL:
+		kvm_write_c0_guest_userlocal(cop0, v);
+		break;
 	case KVM_REG_MIPS_CP0_PAGEMASK:
 		kvm_write_c0_guest_pagemask(cop0, v);
 		break;
 	case KVM_REG_MIPS_CP0_WIRED:
 		kvm_write_c0_guest_wired(cop0, v);
+		break;
+	case KVM_REG_MIPS_CP0_HWRENA:
+		kvm_write_c0_guest_hwrena(cop0, v);
 		break;
 	case KVM_REG_MIPS_CP0_BADVADDR:
 		kvm_write_c0_guest_badvaddr(cop0, v);
···
 	case KVM_REG_MIPS_CP0_STATUS:
 		kvm_write_c0_guest_status(cop0, v);
 		break;
-	case KVM_REG_MIPS_CP0_CAUSE:
-		kvm_write_c0_guest_cause(cop0, v);
+	case KVM_REG_MIPS_CP0_EPC:
+		kvm_write_c0_guest_epc(cop0, v);
 		break;
 	case KVM_REG_MIPS_CP0_ERROREPC:
 		kvm_write_c0_guest_errorepc(cop0, v);
 		break;
+	/* registers to be handled specially */
+	case KVM_REG_MIPS_CP0_COUNT:
+	case KVM_REG_MIPS_CP0_COMPARE:
+	case KVM_REG_MIPS_CP0_CAUSE:
+	case KVM_REG_MIPS_COUNT_CTL:
+	case KVM_REG_MIPS_COUNT_RESUME:
+	case KVM_REG_MIPS_COUNT_HZ:
+		return kvm_mips_callbacks->set_one_reg(vcpu, reg, v);
 	default:
 		return -EINVAL;
 	}
···
 		return -1;
 
 	printk("VCPU Register Dump:\n");
-	printk("\tpc = 0x%08lx\n", vcpu->arch.pc);;
+	printk("\tpc = 0x%08lx\n", vcpu->arch.pc);
 	printk("\texceptions: %08lx\n", vcpu->arch.pending_exceptions);
 
 	for (i = 0; i < 32; i += 4) {
···
 	return 0;
 }
 
-void kvm_mips_comparecount_func(unsigned long data)
+static void kvm_mips_comparecount_func(unsigned long data)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
···
 /*
  * low level hrtimer wake routine.
  */
-enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
+static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.comparecount_timer);
 	kvm_mips_comparecount_func((unsigned long) vcpu);
-	hrtimer_forward_now(&vcpu->arch.comparecount_timer,
-			    ktime_set(0, MS_TO_NS(10)));
-	return HRTIMER_RESTART;
+	return kvm_mips_count_timeout(vcpu);
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)

arch/mips/kvm/kvm_mips_dyntrans.c

···
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
+#include <asm/cacheflush.h>
 
 #include "kvm_mips_comm.h"
 
···
 	    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
 		       (vcpu, (unsigned long) opc));
 	memcpy((void *)kseg0_opc, (void *)&synci_inst, sizeof(uint32_t));
-	mips32_SyncICache(kseg0_opc, 32);
+	local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
 
 	return result;
 }
···
 	    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
 		       (vcpu, (unsigned long) opc));
 	memcpy((void *)kseg0_opc, (void *)&synci_inst, sizeof(uint32_t));
-	mips32_SyncICache(kseg0_opc, 32);
+	local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
 
 	return result;
 }
···
 		    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
 			       (vcpu, (unsigned long) opc));
 		memcpy((void *)kseg0_opc, (void *)&mfc0_inst, sizeof(uint32_t));
-		mips32_SyncICache(kseg0_opc, 32);
+		local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
 	} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
 		local_irq_save(flags);
 		memcpy((void *)opc, (void *)&mfc0_inst, sizeof(uint32_t));
-		mips32_SyncICache((unsigned long) opc, 32);
+		local_flush_icache_range((unsigned long)opc,
+					 (unsigned long)opc + 32);
 		local_irq_restore(flags);
 	} else {
 		kvm_err("%s: Invalid address: %p\n", __func__, opc);
···
 		    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
 			       (vcpu, (unsigned long) opc));
 		memcpy((void *)kseg0_opc, (void *)&mtc0_inst, sizeof(uint32_t));
-		mips32_SyncICache(kseg0_opc, 32);
+		local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
 	} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
 		local_irq_save(flags);
 		memcpy((void *)opc, (void *)&mtc0_inst, sizeof(uint32_t));
-		mips32_SyncICache((unsigned long) opc, 32);
+		local_flush_icache_range((unsigned long)opc,
+					 (unsigned long)opc + 32);
 		local_irq_restore(flags);
 	} else {
 		kvm_err("%s: Invalid address: %p\n", __func__, opc);

arch/mips/kvm/kvm_mips_emul.c

···
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/ktime.h>
 #include <linux/kvm_host.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
···
 	return er;
 }
 
-/* Everytime the compare register is written to, we need to decide when to fire
- * the timer that represents timer ticks to the GUEST.
+/**
+ * kvm_mips_count_disabled() - Find whether the CP0_Count timer is disabled.
+ * @vcpu:	Virtual CPU.
  *
+ * Returns:	1 if the CP0_Count timer is disabled by either the guest
+ *		CP0_Cause.DC bit or the count_ctl.DC bit.
+ *		0 otherwise (in which case CP0_Count timer is running).
  */
-enum emulation_result kvm_mips_emulate_count(struct kvm_vcpu *vcpu)
+static inline int kvm_mips_count_disabled(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	enum emulation_result er = EMULATE_DONE;
+	return	(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC) ||
+		(kvm_read_c0_guest_cause(cop0) & CAUSEF_DC);
+}
 
-	/* If COUNT is enabled */
-	if (!(kvm_read_c0_guest_cause(cop0) & CAUSEF_DC)) {
-		hrtimer_try_to_cancel(&vcpu->arch.comparecount_timer);
-		hrtimer_start(&vcpu->arch.comparecount_timer,
-			      ktime_set(0, MS_TO_NS(10)), HRTIMER_MODE_REL);
-	} else {
-		hrtimer_try_to_cancel(&vcpu->arch.comparecount_timer);
+/**
+ * kvm_mips_ktime_to_count() - Scale ktime_t to a 32-bit count.
+ *
+ * Caches the dynamic nanosecond bias in vcpu->arch.count_dyn_bias.
+ *
+ * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
+ */
+static uint32_t kvm_mips_ktime_to_count(struct kvm_vcpu *vcpu, ktime_t now)
+{
+	s64 now_ns, periods;
+	u64 delta;
+
+	now_ns = ktime_to_ns(now);
+	delta = now_ns + vcpu->arch.count_dyn_bias;
+
+	if (delta >= vcpu->arch.count_period) {
+		/* If delta is out of safe range the bias needs adjusting */
+		periods = div64_s64(now_ns, vcpu->arch.count_period);
+		vcpu->arch.count_dyn_bias = -periods * vcpu->arch.count_period;
+		/* Recalculate delta with new bias */
+		delta = now_ns + vcpu->arch.count_dyn_bias;
 	}
 
-	return er;
+	/*
+	 * We've ensured that:
+	 *   delta < count_period
+	 *
+	 * Therefore the intermediate delta*count_hz will never overflow since
+	 * at the boundary condition:
+	 *   delta = count_period
+	 *   delta = NSEC_PER_SEC * 2^32 / count_hz
+	 *   delta * count_hz = NSEC_PER_SEC * 2^32
+	 */
+	return div_u64(delta * vcpu->arch.count_hz, NSEC_PER_SEC);
+}
+
+/**
+ * kvm_mips_count_time() - Get effective current time.
+ * @vcpu:	Virtual CPU.
+ *
+ * Get effective monotonic ktime. This is usually a straightforward ktime_get(),
+ * except when the master disable bit is set in count_ctl, in which case it is
+ * count_resume, i.e. the time that the count was disabled.
+ *
+ * Returns:	Effective monotonic ktime for CP0_Count.
+ */
+static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC))
+		return vcpu->arch.count_resume;
+
+	return ktime_get();
+}
+
+/**
+ * kvm_mips_read_count_running() - Read the current count value as if running.
+ * @vcpu:	Virtual CPU.
+ * @now:	Kernel time to read CP0_Count at.
+ *
+ * Returns the current guest CP0_Count register at time @now and handles if the
+ * timer interrupt is pending and hasn't been handled yet.
+ *
+ * Returns:	The current value of the guest CP0_Count register.
+ */
+static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
+{
+	ktime_t expires;
+	int running;
+
+	/* Is the hrtimer pending? */
+	expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
+	if (ktime_compare(now, expires) >= 0) {
+		/*
+		 * Cancel it while we handle it so there's no chance of
+		 * interference with the timeout handler.
+		 */
+		running = hrtimer_cancel(&vcpu->arch.comparecount_timer);
+
+		/* Nothing should be waiting on the timeout */
+		kvm_mips_callbacks->queue_timer_int(vcpu);
+
+		/*
+		 * Restart the timer if it was running based on the expiry time
+		 * we read, so that we don't push it back 2 periods.
+		 */
+		if (running) {
+			expires = ktime_add_ns(expires,
+					       vcpu->arch.count_period);
+			hrtimer_start(&vcpu->arch.comparecount_timer, expires,
+				      HRTIMER_MODE_ABS);
+		}
+	}
+
+	/* Return the biased and scaled guest CP0_Count */
+	return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+}
+
+/**
+ * kvm_mips_read_count() - Read the current count value.
+ * @vcpu:	Virtual CPU.
+ *
+ * Read the current guest CP0_Count value, taking into account whether the timer
+ * is stopped.
+ *
+ * Returns:	The current guest CP0_Count value.
+ */
+uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+
+	/* If count disabled just read static copy of count */
+	if (kvm_mips_count_disabled(vcpu))
+		return kvm_read_c0_guest_count(cop0);
+
+	return kvm_mips_read_count_running(vcpu, ktime_get());
+}
+
+/**
+ * kvm_mips_freeze_hrtimer() - Safely stop the hrtimer.
+ * @vcpu:	Virtual CPU.
+ * @count:	Output pointer for CP0_Count value at point of freeze.
+ *
+ * Freeze the hrtimer safely and return both the ktime and the CP0_Count value
+ * at the point it was frozen. It is guaranteed that any pending interrupts at
+ * the point it was frozen are handled, and none after that point.
+ *
+ * This is useful where the time/CP0_Count is needed in the calculation of the
+ * new parameters.
+ *
+ * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
+ *
+ * Returns:	The ktime at the point of freeze.
+ */
+static ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu,
+				       uint32_t *count)
+{
+	ktime_t now;
+
+	/* stop hrtimer before finding time */
+	hrtimer_cancel(&vcpu->arch.comparecount_timer);
+	now = ktime_get();
+
+	/* find count at this point and handle pending hrtimer */
+	*count = kvm_mips_read_count_running(vcpu, now);
+
+	return now;
+}
+
+
+/**
+ * kvm_mips_resume_hrtimer() - Resume hrtimer, updating expiry.
+ * @vcpu:	Virtual CPU.
+ * @now:	ktime at point of resume.
+ * @count:	CP0_Count at point of resume.
+ *
+ * Resumes the timer and updates the timer expiry based on @now and @count.
+ * This can be used in conjunction with kvm_mips_freeze_timer() when timer
+ * parameters need to be changed.
+ *
+ * It is guaranteed that a timer interrupt immediately after resume will be
+ * handled, but not if CP_Compare is exactly at @count. That case is already
+ * handled by kvm_mips_freeze_timer().
+ *
+ * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
+ */
+static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
+				    ktime_t now, uint32_t count)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	uint32_t compare;
+	u64 delta;
+	ktime_t expire;
+
+	/* Calculate timeout (wrap 0 to 2^32) */
+	compare = kvm_read_c0_guest_compare(cop0);
+	delta = (u64)(uint32_t)(compare - count - 1) + 1;
+	delta = div_u64(delta * NSEC_PER_SEC, vcpu->arch.count_hz);
+	expire = ktime_add_ns(now, delta);
+
+	/* Update hrtimer to use new timeout */
+	hrtimer_cancel(&vcpu->arch.comparecount_timer);
+	hrtimer_start(&vcpu->arch.comparecount_timer, expire, HRTIMER_MODE_ABS);
+}
+
+/**
+ * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer.
+ * @vcpu:	Virtual CPU.
+ *
+ * Recalculates and updates the expiry time of the hrtimer. This can be used
+ * after timer parameters have been altered which do not depend on the time that
+ * the change occurs (in those cases kvm_mips_freeze_hrtimer() and
+ * kvm_mips_resume_hrtimer() are used directly).
+ *
+ * It is guaranteed that no timer interrupts will be lost in the process.
+ *
+ * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
+ */
+static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu)
+{
+	ktime_t now;
+	uint32_t count;
+
+	/*
+	 * freeze_hrtimer takes care of a timer interrupts <= count, and
+	 * resume_hrtimer the hrtimer takes care of a timer interrupts > count.
+	 */
+	now = kvm_mips_freeze_hrtimer(vcpu, &count);
+	kvm_mips_resume_hrtimer(vcpu, now, count);
+}
+
+/**
+ * kvm_mips_write_count() - Modify the count and update timer.
+ * @vcpu:	Virtual CPU.
+ * @count:	Guest CP0_Count value to set.
+ *
+ * Sets the CP0_Count value and updates the timer accordingly.
+ */
+void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	ktime_t now;
+
+	/* Calculate bias */
+	now = kvm_mips_count_time(vcpu);
+	vcpu->arch.count_bias = count - kvm_mips_ktime_to_count(vcpu, now);
+
+	if (kvm_mips_count_disabled(vcpu))
+		/* The timer's disabled, adjust the static count */
+		kvm_write_c0_guest_count(cop0, count);
+	else
+		/* Update timeout */
+		kvm_mips_resume_hrtimer(vcpu, now, count);
+}
+
+/**
+ * kvm_mips_init_count() - Initialise timer.
+ * @vcpu:	Virtual CPU.
+ *
+ * Initialise the timer to a sensible frequency, namely 100MHz, zero it, and set
+ * it going if it's enabled.
+ */
+void kvm_mips_init_count(struct kvm_vcpu *vcpu)
+{
+	/* 100 MHz */
+	vcpu->arch.count_hz = 100*1000*1000;
+	vcpu->arch.count_period = div_u64((u64)NSEC_PER_SEC << 32,
+					  vcpu->arch.count_hz);
+	vcpu->arch.count_dyn_bias = 0;
+
+	/* Starting at 0 */
+	kvm_mips_write_count(vcpu, 0);
+}
+
+/**
+ * kvm_mips_set_count_hz() - Update the frequency of the timer.
+ * @vcpu:	Virtual CPU.
+ * @count_hz:	Frequency of CP0_Count timer in Hz.
+ *
+ * Change the frequency of the CP0_Count timer. This is done atomically so that
+ * CP0_Count is continuous and no timer interrupt is lost.
+ *
+ * Returns:	-EINVAL if @count_hz is out of range.
+ *		0 on success.
+ */
+int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int dc;
+	ktime_t now;
+	u32 count;
+
+	/* ensure the frequency is in a sensible range... */
+	if (count_hz <= 0 || count_hz > NSEC_PER_SEC)
+		return -EINVAL;
+	/* ... and has actually changed */
+	if (vcpu->arch.count_hz == count_hz)
+		return 0;
+
+	/* Safely freeze timer so we can keep it continuous */
+	dc = kvm_mips_count_disabled(vcpu);
+	if (dc) {
+		now = kvm_mips_count_time(vcpu);
+		count = kvm_read_c0_guest_count(cop0);
+	} else {
+		now = kvm_mips_freeze_hrtimer(vcpu, &count);
+	}
+
+	/* Update the frequency */
+	vcpu->arch.count_hz = count_hz;
+	vcpu->arch.count_period = div_u64((u64)NSEC_PER_SEC << 32, count_hz);
+	vcpu->arch.count_dyn_bias = 0;
+
+	/* Calculate adjusted bias so dynamic count is unchanged */
+	vcpu->arch.count_bias = count - kvm_mips_ktime_to_count(vcpu, now);
+
+	/* Update and resume hrtimer */
+	if (!dc)
+		kvm_mips_resume_hrtimer(vcpu, now, count);
+	return 0;
+}
+
+/**
+ * kvm_mips_write_compare() - Modify compare and update timer.
+ * @vcpu:	Virtual CPU.
+ * @compare:	New CP0_Compare value.
+ *
+ * Update CP0_Compare to a new value and update the timeout.
+ */
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+
+	/* if unchanged, must just be an ack */
+	if (kvm_read_c0_guest_compare(cop0) == compare)
+		return;
+
+	/* Update compare */
+	kvm_write_c0_guest_compare(cop0, compare);
+
+	/* Update timeout if count enabled */
+	if (!kvm_mips_count_disabled(vcpu))
+		kvm_mips_update_hrtimer(vcpu);
+}
+
+/**
+ * kvm_mips_count_disable() - Disable count.
+ * @vcpu:	Virtual CPU.
+ *
+ * Disable the CP0_Count timer. A timer interrupt on or before the final stop
+ * time will be handled but not after.
+ *
+ * Assumes CP0_Count was previously enabled but now Guest.CP0_Cause.DC or
+ * count_ctl.DC has been set (count disabled).
+ *
+ * Returns:	The time that the timer was stopped.
+ */
+static ktime_t kvm_mips_count_disable(struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	uint32_t count;
+	ktime_t now;
+
+	/* Stop hrtimer */
+	hrtimer_cancel(&vcpu->arch.comparecount_timer);
+
+	/* Set the static count from the dynamic count, handling pending TI */
+	now = ktime_get();
+	count = kvm_mips_read_count_running(vcpu, now);
+	kvm_write_c0_guest_count(cop0, count);
+
+	return now;
+}
+
+/**
+ * kvm_mips_count_disable_cause() - Disable count using CP0_Cause.DC.
+ * @vcpu:	Virtual CPU.
+ *
+ * Disable the CP0_Count timer and set CP0_Cause.DC. A timer interrupt on or
+ * before the final stop time will be handled if the timer isn't disabled by
+ * count_ctl.DC, but not after.
+ *
+ * Assumes CP0_Cause.DC is clear (count enabled).
+ */
+void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+
+	kvm_set_c0_guest_cause(cop0, CAUSEF_DC);
+	if (!(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC))
+		kvm_mips_count_disable(vcpu);
+}
+
+/**
+ * kvm_mips_count_enable_cause() - Enable count using CP0_Cause.DC.
+ * @vcpu:	Virtual CPU.
+ *
+ * Enable the CP0_Count timer and clear CP0_Cause.DC. A timer interrupt after
+ * the start time will be handled if the timer isn't disabled by count_ctl.DC,
+ * potentially before even returning, so the caller should be careful with
+ * ordering of CP0_Cause modifications so as not to lose it.
+ *
+ * Assumes CP0_Cause.DC is set (count disabled).
+ */
+void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	uint32_t count;
+
+	kvm_clear_c0_guest_cause(cop0, CAUSEF_DC);
+
+	/*
+	 * Set the dynamic count to match the static count.
+	 * This starts the hrtimer if count_ctl.DC allows it.
+	 * Otherwise it conveniently updates the biases.
+	 */
+	count = kvm_read_c0_guest_count(cop0);
+	kvm_mips_write_count(vcpu, count);
+}
+
+/**
+ * kvm_mips_set_count_ctl() - Update the count control KVM register.
+ * @vcpu:	Virtual CPU.
+ * @count_ctl:	Count control register new value.
+ *
+ * Set the count control KVM register. The timer is updated accordingly.
+ *
+ * Returns:	-EINVAL if reserved bits are set.
+ *		0 on success.
+ */
+int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	s64 changed = count_ctl ^ vcpu->arch.count_ctl;
+	s64 delta;
+	ktime_t expire, now;
+	uint32_t count, compare;
+
+	/* Only allow defined bits to be changed */
+	if (changed & ~(s64)(KVM_REG_MIPS_COUNT_CTL_DC))
+		return -EINVAL;
+
+	/* Apply new value */
+	vcpu->arch.count_ctl = count_ctl;
+
+	/* Master CP0_Count disable */
+	if (changed & KVM_REG_MIPS_COUNT_CTL_DC) {
+		/* Is CP0_Cause.DC already disabling CP0_Count? */
+		if (kvm_read_c0_guest_cause(cop0) & CAUSEF_DC) {
+			if (count_ctl & KVM_REG_MIPS_COUNT_CTL_DC)
+				/* Just record the current time */
+				vcpu->arch.count_resume = ktime_get();
+		} else if (count_ctl & KVM_REG_MIPS_COUNT_CTL_DC) {
+			/* disable timer and record current time */
+			vcpu->arch.count_resume = kvm_mips_count_disable(vcpu);
+		} else {
+			/*
+			 * Calculate timeout relative to static count at resume
+			 * time (wrap 0 to 2^32).
+			 */
+			count = kvm_read_c0_guest_count(cop0);
+			compare = kvm_read_c0_guest_compare(cop0);
+			delta = (u64)(uint32_t)(compare - count - 1) + 1;
+			delta = div_u64(delta * NSEC_PER_SEC,
+					vcpu->arch.count_hz);
+			expire = ktime_add_ns(vcpu->arch.count_resume, delta);
+
+			/* Handle pending interrupt */
+			now = ktime_get();
+			if (ktime_compare(now, expire) >= 0)
+				/* Nothing should be waiting on the timeout */
+				kvm_mips_callbacks->queue_timer_int(vcpu);
+
+			/* Resume hrtimer without changing bias */
+			count = kvm_mips_read_count_running(vcpu, now);
+			kvm_mips_resume_hrtimer(vcpu, now, count);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * kvm_mips_set_count_resume() - Update the count resume KVM register.
+ * @vcpu:		Virtual CPU.
+ * @count_resume:	Count resume register new value.
+ *
+ * Set the count resume KVM register.
+ *
+ * Returns:	-EINVAL if out of valid range (0..now).
+ *		0 on success.
+ */
+int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume)
+{
+	/*
+	 * It doesn't make sense for the resume time to be in the future, as it
+	 * would be possible for the next interrupt to be more than a full
+	 * period in the future.
+	 */
+	if (count_resume < 0 || count_resume > ktime_to_ns(ktime_get()))
+		return -EINVAL;
+
+	vcpu->arch.count_resume = ns_to_ktime(count_resume);
+	return 0;
+}
+
+/**
+ * kvm_mips_count_timeout() - Push timer forward on timeout.
+ * @vcpu:	Virtual CPU.
+ *
+ * Handle an hrtimer event by push the hrtimer forward a period.
+ *
+ * Returns:	The hrtimer_restart value to return to the hrtimer subsystem.
+ */
+enum hrtimer_restart kvm_mips_count_timeout(struct kvm_vcpu *vcpu)
+{
+	/* Add the Count period to the current expiry time */
+	hrtimer_add_expires_ns(&vcpu->arch.comparecount_timer,
+			       vcpu->arch.count_period);
+	return HRTIMER_RESTART;
 }
 
 enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
···
 #endif
 			/* Get reg */
 			if ((rd == MIPS_CP0_COUNT) && (sel == 0)) {
-				/* XXXKYMA: Run the Guest count register @ 1/4 the rate of the host */
-				vcpu->arch.gprs[rt] = (read_c0_count() >> 2);
+				vcpu->arch.gprs[rt] = kvm_mips_read_count(vcpu);
 			} else if ((rd == MIPS_CP0_ERRCTL) && (sel == 0)) {
 				vcpu->arch.gprs[rt] = 0x0;
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
···
 			}
 			/* Are we writing to COUNT */
 			else if ((rd == MIPS_CP0_COUNT) && (sel == 0)) {
-				/* Linux doesn't seem to write into COUNT, we throw an error
-				 * if we notice a write to COUNT
-				 */
-				/*er = EMULATE_FAIL; */
+				kvm_mips_write_count(vcpu, vcpu->arch.gprs[rt]);
 				goto done;
 			} else if ((rd == MIPS_CP0_COMPARE) && (sel == 0)) {
 				kvm_debug("[%#x] MTCz, COMPARE %#lx <- %#lx\n",
···
 				/* If we are writing to COMPARE */
 				/* Clear pending timer interrupt, if any */
 				kvm_mips_callbacks->dequeue_timer_int(vcpu);
-				kvm_write_c0_guest_compare(cop0,
-							   vcpu->arch.gprs[rt]);
+				kvm_mips_write_compare(vcpu,
+						       vcpu->arch.gprs[rt]);
 			} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
 				kvm_write_c0_guest_status(cop0,
 							  vcpu->arch.gprs[rt]);
···
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
 				kvm_mips_trans_mtc0(inst, opc, vcpu);
 #endif
+			} else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) {
+				uint32_t old_cause, new_cause;
+				old_cause = kvm_read_c0_guest_cause(cop0);
+				new_cause = vcpu->arch.gprs[rt];
+				/* Update R/W bits */
+				kvm_change_c0_guest_cause(cop0, 0x08800300,
+							  new_cause);
+				/* DC bit enabling/disabling timer? */
+				if ((old_cause ^ new_cause) & CAUSEF_DC) {
+					if (new_cause & CAUSEF_DC)
+						kvm_mips_count_disable_cause(vcpu);
+					else
+						kvm_mips_count_enable_cause(vcpu);
+				}
 			} else {
 				cop0->reg[rd][sel] = vcpu->arch.gprs[rt];
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
···
 
 	printk("%s: va: %#lx, unmapped: %#x\n", __func__, va, CKSEG0ADDR(pa));
 
-	mips32_SyncICache(CKSEG0ADDR(pa), 32);
+	local_flush_icache_range(CKSEG0ADDR(pa), 32);
 	return 0;
 }
 
···
 		       struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
-
 #ifdef DEBUG
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
+				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
+	int index;
+
 	/*
 	 * If address not in the guest TLB, then we are in trouble
 	 */
···
 					     current_cpu_data.icache.linesz);
 			break;
 		case 2:	/* Read count register */
-			printk("RDHWR: Cont register\n");
-			arch->gprs[rt] = kvm_read_c0_guest_count(cop0);
+			arch->gprs[rt] = kvm_mips_read_count(vcpu);
 			break;
 		case 3:	/* Count register resolution */
 			switch (current_cpu_data.cputype) {
···
 				er = EMULATE_FAIL;
 			}
 		} else {
-#ifdef DEBUG
 			kvm_debug
 			    ("Injecting hi: %#lx, lo0: %#lx, lo1: %#lx into shadow host TLB\n",
 			     tlb->tlb_hi, tlb->tlb_lo0, tlb->tlb_lo1);
-#endif
 			/* OK we have a Guest TLB entry, now inject it into the shadow host TLB */
 			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
 							     NULL);

arch/mips/kvm/kvm_tlb.c

···
 		return -1;
 	}
 
-	if (idx < 0) {
-		idx = read_c0_random() % current_cpu_data.tlbsize;
-		write_c0_index(idx);
-		mtc0_tlbw_hazard();
-	}
 	write_c0_entrylo0(entrylo0);
 	write_c0_entrylo1(entrylo1);
 	mtc0_tlbw_hazard();
 
-	tlb_write_indexed();
+	if (idx < 0)
+		tlb_write_random();
+	else
+		tlb_write_indexed();
 	tlbw_use_hazard();
 
-#ifdef DEBUG
-	if (debug) {
-		kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] "
-			  "entrylo0(R): 0x%08lx, entrylo1(R): 0x%08lx\n",
-			  vcpu->arch.pc, idx, read_c0_entryhi(),
-			  read_c0_entrylo0(), read_c0_entrylo1());
-	}
-#endif
+	kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0(R): 0x%08lx, entrylo1(R): 0x%08lx\n",
+		  vcpu->arch.pc, idx, read_c0_entryhi(),
+		  read_c0_entrylo0(), read_c0_entrylo1());
 
 	/* Flush D-cache */
 	if (flush_dcache_mask) {
···
 	mtc0_tlbw_hazard();
 	tlbw_use_hazard();
 
-#ifdef DEBUG
 	kvm_debug ("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0 (R): 0x%08lx, entrylo1(R): 0x%08lx\n",
 	     vcpu->arch.pc, read_c0_index(), read_c0_entryhi(),
 	     read_c0_entrylo0(), read_c0_entrylo1());
-#endif
 
 	/* Restore old ASID */
 	write_c0_entryhi(old_entryhi);
···
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
 			(tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
 
-#ifdef DEBUG
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo0, tlb->tlb_lo1);
-#endif
 
 	return kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
 				       tlb->tlb_mask);
···
 		}
 	}
 
-#ifdef DEBUG
 	kvm_debug("%s: entryhi: %#lx, index: %d lo0: %#lx, lo1: %#lx\n",
 		  __func__, entryhi, index, tlb[i].tlb_lo0, tlb[i].tlb_lo1);
-#endif
 
 	return index;
 }
···
 
 	local_irq_restore(flags);
 
-#ifdef DEBUG
 	kvm_debug("Host TLB lookup, %#lx, idx: %2d\n", vaddr, idx);
-#endif
 
 	return idx;
 }
···
 
 	local_irq_restore(flags);
 
-#ifdef DEBUG
-	if (idx > 0) {
+	if (idx > 0)
 		kvm_debug("%s: Invalidated entryhi %#lx @ idx %d\n", __func__,
-			  (va & VPN2_MASK) | (vcpu->arch.asid_map[va & ASID_MASK] & ASID_MASK), idx);
-	}
-#endif
+			  (va & VPN2_MASK) | kvm_mips_get_user_asid(vcpu), idx);
 
 	return 0;
 }
···
 	local_irq_restore(flags);
 }
 
+/**
+ * kvm_mips_migrate_count() - Migrate timer.
+ * @vcpu:	Virtual CPU.
+ *
+ * Migrate CP0_Count hrtimer to the current CPU by cancelling and restarting it
+ * if it was running prior to being cancelled.
+ *
+ * Must be called when the VCPU is migrated to a different CPU to ensure that
+ * timer expiry during guest execution interrupts the guest and causes the
+ * interrupt to be delivered in a timely manner.
+ */
+static void kvm_mips_migrate_count(struct kvm_vcpu *vcpu)
+{
+	if (hrtimer_cancel(&vcpu->arch.comparecount_timer))
+		hrtimer_restart(&vcpu->arch.comparecount_timer);
+}
+
 /* Restore ASID once we are scheduled back after preemption */
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	unsigned long flags;
 	int newasid = 0;
 
-#ifdef DEBUG
 	kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu);
-#endif
 
 	/* Alocate new kernel and user ASIDs if needed */
 
···
 		    vcpu->arch.guest_user_mm.context.asid[cpu];
 		newasid++;
 
-		kvm_info("[%d]: cpu_context: %#lx\n", cpu,
-			 cpu_context(cpu, current->mm));
-		kvm_info("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
-			 cpu, vcpu->arch.guest_kernel_asid[cpu]);
-		kvm_info("[%d]: Allocated new ASID for Guest User: %#x\n", cpu,
-			 vcpu->arch.guest_user_asid[cpu]);
+		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
+			  cpu_context(cpu, current->mm));
+		kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
+			  cpu, vcpu->arch.guest_kernel_asid[cpu]);
+		kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu,
+			  vcpu->arch.guest_user_asid[cpu]);
 	}
 
 	if (vcpu->arch.last_sched_cpu != cpu) {
-		kvm_info("[%d->%d]KVM VCPU[%d] switch\n",
-			 vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
+		kvm_debug("[%d->%d]KVM VCPU[%d] switch\n",
+			  vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
+		/*
+		 * Migrate the timer interrupt to the current CPU so that it
+		 * always interrupts the guest and synchronously triggers a
+		 * guest timer interrupt.
+		 */
+		kvm_mips_migrate_count(vcpu);
 	}
 
 	if (!newasid) {

arch/mips/kvm/kvm_trap_emul.c

···
 		gpa = KVM_INVALID_ADDR;
 	}
 
-#ifdef DEBUG
 	kvm_debug("%s: gva %#lx, gpa: %#llx\n", __func__, gva, gpa);
-#endif
 
 	return gpa;
 }
···
 
 	if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 	    || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-#ifdef DEBUG
 		kvm_debug
 		    ("USER/KSEG23 ADDR TLB MOD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
 		     cause, opc, badvaddr);
-#endif
 		er = kvm_mips_handle_tlbmod(cause, opc, run, vcpu);
 
 		if (er == EMULATE_DONE)
···
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 		   || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-#ifdef DEBUG
 		kvm_debug
 		    ("USER ADDR TLB LD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
 		     cause, opc, badvaddr);
-#endif
 		er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu);
 		if (er == EMULATE_DONE)
 			ret = RESUME_GUEST;
···
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 		   || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-#ifdef DEBUG
 		kvm_debug("USER ADDR TLB ST fault: PC: %#lx, BadVaddr: %#lx\n",
 			  vcpu->arch.pc, badvaddr);
-#endif
 
 		/* User Address (UA) fault, this could happen if
 		 * (1) TLB entry not present/valid in both Guest and shadow host TLBs, in this
···
 
 	if (KVM_GUEST_KERNEL_MODE(vcpu)
 	    && (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1)) {
-#ifdef DEBUG
 		kvm_debug("Emulate Store to MMIO space\n");
-#endif
 		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
 		if (er == EMULATE_FAIL) {
 			printk("Emulate Store to MMIO space failed\n");
···
 	int ret = RESUME_GUEST;
 
 	if (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1) {
-#ifdef DEBUG
 		kvm_debug("Emulate Load from MMIO space @ %#lx\n", badvaddr);
-#endif
 		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
 		if (er == EMULATE_FAIL) {
 			printk("Emulate Load from MMIO space failed\n");
···
 	return 0;
 }
 
+static int kvm_trap_emul_get_one_reg(struct kvm_vcpu *vcpu,
+				     const struct kvm_one_reg *reg,
+				     s64 *v)
+{
+	switch (reg->id) {
+	case KVM_REG_MIPS_CP0_COUNT:
+		*v = kvm_mips_read_count(vcpu);
+		break;
+	case KVM_REG_MIPS_COUNT_CTL:
+		*v = vcpu->arch.count_ctl;
+		break;
+	case KVM_REG_MIPS_COUNT_RESUME:
+		*v = ktime_to_ns(vcpu->arch.count_resume);
+		break;
+	case KVM_REG_MIPS_COUNT_HZ:
+		*v = vcpu->arch.count_hz;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu,
+				     const struct kvm_one_reg *reg,
+				     s64 v)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int ret = 0;
+
+	switch (reg->id) {
+	case KVM_REG_MIPS_CP0_COUNT:
+		kvm_mips_write_count(vcpu, v);
+		break;
+	case KVM_REG_MIPS_CP0_COMPARE:
+		kvm_mips_write_compare(vcpu, v);
+		break;
+	case KVM_REG_MIPS_CP0_CAUSE:
+		/*
+		 * If the timer is stopped or started (DC bit) it must look
+		 * atomic with changes to the interrupt pending bits (TI, IRQ5).
+		 * A timer interrupt should not happen in between.
+		 */
+		if ((kvm_read_c0_guest_cause(cop0) ^ v) & CAUSEF_DC) {
+			if (v & CAUSEF_DC) {
+				/* disable timer first */
+				kvm_mips_count_disable_cause(vcpu);
+				kvm_change_c0_guest_cause(cop0, ~CAUSEF_DC, v);
+			} else {
+				/* enable timer last */
+				kvm_change_c0_guest_cause(cop0, ~CAUSEF_DC, v);
+				kvm_mips_count_enable_cause(vcpu);
+			}
+		} else {
+			kvm_write_c0_guest_cause(cop0, v);
+		}
+		break;
+	case KVM_REG_MIPS_COUNT_CTL:
+		ret = kvm_mips_set_count_ctl(vcpu, v);
+		break;
+	case KVM_REG_MIPS_COUNT_RESUME:
+		ret = kvm_mips_set_count_resume(vcpu, v);
+		break;
+	case KVM_REG_MIPS_COUNT_HZ:
+		ret = kvm_mips_set_count_hz(vcpu, v);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return ret;
+}
+
 static struct kvm_mips_callbacks kvm_trap_emul_callbacks = {
 	/* exit handlers */
 	.handle_cop_unusable = kvm_trap_emul_handle_cop_unusable,
···
 	.dequeue_io_int = kvm_mips_dequeue_io_int_cb,
 	.irq_deliver = kvm_mips_irq_deliver_cb,
 	.irq_clear = kvm_mips_irq_clear_cb,
+	.get_one_reg = kvm_trap_emul_get_one_reg,
+	.set_one_reg = kvm_trap_emul_set_one_reg,
 };
 
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks)

arch/mips/mm/cache.c

···
 void (*flush_icache_range)(unsigned long start, unsigned long end);
 EXPORT_SYMBOL_GPL(flush_icache_range);
 void (*local_flush_icache_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(local_flush_icache_range);
 
 void (*__flush_cache_vmap)(void);
 void (*__flush_cache_vunmap)(void);

arch/mips/mti-malta/malta-time.c

···
 	unsigned int giccount = 0, gicstart = 0;
 #endif
 
-#if defined (CONFIG_KVM_GUEST) && defined (CONFIG_KVM_HOST_FREQ)
-	unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
-
-	/*
-	 * XXXKYMA: hardwire the CPU frequency to Host Freq/4
-	 */
-	count = (CONFIG_KVM_HOST_FREQ * 1000000) >> 3;
-	if ((prid != (PRID_COMP_MIPS | PRID_IMP_20KC)) &&
-	    (prid != (PRID_COMP_MIPS | PRID_IMP_25KF)))
-		count *= 2;
-
-	mips_hpt_frequency = count;
+#if defined(CONFIG_KVM_GUEST) && CONFIG_KVM_GUEST_TIMER_FREQ
+	mips_hpt_frequency = CONFIG_KVM_GUEST_TIMER_FREQ * 1000000;
 	return;
 #endif
 

arch/powerpc/include/asm/disassemble.h

···
 {
 	return (inst >> 11) & 0x7fff;
 }
+
+#define IS_XFORM(inst)	(get_op(inst)  == 31)
+#define IS_DSFORM(inst)	(get_op(inst) >= 56)
+
+/*
+ * Create a DSISR value from the instruction
+ */
+static inline unsigned make_dsisr(unsigned instr)
+{
+	unsigned dsisr;
+
+
+	/* bits  6:15 --> 22:31 */
+	dsisr = (instr & 0x03ff0000) >> 16;
+
+	if (IS_XFORM(instr)) {
+		/* bits 29:30 --> 15:16 */
+		dsisr |= (instr & 0x00000006) << 14;
+		/* bit     25 -->    17 */
+		dsisr |= (instr & 0x00000040) << 8;
+		/* bits 21:24 --> 18:21 */
+		dsisr |= (instr & 0x00000780) << 3;
+	} else {
+		/* bit      5 -->    17 */
+		dsisr |= (instr & 0x04000000) >> 12;
+		/* bits  1: 4 --> 18:21 */
+		dsisr |= (instr & 0x78000000) >> 17;
+		/* bits 30:31 --> 12:13 */
+		if (IS_DSFORM(instr))
+			dsisr |= (instr & 0x00000003) << 18;
+	}
+
+	return dsisr;
+}
 #endif /* __ASM_PPC_DISASSEMBLE_H__ */

arch/powerpc/include/asm/kvm_asm.h

···
 #define BOOK3S_INTERRUPT_PERFMON	0xf00
 #define BOOK3S_INTERRUPT_ALTIVEC	0xf20
 #define BOOK3S_INTERRUPT_VSX		0xf40
+#define BOOK3S_INTERRUPT_FAC_UNAVAIL	0xf60
 #define BOOK3S_INTERRUPT_H_FAC_UNAVAIL	0xf80
 
 #define BOOK3S_IRQPRIO_SYSTEM_RESET		0
···
 #define BOOK3S_IRQPRIO_FP_UNAVAIL		7
 #define BOOK3S_IRQPRIO_ALTIVEC			8
 #define BOOK3S_IRQPRIO_VSX			9
-#define BOOK3S_IRQPRIO_SYSCALL			10
-#define BOOK3S_IRQPRIO_MACHINE_CHECK		11
-#define BOOK3S_IRQPRIO_DEBUG			12
-#define BOOK3S_IRQPRIO_EXTERNAL			13
-#define BOOK3S_IRQPRIO_DECREMENTER		14
-#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	15
-#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		16
-#define BOOK3S_IRQPRIO_MAX			17
+#define BOOK3S_IRQPRIO_FAC_UNAVAIL		10
+#define BOOK3S_IRQPRIO_SYSCALL			11
+#define BOOK3S_IRQPRIO_MACHINE_CHECK		12
+#define BOOK3S_IRQPRIO_DEBUG			13
+#define BOOK3S_IRQPRIO_EXTERNAL			14
+#define BOOK3S_IRQPRIO_DECREMENTER		15
+#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	16
+#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		17
+#define BOOK3S_IRQPRIO_MAX			18
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2

arch/powerpc/include/asm/kvm_book3s.h

···
 	return vcpu->arch.pc;
 }
 
+static inline u64 kvmppc_get_msr(struct kvm_vcpu *vcpu);
 static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
 {
-	return (vcpu->arch.shared->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
+	return (kvmppc_get_msr(vcpu) & MSR_LE) != (MSR_KERNEL & MSR_LE);
 }
 
 static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc)

arch/powerpc/include/asm/kvm_book3s_64.h

···
 	return old == 0;
 }
 
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		>=8KB
+		 *    rrrr rrzz		>=16KB
+		 *    rrrr rzzz		>=32KB
+		 *    rrrr zzzz		>=64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
+}
+
 static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 					     unsigned long pte_index)
 {
-	unsigned long rb, va_low;
+	int b_psize, a_psize;
+	unsigned int penc;
+	unsigned long rb = 0, va_low, sllp;
+	unsigned int lp = (r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
 
+	if (!(v & HPTE_V_LARGE)) {
+		/* both base and actual psize is 4k */
+		b_psize = MMU_PAGE_4K;
+		a_psize = MMU_PAGE_4K;
+	} else {
+		for (b_psize = 0; b_psize < MMU_PAGE_COUNT; b_psize++) {
+
+			/* valid entries have a shift value */
+			if (!mmu_psize_defs[b_psize].shift)
+				continue;
+
+			a_psize = __hpte_actual_psize(lp, b_psize);
+			if (a_psize != -1)
+				break;
+		}
+	}
+	/*
+	 * Ignore the top 14 bits of va
+	 * v have top two bits covering segment size, hence move
+	 * by 16 bits, Also clear the lower HPTE_V_AVPN_SHIFT (7) bits.
+	 * AVA field in v also have the lower 23 bits ignored.
+	 * For base page size 4K we need 14 .. 65 bits (so need to
+	 * collect extra 11 bits)
+	 * For others we need 14..14+i
+	 */
+	/* This covers 14..54 bits of va*/
 	rb = (v & ~0x7fUL) << 16;		/* AVA field */
+	/*
+	 * AVA in v had cleared lower 23 bits. We need to derive
+	 * that from pteg index
+	 */
 	va_low = pte_index >> 3;
 	if (v & HPTE_V_SECONDARY)
 		va_low = ~va_low;
-	/* xor vsid from AVA */
+	/*
+	 * get the vpn bits from va_low using reverse of hashing.
+	 * In v we have va with 23 bits dropped and then left shifted
+	 * HPTE_V_AVPN_SHIFT (7) bits. Now to find vsid we need
+	 * right shift it with (SID_SHIFT - (23 - 7))
+	 */
 	if (!(v & HPTE_V_1TB_SEG))
-		va_low ^= v >> 12;
+		va_low ^= v >> (SID_SHIFT - 16);
 	else
-		va_low ^= v >> 24;
+		va_low ^= v >> (SID_SHIFT_1T - 16);
 	va_low &= 0x7ff;
-	if (v & HPTE_V_LARGE) {
-		rb |= 1;			/* L field */
-		if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-		    (r & 0xff000)) {
-			/* non-16MB large page, must be 64k */
-			/* (masks depend on page size) */
-			rb |= 0x1000;		/* page encoding in LP field */
-			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-			rb |= ((va_low << 4) & 0xf0);	/* AVAL field (P7 doesn't seem to care) */
-		}
-	} else {
-		/* 4kB page */
-		rb |= (va_low & 0x7ff) << 12;	/* remaining 11b of VA */
+
+	switch (b_psize) {
+	case MMU_PAGE_4K:
+		sllp = ((mmu_psize_defs[a_psize].sllp & SLB_VSID_L) >> 6) |
+			((mmu_psize_defs[a_psize].sllp & SLB_VSID_LP) >> 4);
+		rb |= sllp << 5;	/*  AP field */
+		rb |= (va_low & 0x7ff) << 12;	/* remaining 11 bits of AVA */
+		break;
+	default:
+	{
+		int aval_shift;
+		/*
+		 * remaining 7bits of AVA/LP fields
+		 * Also contain the rr bits of LP
+		 */
+		rb |= (va_low & 0x7f) << 16;
+		/*
+		 * Now clear not needed LP bits based on actual psize
+		 */
+		rb &= ~((1ul << mmu_psize_defs[a_psize].shift) - 1);
+		/*
+		 * AVAL field 58..77 - base_page_shift bits of va
+		 * we have space for 58..64 bits, Missing bits should
+		 * be zero filled. +1 is to take care of L bit shift
+		 */
+		aval_shift = 64 - (77 - mmu_psize_defs[b_psize].shift) + 1;
+		rb |= ((va_low << aval_shift) & 0xfe);
+
+		rb |= 1;		/* L field */
+		penc = mmu_psize_defs[b_psize].penc[a_psize];
+		rb |= penc << 12;	/* LP field */
+		break;
+	}
 	}
 	rb |= (v >> 54) & 0x300;		/* B field */
 	return rb;
···
 
 static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 {
+	int size, a_psize;
+	/* Look at the 8 bit LP value */
+	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+
 	/* only handle 4k, 64k and 16M pages for now */
 	if (!(h & HPTE_V_LARGE))
-		return 1ul << 12;		/* 4k page */
-	if ((l & 0xf000) == 0x1000 && cpu_has_feature(CPU_FTR_ARCH_206))
-		return 1ul << 16;		/* 64k page */
-	if ((l & 0xff000) == 0)
-		return 1ul << 24;		/* 16M page */
-	return 0;				/* error */
+		return 1ul << 12;
+	else {
+		for (size = 0; size < MMU_PAGE_COUNT; size++) {
+			/* valid entries have a shift value */
+			if (!mmu_psize_defs[size].shift)
+				continue;
+
+			a_psize = __hpte_actual_psize(lp, size);
+			if (a_psize != -1)
+				return 1ul << mmu_psize_defs[a_psize].shift;
+		}
+
+	}
+	return 0;
 }
 
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)

arch/powerpc/include/asm/kvm_book3s_asm.h

···
 #ifdef CONFIG_PPC_BOOK3S_64
 	u64 cfar;
 	u64 ppr;
+	u64 host_fscr;
 #endif
 };
 
···
 		u64     esid;
 		u64     vsid;
 	} slb[64];			/* guest SLB */
+	u64 shadow_fscr;
 #endif
 };
 

arch/powerpc/include/asm/kvm_booke.h

···
 {
 	return vcpu->arch.fault_dear;
 }
-
-static inline ulong kvmppc_get_msr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.shared->msr;
-}
 #endif /* __ASM_KVM_BOOKE_H__ */

arch/powerpc/include/asm/kvm_host.h

···
 	ulong pc;
 	ulong ctr;
 	ulong lr;
+#ifdef CONFIG_PPC_BOOK3S
 	ulong tar;
+#endif
 
 	ulong xer;
 	u32 cr;
···
 	ulong ppr;
 	ulong pspb;
 	ulong fscr;
+	ulong shadow_fscr;
 	ulong ebbhr;
 	ulong ebbrr;
 	ulong bescr;
···
 #ifdef CONFIG_PPC_BOOK3S
 	ulong fault_dar;
 	u32 fault_dsisr;
+	unsigned long intr_msr;
 #endif
 
 #ifdef CONFIG_BOOKE
···
 	wait_queue_head_t cpu_run;
 
 	struct kvm_vcpu_arch_shared *shared;
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+	bool shared_big_endian;
+#endif
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */
 	unsigned long magic_page_ea; /* effect. addr to map the magic page to */
+	bool disable_kernel_nx;
 
 	int irq_type;		/* one of KVM_IRQ_* */
 	int irq_cpu_id;
···
 	spinlock_t tbacct_lock;
 	u64 busy_stolen;
 	u64 busy_preempt;
-	unsigned long intr_msr;
 #endif
 };
 

arch/powerpc/include/asm/kvm_ppc.h

···
 }
 
 /*
+ * Shared struct helpers. The shared struct can be little or big endian,
+ * depending on the guest endianness. So expose helpers to all of them.
+ */
+static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+	/* Only Book3S_64 PR supports bi-endian for now */
+	return vcpu->arch.shared_big_endian;
+#elif defined(CONFIG_PPC_BOOK3S_64) && defined(__LITTLE_ENDIAN__)
+	/* Book3s_64 HV on little endian is always little endian */
+	return false;
+#else
+	return true;
+#endif
+}
+
+#define SHARED_WRAPPER_GET(reg, size)					\
+static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)	\
+{									\
+	if (kvmppc_shared_big_endian(vcpu))				\
+	       return be##size##_to_cpu(vcpu->arch.shared->reg);	\
+	else								\
+	       return le##size##_to_cpu(vcpu->arch.shared->reg);	\
+}									\
+
+#define SHARED_WRAPPER_SET(reg, size)					\
+static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
+{									\
+	if (kvmppc_shared_big_endian(vcpu))				\
+	       vcpu->arch.shared->reg = cpu_to_be##size(val);		\
+	else								\
+	       vcpu->arch.shared->reg = cpu_to_le##size(val);		\
+}									\
+
+#define SHARED_WRAPPER(reg, size)					\
+	SHARED_WRAPPER_GET(reg, size)					\
+	SHARED_WRAPPER_SET(reg, size)					\
+
+SHARED_WRAPPER(critical, 64)
+SHARED_WRAPPER(sprg0, 64)
+SHARED_WRAPPER(sprg1, 64)
+SHARED_WRAPPER(sprg2, 64)
+SHARED_WRAPPER(sprg3, 64)
+SHARED_WRAPPER(srr0, 64)
+SHARED_WRAPPER(srr1, 64)
+SHARED_WRAPPER(dar, 64)
+SHARED_WRAPPER_GET(msr, 64)
+static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val)
+{
+	if (kvmppc_shared_big_endian(vcpu))
+	       vcpu->arch.shared->msr = cpu_to_be64(val);
+	else
+	       vcpu->arch.shared->msr = cpu_to_le64(val);
+}
+SHARED_WRAPPER(dsisr, 32)
+SHARED_WRAPPER(int_pending, 32)
+SHARED_WRAPPER(sprg4, 64)
+SHARED_WRAPPER(sprg5, 64)
+SHARED_WRAPPER(sprg6, 64)
+SHARED_WRAPPER(sprg7, 64)
+
+static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr)
+{
+	if (kvmppc_shared_big_endian(vcpu))
+	       return be32_to_cpu(vcpu->arch.shared->sr[nr]);
+	else
+	       return le32_to_cpu(vcpu->arch.shared->sr[nr]);
+}
+
+static inline void kvmppc_set_sr(struct kvm_vcpu *vcpu, int nr, u32 val)
+{
+	if (kvmppc_shared_big_endian(vcpu))
+	       vcpu->arch.shared->sr[nr] = cpu_to_be32(val);
+	else
+	       vcpu->arch.shared->sr[nr] = cpu_to_le32(val);
+}
+
+/*
  * Please call after prepare_to_enter. This function puts the lazy ee and irq
  * disabled tracking state back to normal mode, without actually enabling
  * interrupts.
···
 	msr_64bit = MSR_SF;
 #endif
 
-	if (!(vcpu->arch.shared->msr & msr_64bit))
+	if (!(kvmppc_get_msr(vcpu) & msr_64bit))
 		ea = (uint32_t)ea;
 
 	return ea;

arch/powerpc/include/asm/reg.h

···
 #define   MMCR0_PROBLEM_DISABLE MMCR0_FCP
 #define   MMCR0_FCM1	0x10000000UL /* freeze counters while MSR mark = 1 */
 #define   MMCR0_FCM0	0x08000000UL /* freeze counters while MSR mark = 0 */
-#define   MMCR0_PMXE	0x04000000UL /* performance monitor exception enable */
-#define   MMCR0_FCECE	0x02000000UL /* freeze ctrs on enabled cond or event */
+#define   MMCR0_PMXE	ASM_CONST(0x04000000) /* perf mon exception enable */
+#define   MMCR0_FCECE	ASM_CONST(0x02000000) /* freeze ctrs on enabled cond or event */
 #define   MMCR0_TBEE	0x00400000UL /* time base exception enable */
 #define   MMCR0_BHRBA	0x00200000UL /* BHRB Access allowed in userspace */
 #define   MMCR0_EBE	0x00100000UL /* Event based branch enable */
 #define   MMCR0_PMCC	0x000c0000UL /* PMC control */
 #define   MMCR0_PMCC_U6	0x00080000UL /* PMC1-6 are R/W by user (PR) */
 #define   MMCR0_PMC1CE	0x00008000UL /* PMC1 count enable*/
-#define   MMCR0_PMCjCE	0x00004000UL /* PMCj count enable*/
+#define   MMCR0_PMCjCE	ASM_CONST(0x00004000) /* PMCj count enable*/
 #define   MMCR0_TRIGGER	0x00002000UL /* TRIGGER enable */
-#define   MMCR0_PMAO_SYNC 0x00000800UL /* PMU interrupt is synchronous */
-#define   MMCR0_PMAO	0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
+#define   MMCR0_PMAO_SYNC ASM_CONST(0x00000800) /* PMU intr is synchronous */
+#define   MMCR0_C56RUN	ASM_CONST(0x00000100) /* PMC5/6 count when RUN=0 */
+/* performance monitor alert has occurred, set to 0 after handling exception */
+#define   MMCR0_PMAO	ASM_CONST(0x00000080)
 #define   MMCR0_SHRFC	0x00000040UL /* SHRre freeze conditions between threads */
 #define   MMCR0_FC56	0x00000010UL /* freeze counters 5 and 6 */
 #define   MMCR0_FCTI	0x00000008UL /* freeze counters in tags inactive mode */

arch/powerpc/include/asm/reg_booke.h

···
 
 /* Bit definitions for L1CSR0. */
 #define L1CSR0_CPE	0x00010000	/* Data Cache Parity Enable */
+#define L1CSR0_CUL	0x00000400	/* Data Cache Unable to Lock */
 #define L1CSR0_CLFC	0x00000100	/* Cache Lock Bits Flash Clear */
 #define L1CSR0_DCFI	0x00000002	/* Data Cache Flash Invalidate */
 #define L1CSR0_CFI	0x00000002	/* Cache Flash Invalidate */

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

···
 #define KVM_REG_PPC_TCSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
 #define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
-#define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb4)
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
···
 #define KVM_REG_PPC_ARCH_COMPAT	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
 
 #define KVM_REG_PPC_DABRX	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8)
+#define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs

arch/powerpc/include/uapi/asm/kvm_para.h

···
 
 #define KVM_FEATURE_MAGIC_PAGE	1
 
+/* Magic page flags from host to guest */
+
 #define KVM_MAGIC_FEAT_SR		(1 << 0)
 
 /* MASn, ESR, PIR, and high SPRGs */
 #define KVM_MAGIC_FEAT_MAS0_TO_SPRG7	(1 << 1)
+
+/* Magic page flags from guest to host */
+
+#define MAGIC_PAGE_FLAG_NOT_MAPPED_NX	(1 << 0)
 
 
 #endif /* _UAPI__POWERPC_KVM_PARA_H__ */

arch/powerpc/kernel/align.c

···
 #include <asm/cputable.h>
 #include <asm/emulated_ops.h>
 #include <asm/switch_to.h>
+#include <asm/disassemble.h>
 
 struct aligninfo {
 	unsigned char len;
 	unsigned char flags;
 };
 
-#define IS_XFORM(inst)	(((inst) >> 26) == 31)
-#define IS_DSFORM(inst)	(((inst) >> 26) >= 56)
 
 #define INVALID	{ 0, 0 }
 
···
 	INVALID,		/* 11 1 1110 */
 	INVALID,		/* 11 1 1111 */
 };
-
-/*
- * Create a DSISR value from the instruction
- */
-static inline unsigned make_dsisr(unsigned instr)
-{
-	unsigned dsisr;
-
-
-	/* bits  6:15 --> 22:31 */
-	dsisr = (instr & 0x03ff0000) >> 16;
-
-	if (IS_XFORM(instr)) {
-		/* bits 29:30 --> 15:16 */
-		dsisr |= (instr & 0x00000006) << 14;
-		/* bit     25 -->    17 */
-		dsisr |= (instr & 0x00000040) << 8;
-		/* bits 21:24 --> 18:21 */
-		dsisr |= (instr & 0x00000780) << 3;
-	} else {
-		/* bit      5 -->    17 */
-		dsisr |= (instr & 0x04000000) >> 12;
-		/* bits  1: 4 --> 18:21 */
-		dsisr |= (instr & 0x78000000) >> 17;
-		/* bits 30:31 --> 12:13 */
-		if (IS_DSFORM(instr))
-			dsisr |= (instr & 0x00000003) << 18;
-	}
-
-	return dsisr;
-}
 
 /*
  * The dcbz (data cache block zero) instruction

arch/powerpc/kernel/asm-offsets.c

···
 #endif
 #if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
 #include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
 #endif
 
 #ifdef CONFIG_PPC32
···
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+#ifdef CONFIG_PPC_BOOK3S
 	DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar));
+#endif
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
···
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+	DEFINE(VCPU_SHAREDBE, offsetof(struct kvm_vcpu, arch.shared_big_endian));
+#endif
 
 	DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0));
 	DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1));
···
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
 	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
 	DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
-	DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr));
 #endif
 #ifdef CONFIG_PPC_BOOK3S
 	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
···
 	DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
 	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
 	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
+	DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr));
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
 	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
 	DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
+	DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr));
 	DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
 	DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
 	DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
···
 #ifdef CONFIG_PPC64
 	SVCPU_FIELD(SVCPU_SLB, slb);
 	SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
+	SVCPU_FIELD(SVCPU_SHADOW_FSCR, shadow_fscr);
 #endif
 
 	HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
···
 #ifdef CONFIG_PPC_BOOK3S_64
 	HSTATE_FIELD(HSTATE_CFAR, cfar);
 	HSTATE_FIELD(HSTATE_PPR, ppr);
+	HSTATE_FIELD(HSTATE_HOST_FSCR, host_fscr);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #else /* CONFIG_PPC_BOOK3S */

arch/powerpc/kernel/epapr_paravirt.c

···
 		return -1;
 
 	for (i = 0; i < (len / 4); i++) {
-		patch_instruction(epapr_hypercall_start + i, insts[i]);
+		u32 inst = be32_to_cpu(insts[i]);
+		patch_instruction(epapr_hypercall_start + i, inst);
 #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
-		patch_instruction(epapr_ev_idle_start + i, insts[i]);
+		patch_instruction(epapr_ev_idle_start + i, inst);
 #endif
 	}
 

arch/powerpc/kernel/kvm.c

···
 	ulong out[8];
 
 	in[0] = KVM_MAGIC_PAGE;
-	in[1] = KVM_MAGIC_PAGE;
+	in[1] = KVM_MAGIC_PAGE | MAGIC_PAGE_FLAG_NOT_MAPPED_NX;
 
 	epapr_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE));
 

arch/powerpc/kernel/paca.c

···
 /*
  * 3 persistent SLBs are registered here.  The buffer will be zero
  * initially, hence will all be invaild until we actually write them.
+ *
+ * If you make the number of persistent SLB entries dynamic, please also
+ * update PR KVM to flush and restore them accordingly.
  */
 static struct slb_shadow *slb_shadow;
 

arch/powerpc/kvm/Kconfig

···
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
-	depends on !CPU_LITTLE_ENDIAN
 	---help---
 	  Say Y here to get to see options for using your Linux host to run
 	  other operating systems inside virtual machines (guests).
···
 config KVM_BOOK3S_64_HV
 	tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	depends on !CPU_LITTLE_ENDIAN
 	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
 	select CMA

arch/powerpc/kvm/book3s.c

···
 	if (is_kvmppc_hv_enabled(vcpu->kvm))
 		return;
 	if (pending_now)
-		vcpu->arch.shared->int_pending = 1;
+		kvmppc_set_int_pending(vcpu, 1);
 	else if (old_pending)
-		vcpu->arch.shared->int_pending = 0;
+		kvmppc_set_int_pending(vcpu, 0);
 }
 
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
···
 	if (is_kvmppc_hv_enabled(vcpu->kvm))
 		return false;
 
-	crit_raw = vcpu->arch.shared->critical;
+	crit_raw = kvmppc_get_critical(vcpu);
 	crit_r1 = kvmppc_get_gpr(vcpu, 1);
 
 	/* Truncate crit indicators in 32 bit mode */
-	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+	if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
 		crit_raw &= 0xffffffff;
 		crit_r1 &= 0xffffffff;
 	}
···
 	/* Critical section when crit == r1 */
 	crit = (crit_raw == crit_r1);
 	/* ... and we're in supervisor mode */
-	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
+	crit = crit && !(kvmppc_get_msr(vcpu) & MSR_PR);
 
 	return crit;
 }
 
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
-	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
-	vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags;
+	kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
+	kvmppc_set_srr1(vcpu, kvmppc_get_msr(vcpu) | flags);
 	kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
···
 	case 0xd00: prio = BOOK3S_IRQPRIO_DEBUG;		break;
 	case 0xf20: prio = BOOK3S_IRQPRIO_ALTIVEC;		break;
 	case 0xf40: prio = BOOK3S_IRQPRIO_VSX;			break;
+	case 0xf60: prio = BOOK3S_IRQPRIO_FAC_UNAVAIL;		break;
 	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
 	}
 
···
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
+		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
 	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
-		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
+		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
···
 		break;
 	case BOOK3S_IRQPRIO_PERFORMANCE_MONITOR:
 		vec = BOOK3S_INTERRUPT_PERFMON;
+		break;
+	case BOOK3S_IRQPRIO_FAC_UNAVAIL:
+		vec = BOOK3S_INTERRUPT_FAC_UNAVAIL;
 		break;
 	default:
 		deliver = 0;
···
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
-	if (!(vcpu->arch.shared->msr & MSR_SF))
+	if (!(kvmppc_get_msr(vcpu) & MSR_SF))
 		mp_pa = (uint32_t)mp_pa;
 
 	/* Magic page override */
···
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 			bool iswrite, struct kvmppc_pte *pte)
 {
-	int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
+	int relocated = (kvmppc_get_msr(vcpu) & (data ? MSR_DR : MSR_IR));
 	int r;
 
 	if (relocated) {
···
 	regs->ctr = kvmppc_get_ctr(vcpu);
 	regs->lr = kvmppc_get_lr(vcpu);
 	regs->xer = kvmppc_get_xer(vcpu);
-	regs->msr = vcpu->arch.shared->msr;
-	regs->srr0 = vcpu->arch.shared->srr0;
-	regs->srr1 = vcpu->arch.shared->srr1;
+	regs->msr = kvmppc_get_msr(vcpu);
+	regs->srr0 = kvmppc_get_srr0(vcpu);
+	regs->srr1 = kvmppc_get_srr1(vcpu);
 	regs->pid = vcpu->arch.pid;
-	regs->sprg0 = vcpu->arch.shared->sprg0;
-	regs->sprg1 = vcpu->arch.shared->sprg1;
-	regs->sprg2 = vcpu->arch.shared->sprg2;
-	regs->sprg3 = vcpu->arch.shared->sprg3;
-	regs->sprg4 = vcpu->arch.shared->sprg4;
-	regs->sprg5 = vcpu->arch.shared->sprg5;
-	regs->sprg6 = vcpu->arch.shared->sprg6;
-	regs->sprg7 = vcpu->arch.shared->sprg7;
+	regs->sprg0 = kvmppc_get_sprg0(vcpu);
+	regs->sprg1 = kvmppc_get_sprg1(vcpu);
+	regs->sprg2 = kvmppc_get_sprg2(vcpu);
+	regs->sprg3 = kvmppc_get_sprg3(vcpu);
+	regs->sprg4 = kvmppc_get_sprg4(vcpu);
+	regs->sprg5 = kvmppc_get_sprg5(vcpu);
+	regs->sprg6 = kvmppc_get_sprg6(vcpu);
+	regs->sprg7 = kvmppc_get_sprg7(vcpu);
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
···
 	kvmppc_set_lr(vcpu, regs->lr);
 	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
-	vcpu->arch.shared->srr0 = regs->srr0;
-	vcpu->arch.shared->srr1 = regs->srr1;
-	vcpu->arch.shared->sprg0 = regs->sprg0;
-	vcpu->arch.shared->sprg1 = regs->sprg1;
-	vcpu->arch.shared->sprg2 = regs->sprg2;
-	vcpu->arch.shared->sprg3 = regs->sprg3;
-	vcpu->arch.shared->sprg4 = regs->sprg4;
-	vcpu->arch.shared->sprg5 = regs->sprg5;
-	vcpu->arch.shared->sprg6 = regs->sprg6;
-	vcpu->arch.shared->sprg7 = regs->sprg7;
+	kvmppc_set_srr0(vcpu, regs->srr0);
+	kvmppc_set_srr1(vcpu, regs->srr1);
+	kvmppc_set_sprg0(vcpu, regs->sprg0);
+	kvmppc_set_sprg1(vcpu, regs->sprg1);
+	kvmppc_set_sprg2(vcpu, regs->sprg2);
+	kvmppc_set_sprg3(vcpu, regs->sprg3);
+	kvmppc_set_sprg4(vcpu, regs->sprg4);
+	kvmppc_set_sprg5(vcpu, regs->sprg5);
+	kvmppc_set_sprg6(vcpu, regs->sprg6);
+	kvmppc_set_sprg7(vcpu, regs->sprg7);
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
···
 		r = 0;
 		switch (reg->id) {
 		case KVM_REG_PPC_DAR:
-			val = get_reg_val(reg->id, vcpu->arch.shared->dar);
+			val = get_reg_val(reg->id, kvmppc_get_dar(vcpu));
 			break;
 		case KVM_REG_PPC_DSISR:
-			val = get_reg_val(reg->id, vcpu->arch.shared->dsisr);
+			val = get_reg_val(reg->id, kvmppc_get_dsisr(vcpu));
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = reg->id - KVM_REG_PPC_FPR0;
···
 			val = get_reg_val(reg->id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
+		case KVM_REG_PPC_FSCR:
+			val = get_reg_val(reg->id, vcpu->arch.fscr);
+			break;
+		case KVM_REG_PPC_TAR:
+			val = get_reg_val(reg->id, vcpu->arch.tar);
+			break;
+		case KVM_REG_PPC_EBBHR:
+			val = get_reg_val(reg->id, vcpu->arch.ebbhr);
+			break;
+		case KVM_REG_PPC_EBBRR:
+			val = get_reg_val(reg->id, vcpu->arch.ebbrr);
+			break;
+		case KVM_REG_PPC_BESCR:
+			val = get_reg_val(reg->id, vcpu->arch.bescr);
+			break;
 		default:
 			r = -EINVAL;
 			break;
···
 		r = 0;
 		switch (reg->id) {
 		case KVM_REG_PPC_DAR:
-			vcpu->arch.shared->dar = set_reg_val(reg->id, val);
+			kvmppc_set_dar(vcpu, set_reg_val(reg->id, val));
 			break;
 		case KVM_REG_PPC_DSISR:
-			vcpu->arch.shared->dsisr = set_reg_val(reg->id, val);
+			kvmppc_set_dsisr(vcpu, set_reg_val(reg->id, val));
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = reg->id - KVM_REG_PPC_FPR0;
···
 						set_reg_val(reg->id, val));
 			break;
 #endif /* CONFIG_KVM_XICS */
+		case KVM_REG_PPC_FSCR:
+			vcpu->arch.fscr = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_TAR:
+			vcpu->arch.tar = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_EBBHR:
+			vcpu->arch.ebbhr = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_EBBRR:
+			vcpu->arch.ebbrr = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_BESCR:
+			vcpu->arch.bescr = set_reg_val(reg->id, val);
+			break;
 		default:
 			r = -EINVAL;
 			break;

arch/powerpc/kvm/book3s_32_mmu.c

···
 
 static u32 find_sr(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	return vcpu->arch.shared->sr[(eaddr >> 28) & 0xf];
+	return kvmppc_get_sr(vcpu, (eaddr >> 28) & 0xf);
 }
 
 static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
···
 	pteg = (vcpu_book3s->sdr1 & 0xffff0000) | hash;
 
 	dprintk("MMU: pc=0x%lx eaddr=0x%lx sdr1=0x%llx pteg=0x%x vsid=0x%x\n",
-		kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
+		kvmppc_get_pc(vcpu), eaddr, vcpu_book3s->sdr1, pteg,
 		sr_vsid(sre));
 
 	r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT);
···
 		else
 			bat = &vcpu_book3s->ibat[i];
 
-		if (vcpu->arch.shared->msr & MSR_PR) {
+		if (kvmppc_get_msr(vcpu) & MSR_PR) {
 			if (!bat->vp)
 				continue;
 		} else {
···
 	u32 sre;
 	hva_t ptegp;
 	u32 pteg[16];
+	u32 pte0, pte1;
 	u32 ptem = 0;
 	int i;
 	int found = 0;
···
 	}
 
 	for (i=0; i<16; i+=2) {
-		if (ptem == pteg[i]) {
+		pte0 = be32_to_cpu(pteg[i]);
+		pte1 = be32_to_cpu(pteg[i + 1]);
+		if (ptem == pte0) {
 			u8 pp;
 
-			pte->raddr = (pteg[i+1] & ~(0xFFFULL)) | (eaddr & 0xFFF);
-			pp = pteg[i+1] & 3;
+			pte->raddr = (pte1 & ~(0xFFFULL)) | (eaddr & 0xFFF);
+			pp = pte1 & 3;
 
-			if ((sr_kp(sre) &&  (vcpu->arch.shared->msr & MSR_PR)) ||
-			    (sr_ks(sre) && !(vcpu->arch.shared->msr & MSR_PR)))
+			if ((sr_kp(sre) &&  (kvmppc_get_msr(vcpu) & MSR_PR)) ||
+			    (sr_ks(sre) && !(kvmppc_get_msr(vcpu) & MSR_PR)))
 				pp |= 4;
 
 			pte->may_write = false;
···
 			}
 
 			dprintk_pte("MMU: Found PTE -> %x %x - %x\n",
-				    pteg[i], pteg[i+1], pp);
+				    pte0, pte1, pp);
 			found = 1;
 			break;
 		}
···
 	/* Update PTE C and A bits, so the guest's swapper knows we used the
 	   page */
 	if (found) {
-		u32 pte_r = pteg[i+1];
-		char __user *addr = (char __user *) &pteg[i+1];
+		u32 pte_r = pte1;
+		char __user *addr = (char __user *) (ptegp + (i+1) * sizeof(u32));
 
 		/*
 		 * Use single-byte writes to update the HPTE, to
···
 			    to_book3s(vcpu)->sdr1, ptegp);
 		for (i=0; i<16; i+=2) {
 			dprintk_pte("   %02d: 0x%x - 0x%x (0x%x)\n",
-				    i, pteg[i], pteg[i+1], ptem);
+				    i, be32_to_cpu(pteg[i]),
+				    be32_to_cpu(pteg[i+1]), ptem);
 		}
 	}
 
···
 	/* Magic page override */
 	if (unlikely(mp_ea) &&
 	    unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
-	    !(vcpu->arch.shared->msr & MSR_PR)) {
+	    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
 		pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
 		pte->raddr = vcpu->arch.magic_page_pa | (pte->raddr & 0xfff);
 		pte->raddr &= KVM_PAM;
···
 
 static u32 kvmppc_mmu_book3s_32_mfsrin(struct kvm_vcpu *vcpu, u32 srnum)
 {
-	return vcpu->arch.shared->sr[srnum];
+	return kvmppc_get_sr(vcpu, srnum);
 }
 
 static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 					ulong value)
 {
-	vcpu->arch.shared->sr[srnum] = value;
+	kvmppc_set_sr(vcpu, srnum, value);
 	kvmppc_mmu_map_segment(vcpu, srnum << SID_SHIFT);
 }
 
···
 	ulong ea = esid << SID_SHIFT;
 	u32 sr;
 	u64 gvsid = esid;
+	u64 msr = kvmppc_get_msr(vcpu);
 
-	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	if (msr & (MSR_DR|MSR_IR)) {
 		sr = find_sr(vcpu, ea);
 		if (sr_valid(sr))
 			gvsid = sr_vsid(sr);
···
 	/* In case we only have one of MSR_IR or MSR_DR set, let's put
 	   that in the real-mode context (and hope RM doesn't access
 	   high memory) */
-	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	switch (msr & (MSR_DR|MSR_IR)) {
 	case 0:
 		*vsid = VSID_REAL | esid;
 		break;
···
 		BUG();
 	}
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (msr & MSR_PR)
 		*vsid |= VSID_PR;
 
 	return 0;

arch/powerpc/kvm/book3s_32_mmu_host.c

···
 	struct kvmppc_sid_map *map;
 	u16 sid_map_mask;
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (kvmppc_get_msr(vcpu) & MSR_PR)
 		gvsid |= VSID_PR;
 
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
···
 	u16 sid_map_mask;
 	static int backwards_map = 0;
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (kvmppc_get_msr(vcpu) & MSR_PR)
 		gvsid |= VSID_PR;
 
 	/* We might get collisions that trap in preceding order, so let's

arch/powerpc/kvm/book3s_64_mmu.c

···
 
 static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
 {
-	kvmppc_set_msr(vcpu, MSR_SF);
+	kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
 }
 
 static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
···
 	/* Magic page override */
 	if (unlikely(mp_ea) &&
 	    unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
-	    !(vcpu->arch.shared->msr & MSR_PR)) {
+	    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
 		gpte->eaddr = eaddr;
 		gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
 		gpte->raddr = vcpu->arch.magic_page_pa | (gpte->raddr & 0xfff);
···
 		goto no_page_found;
 	}
 
-	if ((vcpu->arch.shared->msr & MSR_PR) && slbe->Kp)
+	if ((kvmppc_get_msr(vcpu) & MSR_PR) && slbe->Kp)
 		key = 4;
-	else if (!(vcpu->arch.shared->msr & MSR_PR) && slbe->Ks)
+	else if (!(kvmppc_get_msr(vcpu) & MSR_PR) && slbe->Ks)
 		key = 4;
 
 	for (i=0; i<16; i+=2) {
+		u64 pte0 = be64_to_cpu(pteg[i]);
+		u64 pte1 = be64_to_cpu(pteg[i + 1]);
+
 		/* Check all relevant fields of 1st dword */
-		if ((pteg[i] & v_mask) == v_val) {
+		if ((pte0 & v_mask) == v_val) {
 			/* If large page bit is set, check pgsize encoding */
 			if (slbe->large &&
 			    (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
-				pgsize = decode_pagesize(slbe, pteg[i+1]);
+				pgsize = decode_pagesize(slbe, pte1);
 				if (pgsize < 0)
 					continue;
 			}
···
 		goto do_second;
 	}
 
-	v = pteg[i];
-	r = pteg[i+1];
+	v = be64_to_cpu(pteg[i]);
+	r = be64_to_cpu(pteg[i+1]);
 	pp = (r & HPTE_R_PP) | key;
 	if (r & HPTE_R_PP0)
 		pp |= 8;
···
 	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
 	gpte->page_size = pgsize;
 	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
+	if (unlikely(vcpu->arch.disable_kernel_nx) &&
+	    !(kvmppc_get_msr(vcpu) & MSR_PR))
+		gpte->may_execute = true;
 	gpte->may_read = false;
 	gpte->may_write = false;
 
···
 		 * non-PAPR platforms such as mac99, and this is
 		 * what real hardware does.
 		 */
-		char __user *addr = (char __user *) &pteg[i+1];
+                char __user *addr = (char __user *) (ptegp + (i + 1) * sizeof(u64));
 		r |= HPTE_R_R;
 		put_user(r >> 8, addr + 6);
 	}
 	if (iswrite && gpte->may_write && !(r & HPTE_R_C)) {
 		/* Set the dirty flag */
 		/* Use a single byte write */
-		char __user *addr = (char __user *) &pteg[i+1];
+                char __user *addr = (char __user *) (ptegp + (i + 1) * sizeof(u64));
 		r |= HPTE_R_C;
 		put_user(r, addr + 7);
 	}
···
 		vcpu->arch.slb[i].origv = 0;
 	}
 
-	if (vcpu->arch.shared->msr & MSR_IR) {
+	if (kvmppc_get_msr(vcpu) & MSR_IR) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 	}
···
 {
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
-	return mp_ea && !(vcpu->arch.shared->msr & MSR_PR) &&
+	return mp_ea && !(kvmppc_get_msr(vcpu) & MSR_PR) &&
 		(mp_ea >> SID_SHIFT) == esid;
 }
 #endif
···
 	u64 gvsid = esid;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 	int pagesize = MMU_PAGE_64K;
+	u64 msr = kvmppc_get_msr(vcpu);
 
-	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	if (msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
 		if (slb) {
 			gvsid = slb->vsid;
···
 		}
 	}
 
-	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	switch (msr & (MSR_DR|MSR_IR)) {
 	case 0:
 		gvsid = VSID_REAL | esid;
 		break;
···
 		gvsid |= VSID_64K;
 #endif
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (kvmppc_get_msr(vcpu) & MSR_PR)
 		gvsid |= VSID_PR;
 
 	*vsid = gvsid;
···
 	/* Catch magic page case */
 	if (unlikely(mp_ea) &&
 	    unlikely(esid == (mp_ea >> SID_SHIFT)) &&
-	    !(vcpu->arch.shared->msr & MSR_PR)) {
+	    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
 		*vsid = VSID_REAL | esid;
 		return 0;
 	}

arch/powerpc/kvm/book3s_64_mmu_host.c

···
 	struct kvmppc_sid_map *map;
 	u16 sid_map_mask;
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (kvmppc_get_msr(vcpu) & MSR_PR)
 		gvsid |= VSID_PR;
 
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
···
 	u16 sid_map_mask;
 	static int backwards_map = 0;
 
-	if (vcpu->arch.shared->msr & MSR_PR)
+	if (kvmppc_get_msr(vcpu) & MSR_PR)
 		gvsid |= VSID_PR;
 
 	/* We might get collisions that trap in preceding order, so let's
···
 	int found_inval = -1;
 	int r;
 
-	if (!svcpu->slb_max)
-		svcpu->slb_max = 1;
-
 	/* Are we overwriting? */
-	for (i = 1; i < svcpu->slb_max; i++) {
+	for (i = 0; i < svcpu->slb_max; i++) {
 		if (!(svcpu->slb[i].esid & SLB_ESID_V))
 			found_inval = i;
 		else if ((svcpu->slb[i].esid & ESID_MASK) == esid) {
···
 	}
 
 	/* Found a spare entry that was invalidated before */
-	if (found_inval > 0) {
+	if (found_inval >= 0) {
 		r = found_inval;
 		goto out;
 	}
···
 	ulong seg_mask = -seg_size;
 	int i;
 
-	for (i = 1; i < svcpu->slb_max; i++) {
+	for (i = 0; i < svcpu->slb_max; i++) {
 		if ((svcpu->slb[i].esid & SLB_ESID_V) &&
 		    (svcpu->slb[i].esid & seg_mask) == ea) {
 			/* Invalidate this entry */
···
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-	svcpu->slb_max = 1;
+	svcpu->slb_max = 0;
 	svcpu->slb[0].esid = 0;
 	svcpu_put(svcpu);
 }

arch/powerpc/kvm/book3s_64_mmu_hv.c

···
 
 long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
-	unsigned long hpt;
+	unsigned long hpt = 0;
 	struct revmap_entry *rev;
 	struct page *page = NULL;
 	long order = KVM_DEFAULT_HPT_ORDER;
···
 	}
 
 	kvm->arch.hpt_cma_alloc = 0;
-	/*
-	 * try first to allocate it from the kernel page allocator.
-	 * We keep the CMA reserved for failed allocation.
-	 */
-	hpt = __get_free_pages(GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT |
-			       __GFP_NOWARN, order - PAGE_SHIFT);
-
-	/* Next try to allocate from the preallocated pool */
-	if (!hpt) {
-		VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
-		page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
-		if (page) {
-			hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
-			kvm->arch.hpt_cma_alloc = 1;
-		} else
-			--order;
+	VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
+	page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
+	if (page) {
+		hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+		kvm->arch.hpt_cma_alloc = 1;
 	}
 
 	/* Lastly try successively smaller sizes from the page allocator */
···
 	struct kvm *kvm = vcpu->kvm;
 	unsigned long *hptep, hpte[3], r;
 	unsigned long mmu_seq, psize, pte_size;
+	unsigned long gpa_base, gfn_base;
 	unsigned long gpa, gfn, hva, pfn;
 	struct kvm_memory_slot *memslot;
 	unsigned long *rmap;
···
 
 	/* Translate the logical address and get the page */
 	psize = hpte_page_size(hpte[0], r);
-	gpa = (r & HPTE_R_RPN & ~(psize - 1)) | (ea & (psize - 1));
+	gpa_base = r & HPTE_R_RPN & ~(psize - 1);
+	gfn_base = gpa_base >> PAGE_SHIFT;
+	gpa = gpa_base | (ea & (psize - 1));
 	gfn = gpa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(kvm, gfn);
 
···
 
 	if (!kvm->arch.using_mmu_notifiers)
 		return -EFAULT;		/* should never get here */
+
+	/*
+	 * This should never happen, because of the slot_is_aligned()
+	 * check in kvmppc_do_h_enter().
+	 */
+	if (gfn_base < memslot->base_gfn)
+		return -EFAULT;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
···
 		goto out_unlock;
 	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
 
-	rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+	/* Always put the HPTE in the rmap chain for the page base address */
+	rmap = &memslot->arch.rmap[gfn_base - memslot->base_gfn];
 	lock_rmap(rmap);
 
 	/* Check if we might have been invalidated; let the guest retry if so */
···
 	kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
 }
 
-static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
+static int vcpus_running(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.vcpus_running) != 0;
+}
+
+/*
+ * Returns the number of system pages that are dirty.
+ * This can be more than 1 if we find a huge-page HPTE.
+ */
+static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp)
 {
 	struct revmap_entry *rev = kvm->arch.revmap;
 	unsigned long head, i, j;
+	unsigned long n;
+	unsigned long v, r;
 	unsigned long *hptep;
-	int ret = 0;
+	int npages_dirty = 0;
 
  retry:
 	lock_rmap(rmapp);
 	if (*rmapp & KVMPPC_RMAP_CHANGED) {
 		*rmapp &= ~KVMPPC_RMAP_CHANGED;
-		ret = 1;
+		npages_dirty = 1;
 	}
 	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
 		unlock_rmap(rmapp);
-		return ret;
+		return npages_dirty;
 	}
 
 	i = head = *rmapp & KVMPPC_RMAP_INDEX;
···
 		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
 		j = rev[i].forw;
 
-		if (!(hptep[1] & HPTE_R_C))
+		/*
+		 * Checking the C (changed) bit here is racy since there
+		 * is no guarantee about when the hardware writes it back.
+		 * If the HPTE is not writable then it is stable since the
+		 * page can't be written to, and we would have done a tlbie
+		 * (which forces the hardware to complete any writeback)
+		 * when making the HPTE read-only.
+		 * If vcpus are running then this call is racy anyway
+		 * since the page could get dirtied subsequently, so we
+		 * expect there to be a further call which would pick up
+		 * any delayed C bit writeback.
+		 * Otherwise we need to do the tlbie even if C==0 in
+		 * order to pick up any delayed writeback of C.
+		 */
+		if (!(hptep[1] & HPTE_R_C) &&
+		    (!hpte_is_writable(hptep[1]) || vcpus_running(kvm)))
 			continue;
 
 		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
···
 		}
 
 		/* Now check and modify the HPTE */
-		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
-			/* need to make it temporarily absent to clear C */
-			hptep[0] |= HPTE_V_ABSENT;
-			kvmppc_invalidate_hpte(kvm, hptep, i);
-			hptep[1] &= ~HPTE_R_C;
-			eieio();
-			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+		if (!(hptep[0] & HPTE_V_VALID))
+			continue;
+
+		/* need to make it temporarily absent so C is stable */
+		hptep[0] |= HPTE_V_ABSENT;
+		kvmppc_invalidate_hpte(kvm, hptep, i);
+		v = hptep[0];
+		r = hptep[1];
+		if (r & HPTE_R_C) {
+			hptep[1] = r & ~HPTE_R_C;
 			if (!(rev[i].guest_rpte & HPTE_R_C)) {
 				rev[i].guest_rpte |= HPTE_R_C;
 				note_hpte_modification(kvm, &rev[i]);
 			}
-			ret = 1;
+			n = hpte_page_size(v, r);
+			n = (n + PAGE_SIZE - 1) >> PAGE_SHIFT;
+			if (n > npages_dirty)
+				npages_dirty = n;
+			eieio();
 		}
-		hptep[0] &= ~HPTE_V_HVLOCK;
+		v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK);
+		v |= HPTE_V_VALID;
+		hptep[0] = v;
 	} while ((i = j) != head);
 
 	unlock_rmap(rmapp);
-	return ret;
+	return npages_dirty;
 }
 
 static void harvest_vpa_dirty(struct kvmppc_vpa *vpa,
···
 long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			     unsigned long *map)
 {
-	unsigned long i;
+	unsigned long i, j;
 	unsigned long *rmapp;
 	struct kvm_vcpu *vcpu;
 
 	preempt_disable();
 	rmapp = memslot->arch.rmap;
 	for (i = 0; i < memslot->npages; ++i) {
-		if (kvm_test_clear_dirty(kvm, rmapp) && map)
-			__set_bit_le(i, map);
+		int npages = kvm_test_clear_dirty_npages(kvm, rmapp);
+		/*
+		 * Note that if npages > 0 then i must be a multiple of npages,
+		 * since we always put huge-page HPTEs in the rmap chain
+		 * corresponding to their page base address.
+		 */
+		if (npages && map)
+			for (j = i; npages; ++j, --npages)
+				__set_bit_le(j, map);
 		++rmapp;
 	}
 

arch/powerpc/kvm/book3s_64_slb.S

···
  * Authors: Alexander Graf <[e-mail]>
  */
 
-#ifdef __LITTLE_ENDIAN__
-#error Need to fix SLB shadow accesses in little endian mode
-#endif
-
-#define SHADOW_SLB_ESID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10))
-#define SHADOW_SLB_VSID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10) + 0x8)
-#define UNBOLT_SLB_ENTRY(num) \
-	ld	r9, SHADOW_SLB_ESID(num)(r12); \
-	/* Invalid? Skip. */; \
-	rldicl. r0, r9, 37, 63; \
-	beq	slb_entry_skip_ ## num; \
-	xoris	r9, r9, SLB_ESID_V@h; \
-	std	r9, SHADOW_SLB_ESID(num)(r12); \
-  slb_entry_skip_ ## num:
-
-#define REBOLT_SLB_ENTRY(num) \
-	ld	r10, SHADOW_SLB_ESID(num)(r11); \
-	cmpdi	r10, 0; \
-	beq	slb_exit_skip_ ## num; \
-	oris	r10, r10, SLB_ESID_V@h; \
-	ld	r9, SHADOW_SLB_VSID(num)(r11); \
-	slbmte	r9, r10; \
-	std	r10, SHADOW_SLB_ESID(num)(r11); \
-slb_exit_skip_ ## num:
+#define SHADOW_SLB_ENTRY_LEN	0x10
+#define OFFSET_ESID(x)		(SHADOW_SLB_ENTRY_LEN * x)
+#define OFFSET_VSID(x)		((SHADOW_SLB_ENTRY_LEN * x) + 8)
 
 /******************************************************************************
  *                                                                            *
···
 	 * SVCPU[LR]  = guest LR
 	 */
 
-	/* Remove LPAR shadow entries */
+BEGIN_FW_FTR_SECTION
 
-#if SLB_NUM_BOLTED == 3
+	/* Declare SLB shadow as 0 entries big */
 
-	ld	r12, PACA_SLBSHADOWPTR(r13)
+	ld	r11, PACA_SLBSHADOWPTR(r13)
+	li	r8, 0
+	stb	r8, 3(r11)
 
-	/* Remove bolted entries */
-	UNBOLT_SLB_ENTRY(0)
-	UNBOLT_SLB_ENTRY(1)
-	UNBOLT_SLB_ENTRY(2)
-	
-#else
-#error unknown number of bolted entries
-#endif
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_LPAR)
 
 	/* Flush SLB */
 
···
 
 	ld	r10, 0(r11)
 
-	rldicl. r0, r10, 37, 63
+	andis.	r9, r10, SLB_ESID_V@h
 	beq	slb_loop_enter_skip
 
 	ld	r9, 8(r11)
···
 	 *
 	 */
 
-	/* Restore bolted entries from the shadow and fix it along the way */
+	/* Remove all SLB entries that are in use. */
 
-	/* We don't store anything in entry 0, so we don't need to take care of it */
+	li	r0, r0
+	slbmte	r0, r0
 	slbia
-	isync
 
-#if SLB_NUM_BOLTED == 3
+	/* Restore bolted entries from the shadow */
 
 	ld	r11, PACA_SLBSHADOWPTR(r13)
 
-	REBOLT_SLB_ENTRY(0)
-	REBOLT_SLB_ENTRY(1)
-	REBOLT_SLB_ENTRY(2)
-	
-#else
-#error unknown number of bolted entries
-#endif
+BEGIN_FW_FTR_SECTION
+
+	/* Declare SLB shadow as SLB_NUM_BOLTED entries big */
+
+	li	r8, SLB_NUM_BOLTED
+	stb	r8, 3(r11)
+
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_LPAR)
+
+	/* Manually load all entries from shadow SLB */
+
+	li	r8, SLBSHADOW_SAVEAREA
+	li	r7, SLBSHADOW_SAVEAREA + 8
+
+	.rept	SLB_NUM_BOLTED
+	LDX_BE	r10, r11, r8
+	cmpdi	r10, 0
+	beq	1f
+	LDX_BE	r9, r11, r7
+	slbmte	r9, r10
+1:	addi	r7, r7, SHADOW_SLB_ENTRY_LEN
+	addi	r8, r8, SHADOW_SLB_ENTRY_LEN
+	.endr
+
+	isync
+	sync
 
 slb_do_exit:
 

arch/powerpc/kvm/book3s_emulate.c

···
 		return false;
 
 	/* Limit user space to its own small SPR set */
-	if ((vcpu->arch.shared->msr & MSR_PR) && level > PRIV_PROBLEM)
+	if ((kvmppc_get_msr(vcpu) & MSR_PR) && level > PRIV_PROBLEM)
 		return false;
 
 	return true;
···
 	int rs = get_rs(inst);
 	int ra = get_ra(inst);
 	int rb = get_rb(inst);
+	u32 inst_sc = 0x44000002;
 
 	switch (get_op(inst)) {
+	case 0:
+		emulated = EMULATE_FAIL;
+		if ((kvmppc_get_msr(vcpu) & MSR_LE) &&
+		    (inst == swab32(inst_sc))) {
+			/*
+			 * This is the byte reversed syscall instruction of our
+			 * hypercall handler. Early versions of LE Linux didn't
+			 * swap the instructions correctly and ended up in
+			 * illegal instructions.
+			 * Just always fail hypercalls on these broken systems.
+			 */
+			kvmppc_set_gpr(vcpu, 3, EV_UNIMPLEMENTED);
+			kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
+			emulated = EMULATE_DONE;
+		}
+		break;
 	case 19:
 		switch (get_xop(inst)) {
 		case OP_19_XOP_RFID:
 		case OP_19_XOP_RFI:
-			kvmppc_set_pc(vcpu, vcpu->arch.shared->srr0);
-			kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
+			kvmppc_set_pc(vcpu, kvmppc_get_srr0(vcpu));
+			kvmppc_set_msr(vcpu, kvmppc_get_srr1(vcpu));
 			*advance = 0;
 			break;
 
···
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
+			kvmppc_set_gpr(vcpu, rt, kvmppc_get_msr(vcpu));
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
 			ulong rs_val = kvmppc_get_gpr(vcpu, rs);
 			if (inst & 0x10000) {
-				ulong new_msr = vcpu->arch.shared->msr;
+				ulong new_msr = kvmppc_get_msr(vcpu);
 				new_msr &= ~(MSR_RI | MSR_EE);
 				new_msr |= rs_val & (MSR_RI | MSR_EE);
-				vcpu->arch.shared->msr = new_msr;
+				kvmppc_set_msr_fast(vcpu, new_msr);
 			} else
 				kvmppc_set_msr(vcpu, rs_val);
 			break;
···
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
 			int i;
 
-		        if ((vcpu->arch.shared->msr & MSR_PR) ||
+		        if ((kvmppc_get_msr(vcpu) & MSR_PR) ||
 			    !vcpu->arch.papr_enabled) {
 				emulated = EMULATE_FAIL;
 				break;
···
 				ra_val = kvmppc_get_gpr(vcpu, ra);
 
 			addr = (ra_val + rb_val) & ~31ULL;
-			if (!(vcpu->arch.shared->msr & MSR_SF))
+			if (!(kvmppc_get_msr(vcpu) & MSR_SF))
 				addr &= 0xffffffff;
 			vaddr = addr;
 
 			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
 			if ((r == -ENOENT) || (r == -EPERM)) {
 				*advance = 0;
-				vcpu->arch.shared->dar = vaddr;
+				kvmppc_set_dar(vcpu, vaddr);
 				vcpu->arch.fault_dar = vaddr;
 
 				dsisr = DSISR_ISSTORE;
···
 				else if (r == -EPERM)
 					dsisr |= DSISR_PROTFAULT;
 
-				vcpu->arch.shared->dsisr = dsisr;
+				kvmppc_set_dsisr(vcpu, dsisr);
 				vcpu->arch.fault_dsisr = dsisr;
 
 				kvmppc_book3s_queue_irqprio(vcpu,
···
 		to_book3s(vcpu)->sdr1 = spr_val;
 		break;
 	case SPRN_DSISR:
-		vcpu->arch.shared->dsisr = spr_val;
+		kvmppc_set_dsisr(vcpu, spr_val);
 		break;
 	case SPRN_DAR:
-		vcpu->arch.shared->dar = spr_val;
+		kvmppc_set_dar(vcpu, spr_val);
 		break;
 	case SPRN_HIOR:
 		to_book3s(vcpu)->hior = spr_val;
···
 	case SPRN_GQR7:
 		to_book3s(vcpu)->gqr[sprn - SPRN_GQR0] = spr_val;
 		break;
+	case SPRN_FSCR:
+		vcpu->arch.fscr = spr_val;
+		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case SPRN_BESCR:
+		vcpu->arch.bescr = spr_val;
+		break;
+	case SPRN_EBBHR:
+		vcpu->arch.ebbhr = spr_val;
+		break;
+	case SPRN_EBBRR:
+		vcpu->arch.ebbrr = spr_val;
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case SPRN_TFHAR:
+		vcpu->arch.tfhar = spr_val;
+		break;
+	case SPRN_TEXASR:
+		vcpu->arch.texasr = spr_val;
+		break;
+	case SPRN_TFIAR:
+		vcpu->arch.tfiar = spr_val;
+		break;
+#endif
+#endif
 	case SPRN_ICTC:
 	case SPRN_THRM1:
 	case SPRN_THRM2:
···
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
 	case SPRN_DABR:
+#ifdef CONFIG_PPC_BOOK3S_64
+	case SPRN_MMCRS:
+	case SPRN_MMCRA:
+	case SPRN_MMCR0:
+	case SPRN_MMCR1:
+	case SPRN_MMCR2:
+#endif
 		break;
 unprivileged:
 	default:
···
 		*spr_val = to_book3s(vcpu)->sdr1;
 		break;
 	case SPRN_DSISR:
-		*spr_val = vcpu->arch.shared->dsisr;
+		*spr_val = kvmppc_get_dsisr(vcpu);
 		break;
 	case SPRN_DAR:
-		*spr_val = vcpu->arch.shared->dar;
+		*spr_val = kvmppc_get_dar(vcpu);
 		break;
 	case SPRN_HIOR:
 		*spr_val = to_book3s(vcpu)->hior;
···
 	case SPRN_GQR7:
 		*spr_val = to_book3s(vcpu)->gqr[sprn - SPRN_GQR0];
 		break;
+	case SPRN_FSCR:
+		*spr_val = vcpu->arch.fscr;
+		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case SPRN_BESCR:
+		*spr_val = vcpu->arch.bescr;
+		break;
+	case SPRN_EBBHR:
+		*spr_val = vcpu->arch.ebbhr;
+		break;
+	case SPRN_EBBRR:
+		*spr_val = vcpu->arch.ebbrr;
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case SPRN_TFHAR:
+		*spr_val = vcpu->arch.tfhar;
+		break;
+	case SPRN_TEXASR:
+		*spr_val = vcpu->arch.texasr;
+		break;
+	case SPRN_TFIAR:
+		*spr_val = vcpu->arch.tfiar;
+		break;
+#endif
+#endif
 	case SPRN_THRM1:
 	case SPRN_THRM2:
 	case SPRN_THRM3:
···
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
 	case SPRN_DABR:
+#ifdef CONFIG_PPC_BOOK3S_64
+	case SPRN_MMCRS:
+	case SPRN_MMCRA:
+	case SPRN_MMCR0:
+	case SPRN_MMCR1:
+	case SPRN_MMCR2:
+	case SPRN_TIR:
+#endif
 		*spr_val = 0;
 		break;
 	default:
···
 
 u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst)
 {
-	u32 dsisr = 0;
-
-	/*
-	 * This is what the spec says about DSISR bits (not mentioned = 0):
-	 *
-	 * 12:13		[DS]	Set to bits 30:31
-	 * 15:16		[X]	Set to bits 29:30
-	 * 17			[X]	Set to bit 25
-	 *			[D/DS]	Set to bit 5
-	 * 18:21		[X]	Set to bits 21:24
-	 *			[D/DS]	Set to bits 1:4
-	 * 22:26			Set to bits 6:10 (RT/RS/FRT/FRS)
-	 * 27:31			Set to bits 11:15 (RA)
-	 */
-
-	switch (get_op(inst)) {
-	/* D-form */
-	case OP_LFS:
-	case OP_LFD:
-	case OP_STFD:
-	case OP_STFS:
-		dsisr |= (inst >> 12) & 0x4000;	/* bit 17 */
-		dsisr |= (inst >> 17) & 0x3c00; /* bits 18:21 */
-		break;
-	/* X-form */
-	case 31:
-		dsisr |= (inst << 14) & 0x18000; /* bits 15:16 */
-		dsisr |= (inst << 8)  & 0x04000; /* bit 17 */
-		dsisr |= (inst << 3)  & 0x03c00; /* bits 18:21 */
-		break;
-	default:
-		printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst);
-		break;
-	}
-
-	dsisr |= (inst >> 16) & 0x03ff; /* bits 22:31 */
-
-	return dsisr;
+	return make_dsisr(inst);
 }
 
 ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst)
 {
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * Linux's fix_alignment() assumes that DAR is valid, so can we
+	 */
+	return vcpu->arch.fault_dar;
+#else
 	ulong dar = 0;
 	ulong ra = get_ra(inst);
 	ulong rb = get_rb(inst);
···
 	}
 
 	return dar;
+#endif
 }

arch/powerpc/kvm/book3s_exports.c

···
  */
 
 #include <linux/export.h>
+#include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE

arch/powerpc/kvm/book3s_hv.c

···
 	case KVM_REG_PPC_IAMR:
 		*val = get_reg_val(id, vcpu->arch.iamr);
 		break;
-	case KVM_REG_PPC_FSCR:
-		*val = get_reg_val(id, vcpu->arch.fscr);
-		break;
 	case KVM_REG_PPC_PSPB:
 		*val = get_reg_val(id, vcpu->arch.pspb);
-		break;
-	case KVM_REG_PPC_EBBHR:
-		*val = get_reg_val(id, vcpu->arch.ebbhr);
-		break;
-	case KVM_REG_PPC_EBBRR:
-		*val = get_reg_val(id, vcpu->arch.ebbrr);
-		break;
-	case KVM_REG_PPC_BESCR:
-		*val = get_reg_val(id, vcpu->arch.bescr);
-		break;
-	case KVM_REG_PPC_TAR:
-		*val = get_reg_val(id, vcpu->arch.tar);
 		break;
 	case KVM_REG_PPC_DPDES:
 		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
···
 	case KVM_REG_PPC_IAMR:
 		vcpu->arch.iamr = set_reg_val(id, *val);
 		break;
-	case KVM_REG_PPC_FSCR:
-		vcpu->arch.fscr = set_reg_val(id, *val);
-		break;
 	case KVM_REG_PPC_PSPB:
 		vcpu->arch.pspb = set_reg_val(id, *val);
-		break;
-	case KVM_REG_PPC_EBBHR:
-		vcpu->arch.ebbhr = set_reg_val(id, *val);
-		break;
-	case KVM_REG_PPC_EBBRR:
-		vcpu->arch.ebbrr = set_reg_val(id, *val);
-		break;
-	case KVM_REG_PPC_BESCR:
-		vcpu->arch.bescr = set_reg_val(id, *val);
-		break;
-	case KVM_REG_PPC_TAR:
-		vcpu->arch.tar = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_DPDES:
 		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
···
 		goto free_vcpu;
 
 	vcpu->arch.shared = &vcpu->arch.shregs;
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	/*
+	 * The shared struct is never shared on HV,
+	 * so we can always use host endianness
+	 */
+#ifdef __BIG_ENDIAN__
+	vcpu->arch.shared_big_endian = true;
+#else
+	vcpu->arch.shared_big_endian = false;
+#endif
+#endif
 	vcpu->arch.mmcr[0] = MMCR0_FC;
 	vcpu->arch.ctrl = CTRL_RUNLATCH;
 	/* default to host PVR, since we can't spoof it */
···
 	 * support pte_enc here
 	 */
 	(*sps)->enc[0].pte_enc = def->penc[linux_psize];
+	/*
+	 * Add 16MB MPSS support if host supports it
+	 */
+	if (linux_psize != MMU_PAGE_16M && def->penc[MMU_PAGE_16M] != -1) {
+		(*sps)->enc[1].page_shift = 24;
+		(*sps)->enc[1].pte_enc = def->penc[MMU_PAGE_16M];
+	}
 	(*sps)++;
 }
 

arch/powerpc/kvm/book3s_hv_rm_mmu.c

···
 
 	/*
 	 * If there is only one vcore, and it's currently running,
+	 * as indicated by local_paca->kvm_hstate.kvm_vcpu being set,
 	 * we can use tlbiel as long as we mark all other physical
 	 * cores as potentially having stale TLB entries for this lpid.
 	 * If we're not using MMU notifiers, we never take pages away
 	 * from the guest, so we can use tlbiel if requested.
 	 * Otherwise, don't use tlbiel.
 	 */
-	if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcore)
+	if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcpu)
 		global = 0;
 	else if (kvm->arch.using_mmu_notifiers)
 		global = 1;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 	lbz	r4, LPPACA_PMCINUSE(r3)
 	cmpwi	r4, 0
 	beq	23f			/* skip if not */
+BEGIN_FTR_SECTION
+	ld	r3, HSTATE_MMCR(r13)
+	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r4, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
 	lwz	r3, HSTATE_PMC(r13)
 	lwz	r4, HSTATE_PMC + 4(r13)
 	lwz	r5, HSTATE_PMC + 8(r13)
···
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
 	isync
+BEGIN_FTR_SECTION
+	ld	r3, VCPU_MMCR(r4)
+	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r5, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
 	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
 	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
 	lwz	r6, VCPU_PMC + 8(r4)
···
 25:
 	/* Save PMU registers if requested */
 	/* r8 and cr0.eq are live here */
+BEGIN_FTR_SECTION
+	/*
+	 * POWER8 seems to have a hardware bug where setting
+	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
+	 * when some counters are already negative doesn't seem
+	 * to cause a performance monitor alert (and hence interrupt).
+	 * The effect of this is that when saving the PMU state,
+	 * if there is no PMU alert pending when we read MMCR0
+	 * before freezing the counters, but one becomes pending
+	 * before we read the counters, we lose it.
+	 * To work around this, we need a way to freeze the counters
+	 * before reading MMCR0.  Normally, freezing the counters
+	 * is done by writing MMCR0 (to set MMCR0[FC]) which
+	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
+	 * we can also freeze the counters using MMCR2, by writing
+	 * 1s to all the counter freeze condition bits (there are
+	 * 9 bits each for 6 counters).
+	 */
+	li	r3, -1			/* set all freeze bits */
+	clrrdi	r3, r3, 10
+	mfspr	r10, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
···
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
 	std	r6, VCPU_MMCR + 16(r9)
+BEGIN_FTR_SECTION
+	std	r10, VCPU_MMCR + 24(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	std	r7, VCPU_SIAR(r9)
 	std	r8, VCPU_SDAR(r9)
 	mfspr	r3, SPRN_PMC1
···
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 BEGIN_FTR_SECTION
-	mfspr	r4, SPRN_MMCR2
 	mfspr	r5, SPRN_SIER
 	mfspr	r6, SPRN_SPMC1
 	mfspr	r7, SPRN_SPMC2
 	mfspr	r8, SPRN_MMCRS
-	std	r4, VCPU_MMCR + 24(r9)
 	std	r5, VCPU_SIER(r9)
 	stw	r6, VCPU_PMC + 24(r9)
 	stw	r7, VCPU_PMC + 28(r9)
···
 	beq	mc_cont
 	/* If not, deliver a machine check.  SRR0/1 are already set */
 	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
+	ld	r11, VCPU_MSR(r9)
 	bl	kvmppc_msr_interrupt
 	b	fast_interrupt_c_return
 
···
 	/* ... if transactional, change to suspended */
 	li	r0, 1
 1:	rldimi	r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	blr
+
+/*
+ * This works around a hardware bug on POWER8E processors, where
+ * writing a 1 to the MMCR0[PMAO] bit doesn't generate a
+ * performance monitor interrupt.  Instead, when we need to have
+ * an interrupt pending, we have to arrange for a counter to overflow.
+ */
+kvmppc_fix_pmao:
+	li	r3, 0
+	mtspr	SPRN_MMCR2, r3
+	lis	r3, (MMCR0_PMXE | MMCR0_FCECE)@h
+	ori	r3, r3, MMCR0_PMCjCE | MMCR0_C56RUN
+	mtspr	SPRN_MMCR0, r3
+	lis	r3, 0x7fff
+	ori	r3, r3, 0xffff
+	mtspr	SPRN_PMC6, r3
+	isync
 	blr

arch/powerpc/kvm/book3s_interrupts.S

···
 	stb	r3, HSTATE_RESTORE_HID5(r13)
 
 	/* Load up guest SPRG3 value, since it's user readable */
-	ld	r3, VCPU_SHARED(r4)
-	ld	r3, VCPU_SHARED_SPRG3(r3)
+	lwz	r3, VCPU_SHAREDBE(r4)
+	cmpwi	r3, 0
+	ld	r5, VCPU_SHARED(r4)
+	beq	sprg3_little_endian
+sprg3_big_endian:
+#ifdef __BIG_ENDIAN__
+	ld	r3, VCPU_SHARED_SPRG3(r5)
+#else
+	addi	r5, r5, VCPU_SHARED_SPRG3
+	ldbrx	r3, 0, r5
+#endif
+	b	after_sprg3_load
+sprg3_little_endian:
+#ifdef __LITTLE_ENDIAN__
+	ld	r3, VCPU_SHARED_SPRG3(r5)
+#else
+	addi	r5, r5, VCPU_SHARED_SPRG3
+	ldbrx	r3, 0, r5
+#endif
+
+after_sprg3_load:
 	mtspr	SPRN_SPRG3, r3
 #endif /* CONFIG_PPC_BOOK3S_64 */
 

arch/powerpc/kvm/book3s_paired_singles.c

···
 
 static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
 {
-	u64 dsisr;
-	struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
+	u32 dsisr;
+	u64 msr = kvmppc_get_msr(vcpu);
 
-	shared->msr = kvmppc_set_field(shared->msr, 33, 36, 0);
-	shared->msr = kvmppc_set_field(shared->msr, 42, 47, 0);
-	shared->dar = eaddr;
+	msr = kvmppc_set_field(msr, 33, 36, 0);
+	msr = kvmppc_set_field(msr, 42, 47, 0);
+	kvmppc_set_msr(vcpu, msr);
+	kvmppc_set_dar(vcpu, eaddr);
 	/* Page Fault */
 	dsisr = kvmppc_set_field(0, 33, 33, 1);
 	if (is_store)
-		shared->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
+		dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
+	kvmppc_set_dsisr(vcpu, dsisr);
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
 }
 
···
 	if (!kvmppc_inst_is_paired_single(vcpu, inst))
 		return EMULATE_FAIL;
 
-	if (!(vcpu->arch.shared->msr & MSR_FP)) {
+	if (!(kvmppc_get_msr(vcpu) & MSR_FP)) {
 		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL);
 		return EMULATE_AGAIN;
 	}

arch/powerpc/kvm/book3s_pr.c

···
 
 static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 			     ulong msr);
+static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 
 /* Some compatibility defines */
 #ifdef CONFIG_PPC_BOOK3S_32
···
 #endif
 
 	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
+	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
 	vcpu->cpu = -1;
 }
 
···
 	svcpu->ctr = vcpu->arch.ctr;
 	svcpu->lr  = vcpu->arch.lr;
 	svcpu->pc  = vcpu->arch.pc;
+#ifdef CONFIG_PPC_BOOK3S_64
+	svcpu->shadow_fscr = vcpu->arch.shadow_fscr;
+#endif
 	svcpu->in_use = true;
 }
 
···
 	vcpu->arch.fault_dar   = svcpu->fault_dar;
 	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
 	vcpu->arch.last_inst   = svcpu->last_inst;
+#ifdef CONFIG_PPC_BOOK3S_64
+	vcpu->arch.shadow_fscr = svcpu->shadow_fscr;
+#endif
 	svcpu->in_use = false;
 
 out:
···
 
 static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 {
-	ulong smsr = vcpu->arch.shared->msr;
+	ulong guest_msr = kvmppc_get_msr(vcpu);
+	ulong smsr = guest_msr;
 
 	/* Guest MSR values */
-	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE;
+	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_LE;
 	/* Process MSR values */
 	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
 	/* External providers the guest reserved */
-	smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
+	smsr |= (guest_msr & vcpu->arch.guest_owned_ext);
 	/* 64-bit Process MSR values */
 #ifdef CONFIG_PPC_BOOK3S_64
 	smsr |= MSR_ISF | MSR_HV;
···
 
 static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 {
-	ulong old_msr = vcpu->arch.shared->msr;
+	ulong old_msr = kvmppc_get_msr(vcpu);
 
 #ifdef EXIT_DEBUG
 	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
 #endif
 
 	msr &= to_book3s(vcpu)->msr_mask;
-	vcpu->arch.shared->msr = msr;
+	kvmppc_set_msr_fast(vcpu, msr);
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	if (msr & MSR_POW) {
···
 
 			/* Unset POW bit after we woke up */
 			msr &= ~MSR_POW;
-			vcpu->arch.shared->msr = msr;
+			kvmppc_set_msr_fast(vcpu, msr);
 		}
 	}
 
-	if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
+	if ((kvmppc_get_msr(vcpu) & (MSR_PR|MSR_IR|MSR_DR)) !=
 		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
···
 	}
 
 	/* Preload FPU if it's enabled */
-	if (vcpu->arch.shared->msr & MSR_FP)
+	if (kvmppc_get_msr(vcpu) & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 }
 
···
 
 	/* patch dcbz into reserved instruction, so we trap */
 	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
-		if ((page[i] & 0xff0007ff) == INS_DCBZ)
-			page[i] &= 0xfffffff7;
+		if ((be32_to_cpu(page[i]) & 0xff0007ff) == INS_DCBZ)
+			page[i] &= cpu_to_be32(0xfffffff7);
 
 	kunmap_atomic(page);
 	put_page(hpage);
···
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
-	if (!(vcpu->arch.shared->msr & MSR_SF))
+	if (!(kvmppc_get_msr(vcpu) & MSR_SF))
 		mp_pa = (uint32_t)mp_pa;
 
 	if (unlikely(mp_pa) &&
···
 	int page_found = 0;
 	struct kvmppc_pte pte;
 	bool is_mmio = false;
-	bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
-	bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
+	bool dr = (kvmppc_get_msr(vcpu) & MSR_DR) ? true : false;
+	bool ir = (kvmppc_get_msr(vcpu) & MSR_IR) ? true : false;
 	u64 vsid;
 
 	relocated = data ? dr : ir;
···
 		pte.page_size = MMU_PAGE_64K;
 	}
 
-	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	switch (kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) {
 	case 0:
 		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
 		break;
···
 	case MSR_IR:
 		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
 
-		if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
+		if ((kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) == MSR_DR)
 			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
 		else
 			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
···
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr;
-		vcpu->arch.shared->msr |=
-			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
+		u64 ssrr1 = vcpu->arch.shadow_srr1;
+		u64 msr = kvmppc_get_msr(vcpu);
+		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
+		kvmppc_set_dsisr(vcpu, vcpu->arch.fault_dsisr);
+		kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
-		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
-		vcpu->arch.shared->msr |=
-			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
+		u32 dsisr = vcpu->arch.fault_dsisr;
+		u64 ssrr1 = vcpu->arch.shadow_srr1;
+		u64 msr = kvmppc_get_msr(vcpu);
+		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
+		dsisr = (dsisr & ~DSISR_NOHPTE) | DSISR_PROTFAULT;
+		kvmppc_set_dsisr(vcpu, dsisr);
+		kvmppc_set_msr_fast(vcpu, msr | (ssrr1 & 0xf8000000ULL));
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+		kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
 		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
 	} else if (!is_mmio &&
 		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
···
 	kvmppc_recalc_shadow_msr(vcpu);
 }
 
+/* Give up facility (TAR / EBB / DSCR) */
+static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (!(vcpu->arch.shadow_fscr & (1ULL << fac))) {
+		/* Facility not available to the guest, ignore giveup request*/
+		return;
+	}
+
+	switch (fac) {
+	case FSCR_TAR_LG:
+		vcpu->arch.tar = mfspr(SPRN_TAR);
+		mtspr(SPRN_TAR, current->thread.tar);
+		vcpu->arch.shadow_fscr &= ~FSCR_TAR;
+		break;
+	}
+#endif
+}
+
 static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
 {
 	ulong srr0 = kvmppc_get_pc(vcpu);
···
 
 	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
 	if (ret == -ENOENT) {
-		ulong msr = vcpu->arch.shared->msr;
+		ulong msr = kvmppc_get_msr(vcpu);
 
 		msr = kvmppc_set_field(msr, 33, 33, 1);
 		msr = kvmppc_set_field(msr, 34, 36, 0);
-		vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
+		msr = kvmppc_set_field(msr, 42, 47, 0);
+		kvmppc_set_msr_fast(vcpu, msr);
 		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
 		return EMULATE_AGAIN;
 	}
···
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
 		return RESUME_GUEST;
 
-	if (!(vcpu->arch.shared->msr & msr)) {
+	if (!(kvmppc_get_msr(vcpu) & msr)) {
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		return RESUME_GUEST;
 	}
···
 #endif
 
 	if (msr & MSR_FP) {
+		preempt_disable();
 		enable_kernel_fp();
 		load_fp_state(&vcpu->arch.fp);
 		t->fp_save_area = &vcpu->arch.fp;
+		preempt_enable();
 	}
 
 	if (msr & MSR_VEC) {
 #ifdef CONFIG_ALTIVEC
+		preempt_disable();
 		enable_kernel_altivec();
 		load_vr_state(&vcpu->arch.vr);
 		t->vr_save_area = &vcpu->arch.vr;
+		preempt_enable();
 #endif
 	}
 
···
 		return;
 
 	if (lost_ext & MSR_FP) {
+		preempt_disable();
 		enable_kernel_fp();
 		load_fp_state(&vcpu->arch.fp);
+		preempt_enable();
 	}
 #ifdef CONFIG_ALTIVEC
 	if (lost_ext & MSR_VEC) {
+		preempt_disable();
 		enable_kernel_altivec();
 		load_vr_state(&vcpu->arch.vr);
+		preempt_enable();
 	}
 #endif
 	current->thread.regs->msr |= lost_ext;
 }
+
+#ifdef CONFIG_PPC_BOOK3S_64
+
+static void kvmppc_trigger_fac_interrupt(struct kvm_vcpu *vcpu, ulong fac)
+{
+	/* Inject the Interrupt Cause field and trigger a guest interrupt */
+	vcpu->arch.fscr &= ~(0xffULL << 56);
+	vcpu->arch.fscr |= (fac << 56);
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
+}
+
+static void kvmppc_emulate_fac(struct kvm_vcpu *vcpu, ulong fac)
+{
+	enum emulation_result er = EMULATE_FAIL;
+
+	if (!(kvmppc_get_msr(vcpu) & MSR_PR))
+		er = kvmppc_emulate_instruction(vcpu->run, vcpu);
+
+	if ((er != EMULATE_DONE) && (er != EMULATE_AGAIN)) {
+		/* Couldn't emulate, trigger interrupt in guest */
+		kvmppc_trigger_fac_interrupt(vcpu, fac);
+	}
+}
+
+/* Enable facilities (TAR, EBB, DSCR) for the guest */
+static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac)
+{
+	bool guest_fac_enabled;
+	BUG_ON(!cpu_has_feature(CPU_FTR_ARCH_207S));
+
+	/*
+	 * Not every facility is enabled by FSCR bits, check whether the
+	 * guest has this facility enabled at all.
+	 */
+	switch (fac) {
+	case FSCR_TAR_LG:
+	case FSCR_EBB_LG:
+		guest_fac_enabled = (vcpu->arch.fscr & (1ULL << fac));
+		break;
+	case FSCR_TM_LG:
+		guest_fac_enabled = kvmppc_get_msr(vcpu) & MSR_TM;
+		break;
+	default:
+		guest_fac_enabled = false;
+		break;
+	}
+
+	if (!guest_fac_enabled) {
+		/* Facility not enabled by the guest */
+		kvmppc_trigger_fac_interrupt(vcpu, fac);
+		return RESUME_GUEST;
+	}
+
+	switch (fac) {
+	case FSCR_TAR_LG:
+		/* TAR switching isn't lazy in Linux yet */
+		current->thread.tar = mfspr(SPRN_TAR);
+		mtspr(SPRN_TAR, vcpu->arch.tar);
+		vcpu->arch.shadow_fscr |= FSCR_TAR;
+		break;
+	default:
+		kvmppc_emulate_fac(vcpu, fac);
+		break;
+	}
+
+	return RESUME_GUEST;
+}
+#endif
 
 int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			  unsigned int exit_nr)
···
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		} else {
-			vcpu->arch.shared->msr |= shadow_srr1 & 0x58000000;
+			u64 msr = kvmppc_get_msr(vcpu);
+			msr |= shadow_srr1 & 0x58000000;
+			kvmppc_set_msr_fast(vcpu, msr);
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
···
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 			srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		} else {
-			vcpu->arch.shared->dar = dar;
-			vcpu->arch.shared->dsisr = fault_dsisr;
+			kvmppc_set_dar(vcpu, dar);
+			kvmppc_set_dsisr(vcpu, fault_dsisr);
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
···
 	}
 	case BOOK3S_INTERRUPT_DATA_SEGMENT:
 		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
-			vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+			kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu));
 			kvmppc_book3s_queue_irqprio(vcpu,
 				BOOK3S_INTERRUPT_DATA_SEGMENT);
 		}
···
 program_interrupt:
 		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
 
-		if (vcpu->arch.shared->msr & MSR_PR) {
+		if (kvmppc_get_msr(vcpu) & MSR_PR) {
 #ifdef EXIT_DEBUG
 			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
 #endif
···
 	case BOOK3S_INTERRUPT_SYSCALL:
 		if (vcpu->arch.papr_enabled &&
 		    (kvmppc_get_last_sc(vcpu) == 0x44000022) &&
-		    !(vcpu->arch.shared->msr & MSR_PR)) {
+		    !(kvmppc_get_msr(vcpu) & MSR_PR)) {
 			/* SC 1 papr hypercalls */
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
 			int i;
···
 				gprs[i] = kvmppc_get_gpr(vcpu, i);
 			vcpu->arch.osi_needed = 1;
 			r = RESUME_HOST_NV;
-		} else if (!(vcpu->arch.shared->msr & MSR_PR) &&
+		} else if (!(kvmppc_get_msr(vcpu) & MSR_PR) &&
 		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
 			/* KVM PV hypercalls */
 			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
···
 	}
 	case BOOK3S_INTERRUPT_ALIGNMENT:
 		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
-			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
-				kvmppc_get_last_inst(vcpu));
-			vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
-				kvmppc_get_last_inst(vcpu));
+			u32 last_inst = kvmppc_get_last_inst(vcpu);
+			u32 dsisr;
+			u64 dar;
+
+			dsisr = kvmppc_alignment_dsisr(vcpu, last_inst);
+			dar = kvmppc_alignment_dar(vcpu, last_inst);
+
+			kvmppc_set_dsisr(vcpu, dsisr);
+			kvmppc_set_dar(vcpu, dar);
+
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		}
 		r = RESUME_GUEST;
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case BOOK3S_INTERRUPT_FAC_UNAVAIL:
+		kvmppc_handle_fac(vcpu, vcpu->arch.shadow_fscr >> 56);
+		r = RESUME_GUEST;
+		break;
+#endif
 	case BOOK3S_INTERRUPT_MACHINE_CHECK:
 	case BOOK3S_INTERRUPT_TRACE:
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
···
 		}
 	} else {
 		for (i = 0; i < 16; i++)
-			sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];
+			sregs->u.s.ppc32.sr[i] = kvmppc_get_sr(vcpu, i);
 
 		for (i = 0; i < 8; i++) {
 			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
···
 	case KVM_REG_PPC_HIOR:
 		*val = get_reg_val(id, to_book3s(vcpu)->hior);
 		break;
+	case KVM_REG_PPC_LPCR:
+		/*
+		 * We are only interested in the LPCR_ILE bit
+		 */
+		if (vcpu->arch.intr_msr & MSR_LE)
+			*val = get_reg_val(id, LPCR_ILE);
+		else
+			*val = get_reg_val(id, 0);
+		break;
 	default:
 		r = -EINVAL;
 		break;
 	}
 
 	return r;
+}
+
+static void kvmppc_set_lpcr_pr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+{
+	if (new_lpcr & LPCR_ILE)
+		vcpu->arch.intr_msr |= MSR_LE;
+	else
+		vcpu->arch.intr_msr &= ~MSR_LE;
 }
 
 static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
···
 	case KVM_REG_PPC_HIOR:
 		to_book3s(vcpu)->hior = set_reg_val(id, *val);
 		to_book3s(vcpu)->hior_explicit = true;
+		break;
+	case KVM_REG_PPC_LPCR:
+		kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val));
 		break;
 	default:
 		r = -EINVAL;
···
 		goto uninit_vcpu;
 	/* the real shared page fills the last 4k of our page */
 	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
-
 #ifdef CONFIG_PPC_BOOK3S_64
+	/* Always start the shared struct in native endian mode */
+#ifdef __BIG_ENDIAN__
+        vcpu->arch.shared_big_endian = true;
+#else
+        vcpu->arch.shared_big_endian = false;
+#endif
+
 	/*
 	 * Default to the same as the host if we're on sufficiently
 	 * recent machine that we have 1TB segments;
···
 	vcpu->arch.pvr = 0x3C0301;
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		vcpu->arch.pvr = mfspr(SPRN_PVR);
+	vcpu->arch.intr_msr = MSR_SF;
 #else
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
···
 	kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr);
 	vcpu->arch.slb_nr = 64;
 
-	vcpu->arch.shadow_msr = MSR_USER64;
+	vcpu->arch.shadow_msr = MSR_USER64 & ~MSR_LE;
 
 	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
···
 #endif
 
 	/* Preload FPU if it's enabled */
-	if (vcpu->arch.shared->msr & MSR_FP)
+	if (kvmppc_get_msr(vcpu) & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
 	kvmppc_fix_ee_before_entry();
···
 
 	/* Make sure we save the guest FPU/Altivec/VSX state */
 	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
+
+	/* Make sure we save the guest TAR/EBB/DSCR state */
+	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
 
 out:
 	vcpu->mode = OUTSIDE_GUEST_MODE;

arch/powerpc/kvm/book3s_pr_papr.c

···
 		for (i = 0; ; ++i) {
 			if (i == 8)
 				goto done;
-			if ((*hpte & HPTE_V_VALID) == 0)
+			if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0)
 				break;
 			hpte += 2;
 		}
···
 			goto done;
 	}
 
-	hpte[0] = kvmppc_get_gpr(vcpu, 6);
-	hpte[1] = kvmppc_get_gpr(vcpu, 7);
+	hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6));
+	hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7));
 	pteg_addr += i * HPTE_SIZE;
 	copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
 	kvmppc_set_gpr(vcpu, 4, pte_index | i);
···
 	pteg = get_pteg_addr(vcpu, pte_index);
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+	pte[0] = be64_to_cpu(pte[0]);
+	pte[1] = be64_to_cpu(pte[1]);
 
 	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
···
 
 		pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
 		copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+		pte[0] = be64_to_cpu(pte[0]);
+		pte[1] = be64_to_cpu(pte[1]);
 
 		/* tsl = AVPN */
 		flags = (tsh & H_BULK_REMOVE_FLAGS) >> 26;
···
 	pteg = get_pteg_addr(vcpu, pte_index);
 	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+	pte[0] = be64_to_cpu(pte[0]);
+	pte[1] = be64_to_cpu(pte[1]);
 
 	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
···
 
 	rb = compute_tlbie_rb(v, r, pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
+	pte[0] = cpu_to_be64(pte[0]);
+	pte[1] = cpu_to_be64(pte[1]);
 	copy_to_user((void __user *)pteg, pte, sizeof(pte));
 	ret = H_SUCCESS;
 
···
 	case H_PUT_TCE:
 		return kvmppc_h_pr_put_tce(vcpu);
 	case H_CEDE:
-		vcpu->arch.shared->msr |= MSR_EE;
+		kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE);
 		kvm_vcpu_block(vcpu);
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;

arch/powerpc/kvm/book3s_rtas.c

···
 	return rc;
 }
 
+static void kvmppc_rtas_swap_endian_in(struct rtas_args *args)
+{
+#ifdef __LITTLE_ENDIAN__
+	int i;
+
+	args->token = be32_to_cpu(args->token);
+	args->nargs = be32_to_cpu(args->nargs);
+	args->nret = be32_to_cpu(args->nret);
+	for (i = 0; i < args->nargs; i++)
+		args->args[i] = be32_to_cpu(args->args[i]);
+#endif
+}
+
+static void kvmppc_rtas_swap_endian_out(struct rtas_args *args)
+{
+#ifdef __LITTLE_ENDIAN__
+	int i;
+
+	for (i = 0; i < args->nret; i++)
+		args->args[i] = cpu_to_be32(args->args[i]);
+	args->token = cpu_to_be32(args->token);
+	args->nargs = cpu_to_be32(args->nargs);
+	args->nret = cpu_to_be32(args->nret);
+#endif
+}
+
 int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 {
 	struct rtas_token_definition *d;
···
 	rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 	if (rc)
 		goto fail;
+
+	kvmppc_rtas_swap_endian_in(&args);
 
 	/*
 	 * args->rets is a pointer into args->args. Now that we've
···
 
 	if (rc == 0) {
 		args.rets = orig_rets;
+		kvmppc_rtas_swap_endian_out(&args);
 		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 		if (rc)
 			goto fail;

arch/powerpc/kvm/book3s_segment.S

···
 	LOAD_GUEST_SEGMENTS
 
 #ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+	/* Save host FSCR */
+	mfspr	r8, SPRN_FSCR
+	std	r8, HSTATE_HOST_FSCR(r13)
+	/* Set FSCR during guest execution */
+	ld	r9, SVCPU_SHADOW_FSCR(r13)
+	mtspr	SPRN_FSCR, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	/* Some guests may need to have dcbz set to 32 byte length.
 	 *
 	 * Usually we ensure that by patching the guest's instructions
···
 	cmpwi	r12, BOOK3S_INTERRUPT_H_EMUL_ASSIST
 	beq-	ld_last_inst
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+BEGIN_FTR_SECTION
+	cmpwi	r12, BOOK3S_INTERRUPT_FAC_UNAVAIL
+	beq-	ld_last_inst
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 #endif
 
 	b	no_ld_last_inst
···
 	mtspr   SPRN_HID5,r5
 
 no_dcbz32_off:
+
+BEGIN_FTR_SECTION
+	/* Save guest FSCR on a FAC_UNAVAIL interrupt */
+	cmpwi	r12, BOOK3S_INTERRUPT_FAC_UNAVAIL
+	bne+	no_fscr_save
+	mfspr	r7, SPRN_FSCR
+	std	r7, SVCPU_SHADOW_FSCR(r13)
+no_fscr_save:
+	/* Restore host FSCR */
+	ld	r8, HSTATE_HOST_FSCR(r13)
+	mtspr	SPRN_FSCR, r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 #endif /* CONFIG_PPC_BOOK3S_64 */
 

arch/powerpc/kvm/e500_emulate.c

···
 #include "booke.h"
 #include "e500.h"
 
+#define XOP_DCBTLS  166
 #define XOP_MSGSND  206
 #define XOP_MSGCLR  238
 #define XOP_TLBIVAX 786
···
 	return emulated;
 }
 
+static int kvmppc_e500_emul_dcbtls(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	/* Always fail to lock the cache */
+	vcpu_e500->l1csr0 |= L1CSR0_CUL;
+	return EMULATE_DONE;
+}
+
 int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				unsigned int inst, int *advance)
 {
···
 	switch (get_op(inst)) {
 	case 31:
 		switch (get_xop(inst)) {
+
+		case XOP_DCBTLS:
+			emulated = kvmppc_e500_emul_dcbtls(vcpu);
+			break;
 
 #ifdef CONFIG_KVM_E500MC
 		case XOP_MSGSND:
···
 		break;
 	case SPRN_L1CSR1:
 		vcpu_e500->l1csr1 = spr_val;
+		vcpu_e500->l1csr1 &= ~(L1CSR1_ICFI | L1CSR1_ICLFR);
 		break;
 	case SPRN_HID0:
 		vcpu_e500->hid0 = spr_val;

arch/powerpc/kvm/emulate.c

···
 
 	switch (sprn) {
 	case SPRN_SRR0:
-		vcpu->arch.shared->srr0 = spr_val;
+		kvmppc_set_srr0(vcpu, spr_val);
 		break;
 	case SPRN_SRR1:
-		vcpu->arch.shared->srr1 = spr_val;
+		kvmppc_set_srr1(vcpu, spr_val);
 		break;
 
 	/* XXX We need to context-switch the timebase for
···
 		break;
 
 	case SPRN_SPRG0:
-		vcpu->arch.shared->sprg0 = spr_val;
+		kvmppc_set_sprg0(vcpu, spr_val);
 		break;
 	case SPRN_SPRG1:
-		vcpu->arch.shared->sprg1 = spr_val;
+		kvmppc_set_sprg1(vcpu, spr_val);
 		break;
 	case SPRN_SPRG2:
-		vcpu->arch.shared->sprg2 = spr_val;
+		kvmppc_set_sprg2(vcpu, spr_val);
 		break;
 	case SPRN_SPRG3:
-		vcpu->arch.shared->sprg3 = spr_val;
+		kvmppc_set_sprg3(vcpu, spr_val);
 		break;
 
 	/* PIR can legally be written, but we ignore it */
···
 
 	switch (sprn) {
 	case SPRN_SRR0:
-		spr_val = vcpu->arch.shared->srr0;
+		spr_val = kvmppc_get_srr0(vcpu);
 		break;
 	case SPRN_SRR1:
-		spr_val = vcpu->arch.shared->srr1;
+		spr_val = kvmppc_get_srr1(vcpu);
 		break;
 	case SPRN_PVR:
 		spr_val = vcpu->arch.pvr;
···
 		break;
 
 	case SPRN_SPRG0:
-		spr_val = vcpu->arch.shared->sprg0;
+		spr_val = kvmppc_get_sprg0(vcpu);
 		break;
 	case SPRN_SPRG1:
-		spr_val = vcpu->arch.shared->sprg1;
+		spr_val = kvmppc_get_sprg1(vcpu);
 		break;
 	case SPRN_SPRG2:
-		spr_val = vcpu->arch.shared->sprg2;
+		spr_val = kvmppc_get_sprg2(vcpu);
 		break;
 	case SPRN_SPRG3:
-		spr_val = vcpu->arch.shared->sprg3;
+		spr_val = kvmppc_get_sprg3(vcpu);
 		break;
 	/* Note: SPRG4-7 are user-readable, so we don't get
 	 * a trap. */

arch/powerpc/kvm/mpic.c

···
 				      u32 val, int idx);
 static int openpic_cpu_read_internal(void *opaque, gpa_t addr,
 				     u32 *ptr, int idx);
+static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ,
+				    uint32_t val);
 
 enum irq_type {
 	IRQ_TYPE_NORMAL = 0,
···
 	/* Initialise IRQ sources */
 	for (i = 0; i < opp->max_irq; i++) {
 		opp->src[i].ivpr = opp->ivpr_reset;
-		opp->src[i].idr = opp->idr_reset;
 
 		switch (opp->src[i].type) {
 		case IRQ_TYPE_NORMAL:
···
 		case IRQ_TYPE_FSLSPECIAL:
 			break;
 		}
+
+		write_IRQreg_idr(opp, i, opp->idr_reset);
 	}
 	/* Initialise IRQ destinations */
 	for (i = 0; i < MAX_CPU; i++) {

arch/powerpc/kvm/powerpc.c

···
 }
 EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
 
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+static void kvmppc_swab_shared(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
+	int i;
+
+	shared->sprg0 = swab64(shared->sprg0);
+	shared->sprg1 = swab64(shared->sprg1);
+	shared->sprg2 = swab64(shared->sprg2);
+	shared->sprg3 = swab64(shared->sprg3);
+	shared->srr0 = swab64(shared->srr0);
+	shared->srr1 = swab64(shared->srr1);
+	shared->dar = swab64(shared->dar);
+	shared->msr = swab64(shared->msr);
+	shared->dsisr = swab32(shared->dsisr);
+	shared->int_pending = swab32(shared->int_pending);
+	for (i = 0; i < ARRAY_SIZE(shared->sr); i++)
+		shared->sr[i] = swab32(shared->sr[i]);
+}
+#endif
+
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
 	int nr = kvmppc_get_gpr(vcpu, 11);
···
 	unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
 	unsigned long r2 = 0;
 
-	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+	if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
 		/* 32 bit mode */
 		param1 &= 0xffffffff;
 		param2 &= 0xffffffff;
···
 	switch (nr) {
 	case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
 	{
-		vcpu->arch.magic_page_pa = param1;
-		vcpu->arch.magic_page_ea = param2;
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+		/* Book3S can be little endian, find it out here */
+		int shared_big_endian = true;
+		if (vcpu->arch.intr_msr & MSR_LE)
+			shared_big_endian = false;
+		if (shared_big_endian != vcpu->arch.shared_big_endian)
+			kvmppc_swab_shared(vcpu);
+		vcpu->arch.shared_big_endian = shared_big_endian;
+#endif
+
+		if (!(param2 & MAGIC_PAGE_FLAG_NOT_MAPPED_NX)) {
+			/*
+			 * Older versions of the Linux magic page code had
+			 * a bug where they would map their trampoline code
+			 * NX. If that's the case, remove !PR NX capability.
+			 */
+			vcpu->arch.disable_kernel_nx = true;
+			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+		}
+
+		vcpu->arch.magic_page_pa = param1 & ~0xfffULL;
+		vcpu->arch.magic_page_ea = param2 & ~0xfffULL;
 
 		r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
 
···
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_PPC_ALLOC_HTAB:
 	case KVM_CAP_PPC_RTAS:
+	case KVM_CAP_PPC_FIXUP_HCALL:
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
···
 	u32 inst_nop = 0x60000000;
 #ifdef CONFIG_KVM_BOOKE_HV
 	u32 inst_sc1 = 0x44000022;
-	pvinfo->hcall[0] = inst_sc1;
-	pvinfo->hcall[1] = inst_nop;
-	pvinfo->hcall[2] = inst_nop;
-	pvinfo->hcall[3] = inst_nop;
+	pvinfo->hcall[0] = cpu_to_be32(inst_sc1);
+	pvinfo->hcall[1] = cpu_to_be32(inst_nop);
+	pvinfo->hcall[2] = cpu_to_be32(inst_nop);
+	pvinfo->hcall[3] = cpu_to_be32(inst_nop);
 #else
 	u32 inst_lis = 0x3c000000;
 	u32 inst_ori = 0x60000000;
···
 	 *    sc
 	 *    nop
 	 */
-	pvinfo->hcall[0] = inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask);
-	pvinfo->hcall[1] = inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask);
-	pvinfo->hcall[2] = inst_sc;
-	pvinfo->hcall[3] = inst_nop;
+	pvinfo->hcall[0] = cpu_to_be32(inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask));
+	pvinfo->hcall[1] = cpu_to_be32(inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask));
+	pvinfo->hcall[2] = cpu_to_be32(inst_sc);
+	pvinfo->hcall[3] = cpu_to_be32(inst_nop);
 #endif
 
 	pvinfo->flags = KVM_PPC_PVINFO_FLAGS_EV_IDLE;

arch/powerpc/kvm/trace_pr.h

···
 		__entry->exit_nr	= exit_nr;
 		__entry->pc		= kvmppc_get_pc(vcpu);
 		__entry->dar		= kvmppc_get_fault_dar(vcpu);
-		__entry->msr		= vcpu->arch.shared->msr;
+		__entry->msr		= kvmppc_get_msr(vcpu);
 		__entry->srr1		= vcpu->arch.shadow_srr1;
 		__entry->last_inst	= vcpu->arch.last_inst;
 	),

arch/powerpc/mm/slb.c

···
 static void __slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
-	 * appropriately too. */
+	 * and PR KVM appropriately too. */
 	unsigned long linear_llp, vmalloc_llp, lflags, vflags;
 	unsigned long ksp_esid_data, ksp_vsid_data;
 

arch/s390/include/asm/ctl_reg.h

···
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
+union ctlreg0 {
+	unsigned long val;
+	struct {
+#ifdef CONFIG_64BIT
+		unsigned long	   : 32;
+#endif
+		unsigned long	   : 3;
+		unsigned long lap  : 1; /* Low-address-protection control */
+		unsigned long	   : 4;
+		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
+		unsigned long	   : 23;
+	};
+};
+
 #ifdef CONFIG_SMP
 # define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
 # define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)

arch/s390/include/asm/kvm_host.h

···
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
 
+#define SIGP_CTRL_C	0x00800000
+
 struct sca_entry {
-	atomic_t scn;
+	atomic_t ctrl;
 	__u32	reserved;
 	__u64	sda;
 	__u64	reserved2[2];
 } __attribute__((packed));
 
+union ipte_control {
+	unsigned long val;
+	struct {
+		unsigned long k  : 1;
+		unsigned long kh : 31;
+		unsigned long kg : 32;
+	};
+};
 
 struct sca_block {
-	__u64	ipte_control;
+	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
···
 #define CPUSTAT_ZARCH      0x00000800
 #define CPUSTAT_MCDS       0x00000100
 #define CPUSTAT_SM         0x00000080
+#define CPUSTAT_IBS        0x00000040
 #define CPUSTAT_G          0x00000008
 #define CPUSTAT_GED        0x00000004
 #define CPUSTAT_J          0x00000002
···
 
 struct kvm_s390_sie_block {
 	atomic_t cpuflags;		/* 0x0000 */
-	__u32	prefix;			/* 0x0004 */
+	__u32 : 1;			/* 0x0004 */
+	__u32 prefix : 18;
+	__u32 : 13;
 	__u8	reserved08[4];		/* 0x0008 */
 #define PROG_IN_SIE (1<<0)
 	__u32	prog0c;			/* 0x000c */
···
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
 #define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
-#define ICTL_LPSW 0x00400000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
+#define ICTL_TPROT	0x00000200
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
 	__u8	icptcode;		/* 0x0050 */
 	__u8	reserved51;		/* 0x0051 */
 	__u16	ihcpu;			/* 0x0052 */
···
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[30];		/* 0x00b0 */
-	__u16   iprcc;			/* 0x00ce */
-	__u8	reservedd0[48];		/* 0x00d0 */
+	__u8	reservedb0[20];		/* 0x00b0 */
+	__u16	extcpuaddr;		/* 0x00c4 */
+	__u16	eic;			/* 0x00c6 */
+	__u32	reservedc8;		/* 0x00c8 */
+	__u16	pgmilc;			/* 0x00cc */
+	__u16	iprcc;			/* 0x00ce */
+	__u32	dxc;			/* 0x00d0 */
+	__u16	mcn;			/* 0x00d4 */
+	__u8	perc;			/* 0x00d6 */
+	__u8	peratmid;		/* 0x00d7 */
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	__u64	tecmc;			/* 0x00e8 */
+	__u8	reservedf0[16];		/* 0x00f0 */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
···
 	u32 exit_instruction;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
+	u32 instruction_stctl;
+	u32 instruction_stctg;
 	u32 exit_program_interruption;
 	u32 exit_instr_and_program;
 	u32 deliver_external_call;
···
 	u32 instruction_stpx;
 	u32 instruction_stap;
 	u32 instruction_storage_key;
+	u32 instruction_ipte_interlock;
 	u32 instruction_stsch;
 	u32 instruction_chsc;
 	u32 instruction_stsi;
···
 	u32 diagnose_9c;
 };
 
-#define PGM_OPERATION            0x01
-#define PGM_PRIVILEGED_OP	 0x02
-#define PGM_EXECUTE              0x03
-#define PGM_PROTECTION           0x04
-#define PGM_ADDRESSING           0x05
-#define PGM_SPECIFICATION        0x06
-#define PGM_DATA                 0x07
+#define PGM_OPERATION			0x01
+#define PGM_PRIVILEGED_OP		0x02
+#define PGM_EXECUTE			0x03
+#define PGM_PROTECTION			0x04
+#define PGM_ADDRESSING			0x05
+#define PGM_SPECIFICATION		0x06
+#define PGM_DATA			0x07
+#define PGM_FIXED_POINT_OVERFLOW	0x08
+#define PGM_FIXED_POINT_DIVIDE		0x09
+#define PGM_DECIMAL_OVERFLOW		0x0a
+#define PGM_DECIMAL_DIVIDE		0x0b
+#define PGM_HFP_EXPONENT_OVERFLOW	0x0c
+#define PGM_HFP_EXPONENT_UNDERFLOW	0x0d
+#define PGM_HFP_SIGNIFICANCE		0x0e
+#define PGM_HFP_DIVIDE			0x0f
+#define PGM_SEGMENT_TRANSLATION		0x10
+#define PGM_PAGE_TRANSLATION		0x11
+#define PGM_TRANSLATION_SPEC		0x12
+#define PGM_SPECIAL_OPERATION		0x13
+#define PGM_OPERAND			0x15
+#define PGM_TRACE_TABEL			0x16
+#define PGM_SPACE_SWITCH		0x1c
+#define PGM_HFP_SQUARE_ROOT		0x1d
+#define PGM_PC_TRANSLATION_SPEC		0x1f
+#define PGM_AFX_TRANSLATION		0x20
+#define PGM_ASX_TRANSLATION		0x21
+#define PGM_LX_TRANSLATION		0x22
+#define PGM_EX_TRANSLATION		0x23
+#define PGM_PRIMARY_AUTHORITY		0x24
+#define PGM_SECONDARY_AUTHORITY		0x25
+#define PGM_LFX_TRANSLATION		0x26
+#define PGM_LSX_TRANSLATION		0x27
+#define PGM_ALET_SPECIFICATION		0x28
+#define PGM_ALEN_TRANSLATION		0x29
+#define PGM_ALE_SEQUENCE		0x2a
+#define PGM_ASTE_VALIDITY		0x2b
+#define PGM_ASTE_SEQUENCE		0x2c
+#define PGM_EXTENDED_AUTHORITY		0x2d
+#define PGM_LSTE_SEQUENCE		0x2e
+#define PGM_ASTE_INSTANCE		0x2f
+#define PGM_STACK_FULL			0x30
+#define PGM_STACK_EMPTY			0x31
+#define PGM_STACK_SPECIFICATION		0x32
+#define PGM_STACK_TYPE			0x33
+#define PGM_STACK_OPERATION		0x34
+#define PGM_ASCE_TYPE			0x38
+#define PGM_REGION_FIRST_TRANS		0x39
+#define PGM_REGION_SECOND_TRANS		0x3a
+#define PGM_REGION_THIRD_TRANS		0x3b
+#define PGM_MONITOR			0x40
+#define PGM_PER				0x80
+#define PGM_CRYPTO_OPERATION		0x119
 
 struct kvm_s390_interrupt_info {
 	struct list_head list;
···
 	unsigned int irq_count;
 };
 
+struct kvm_hw_wp_info_arch {
+	unsigned long addr;
+	unsigned long phys_addr;
+	int len;
+	char *old_data;
+};
+
+struct kvm_hw_bp_info_arch {
+	unsigned long addr;
+	int len;
+};
+
+/*
+ * Only the upper 16 bits of kvm_guest_debug->control are arch specific.
+ * Further KVM_GUESTDBG flags which an be used from userspace can be found in
+ * arch/s390/include/uapi/asm/kvm.h
+ */
+#define KVM_GUESTDBG_EXIT_PENDING 0x10000000
+
+#define guestdbg_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)
+#define guestdbg_sstep_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+#define guestdbg_hw_bp_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+#define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \
+		(vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING))
+
+struct kvm_guestdbg_info_arch {
+	unsigned long cr0;
+	unsigned long cr9;
+	unsigned long cr10;
+	unsigned long cr11;
+	struct kvm_hw_bp_info_arch *hw_bp_info;
+	struct kvm_hw_wp_info_arch *hw_wp_info;
+	int nr_hw_bp;
+	int nr_hw_wp;
+	unsigned long last_bp;
+};
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
···
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
+	struct kvm_s390_pgm_info pgm;
 	union  {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
 	struct gmap *gmap;
+	struct kvm_guestdbg_info_arch guestdbg;
 #define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
 	unsigned long pfault_token;
 	unsigned long pfault_select;
···
 	struct gmap *gmap;
 	int css_support;
 	int use_irqchip;
+	int use_cmma;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
+	wait_queue_head_t ipte_wq;
+	spinlock_t start_stop_lock;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)

arch/s390/include/asm/lowcore.h

···
 	__u16	pgm_code;			/* 0x008e */
 	__u32	trans_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u32	per_address;			/* 0x0098 */
 	__u32	monitor_code;			/* 0x009c */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00b8-0x00a4];	/* 0x00a4 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
···
 	__u16	pgm_code;			/* 0x008e */
 	__u32	data_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u64	per_address;			/* 0x0098 */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
 	__u64	trans_exc_code;			/* 0x00a8 */
 	__u64	monitor_code;			/* 0x00b0 */

arch/s390/include/asm/mmu.h

···
 	unsigned long vdso_base;
 	/* The mmu context has extended page tables. */
 	unsigned int has_pgste:1;
+	/* The mmu context uses storage keys. */
+	unsigned int use_skey:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \

arch/s390/include/asm/mmu_context.h

···
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
 	mm->context.has_pgste = 0;
+	mm->context.use_skey = 0;
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;

arch/s390/include/asm/pgalloc.h

···
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
-void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
+			    bool init_skey);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);
 

arch/s390/include/asm/pgtable.h

···
 #define PGSTE_HC_BIT	0x00200000UL
 #define PGSTE_GR_BIT	0x00040000UL
 #define PGSTE_GC_BIT	0x00020000UL
-#define PGSTE_IN_BIT	0x00008000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x00008000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x00004000UL	/* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
···
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_IN_BIT	0x0000800000000000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
···
 #endif
 	return 0;
 }
+
+static inline int mm_use_skey(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+	if (mm->context.use_skey)
+		return 1;
+#endif
+	return 0;
+}
+
 /*
  * pgd/pmd/pte query functions
  */
···
 #endif
 }
 
-static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
+static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste,
+				       struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address, bits, skey;
 
-	if (pte_val(*ptep) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
 	skey = (unsigned long) page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-	if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) {
-		/* Transfer dirty + referenced bit to host bits in pgste */
-		pgste_val(pgste) |= bits << 52;
-		page_set_storage_key(address, skey ^ bits, 0);
-	} else if (!(pgste_val(pgste) & PGSTE_HR_BIT) &&
-		   (bits & _PAGE_REFERENCED)) {
-		/* Transfer referenced bit to host bit in pgste */
-		pgste_val(pgste) |= PGSTE_HR_BIT;
-		page_reset_referenced(address);
-	}
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
 	/* Copy page access key and fetch protection bit to pgste */
···
 
 }
 
-static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	if (pte_val(*ptep) & _PAGE_INVALID)
-		return pgste;
-	/* Get referenced bit from storage key */
-	if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK))
-		pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT;
-#endif
-	return pgste;
-}
-
-static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
+static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
+				 struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address;
 	unsigned long nkey;
 
-	if (pte_val(entry) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
 		return;
 	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
 	address = pte_val(entry) & PAGE_MASK;
···
 	 * key C/R to 0.
 	 */
 	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	page_set_storage_key(address, nkey, 0);
 #endif
 }
 
-static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
+static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
-	if (!MACHINE_HAS_ESOP &&
-	    (pte_val(entry) & _PAGE_PRESENT) &&
-	    (pte_val(entry) & _PAGE_WRITE)) {
-		/*
-		 * Without enhanced suppression-on-protection force
-		 * the dirty bit on for all writable ptes.
-		 */
-		pte_val(entry) |= _PAGE_DIRTY;
-		pte_val(entry) &= ~_PAGE_PROTECT;
+	if ((pte_val(entry) & _PAGE_PRESENT) &&
+	    (pte_val(entry) & _PAGE_WRITE) &&
+	    !(pte_val(entry) & _PAGE_INVALID)) {
+		if (!MACHINE_HAS_ESOP) {
+			/*
+			 * Without enhanced suppression-on-protection force
+			 * the dirty bit on for all writable ptes.
+			 */
+			pte_val(entry) |= _PAGE_DIRTY;
+			pte_val(entry) &= ~_PAGE_PROTECT;
+		}
+		if (!(pte_val(entry) & _PAGE_PROTECT))
+			/* This pte allows write access, set user-dirty */
+			pgste_val(pgste) |= PGSTE_UC_BIT;
 	}
 	*ptep = entry;
+	return pgste;
 }
 
 /**
···
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
 void __gmap_zap(unsigned long address, struct gmap *);
+bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);
+
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
···
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
-		pgste_set_key(ptep, pgste, entry);
-		pgste_set_pte(ptep, entry);
+		pgste_set_key(ptep, pgste, entry, mm);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else {
 		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
···
 }
 #endif
 
-/*
- * Get (and clear) the user dirty bit for a pte.
- */
-static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int dirty = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_all(ptep, pgste);
-		dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT);
-		pgste_val(pgste) &= ~PGSTE_HC_BIT;
-		pgste_set_unlock(ptep, pgste);
-		return dirty;
-	}
-	return dirty;
-}
-
-/*
- * Get (and clear) the user referenced bit for a pte.
- */
-static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int young = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_young(ptep, pgste);
-		young = !!(pgste_val(pgste) & PGSTE_HR_BIT);
-		pgste_val(pgste) &= ~PGSTE_HR_BIT;
-		pgste_set_unlock(ptep, pgste);
-	}
-	return young;
-}
-
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
 	unsigned long pto = (unsigned long) ptep;
···
 	atomic_sub(0x10000, &mm->context.attach_count);
 }
 
+/*
+ * Get (and clear) the user dirty bit for a pte.
+ */
+static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
+						 unsigned long addr,
+						 pte_t *ptep)
+{
+	pgste_t pgste;
+	pte_t pte;
+	int dirty;
+
+	if (!mm_has_pgste(mm))
+		return 0;
+	pgste = pgste_get_lock(ptep);
+	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
+	pgste_val(pgste) &= ~PGSTE_UC_BIT;
+	pte = *ptep;
+	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
+		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		__ptep_ipte(addr, ptep);
+		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
+			pte_val(pte) |= _PAGE_PROTECT;
+		else
+			pte_val(pte) |= _PAGE_INVALID;
+		*ptep = pte;
+	}
+	pgste_set_unlock(ptep, pgste);
+	return dirty;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
···
 	pte = pte_mkold(pte);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, pte);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
···
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
···
 	ptep_flush_lazy(mm, address, ptep);
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set(ptep, pgste);
 	}
 	return pte;
···
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get(ptep);
-		pgste_set_key(ptep, pgste, pte);
-		pgste_set_pte(ptep, pte);
+		pgste_set_key(ptep, pgste, pte, mm);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
···
 		if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
 		    _PGSTE_GPS_USAGE_UNUSED)
 			pte_val(pte) |= _PAGE_UNUSED;
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, vma->vm_mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
···
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (!full && mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
···
 		pte = pte_wrprotect(pte);
 
 		if (mm_has_pgste(mm)) {
-			pgste_set_pte(ptep, pte);
+			pgste = pgste_set_pte(ptep, pgste, pte);
 			pgste_set_unlock(ptep, pgste);
 		} else
 			*ptep = pte;
···
 	ptep_flush_direct(vma->vm_mm, address, ptep);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, entry);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = entry;
···
 extern int vmem_add_mapping(unsigned long start, unsigned long size);
 extern int vmem_remove_mapping(unsigned long start, unsigned long size);
 extern int s390_enable_sie(void);
+extern void s390_enable_skey(void);
 
 /*
  * No page table caches to initialise

arch/s390/include/asm/ptrace.h

···
 			 PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | \
 			 PSW_MASK_PSTATE | PSW_ASC_PRIMARY)
 
+struct psw_bits {
+	unsigned long long	: 1;
+	unsigned long long r	: 1; /* PER-Mask */
+	unsigned long long	: 3;
+	unsigned long long t	: 1; /* DAT Mode */
+	unsigned long long i	: 1; /* Input/Output Mask */
+	unsigned long long e	: 1; /* External Mask */
+	unsigned long long key	: 4; /* PSW Key */
+	unsigned long long	: 1;
+	unsigned long long m	: 1; /* Machine-Check Mask */
+	unsigned long long w	: 1; /* Wait State */
+	unsigned long long p	: 1; /* Problem State */
+	unsigned long long as	: 2; /* Address Space Control */
+	unsigned long long cc	: 2; /* Condition Code */
+	unsigned long long pm	: 4; /* Program Mask */
+	unsigned long long ri	: 1; /* Runtime Instrumentation */
+	unsigned long long	: 6;
+	unsigned long long eaba : 2; /* Addressing Mode */
+#ifdef CONFIG_64BIT
+	unsigned long long	: 31;
+	unsigned long long ia	: 64;/* Instruction Address */
+#else
+	unsigned long long ia	: 31;/* Instruction Address */
+#endif
+};
+
+enum {
+	PSW_AMODE_24BIT = 0,
+	PSW_AMODE_31BIT = 1,
+	PSW_AMODE_64BIT = 3
+};
+
+enum {
+	PSW_AS_PRIMARY	 = 0,
+	PSW_AS_ACCREG	 = 1,
+	PSW_AS_SECONDARY = 2,
+	PSW_AS_HOME	 = 3
+};
+
+#define psw_bits(__psw) (*({			\
+	typecheck(psw_t, __psw);		\
+	&(*(struct psw_bits *)(&(__psw)));	\
+}))
+
 /*
  * The pt_regs struct defines the way the registers are stored on
  * the stack during a system call.

arch/s390/include/asm/sclp.h

···
 
 struct sclp_cpu_entry {
 	u8 address;
-	u8 reserved0[13];
+	u8 reserved0[2];
+	u8 : 3;
+	u8 siif : 1;
+	u8 : 4;
+	u8 reserved2[10];
 	u8 type;
 	u8 reserved1;
 } __attribute__((packed));
···
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 unsigned long sclp_get_hsa_size(void);
 void sclp_early_detect(void);
+int sclp_has_siif(void);
+unsigned int sclp_get_ibc(void);
 
 #endif /* _ASM_S390_SCLP_H */

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

···
 #include <linux/types.h>
 
 #define __KVM_S390
+#define __KVM_HAVE_GUEST_DEBUG
 
 /* Device control API: s390-specific devices */
 #define KVM_DEV_FLIC_GET_ALL_IRQS	1
···
 	__u64 addr;
 };
 
+/* kvm attr_group  on vm fd */
+#define KVM_S390_VM_MEM_CTRL		0
+
+/* kvm attributes for mem_ctrl */
+#define KVM_S390_VM_MEM_ENABLE_CMMA	0
+#define KVM_S390_VM_MEM_CLR_CMMA	1
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */
···
 	__u64 fprs[16];
 };
 
+#define KVM_GUESTDBG_USE_HW_BP		0x00010000
+
+#define KVM_HW_BP			1
+#define KVM_HW_WP_WRITE			2
+#define KVM_SINGLESTEP			4
+
 struct kvm_debug_exit_arch {
+	__u64 addr;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
+};
+
+struct kvm_hw_breakpoint {
+	__u64 addr;
+	__u64 phys_addr;
+	__u64 len;
+	__u8 type;
+	__u8 pad[7]; /* Should be set to 0 */
 };
 
 /* for KVM_SET_GUEST_DEBUG */
 struct kvm_guest_debug_arch {
+	__u32 nr_hw_bp;
+	__u32 pad; /* Should be set to 0 */
+	struct kvm_hw_breakpoint __user *hw_bp;
 };
 
 #define KVM_SYNC_PREFIX (1UL << 0)

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

···
+#ifndef _UAPI_ASM_S390_SIE_H
+#define _UAPI_ASM_S390_SIE_H
+
+#include <asm/sigp.h>
+
+#define diagnose_codes						\
+	{ 0x10, "DIAG (0x10) release pages" },			\
+	{ 0x44, "DIAG (0x44) time slice end" },			\
+	{ 0x9c, "DIAG (0x9c) time slice end directed" },	\
+	{ 0x204, "DIAG (0x204) logical-cpu utilization" },	\
+	{ 0x258, "DIAG (0x258) page-reference services" },	\
+	{ 0x308, "DIAG (0x308) ipl functions" },		\
+	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
+	{ 0x501, "DIAG (0x501) KVM breakpoint" }
+
+#define sigp_order_codes						\
+	{ SIGP_SENSE, "SIGP sense" },					\
+	{ SIGP_EXTERNAL_CALL, "SIGP external call" },			\
+	{ SIGP_EMERGENCY_SIGNAL, "SIGP emergency signal" },		\
+	{ SIGP_STOP, "SIGP stop" },					\
+	{ SIGP_STOP_AND_STORE_STATUS, "SIGP stop and store status" },	\
+	{ SIGP_SET_ARCHITECTURE, "SIGP set architecture" },		\
+	{ SIGP_SET_PREFIX, "SIGP set prefix" },				\
+	{ SIGP_SENSE_RUNNING, "SIGP sense running" },			\
+	{ SIGP_RESTART, "SIGP restart" },				\
+	{ SIGP_INITIAL_CPU_RESET, "SIGP initial cpu reset" },		\
+	{ SIGP_STORE_STATUS_AT_ADDRESS, "SIGP store status at address" }
+
+#define icpt_prog_codes						\
+	{ 0x0001, "Prog Operation" },				\
+	{ 0x0002, "Prog Privileged Operation" },		\
+	{ 0x0003, "Prog Execute" },				\
+	{ 0x0004, "Prog Protection" },				\
+	{ 0x0005, "Prog Addressing" },				\
+	{ 0x0006, "Prog Specification" },			\
+	{ 0x0007, "Prog Data" },				\
+	{ 0x0008, "Prog Fixedpoint overflow" },			\
+	{ 0x0009, "Prog Fixedpoint divide" },			\
+	{ 0x000A, "Prog Decimal overflow" },			\
+	{ 0x000B, "Prog Decimal divide" },			\
+	{ 0x000C, "Prog HFP exponent overflow" },		\
+	{ 0x000D, "Prog HFP exponent underflow" },		\
+	{ 0x000E, "Prog HFP significance" },			\
+	{ 0x000F, "Prog HFP divide" },				\
+	{ 0x0010, "Prog Segment translation" },			\
+	{ 0x0011, "Prog Page translation" },			\
+	{ 0x0012, "Prog Translation specification" },		\
+	{ 0x0013, "Prog Special operation" },			\
+	{ 0x0015, "Prog Operand" },				\
+	{ 0x0016, "Prog Trace table" },				\
+	{ 0x0017, "Prog ASNtranslation specification" },	\
+	{ 0x001C, "Prog Spaceswitch event" },			\
+	{ 0x001D, "Prog HFP square root" },			\
+	{ 0x001F, "Prog PCtranslation specification" },		\
+	{ 0x0020, "Prog AFX translation" },			\
+	{ 0x0021, "Prog ASX translation" },			\
+	{ 0x0022, "Prog LX translation" },			\
+	{ 0x0023, "Prog EX translation" },			\
+	{ 0x0024, "Prog Primary authority" },			\
+	{ 0x0025, "Prog Secondary authority" },			\
+	{ 0x0026, "Prog LFXtranslation exception" },		\
+	{ 0x0027, "Prog LSXtranslation exception" },		\
+	{ 0x0028, "Prog ALET specification" },			\
+	{ 0x0029, "Prog ALEN translation" },			\
+	{ 0x002A, "Prog ALE sequence" },			\
+	{ 0x002B, "Prog ASTE validity" },			\
+	{ 0x002C, "Prog ASTE sequence" },			\
+	{ 0x002D, "Prog Extended authority" },			\
+	{ 0x002E, "Prog LSTE sequence" },			\
+	{ 0x002F, "Prog ASTE instance" },			\
+	{ 0x0030, "Prog Stack full" },				\
+	{ 0x0031, "Prog Stack empty" },				\
+	{ 0x0032, "Prog Stack specification" },			\
+	{ 0x0033, "Prog Stack type" },				\
+	{ 0x0034, "Prog Stack operation" },			\
+	{ 0x0039, "Prog Region first translation" },		\
+	{ 0x003A, "Prog Region second translation" },		\
+	{ 0x003B, "Prog Region third translation" },		\
+	{ 0x0040, "Prog Monitor event" },			\
+	{ 0x0080, "Prog PER event" },				\
+	{ 0x0119, "Prog Crypto operation" }
+
+#define exit_code_ipa0(ipa0, opcode, mnemonic)		\
+	{ (ipa0 << 8 | opcode), #ipa0 " " mnemonic }
+#define exit_code(opcode, mnemonic)			\
+	{ opcode, mnemonic }
+
+#define icpt_insn_codes				\
+	exit_code_ipa0(0x01, 0x01, "PR"),	\
+	exit_code_ipa0(0x01, 0x04, "PTFF"),	\
+	exit_code_ipa0(0x01, 0x07, "SCKPF"),	\
+	exit_code_ipa0(0xAA, 0x00, "RINEXT"),	\
+	exit_code_ipa0(0xAA, 0x01, "RION"),	\
+	exit_code_ipa0(0xAA, 0x02, "TRIC"),	\
+	exit_code_ipa0(0xAA, 0x03, "RIOFF"),	\
+	exit_code_ipa0(0xAA, 0x04, "RIEMIT"),	\
+	exit_code_ipa0(0xB2, 0x02, "STIDP"),	\
+	exit_code_ipa0(0xB2, 0x04, "SCK"),	\
+	exit_code_ipa0(0xB2, 0x05, "STCK"),	\
+	exit_code_ipa0(0xB2, 0x06, "SCKC"),	\
+	exit_code_ipa0(0xB2, 0x07, "STCKC"),	\
+	exit_code_ipa0(0xB2, 0x08, "SPT"),	\
+	exit_code_ipa0(0xB2, 0x09, "STPT"),	\
+	exit_code_ipa0(0xB2, 0x0d, "PTLB"),	\
+	exit_code_ipa0(0xB2, 0x10, "SPX"),	\
+	exit_code_ipa0(0xB2, 0x11, "STPX"),	\
+	exit_code_ipa0(0xB2, 0x12, "STAP"),	\
+	exit_code_ipa0(0xB2, 0x14, "SIE"),	\
+	exit_code_ipa0(0xB2, 0x16, "SETR"),	\
+	exit_code_ipa0(0xB2, 0x17, "STETR"),	\
+	exit_code_ipa0(0xB2, 0x18, "PC"),	\
+	exit_code_ipa0(0xB2, 0x20, "SERVC"),	\
+	exit_code_ipa0(0xB2, 0x28, "PT"),	\
+	exit_code_ipa0(0xB2, 0x29, "ISKE"),	\
+	exit_code_ipa0(0xB2, 0x2a, "RRBE"),	\
+	exit_code_ipa0(0xB2, 0x2b, "SSKE"),	\
+	exit_code_ipa0(0xB2, 0x2c, "TB"),	\
+	exit_code_ipa0(0xB2, 0x2e, "PGIN"),	\
+	exit_code_ipa0(0xB2, 0x2f, "PGOUT"),	\
+	exit_code_ipa0(0xB2, 0x30, "CSCH"),	\
+	exit_code_ipa0(0xB2, 0x31, "HSCH"),	\
+	exit_code_ipa0(0xB2, 0x32, "MSCH"),	\
+	exit_code_ipa0(0xB2, 0x33, "SSCH"),	\
+	exit_code_ipa0(0xB2, 0x34, "STSCH"),	\
+	exit_code_ipa0(0xB2, 0x35, "TSCH"),	\
+	exit_code_ipa0(0xB2, 0x36, "TPI"),	\
+	exit_code_ipa0(0xB2, 0x37, "SAL"),	\
+	exit_code_ipa0(0xB2, 0x38, "RSCH"),	\
+	exit_code_ipa0(0xB2, 0x39, "STCRW"),	\
+	exit_code_ipa0(0xB2, 0x3a, "STCPS"),	\
+	exit_code_ipa0(0xB2, 0x3b, "RCHP"),	\
+	exit_code_ipa0(0xB2, 0x3c, "SCHM"),	\
+	exit_code_ipa0(0xB2, 0x40, "BAKR"),	\
+	exit_code_ipa0(0xB2, 0x48, "PALB"),	\
+	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
+	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
+	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
+	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
+	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\
+	exit_code_ipa0(0xB2, 0x74, "SIGA"),	\
+	exit_code_ipa0(0xB2, 0x76, "XSCH"),	\
+	exit_code_ipa0(0xB2, 0x78, "STCKE"),	\
+	exit_code_ipa0(0xB2, 0x7c, "STCKF"),	\
+	exit_code_ipa0(0xB2, 0x7d, "STSI"),	\
+	exit_code_ipa0(0xB2, 0xb0, "STFLE"),	\
+	exit_code_ipa0(0xB2, 0xb1, "STFL"),	\
+	exit_code_ipa0(0xB2, 0xb2, "LPSWE"),	\
+	exit_code_ipa0(0xB2, 0xf8, "TEND"),	\
+	exit_code_ipa0(0xB2, 0xfc, "TABORT"),	\
+	exit_code_ipa0(0xB9, 0x1e, "KMAC"),	\
+	exit_code_ipa0(0xB9, 0x28, "PCKMO"),	\
+	exit_code_ipa0(0xB9, 0x2a, "KMF"),	\
+	exit_code_ipa0(0xB9, 0x2b, "KMO"),	\
+	exit_code_ipa0(0xB9, 0x2d, "KMCTR"),	\
+	exit_code_ipa0(0xB9, 0x2e, "KM"),	\
+	exit_code_ipa0(0xB9, 0x2f, "KMC"),	\
+	exit_code_ipa0(0xB9, 0x3e, "KIMD"),	\
+	exit_code_ipa0(0xB9, 0x3f, "KLMD"),	\
+	exit_code_ipa0(0xB9, 0x8a, "CSPG"),	\
+	exit_code_ipa0(0xB9, 0x8d, "EPSW"),	\
+	exit_code_ipa0(0xB9, 0x8e, "IDTE"),	\
+	exit_code_ipa0(0xB9, 0x8f, "CRDTE"),	\
+	exit_code_ipa0(0xB9, 0x9c, "EQBS"),	\
+	exit_code_ipa0(0xB9, 0xa2, "PTF"),	\
+	exit_code_ipa0(0xB9, 0xab, "ESSA"),	\
+	exit_code_ipa0(0xB9, 0xae, "RRBM"),	\
+	exit_code_ipa0(0xB9, 0xaf, "PFMF"),	\
+	exit_code_ipa0(0xE3, 0x03, "LRAG"),	\
+	exit_code_ipa0(0xE3, 0x13, "LRAY"),	\
+	exit_code_ipa0(0xE3, 0x25, "NTSTG"),	\
+	exit_code_ipa0(0xE5, 0x00, "LASP"),	\
+	exit_code_ipa0(0xE5, 0x01, "TPROT"),	\
+	exit_code_ipa0(0xE5, 0x60, "TBEGIN"),	\
+	exit_code_ipa0(0xE5, 0x61, "TBEGINC"),	\
+	exit_code_ipa0(0xEB, 0x25, "STCTG"),	\
+	exit_code_ipa0(0xEB, 0x2f, "LCTLG"),	\
+	exit_code_ipa0(0xEB, 0x60, "LRIC"),	\
+	exit_code_ipa0(0xEB, 0x61, "STRIC"),	\
+	exit_code_ipa0(0xEB, 0x62, "MRIC"),	\
+	exit_code_ipa0(0xEB, 0x8a, "SQBS"),	\
+	exit_code_ipa0(0xC8, 0x01, "ECTG"),	\
+	exit_code(0x0a, "SVC"),			\
+	exit_code(0x80, "SSM"),			\
+	exit_code(0x82, "LPSW"),		\
+	exit_code(0x83, "DIAG"),		\
+	exit_code(0xae, "SIGP"),		\
+	exit_code(0xac, "STNSM"),		\
+	exit_code(0xad, "STOSM"),		\
+	exit_code(0xb1, "LRA"),			\
+	exit_code(0xb6, "STCTL"),		\
+	exit_code(0xb7, "LCTL"),		\
+	exit_code(0xee, "PLO")
+
+#define sie_intercept_code					\
+	{ 0x00, "Host interruption" },				\
+	{ 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" },				\
+	{ 0x2c, "Operation exception" },			\
+	{ 0x38, "Partial-execution" },				\
+	{ 0x3c, "I/O interruption" },				\
+	{ 0x40, "I/O instruction" },				\
+	{ 0x48, "Timing subset" }
+
+/*
+ * This is the simple interceptable instructions decoder.
+ *
+ * It will be used as userspace interface and it can be used in places
+ * that does not allow to use general decoder functions,
+ * such as trace events declarations.
+ *
+ * Some userspace tools may want to parse this code
+ * and would be confused by switch(), if() and other statements,
+ * but they can understand conditional operator.
+ */
+#define INSN_DECODE_IPA0(ipa0, insn, rshift, mask)		\
+	(insn >> 56) == (ipa0) ?				\
+		((ipa0 << 8) | ((insn >> rshift) & mask)) :
+
+#define INSN_DECODE(insn) (insn >> 56)
+
+/*
+ * The macro icpt_insn_decoder() takes an intercepted instruction
+ * and returns a key, which can be used to find a mnemonic name
+ * of the instruction in the icpt_insn_codes table.
+ */
+#define icpt_insn_decoder(insn)			\
+	INSN_DECODE_IPA0(0x01, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f)	\
+	INSN_DECODE_IPA0(0xb2, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xb9, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe3, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xe5, insn, 48, 0xff)	\
+	INSN_DECODE_IPA0(0xeb, insn, 16, 0xff)	\
+	INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f)	\
+	INSN_DECODE(insn)
+
+#endif /* _UAPI_ASM_S390_SIE_H */

arch/s390/kernel/asm-offsets.c

···
 	DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc));
 	DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code));
 	DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code));
-	DEFINE(__LC_PER_CAUSE, offsetof(struct _lowcore, per_perc_atmid));
+	DEFINE(__LC_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num));
+	DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code));
+	DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_atmid));
 	DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address));
-	DEFINE(__LC_PER_PAID, offsetof(struct _lowcore, per_access_id));
-	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id));
+	DEFINE(__LC_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id));
+	DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id));
+	DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id));
+	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id));
+	DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code));
 	DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id));
 	DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr));
 	DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm));
 	DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word));
 	DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list));
 	DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code));
+	DEFINE(__LC_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_code));
 	DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw));
 	DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw));
 	DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw));
···
 #ifdef CONFIG_32BIT
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr));
 #else /* CONFIG_32BIT */
+	DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code));
+	DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address));
 	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
 	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
 	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));

arch/s390/kernel/entry.S

···
 	jz	pgm_kprobe
 	oi	__PT_FLAGS+3(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(4,%r1),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r1),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	l	%r1,BASED(.Ljump_table)

arch/s390/kernel/entry64.S

···
 	jz	pgm_kprobe
 	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
-	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CAUSE
-	mvc	__THREAD_per_paid(1,%r14),__LC_PER_PAID
+	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
 0:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table

arch/s390/kvm/Makefile

···
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
-kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o
+kvm-objs += diag.o gaccess.o guestdbg.o
+
 obj-$(CONFIG_KVM) += kvm.o

arch/s390/kvm/diag.c

···
 static int diag_release_pages(struct kvm_vcpu *vcpu)
 {
 	unsigned long start, end;
-	unsigned long prefix  = vcpu->arch.sie_block->prefix;
+	unsigned long prefix  = kvm_s390_get_prefix(vcpu);
 
 	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;
···
 	int rc;
 	u16 rx = (vcpu->arch.sie_block->ipa & 0xf0) >> 4;
 	u16 ry = (vcpu->arch.sie_block->ipa & 0x0f);
-	unsigned long hva_token = KVM_HVA_ERR_BAD;
 
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	if (copy_from_guest(vcpu, &parm, vcpu->run->s.regs.gprs[rx], sizeof(parm)))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 	if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
···
 		    parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL)
 			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-		hva_token = gfn_to_hva(vcpu->kvm, gpa_to_gfn(parm.token_addr));
-		if (kvm_is_error_hva(hva_token))
+		if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		vcpu->arch.pfault_token = parm.token_addr;
···
 
 	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
 	switch (subcode) {
-	case 0:
-	case 1:
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
-		return -EOPNOTSUPP;
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	case 4:
 		vcpu->run->s390_reset_flags = 0;
-		page_table_reset_pgste(current->mm, 0, TASK_SIZE);
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_vcpu_stop(vcpu);
 	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;

arch/s390/kvm/gaccess.c

···
+/*
+ * guest access functions
+ *
+ * Copyright IBM Corp. 2014
+ *
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/err.h>
+#include <asm/pgtable.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+union asce {
+	unsigned long val;
+	struct {
+		unsigned long origin : 52; /* Region- or Segment-Table Origin */
+		unsigned long	 : 2;
+		unsigned long g  : 1; /* Subspace Group Control */
+		unsigned long p  : 1; /* Private Space Control */
+		unsigned long s  : 1; /* Storage-Alteration-Event Control */
+		unsigned long x  : 1; /* Space-Switch-Event Control */
+		unsigned long r  : 1; /* Real-Space Control */
+		unsigned long	 : 1;
+		unsigned long dt : 2; /* Designation-Type Control */
+		unsigned long tl : 2; /* Region- or Segment-Table Length */
+	};
+};
+
+enum {
+	ASCE_TYPE_SEGMENT = 0,
+	ASCE_TYPE_REGION3 = 1,
+	ASCE_TYPE_REGION2 = 2,
+	ASCE_TYPE_REGION1 = 3
+};
+
+union region1_table_entry {
+	unsigned long val;
+	struct {
+		unsigned long rto: 52;/* Region-Table Origin */
+		unsigned long	 : 2;
+		unsigned long p  : 1; /* DAT-Protection Bit */
+		unsigned long	 : 1;
+		unsigned long tf : 2; /* Region-Second-Table Offset */
+		unsigned long i  : 1; /* Region-Invalid Bit */
+		unsigned long	 : 1;
+		unsigned long tt : 2; /* Table-Type Bits */
+		unsigned long tl : 2; /* Region-Second-Table Length */
+	};
+};
+
+union region2_table_entry {
+	unsigned long val;
+	struct {
+		unsigned long rto: 52;/* Region-Table Origin */
+		unsigned long	 : 2;
+		unsigned long p  : 1; /* DAT-Protection Bit */
+		unsigned long	 : 1;
+		unsigned long tf : 2; /* Region-Third-Table Offset */
+		unsigned long i  : 1; /* Region-Invalid Bit */
+		unsigned long	 : 1;
+		unsigned long tt : 2; /* Table-Type Bits */
+		unsigned long tl : 2; /* Region-Third-Table Length */
+	};
+};
+
+struct region3_table_entry_fc0 {
+	unsigned long sto: 52;/* Segment-Table Origin */
+	unsigned long	 : 1;
+	unsigned long fc : 1; /* Format-Control */
+	unsigned long p  : 1; /* DAT-Protection Bit */
+	unsigned long	 : 1;
+	unsigned long tf : 2; /* Segment-Table Offset */
+	unsigned long i  : 1; /* Region-Invalid Bit */
+	unsigned long cr : 1; /* Common-Region Bit */
+	unsigned long tt : 2; /* Table-Type Bits */
+	unsigned long tl : 2; /* Segment-Table Length */
+};
+
+struct region3_table_entry_fc1 {
+	unsigned long rfaa : 33; /* Region-Frame Absolute Address */
+	unsigned long	 : 14;
+	unsigned long av : 1; /* ACCF-Validity Control */
+	unsigned long acc: 4; /* Access-Control Bits */
+	unsigned long f  : 1; /* Fetch-Protection Bit */
+	unsigned long fc : 1; /* Format-Control */
+	unsigned long p  : 1; /* DAT-Protection Bit */
+	unsigned long co : 1; /* Change-Recording Override */
+	unsigned long	 : 2;
+	unsigned long i  : 1; /* Region-Invalid Bit */
+	unsigned long cr : 1; /* Common-Region Bit */
+	unsigned long tt : 2; /* Table-Type Bits */
+	unsigned long	 : 2;
+};
+
+union region3_table_entry {
+	unsigned long val;
+	struct region3_table_entry_fc0 fc0;
+	struct region3_table_entry_fc1 fc1;
+	struct {
+		unsigned long	 : 53;
+		unsigned long fc : 1; /* Format-Control */
+		unsigned long	 : 4;
+		unsigned long i  : 1; /* Region-Invalid Bit */
+		unsigned long cr : 1; /* Common-Region Bit */
+		unsigned long tt : 2; /* Table-Type Bits */
+		unsigned long	 : 2;
+	};
+};
+
+struct segment_entry_fc0 {
+	unsigned long pto: 53;/* Page-Table Origin */
+	unsigned long fc : 1; /* Format-Control */
+	unsigned long p  : 1; /* DAT-Protection Bit */
+	unsigned long	 : 3;
+	unsigned long i  : 1; /* Segment-Invalid Bit */
+	unsigned long cs : 1; /* Common-Segment Bit */
+	unsigned long tt : 2; /* Table-Type Bits */
+	unsigned long	 : 2;
+};
+
+struct segment_entry_fc1 {
+	unsigned long sfaa : 44; /* Segment-Frame Absolute Address */
+	unsigned long	 : 3;
+	unsigned long av : 1; /* ACCF-Validity Control */
+	unsigned long acc: 4; /* Access-Control Bits */
+	unsigned long f  : 1; /* Fetch-Protection Bit */
+	unsigned long fc : 1; /* Format-Control */
+	unsigned long p  : 1; /* DAT-Protection Bit */
+	unsigned long co : 1; /* Change-Recording Override */
+	unsigned long	 : 2;
+	unsigned long i  : 1; /* Segment-Invalid Bit */
+	unsigned long cs : 1; /* Common-Segment Bit */
+	unsigned long tt : 2; /* Table-Type Bits */
+	unsigned long	 : 2;
+};
+
+union segment_table_entry {
+	unsigned long val;
+	struct segment_entry_fc0 fc0;
+	struct segment_entry_fc1 fc1;
+	struct {
+		unsigned long	 : 53;
+		unsigned long fc : 1; /* Format-Control */
+		unsigned long	 : 4;
+		unsigned long i  : 1; /* Segment-Invalid Bit */
+		unsigned long cs : 1; /* Common-Segment Bit */
+		unsigned long tt : 2; /* Table-Type Bits */
+		unsigned long	 : 2;
+	};
+};
+
+enum {
+	TABLE_TYPE_SEGMENT = 0,
+	TABLE_TYPE_REGION3 = 1,
+	TABLE_TYPE_REGION2 = 2,
+	TABLE_TYPE_REGION1 = 3
+};
+
+union page_table_entry {
+	unsigned long val;
+	struct {
+		unsigned long pfra : 52; /* Page-Frame Real Address */
+		unsigned long z  : 1; /* Zero Bit */
+		unsigned long i  : 1; /* Page-Invalid Bit */
+		unsigned long p  : 1; /* DAT-Protection Bit */
+		unsigned long co : 1; /* Change-Recording Override */
+		unsigned long	 : 8;
+	};
+};
+
+/*
+ * vaddress union in order to easily decode a virtual address into its
+ * region first index, region second index etc. parts.
+ */
+union vaddress {
+	unsigned long addr;
+	struct {
+		unsigned long rfx : 11;
+		unsigned long rsx : 11;
+		unsigned long rtx : 11;
+		unsigned long sx  : 11;
+		unsigned long px  : 8;
+		unsigned long bx  : 12;
+	};
+	struct {
+		unsigned long rfx01 : 2;
+		unsigned long	    : 9;
+		unsigned long rsx01 : 2;
+		unsigned long	    : 9;
+		unsigned long rtx01 : 2;
+		unsigned long	    : 9;
+		unsigned long sx01  : 2;
+		unsigned long	    : 29;
+	};
+};
+
+/*
+ * raddress union which will contain the result (real or absolute address)
+ * after a page table walk. The rfaa, sfaa and pfra members are used to
+ * simply assign them the value of a region, segment or page table entry.
+ */
+union raddress {
+	unsigned long addr;
+	unsigned long rfaa : 33; /* Region-Frame Absolute Address */
+	unsigned long sfaa : 44; /* Segment-Frame Absolute Address */
+	unsigned long pfra : 52; /* Page-Frame Real Address */
+};
+
+static int ipte_lock_count;
+static DEFINE_MUTEX(ipte_mutex);
+
+int ipte_lock_held(struct kvm_vcpu *vcpu)
+{
+	union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+
+	if (vcpu->arch.sie_block->eca & 1)
+		return ic->kh != 0;
+	return ipte_lock_count != 0;
+}
+
+static void ipte_lock_simple(struct kvm_vcpu *vcpu)
+{
+	union ipte_control old, new, *ic;
+
+	mutex_lock(&ipte_mutex);
+	ipte_lock_count++;
+	if (ipte_lock_count > 1)
+		goto out;
+	ic = &vcpu->kvm->arch.sca->ipte_control;
+	do {
+		old = ACCESS_ONCE(*ic);
+		while (old.k) {
+			cond_resched();
+			old = ACCESS_ONCE(*ic);
+		}
+		new = old;
+		new.k = 1;
+	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+out:
+	mutex_unlock(&ipte_mutex);
+}
+
+static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
+{
+	union ipte_control old, new, *ic;
+
+	mutex_lock(&ipte_mutex);
+	ipte_lock_count--;
+	if (ipte_lock_count)
+		goto out;
+	ic = &vcpu->kvm->arch.sca->ipte_control;
+	do {
+		new = old = ACCESS_ONCE(*ic);
+		new.k = 0;
+	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	if (!ipte_lock_count)
+		wake_up(&vcpu->kvm->arch.ipte_wq);
+out:
+	mutex_unlock(&ipte_mutex);
+}
+
+static void ipte_lock_siif(struct kvm_vcpu *vcpu)
+{
+	union ipte_control old, new, *ic;
+
+	ic = &vcpu->kvm->arch.sca->ipte_control;
+	do {
+		old = ACCESS_ONCE(*ic);
+		while (old.kg) {
+			cond_resched();
+			old = ACCESS_ONCE(*ic);
+		}
+		new = old;
+		new.k = 1;
+		new.kh++;
+	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+}
+
+static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
+{
+	union ipte_control old, new, *ic;
+
+	ic = &vcpu->kvm->arch.sca->ipte_control;
+	do {
+		new = old = ACCESS_ONCE(*ic);
+		new.kh--;
+		if (!new.kh)
+			new.k = 0;
+	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+	if (!new.kh)
+		wake_up(&vcpu->kvm->arch.ipte_wq);
+}
+
+void ipte_lock(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.sie_block->eca & 1)
+		ipte_lock_siif(vcpu);
+	else
+		ipte_lock_simple(vcpu);
+}
+
+void ipte_unlock(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.sie_block->eca & 1)
+		ipte_unlock_siif(vcpu);
+	else
+		ipte_unlock_simple(vcpu);
+}
+
+static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu)
+{
+	switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
+	case PSW_AS_PRIMARY:
+		return vcpu->arch.sie_block->gcr[1];
+	case PSW_AS_SECONDARY:
+		return vcpu->arch.sie_block->gcr[7];
+	case PSW_AS_HOME:
+		return vcpu->arch.sie_block->gcr[13];
+	}
+	return 0;
+}
+
+static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
+{
+	return kvm_read_guest(kvm, gpa, val, sizeof(*val));
+}
+
+/**
+ * guest_translate - translate a guest virtual into a guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: guest virtual address
+ * @gpa: points to where guest physical (absolute) address should be stored
+ * @write: indicates if access is a write access
+ *
+ * Translate a guest virtual address into a guest absolute address by means
+ * of dynamic address translation as specified by the architecuture.
+ * If the resulting absolute address is not available in the configuration
+ * an addressing exception is indicated and @gpa will not be changed.
+ *
+ * Returns: - zero on success; @gpa contains the resulting absolute address
+ *	    - a negative value if guest access failed due to e.g. broken
+ *	      guest mapping
+ *	    - a positve value if an access exception happened. In this case
+ *	      the returned value is the program interruption code as defined
+ *	      by the architecture
+ */
+static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
+				     unsigned long *gpa, int write)
+{
+	union vaddress vaddr = {.addr = gva};
+	union raddress raddr = {.addr = gva};
+	union page_table_entry pte;
+	int dat_protection = 0;
+	union ctlreg0 ctlreg0;
+	unsigned long ptr;
+	int edat1, edat2;
+	union asce asce;
+
+	ctlreg0.val = vcpu->arch.sie_block->gcr[0];
+	edat1 = ctlreg0.edat && test_vfacility(8);
+	edat2 = edat1 && test_vfacility(78);
+	asce.val = get_vcpu_asce(vcpu);
+	if (asce.r)
+		goto real_address;
+	ptr = asce.origin * 4096;
+	switch (asce.dt) {
+	case ASCE_TYPE_REGION1:
+		if (vaddr.rfx01 > asce.tl)
+			return PGM_REGION_FIRST_TRANS;
+		ptr += vaddr.rfx * 8;
+		break;
+	case ASCE_TYPE_REGION2:
+		if (vaddr.rfx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.rsx01 > asce.tl)
+			return PGM_REGION_SECOND_TRANS;
+		ptr += vaddr.rsx * 8;
+		break;
+	case ASCE_TYPE_REGION3:
+		if (vaddr.rfx || vaddr.rsx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.rtx01 > asce.tl)
+			return PGM_REGION_THIRD_TRANS;
+		ptr += vaddr.rtx * 8;
+		break;
+	case ASCE_TYPE_SEGMENT:
+		if (vaddr.rfx || vaddr.rsx || vaddr.rtx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.sx01 > asce.tl)
+			return PGM_SEGMENT_TRANSLATION;
+		ptr += vaddr.sx * 8;
+		break;
+	}
+	switch (asce.dt) {
+	case ASCE_TYPE_REGION1:	{
+		union region1_table_entry rfte;
+
+		if (kvm_is_error_gpa(vcpu->kvm, ptr))
+			return PGM_ADDRESSING;
+		if (deref_table(vcpu->kvm, ptr, &rfte.val))
+			return -EFAULT;
+		if (rfte.i)
+			return PGM_REGION_FIRST_TRANS;
+		if (rfte.tt != TABLE_TYPE_REGION1)
+			return PGM_TRANSLATION_SPEC;
+		if (vaddr.rsx01 < rfte.tf || vaddr.rsx01 > rfte.tl)
+			return PGM_REGION_SECOND_TRANS;
+		if (edat1)
+			dat_protection |= rfte.p;
+		ptr = rfte.rto * 4096 + vaddr.rsx * 8;
+	}
+		/* fallthrough */
+	case ASCE_TYPE_REGION2: {
+		union region2_table_entry rste;
+
+		if (kvm_is_error_gpa(vcpu->kvm, ptr))
+			return PGM_ADDRESSING;
+		if (deref_table(vcpu->kvm, ptr, &rste.val))
+			return -EFAULT;
+		if (rste.i)
+			return PGM_REGION_SECOND_TRANS;
+		if (rste.tt != TABLE_TYPE_REGION2)
+			return PGM_TRANSLATION_SPEC;
+		if (vaddr.rtx01 < rste.tf || vaddr.rtx01 > rste.tl)
+			return PGM_REGION_THIRD_TRANS;
+		if (edat1)
+			dat_protection |= rste.p;
+		ptr = rste.rto * 4096 + vaddr.rtx * 8;
+	}
+		/* fallthrough */
+	case ASCE_TYPE_REGION3: {
+		union region3_table_entry rtte;
+
+		if (kvm_is_error_gpa(vcpu->kvm, ptr))
+			return PGM_ADDRESSING;
+		if (deref_table(vcpu->kvm, ptr, &rtte.val))
+			return -EFAULT;
+		if (rtte.i)
+			return PGM_REGION_THIRD_TRANS;
+		if (rtte.tt != TABLE_TYPE_REGION3)
+			return PGM_TRANSLATION_SPEC;
+		if (rtte.cr && asce.p && edat2)
+			return PGM_TRANSLATION_SPEC;
+		if (rtte.fc && edat2) {
+			dat_protection |= rtte.fc1.p;
+			raddr.rfaa = rtte.fc1.rfaa;
+			goto absolute_address;
+		}
+		if (vaddr.sx01 < rtte.fc0.tf)
+			return PGM_SEGMENT_TRANSLATION;
+		if (vaddr.sx01 > rtte.fc0.tl)
+			return PGM_SEGMENT_TRANSLATION;
+		if (edat1)
+			dat_protection |= rtte.fc0.p;
+		ptr = rtte.fc0.sto * 4096 + vaddr.sx * 8;
+	}
+		/* fallthrough */
+	case ASCE_TYPE_SEGMENT: {
+		union segment_table_entry ste;
+
+		if (kvm_is_error_gpa(vcpu->kvm, ptr))
+			return PGM_ADDRESSING;
+		if (deref_table(vcpu->kvm, ptr, &ste.val))
+			return -EFAULT;
+		if (ste.i)
+			return PGM_SEGMENT_TRANSLATION;
+		if (ste.tt != TABLE_TYPE_SEGMENT)
+			return PGM_TRANSLATION_SPEC;
+		if (ste.cs && asce.p)
+			return PGM_TRANSLATION_SPEC;
+		if (ste.fc && edat1) {
+			dat_protection |= ste.fc1.p;
+			raddr.sfaa = ste.fc1.sfaa;
+			goto absolute_address;
+		}
+		dat_protection |= ste.fc0.p;
+		ptr = ste.fc0.pto * 2048 + vaddr.px * 8;
+	}
+	}
+	if (kvm_is_error_gpa(vcpu->kvm, ptr))
+		return PGM_ADDRESSING;
+	if (deref_table(vcpu->kvm, ptr, &pte.val))
+		return -EFAULT;
+	if (pte.i)
+		return PGM_PAGE_TRANSLATION;
+	if (pte.z)
+		return PGM_TRANSLATION_SPEC;
+	if (pte.co && !edat1)
+		return PGM_TRANSLATION_SPEC;
+	dat_protection |= pte.p;
+	raddr.pfra = pte.pfra;
+real_address:
+	raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
+absolute_address:
+	if (write && dat_protection)
+		return PGM_PROTECTION;
+	if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
+		return PGM_ADDRESSING;
+	*gpa = raddr.addr;
+	return 0;
+}
+
+static inline int is_low_address(unsigned long ga)
+{
+	/* Check for address ranges 0..511 and 4096..4607 */
+	return (ga & ~0x11fful) == 0;
+}
+
+static int low_address_protection_enabled(struct kvm_vcpu *vcpu)
+{
+	union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]};
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	union asce asce;
+
+	if (!ctlreg0.lap)
+		return 0;
+	asce.val = get_vcpu_asce(vcpu);
+	if (psw_bits(*psw).t && asce.p)
+		return 0;
+	return 1;
+}
+
+struct trans_exc_code_bits {
+	unsigned long addr : 52; /* Translation-exception Address */
+	unsigned long fsi  : 2;  /* Access Exception Fetch/Store Indication */
+	unsigned long	   : 7;
+	unsigned long b61  : 1;
+	unsigned long as   : 2;  /* ASCE Identifier */
+};
+
+enum {
+	FSI_UNKNOWN = 0, /* Unknown wether fetch or store */
+	FSI_STORE   = 1, /* Exception was due to store operation */
+	FSI_FETCH   = 2  /* Exception was due to fetch operation */
+};
+
+static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
+			    unsigned long *pages, unsigned long nr_pages,
+			    int write)
+{
+	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	struct trans_exc_code_bits *tec_bits;
+	int lap_enabled, rc;
+
+	memset(pgm, 0, sizeof(*pgm));
+	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
+	tec_bits->fsi = write ? FSI_STORE : FSI_FETCH;
+	tec_bits->as = psw_bits(*psw).as;
+	lap_enabled = low_address_protection_enabled(vcpu);
+	while (nr_pages) {
+		ga = kvm_s390_logical_to_effective(vcpu, ga);
+		tec_bits->addr = ga >> PAGE_SHIFT;
+		if (write && lap_enabled && is_low_address(ga)) {
+			pgm->code = PGM_PROTECTION;
+			return pgm->code;
+		}
+		ga &= PAGE_MASK;
+		if (psw_bits(*psw).t) {
+			rc = guest_translate(vcpu, ga, pages, write);
+			if (rc < 0)
+				return rc;
+			if (rc == PGM_PROTECTION)
+				tec_bits->b61 = 1;
+			if (rc)
+				pgm->code = rc;
+		} else {
+			*pages = kvm_s390_real_to_abs(vcpu, ga);
+			if (kvm_is_error_gpa(vcpu->kvm, *pages))
+				pgm->code = PGM_ADDRESSING;
+		}
+		if (pgm->code)
+			return pgm->code;
+		ga += PAGE_SIZE;
+		pages++;
+		nr_pages--;
+	}
+	return 0;
+}
+
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+		 unsigned long len, int write)
+{
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	unsigned long _len, nr_pages, gpa, idx;
+	unsigned long pages_array[2];
+	unsigned long *pages;
+	int need_ipte_lock;
+	union asce asce;
+	int rc;
+
+	if (!len)
+		return 0;
+	/* Access register mode is not supported yet. */
+	if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG)
+		return -EOPNOTSUPP;
+	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
+	pages = pages_array;
+	if (nr_pages > ARRAY_SIZE(pages_array))
+		pages = vmalloc(nr_pages * sizeof(unsigned long));
+	if (!pages)
+		return -ENOMEM;
+	asce.val = get_vcpu_asce(vcpu);
+	need_ipte_lock = psw_bits(*psw).t && !asce.r;
+	if (need_ipte_lock)
+		ipte_lock(vcpu);
+	rc = guest_page_range(vcpu, ga, pages, nr_pages, write);
+	for (idx = 0; idx < nr_pages && !rc; idx++) {
+		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
+		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
+		if (write)
+			rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
+		else
+			rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
+		len -= _len;
+		ga += _len;
+		data += _len;
+	}
+	if (need_ipte_lock)
+		ipte_unlock(vcpu);
+	if (nr_pages > ARRAY_SIZE(pages_array))
+		vfree(pages);
+	return rc;
+}
+
+int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
+		      void *data, unsigned long len, int write)
+{
+	unsigned long _len, gpa;
+	int rc = 0;
+
+	while (len && !rc) {
+		gpa = kvm_s390_real_to_abs(vcpu, gra);
+		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
+		if (write)
+			rc = write_guest_abs(vcpu, gpa, data, _len);
+		else
+			rc = read_guest_abs(vcpu, gpa, data, _len);
+		len -= _len;
+		gra += _len;
+		data += _len;
+	}
+	return rc;
+}
+
+/**
+ * guest_translate_address - translate guest logical into guest absolute address
+ *
+ * Parameter semantics are the same as the ones from guest_translate.
+ * The memory contents at the guest address are not changed.
+ *
+ * Note: The IPTE lock is not taken during this function, so the caller
+ * has to take care of this.
+ */
+int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
+			    unsigned long *gpa, int write)
+{
+	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	struct trans_exc_code_bits *tec;
+	union asce asce;
+	int rc;
+
+	/* Access register mode is not supported yet. */
+	if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG)
+		return -EOPNOTSUPP;
+
+	gva = kvm_s390_logical_to_effective(vcpu, gva);
+	memset(pgm, 0, sizeof(*pgm));
+	tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
+	tec->as = psw_bits(*psw).as;
+	tec->fsi = write ? FSI_STORE : FSI_FETCH;
+	tec->addr = gva >> PAGE_SHIFT;
+	if (is_low_address(gva) && low_address_protection_enabled(vcpu)) {
+		if (write) {
+			rc = pgm->code = PGM_PROTECTION;
+			return rc;
+		}
+	}
+
+	asce.val = get_vcpu_asce(vcpu);
+	if (psw_bits(*psw).t && !asce.r) {	/* Use DAT? */
+		rc = guest_translate(vcpu, gva, gpa, write);
+		if (rc > 0) {
+			if (rc == PGM_PROTECTION)
+				tec->b61 = 1;
+			pgm->code = rc;
+		}
+	} else {
+		rc = 0;
+		*gpa = kvm_s390_real_to_abs(vcpu, gva);
+		if (kvm_is_error_gpa(vcpu->kvm, *gpa))
+			rc = pgm->code = PGM_ADDRESSING;
+	}
+
+	return rc;
+}
+
+/**
+ * kvm_s390_check_low_addr_protection - check for low-address protection
+ * @ga: Guest address
+ *
+ * Checks whether an address is subject to low-address protection and set
+ * up vcpu->arch.pgm accordingly if necessary.
+ *
+ * Return: 0 if no protection exception, or PGM_PROTECTION if protected.
+ */
+int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga)
+{
+	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	struct trans_exc_code_bits *tec_bits;
+
+	if (!is_low_address(ga) || !low_address_protection_enabled(vcpu))
+		return 0;
+
+	memset(pgm, 0, sizeof(*pgm));
+	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
+	tec_bits->fsi = FSI_STORE;
+	tec_bits->as = psw_bits(*psw).as;
+	tec_bits->addr = ga >> PAGE_SHIFT;
+	pgm->code = PGM_PROTECTION;
+
+	return pgm->code;
+}

arch/s390/kvm/gaccess.h

···
 /*
  * access guest memory
  *
- * Copyright IBM Corp. 2008, 2009
+ * Copyright IBM Corp. 2008, 2014
  *
  * 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)
···
 
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
 #include "kvm-s390.h"
 
-/* Convert real to absolute address by applying the prefix of the CPU */
+/**
+ * kvm_s390_real_to_abs - convert guest real address to guest absolute address
+ * @vcpu - guest virtual cpu
+ * @gra - guest real address
+ *
+ * Returns the guest absolute address that corresponds to the passed guest real
+ * address @gra of a virtual guest cpu by applying its prefix.
+ */
 static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu,
-						 unsigned long gaddr)
+						 unsigned long gra)
 {
-	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	if (gaddr < 2 * PAGE_SIZE)
-		gaddr += prefix;
-	else if (gaddr >= prefix && gaddr < prefix + 2 * PAGE_SIZE)
-		gaddr -= prefix;
-	return gaddr;
+	unsigned long prefix  = kvm_s390_get_prefix(vcpu);
+
+	if (gra < 2 * PAGE_SIZE)
+		gra += prefix;
+	else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE)
+		gra -= prefix;
+	return gra;
 }
 
-static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu,
-					  void __user *gptr,
-					  int prefixing)
+/**
+ * kvm_s390_logical_to_effective - convert guest logical to effective address
+ * @vcpu: guest virtual cpu
+ * @ga: guest logical address
+ *
+ * Convert a guest vcpu logical address to a guest vcpu effective address by
+ * applying the rules of the vcpu's addressing mode defined by PSW bits 31
+ * and 32 (extendended/basic addressing mode).
+ *
+ * Depending on the vcpu's addressing mode the upper 40 bits (24 bit addressing
+ * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing mode)
+ * of @ga will be zeroed and the remaining bits will be returned.
+ */
+static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu,
+							  unsigned long ga)
 {
-	unsigned long gaddr = (unsigned long) gptr;
-	unsigned long uaddr;
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
 
-	if (prefixing)
-		gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
-	uaddr = gmap_fault(gaddr, vcpu->arch.gmap);
-	if (IS_ERR_VALUE(uaddr))
-		uaddr = -EFAULT;
-	return (void __user *)uaddr;
+	if (psw_bits(*psw).eaba == PSW_AMODE_64BIT)
+		return ga;
+	if (psw_bits(*psw).eaba == PSW_AMODE_31BIT)
+		return ga & ((1UL << 31) - 1);
+	return ga & ((1UL << 24) - 1);
 }
 
-#define get_guest(vcpu, x, gptr)				\
+/*
+ * put_guest_lc, read_guest_lc and write_guest_lc are guest access functions
+ * which shall only be used to access the lowcore of a vcpu.
+ * These functions should be used for e.g. interrupt handlers where no
+ * guest memory access protection facilities, like key or low address
+ * protection, are applicable.
+ * At a later point guest vcpu lowcore access should happen via pinned
+ * prefix pages, so that these pages can be accessed directly via the
+ * kernel mapping. All of these *_lc functions can be removed then.
+ */
+
+/**
+ * put_guest_lc - write a simple variable to a guest vcpu's lowcore
+ * @vcpu: virtual cpu
+ * @x: value to copy to guest
+ * @gra: vcpu's destination guest real address
+ *
+ * Copies a simple value from kernel space to a guest vcpu's lowcore.
+ * The size of the variable may be 1, 2, 4 or 8 bytes. The destination
+ * must be located in the vcpu's lowcore. Otherwise the result is undefined.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * Note: an error indicates that either the kernel is out of memory or
+ *	 the guest memory mapping is broken. In any case the best solution
+ *	 would be to terminate the guest.
+ *	 It is wrong to inject a guest exception.
+ */
+#define put_guest_lc(vcpu, x, gra)				\
 ({								\
-	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
-	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
-	int __ret;						\
+	struct kvm_vcpu *__vcpu = (vcpu);			\
+	__typeof__(*(gra)) __x = (x);				\
+	unsigned long __gpa;					\
 								\
-	if (IS_ERR((void __force *)__uptr)) {			\
-		__ret = PTR_ERR((void __force *)__uptr);	\
-	} else {						\
-		BUG_ON((unsigned long)__uptr & __mask);		\
-		__ret = get_user(x, __uptr);			\
-	}							\
-	__ret;							\
+	__gpa = (unsigned long)(gra);				\
+	__gpa += kvm_s390_get_prefix(__vcpu);			\
+	kvm_write_guest(__vcpu->kvm, __gpa, &__x, sizeof(__x));	\
 })
 
-#define put_guest(vcpu, x, gptr)				\
-({								\
-	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
-	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
-	int __ret;						\
-								\
-	if (IS_ERR((void __force *)__uptr)) {			\
-		__ret = PTR_ERR((void __force *)__uptr);	\
-	} else {						\
-		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)
+/**
+ * write_guest_lc - copy data from kernel space to guest vcpu's lowcore
+ * @vcpu: virtual cpu
+ * @gra: vcpu's source guest real address
+ * @data: source address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy data from kernel space to guest vcpu's lowcore. The entire range must
+ * be located within the vcpu's lowcore, otherwise the result is undefined.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * Note: an error indicates that either the kernel is out of memory or
+ *	 the guest memory mapping is broken. In any case the best solution
+ *	 would be to terminate the guest.
+ *	 It is wrong to inject a guest exception.
+ */
+static inline __must_check
+int write_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
+		   unsigned long len)
 {
-	unsigned long _len, rc;
-	void __user *uptr;
+	unsigned long gpa = gra + kvm_s390_get_prefix(vcpu);
 
-	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;
+	return kvm_write_guest(vcpu->kvm, gpa, data, len);
 }
 
-#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)
+/**
+ * read_guest_lc - copy data from guest vcpu's lowcore to kernel space
+ * @vcpu: virtual cpu
+ * @gra: vcpu's source guest real address
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy data from guest vcpu's lowcore to kernel space. The entire range must
+ * be located within the vcpu's lowcore, otherwise the result is undefined.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * Note: an error indicates that either the kernel is out of memory or
+ *	 the guest memory mapping is broken. In any case the best solution
+ *	 would be to terminate the guest.
+ *	 It is wrong to inject a guest exception.
+ */
+static inline __must_check
+int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
+		  unsigned long len)
+{
+	unsigned long gpa = gra + kvm_s390_get_prefix(vcpu);
+
+	return kvm_read_guest(vcpu->kvm, gpa, data, len);
+}
+
+int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
+			    unsigned long *gpa, int write);
+
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+		 unsigned long len, int write);
+
+int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
+		      void *data, unsigned long len, int write);
+
+/**
+ * write_guest - copy data from kernel space to guest space
+ * @vcpu: virtual cpu
+ * @ga: guest address
+ * @data: source address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @data (kernel space) to @ga (guest address).
+ * In order to copy data to guest space the PSW of the vcpu is inspected:
+ * If DAT is off data will be copied to guest real or absolute memory.
+ * If DAT is on data will be copied to the address space as specified by
+ * the address space bits of the PSW:
+ * Primary, secondory or home space (access register mode is currently not
+ * implemented).
+ * The addressing mode of the PSW is also inspected, so that address wrap
+ * around is taken into account for 24-, 31- and 64-bit addressing mode,
+ * if the to be copied data crosses page boundaries in guest address space.
+ * In addition also low address and DAT protection are inspected before
+ * copying any data (key protection is currently not implemented).
+ *
+ * This function modifies the 'struct kvm_s390_pgm_info pgm' member of @vcpu.
+ * In case of an access exception (e.g. protection exception) pgm will contain
+ * all data necessary so that a subsequent call to 'kvm_s390_inject_prog_vcpu()'
+ * will inject a correct exception into the guest.
+ * If no access exception happened, the contents of pgm are undefined when
+ * this function returns.
+ *
+ * Returns:  - zero on success
+ *	     - a negative value if e.g. the guest mapping is broken or in
+ *	       case of out-of-memory. In this case the contents of pgm are
+ *	       undefined. Also parts of @data may have been copied to guest
+ *	       space.
+ *	     - a positive value if an access exception happened. In this case
+ *	       the returned value is the program interruption code and the
+ *	       contents of pgm may be used to inject an exception into the
+ *	       guest. No data has been copied to guest space.
+ *
+ * Note: in case an access exception is recognized no data has been copied to
+ *	 guest space (this is also true, if the to be copied data would cross
+ *	 one or more page boundaries in guest space).
+ *	 Therefore this function may be used for nullifying and suppressing
+ *	 instruction emulation.
+ *	 It may also be used for terminating instructions, if it is undefined
+ *	 if data has been changed in guest space in case of an exception.
+ */
+static inline __must_check
+int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+		unsigned long len)
+{
+	return access_guest(vcpu, ga, data, len, 1);
+}
+
+/**
+ * read_guest - copy data from guest space to kernel space
+ * @vcpu: virtual cpu
+ * @ga: guest address
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @ga (guest address) to @data (kernel space).
+ *
+ * The behaviour of read_guest is identical to write_guest, except that
+ * data will be copied from guest space to kernel space.
+ */
+static inline __must_check
+int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+	       unsigned long len)
+{
+	return access_guest(vcpu, ga, data, len, 0);
+}
+
+/**
+ * write_guest_abs - copy data from kernel space to guest space absolute
+ * @vcpu: virtual cpu
+ * @gpa: guest physical (absolute) address
+ * @data: source address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @data (kernel space) to @gpa (guest absolute address).
+ * It is up to the caller to ensure that the entire guest memory range is
+ * valid memory before calling this function.
+ * Guest low address and key protection are not checked.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * If an error occurs data may have been copied partially to guest memory.
+ */
+static inline __must_check
+int write_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data,
+		    unsigned long len)
+{
+	return kvm_write_guest(vcpu->kvm, gpa, data, len);
+}
+
+/**
+ * read_guest_abs - copy data from guest space absolute to kernel space
+ * @vcpu: virtual cpu
+ * @gpa: guest physical (absolute) address
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @gpa (guest absolute address) to @data (kernel space).
+ * It is up to the caller to ensure that the entire guest memory range is
+ * valid memory before calling this function.
+ * Guest key protection is not checked.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * If an error occurs data may have been copied partially to kernel space.
+ */
+static inline __must_check
+int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data,
+		   unsigned long len)
+{
+	return kvm_read_guest(vcpu->kvm, gpa, data, len);
+}
+
+/**
+ * write_guest_real - copy data from kernel space to guest space real
+ * @vcpu: virtual cpu
+ * @gra: guest real address
+ * @data: source address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @data (kernel space) to @gra (guest real address).
+ * It is up to the caller to ensure that the entire guest memory range is
+ * valid memory before calling this function.
+ * Guest low address and key protection are not checked.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * If an error occurs data may have been copied partially to guest memory.
+ */
+static inline __must_check
+int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
+		     unsigned long len)
+{
+	return access_guest_real(vcpu, gra, data, len, 1);
+}
+
+/**
+ * read_guest_real - copy data from guest space real to kernel space
+ * @vcpu: virtual cpu
+ * @gra: guest real address
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @gra (guest real address) to @data (kernel space).
+ * It is up to the caller to ensure that the entire guest memory range is
+ * valid memory before calling this function.
+ * Guest key protection is not checked.
+ *
+ * Returns zero on success or -EFAULT on error.
+ *
+ * If an error occurs data may have been copied partially to kernel space.
+ */
+static inline __must_check
+int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
+		    unsigned long len)
+{
+	return access_guest_real(vcpu, gra, data, len, 0);
+}
+
+void ipte_lock(struct kvm_vcpu *vcpu);
+void ipte_unlock(struct kvm_vcpu *vcpu);
+int ipte_lock_held(struct kvm_vcpu *vcpu);
+int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga);
 
 #endif /* __KVM_S390_GACCESS_H */

arch/s390/kvm/guestdbg.c

···
+/*
+ * kvm guest debug support
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * 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): David Hildenbrand <[e-mail]>
+ */
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+/*
+ * Extends the address range given by *start and *stop to include the address
+ * range starting with estart and the length len. Takes care of overflowing
+ * intervals and tries to minimize the overall intervall size.
+ */
+static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len)
+{
+	u64 estop;
+
+	if (len > 0)
+		len--;
+	else
+		len = 0;
+
+	estop = estart + len;
+
+	/* 0-0 range represents "not set" */
+	if ((*start == 0) && (*stop == 0)) {
+		*start = estart;
+		*stop = estop;
+	} else if (*start <= *stop) {
+		/* increase the existing range */
+		if (estart < *start)
+			*start = estart;
+		if (estop > *stop)
+			*stop = estop;
+	} else {
+		/* "overflowing" interval, whereby *stop > *start */
+		if (estart <= *stop) {
+			if (estop > *stop)
+				*stop = estop;
+		} else if (estop > *start) {
+			if (estart < *start)
+				*start = estart;
+		}
+		/* minimize the range */
+		else if ((estop - *stop) < (*start - estart))
+			*stop = estop;
+		else
+			*start = estart;
+	}
+}
+
+#define MAX_INST_SIZE 6
+
+static void enable_all_hw_bp(struct kvm_vcpu *vcpu)
+{
+	unsigned long start, len;
+	u64 *cr9 = &vcpu->arch.sie_block->gcr[9];
+	u64 *cr10 = &vcpu->arch.sie_block->gcr[10];
+	u64 *cr11 = &vcpu->arch.sie_block->gcr[11];
+	int i;
+
+	if (vcpu->arch.guestdbg.nr_hw_bp <= 0 ||
+	    vcpu->arch.guestdbg.hw_bp_info == NULL)
+		return;
+
+	/*
+	 * If the guest is not interrested in branching events, we can savely
+	 * limit them to the PER address range.
+	 */
+	if (!(*cr9 & PER_EVENT_BRANCH))
+		*cr9 |= PER_CONTROL_BRANCH_ADDRESS;
+	*cr9 |= PER_EVENT_IFETCH | PER_EVENT_BRANCH;
+
+	for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) {
+		start = vcpu->arch.guestdbg.hw_bp_info[i].addr;
+		len = vcpu->arch.guestdbg.hw_bp_info[i].len;
+
+		/*
+		 * The instruction in front of the desired bp has to
+		 * report instruction-fetching events
+		 */
+		if (start < MAX_INST_SIZE) {
+			len += start;
+			start = 0;
+		} else {
+			start -= MAX_INST_SIZE;
+			len += MAX_INST_SIZE;
+		}
+
+		extend_address_range(cr10, cr11, start, len);
+	}
+}
+
+static void enable_all_hw_wp(struct kvm_vcpu *vcpu)
+{
+	unsigned long start, len;
+	u64 *cr9 = &vcpu->arch.sie_block->gcr[9];
+	u64 *cr10 = &vcpu->arch.sie_block->gcr[10];
+	u64 *cr11 = &vcpu->arch.sie_block->gcr[11];
+	int i;
+
+	if (vcpu->arch.guestdbg.nr_hw_wp <= 0 ||
+	    vcpu->arch.guestdbg.hw_wp_info == NULL)
+		return;
+
+	/* if host uses storage alternation for special address
+	 * spaces, enable all events and give all to the guest */
+	if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) {
+		*cr9 &= ~PER_CONTROL_ALTERATION;
+		*cr10 = 0;
+		*cr11 = PSW_ADDR_INSN;
+	} else {
+		*cr9 &= ~PER_CONTROL_ALTERATION;
+		*cr9 |= PER_EVENT_STORE;
+
+		for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) {
+			start = vcpu->arch.guestdbg.hw_wp_info[i].addr;
+			len = vcpu->arch.guestdbg.hw_wp_info[i].len;
+
+			extend_address_range(cr10, cr11, start, len);
+		}
+	}
+}
+
+void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.guestdbg.cr0 = vcpu->arch.sie_block->gcr[0];
+	vcpu->arch.guestdbg.cr9 = vcpu->arch.sie_block->gcr[9];
+	vcpu->arch.guestdbg.cr10 = vcpu->arch.sie_block->gcr[10];
+	vcpu->arch.guestdbg.cr11 = vcpu->arch.sie_block->gcr[11];
+}
+
+void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.sie_block->gcr[0] = vcpu->arch.guestdbg.cr0;
+	vcpu->arch.sie_block->gcr[9] = vcpu->arch.guestdbg.cr9;
+	vcpu->arch.sie_block->gcr[10] = vcpu->arch.guestdbg.cr10;
+	vcpu->arch.sie_block->gcr[11] = vcpu->arch.guestdbg.cr11;
+}
+
+void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * TODO: if guest psw has per enabled, otherwise 0s!
+	 * This reduces the amount of reported events.
+	 * Need to intercept all psw changes!
+	 */
+
+	if (guestdbg_sstep_enabled(vcpu)) {
+		/* disable timer (clock-comparator) interrupts */
+		vcpu->arch.sie_block->gcr[0] &= ~0x800ul;
+		vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH;
+		vcpu->arch.sie_block->gcr[10] = 0;
+		vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN;
+	}
+
+	if (guestdbg_hw_bp_enabled(vcpu)) {
+		enable_all_hw_bp(vcpu);
+		enable_all_hw_wp(vcpu);
+	}
+
+	/* TODO: Instruction-fetching-nullification not allowed for now */
+	if (vcpu->arch.sie_block->gcr[9] & PER_EVENT_NULLIFICATION)
+		vcpu->arch.sie_block->gcr[9] &= ~PER_EVENT_NULLIFICATION;
+}
+
+#define MAX_WP_SIZE 100
+
+static int __import_wp_info(struct kvm_vcpu *vcpu,
+			    struct kvm_hw_breakpoint *bp_data,
+			    struct kvm_hw_wp_info_arch *wp_info)
+{
+	int ret = 0;
+	wp_info->len = bp_data->len;
+	wp_info->addr = bp_data->addr;
+	wp_info->phys_addr = bp_data->phys_addr;
+	wp_info->old_data = NULL;
+
+	if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE)
+		return -EINVAL;
+
+	wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL);
+	if (!wp_info->old_data)
+		return -ENOMEM;
+	/* try to backup the original value */
+	ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data,
+			 wp_info->len);
+	if (ret) {
+		kfree(wp_info->old_data);
+		wp_info->old_data = NULL;
+	}
+
+	return ret;
+}
+
+#define MAX_BP_COUNT 50
+
+int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
+			    struct kvm_guest_debug *dbg)
+{
+	int ret = 0, nr_wp = 0, nr_bp = 0, i, size;
+	struct kvm_hw_breakpoint *bp_data = NULL;
+	struct kvm_hw_wp_info_arch *wp_info = NULL;
+	struct kvm_hw_bp_info_arch *bp_info = NULL;
+
+	if (dbg->arch.nr_hw_bp <= 0 || !dbg->arch.hw_bp)
+		return 0;
+	else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT)
+		return -EINVAL;
+
+	size = dbg->arch.nr_hw_bp * sizeof(struct kvm_hw_breakpoint);
+	bp_data = kmalloc(size, GFP_KERNEL);
+	if (!bp_data) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	if (copy_from_user(bp_data, dbg->arch.hw_bp, size)) {
+		ret = -EFAULT;
+		goto error;
+	}
+
+	for (i = 0; i < dbg->arch.nr_hw_bp; i++) {
+		switch (bp_data[i].type) {
+		case KVM_HW_WP_WRITE:
+			nr_wp++;
+			break;
+		case KVM_HW_BP:
+			nr_bp++;
+			break;
+		default:
+			break;
+		}
+	}
+
+	size = nr_wp * sizeof(struct kvm_hw_wp_info_arch);
+	if (size > 0) {
+		wp_info = kmalloc(size, GFP_KERNEL);
+		if (!wp_info) {
+			ret = -ENOMEM;
+			goto error;
+		}
+	}
+	size = nr_bp * sizeof(struct kvm_hw_bp_info_arch);
+	if (size > 0) {
+		bp_info = kmalloc(size, GFP_KERNEL);
+		if (!bp_info) {
+			ret = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for (nr_wp = 0, nr_bp = 0, i = 0; i < dbg->arch.nr_hw_bp; i++) {
+		switch (bp_data[i].type) {
+		case KVM_HW_WP_WRITE:
+			ret = __import_wp_info(vcpu, &bp_data[i],
+					       &wp_info[nr_wp]);
+			if (ret)
+				goto error;
+			nr_wp++;
+			break;
+		case KVM_HW_BP:
+			bp_info[nr_bp].len = bp_data[i].len;
+			bp_info[nr_bp].addr = bp_data[i].addr;
+			nr_bp++;
+			break;
+		}
+	}
+
+	vcpu->arch.guestdbg.nr_hw_bp = nr_bp;
+	vcpu->arch.guestdbg.hw_bp_info = bp_info;
+	vcpu->arch.guestdbg.nr_hw_wp = nr_wp;
+	vcpu->arch.guestdbg.hw_wp_info = wp_info;
+	return 0;
+error:
+	kfree(bp_data);
+	kfree(wp_info);
+	kfree(bp_info);
+	return ret;
+}
+
+void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_hw_wp_info_arch *hw_wp_info = NULL;
+
+	for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) {
+		hw_wp_info = &vcpu->arch.guestdbg.hw_wp_info[i];
+		kfree(hw_wp_info->old_data);
+		hw_wp_info->old_data = NULL;
+	}
+	kfree(vcpu->arch.guestdbg.hw_wp_info);
+	vcpu->arch.guestdbg.hw_wp_info = NULL;
+
+	kfree(vcpu->arch.guestdbg.hw_bp_info);
+	vcpu->arch.guestdbg.hw_bp_info = NULL;
+
+	vcpu->arch.guestdbg.nr_hw_wp = 0;
+	vcpu->arch.guestdbg.nr_hw_bp = 0;
+}
+
+static inline int in_addr_range(u64 addr, u64 a, u64 b)
+{
+	if (a <= b)
+		return (addr >= a) && (addr <= b);
+	else
+		/* "overflowing" interval */
+		return (addr <= a) && (addr >= b);
+}
+
+#define end_of_range(bp_info) (bp_info->addr + bp_info->len - 1)
+
+static struct kvm_hw_bp_info_arch *find_hw_bp(struct kvm_vcpu *vcpu,
+					      unsigned long addr)
+{
+	struct kvm_hw_bp_info_arch *bp_info = vcpu->arch.guestdbg.hw_bp_info;
+	int i;
+
+	if (vcpu->arch.guestdbg.nr_hw_bp == 0)
+		return NULL;
+
+	for (i = 0; i < vcpu->arch.guestdbg.nr_hw_bp; i++) {
+		/* addr is directly the start or in the range of a bp */
+		if (addr == bp_info->addr)
+			goto found;
+		if (bp_info->len > 0 &&
+		    in_addr_range(addr, bp_info->addr, end_of_range(bp_info)))
+			goto found;
+
+		bp_info++;
+	}
+
+	return NULL;
+found:
+	return bp_info;
+}
+
+static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_hw_wp_info_arch *wp_info = NULL;
+	void *temp = NULL;
+
+	if (vcpu->arch.guestdbg.nr_hw_wp == 0)
+		return NULL;
+
+	for (i = 0; i < vcpu->arch.guestdbg.nr_hw_wp; i++) {
+		wp_info = &vcpu->arch.guestdbg.hw_wp_info[i];
+		if (!wp_info || !wp_info->old_data || wp_info->len <= 0)
+			continue;
+
+		temp = kmalloc(wp_info->len, GFP_KERNEL);
+		if (!temp)
+			continue;
+
+		/* refetch the wp data and compare it to the old value */
+		if (!read_guest(vcpu, wp_info->phys_addr, temp,
+				wp_info->len)) {
+			if (memcmp(temp, wp_info->old_data, wp_info->len)) {
+				kfree(temp);
+				return wp_info;
+			}
+		}
+		kfree(temp);
+		temp = NULL;
+	}
+
+	return NULL;
+}
+
+void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu)
+{
+	vcpu->run->exit_reason = KVM_EXIT_DEBUG;
+	vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING;
+}
+
+#define per_bp_event(code) \
+			(code & (PER_EVENT_IFETCH | PER_EVENT_BRANCH))
+#define per_write_wp_event(code) \
+			(code & (PER_EVENT_STORE | PER_EVENT_STORE_REAL))
+
+static int debug_exit_required(struct kvm_vcpu *vcpu)
+{
+	u32 perc = (vcpu->arch.sie_block->perc << 24);
+	struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch;
+	struct kvm_hw_wp_info_arch *wp_info = NULL;
+	struct kvm_hw_bp_info_arch *bp_info = NULL;
+	unsigned long addr = vcpu->arch.sie_block->gpsw.addr;
+	unsigned long peraddr = vcpu->arch.sie_block->peraddr;
+
+	if (guestdbg_hw_bp_enabled(vcpu)) {
+		if (per_write_wp_event(perc) &&
+		    vcpu->arch.guestdbg.nr_hw_wp > 0) {
+			wp_info = any_wp_changed(vcpu);
+			if (wp_info) {
+				debug_exit->addr = wp_info->addr;
+				debug_exit->type = KVM_HW_WP_WRITE;
+				goto exit_required;
+			}
+		}
+		if (per_bp_event(perc) &&
+			 vcpu->arch.guestdbg.nr_hw_bp > 0) {
+			bp_info = find_hw_bp(vcpu, addr);
+			/* remove duplicate events if PC==PER address */
+			if (bp_info && (addr != peraddr)) {
+				debug_exit->addr = addr;
+				debug_exit->type = KVM_HW_BP;
+				vcpu->arch.guestdbg.last_bp = addr;
+				goto exit_required;
+			}
+			/* breakpoint missed */
+			bp_info = find_hw_bp(vcpu, peraddr);
+			if (bp_info && vcpu->arch.guestdbg.last_bp != peraddr) {
+				debug_exit->addr = peraddr;
+				debug_exit->type = KVM_HW_BP;
+				goto exit_required;
+			}
+		}
+	}
+	if (guestdbg_sstep_enabled(vcpu) && per_bp_event(perc)) {
+		debug_exit->addr = addr;
+		debug_exit->type = KVM_SINGLESTEP;
+		goto exit_required;
+	}
+
+	return 0;
+exit_required:
+	return 1;
+}
+
+#define guest_per_enabled(vcpu) \
+			     (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER)
+
+static void filter_guest_per_event(struct kvm_vcpu *vcpu)
+{
+	u32 perc = vcpu->arch.sie_block->perc << 24;
+	u64 peraddr = vcpu->arch.sie_block->peraddr;
+	u64 addr = vcpu->arch.sie_block->gpsw.addr;
+	u64 cr9 = vcpu->arch.sie_block->gcr[9];
+	u64 cr10 = vcpu->arch.sie_block->gcr[10];
+	u64 cr11 = vcpu->arch.sie_block->gcr[11];
+	/* filter all events, demanded by the guest */
+	u32 guest_perc = perc & cr9 & PER_EVENT_MASK;
+
+	if (!guest_per_enabled(vcpu))
+		guest_perc = 0;
+
+	/* filter "successful-branching" events */
+	if (guest_perc & PER_EVENT_BRANCH &&
+	    cr9 & PER_CONTROL_BRANCH_ADDRESS &&
+	    !in_addr_range(addr, cr10, cr11))
+		guest_perc &= ~PER_EVENT_BRANCH;
+
+	/* filter "instruction-fetching" events */
+	if (guest_perc & PER_EVENT_IFETCH &&
+	    !in_addr_range(peraddr, cr10, cr11))
+		guest_perc &= ~PER_EVENT_IFETCH;
+
+	/* All other PER events will be given to the guest */
+	/* TODO: Check alterated address/address space */
+
+	vcpu->arch.sie_block->perc = guest_perc >> 24;
+
+	if (!guest_perc)
+		vcpu->arch.sie_block->iprcc &= ~PGM_PER;
+}
+
+void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
+{
+	if (debug_exit_required(vcpu))
+		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
+
+	filter_guest_per_event(vcpu);
+}

arch/s390/kvm/intercept.c

···
 /*
  * in-kernel handling for sie intercepts
  *
- * Copyright IBM Corp. 2008, 2009
+ * Copyright IBM Corp. 2008, 2014
  *
  * 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)
···
 #include <linux/pagemap.h>
 
 #include <asm/kvm_host.h>
+#include <asm/asm-offsets.h>
+#include <asm/irq.h>
 
 #include "kvm-s390.h"
 #include "gaccess.h"
···
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
+	[0xb6] = kvm_s390_handle_stctl,
 	[0xb7] = kvm_s390_handle_lctl,
 	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
···
 		break;
 	case 0x10:
 		vcpu->stat.exit_external_request++;
-		break;
-	case 0x14:
-		vcpu->stat.exit_external_interrupt++;
 		break;
 	default:
 		break; /* nothing */
···
 	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
 
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
-		atomic_set_mask(CPUSTAT_STOPPED,
-				&vcpu->arch.sie_block->cpuflags);
+		kvm_s390_vcpu_stop(vcpu);
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
 		rc = -EOPNOTSUPP;
···
 	return -EOPNOTSUPP;
 }
 
+static void __extract_prog_irq(struct kvm_vcpu *vcpu,
+			       struct kvm_s390_pgm_info *pgm_info)
+{
+	memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
+	pgm_info->code = vcpu->arch.sie_block->iprcc;
+
+	switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
+	case PGM_AFX_TRANSLATION:
+	case PGM_ASX_TRANSLATION:
+	case PGM_EX_TRANSLATION:
+	case PGM_LFX_TRANSLATION:
+	case PGM_LSTE_SEQUENCE:
+	case PGM_LSX_TRANSLATION:
+	case PGM_LX_TRANSLATION:
+	case PGM_PRIMARY_AUTHORITY:
+	case PGM_SECONDARY_AUTHORITY:
+	case PGM_SPACE_SWITCH:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		break;
+	case PGM_ALEN_TRANSLATION:
+	case PGM_ALE_SEQUENCE:
+	case PGM_ASTE_INSTANCE:
+	case PGM_ASTE_SEQUENCE:
+	case PGM_ASTE_VALIDITY:
+	case PGM_EXTENDED_AUTHORITY:
+		pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+		break;
+	case PGM_ASCE_TYPE:
+	case PGM_PAGE_TRANSLATION:
+	case PGM_REGION_FIRST_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_SEGMENT_TRANSLATION:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info->op_access_id  = vcpu->arch.sie_block->oai;
+		break;
+	case PGM_MONITOR:
+		pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
+		pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+		break;
+	case PGM_DATA:
+		pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
+		break;
+	case PGM_PROTECTION:
+		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		break;
+	default:
+		break;
+	}
+
+	if (vcpu->arch.sie_block->iprcc & PGM_PER) {
+		pgm_info->per_code = vcpu->arch.sie_block->perc;
+		pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
+		pgm_info->per_address = vcpu->arch.sie_block->peraddr;
+		pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+	}
+}
+
+/*
+ * restore ITDB to program-interruption TDB in guest lowcore
+ * and set TX abort indication if required
+*/
+static int handle_itdb(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_itdb *itdb;
+	int rc;
+
+	if (!IS_TE_ENABLED(vcpu) || !IS_ITDB_VALID(vcpu))
+		return 0;
+	if (current->thread.per_flags & PER_FLAG_NO_TE)
+		return 0;
+	itdb = (struct kvm_s390_itdb *)vcpu->arch.sie_block->itdba;
+	rc = write_guest_lc(vcpu, __LC_PGM_TDB, itdb, sizeof(*itdb));
+	if (rc)
+		return rc;
+	memset(itdb, 0, sizeof(*itdb));
+
+	return 0;
+}
+
+#define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER)
+
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s390_pgm_info pgm_info;
+	psw_t psw;
+	int rc;
+
 	vcpu->stat.exit_program_interruption++;
 
-	/* Restore ITDB to Program-Interruption TDB in guest memory */
-	if (IS_TE_ENABLED(vcpu) &&
-	    !(current->thread.per_flags & PER_FLAG_NO_TE) &&
-	    IS_ITDB_VALID(vcpu)) {
-		copy_to_guest(vcpu, TDB_ADDR, vcpu->arch.sie_block->itdba,
-			      sizeof(struct kvm_s390_itdb));
-		memset((void *) vcpu->arch.sie_block->itdba, 0,
-		       sizeof(struct kvm_s390_itdb));
+	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
+		kvm_s390_handle_per_event(vcpu);
+		/* the interrupt might have been filtered out completely */
+		if (vcpu->arch.sie_block->iprcc == 0)
+			return 0;
 	}
 
 	trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
-	return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
+	if (vcpu->arch.sie_block->iprcc == PGM_SPECIFICATION) {
+		rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &psw, sizeof(psw_t));
+		if (rc)
+			return rc;
+		/* Avoid endless loops of specification exceptions */
+		if (!is_valid_psw(&psw))
+			return -EOPNOTSUPP;
+	}
+	rc = handle_itdb(vcpu);
+	if (rc)
+		return rc;
+
+	__extract_prog_irq(vcpu, &pgm_info);
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
···
 	return rc2;
 }
 
+/**
+ * handle_external_interrupt - used for external interruption interceptions
+ *
+ * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
+ * the new PSW does not have external interrupts disabled. In the first case,
+ * we've got to deliver the interrupt manually, and in the second case, we
+ * drop to userspace to handle the situation there.
+ */
+static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+{
+	u16 eic = vcpu->arch.sie_block->eic;
+	struct kvm_s390_interrupt irq;
+	psw_t newpsw;
+	int rc;
+
+	vcpu->stat.exit_external_interrupt++;
+
+	rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t));
+	if (rc)
+		return rc;
+	/* We can not handle clock comparator or timer interrupt with bad PSW */
+	if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) &&
+	    (newpsw.mask & PSW_MASK_EXT))
+		return -EOPNOTSUPP;
+
+	switch (eic) {
+	case EXT_IRQ_CLK_COMP:
+		irq.type = KVM_S390_INT_CLOCK_COMP;
+		break;
+	case EXT_IRQ_CPU_TIMER:
+		irq.type = KVM_S390_INT_CPU_TIMER;
+		break;
+	case EXT_IRQ_EXTERNAL_CALL:
+		if (kvm_s390_si_ext_call_pending(vcpu))
+			return 0;
+		irq.type = KVM_S390_INT_EXTERNAL_CALL;
+		irq.parm = vcpu->arch.sie_block->extcpuaddr;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return kvm_s390_inject_vcpu(vcpu, &irq);
+}
+
+/**
+ * Handle MOVE PAGE partial execution interception.
+ *
+ * This interception can only happen for guests with DAT disabled and
+ * addresses that are currently not mapped in the host. Thus we try to
+ * set up the mappings for the corresponding user pages here (or throw
+ * addressing exceptions in case of illegal guest addresses).
+ */
+static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
+{
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	unsigned long srcaddr, dstaddr;
+	int reg1, reg2, rc;
+
+	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
+
+	/* Make sure that the source is paged-in */
+	srcaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg2]);
+	if (kvm_is_error_gpa(vcpu->kvm, srcaddr))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
+	if (rc != 0)
+		return rc;
+
+	/* Make sure that the destination is paged-in */
+	dstaddr = kvm_s390_real_to_abs(vcpu, vcpu->run->s.regs.gprs[reg1]);
+	if (kvm_is_error_gpa(vcpu->kvm, dstaddr))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
+	if (rc != 0)
+		return rc;
+
+	psw->addr = __rewind_psw(*psw, 4);
+
+	return 0;
+}
+
+static int handle_partial_execution(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.sie_block->ipa == 0xb254)	/* MVPG */
+		return handle_mvpg_pei(vcpu);
+	if (vcpu->arch.sie_block->ipa >> 8 == 0xae)	/* SIGP */
+		return kvm_s390_handle_sigp_pei(vcpu);
+
+	return -EOPNOTSUPP;
+}
+
 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,
+	[0x14 >> 2] = handle_external_interrupt,
 	[0x18 >> 2] = handle_noop,
 	[0x1C >> 2] = kvm_s390_handle_wait,
 	[0x20 >> 2] = handle_validity,
 	[0x28 >> 2] = handle_stop,
+	[0x38 >> 2] = handle_partial_execution,
 };
 
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)

arch/s390/kvm/interrupt.c

···
 #define IOINT_CSSID_MASK 0x03fc0000
 #define IOINT_AI_MASK 0x04000000
 
+static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu);
+
 static int is_ioint(u64 type)
 {
 	return ((type & 0xfffe0000u) != 0xfffe0000u);
···
 	return 1;
 }
 
+static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
+{
+	if (psw_extint_disabled(vcpu) ||
+	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+		return 0;
+	if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
+		/* No timer interrupts when single stepping */
+		return 0;
+	return 1;
+}
+
 static u64 int_word_to_isc_bits(u32 int_word)
 {
 	u8 isc = (int_word & 0x38000000) >> 27;
···
 		if (psw_extint_disabled(vcpu))
 			return 0;
 		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_CLOCK_COMP:
+		return ckc_interrupts_enabled(vcpu);
+	case KVM_S390_INT_CPU_TIMER:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x400ul)
 			return 1;
 		return 0;
 	case KVM_S390_INT_SERVICE:
···
 
 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);
+	atomic_clear_mask(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;
+	vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
+
+	if (guestdbg_enabled(vcpu)) {
+		vcpu->arch.sie_block->lctl |= (LCTL_CR0 | LCTL_CR9 |
+					       LCTL_CR10 | LCTL_CR11);
+		vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT);
+	}
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
···
 	case KVM_S390_INT_PFAULT_INIT:
 	case KVM_S390_INT_PFAULT_DONE:
 	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_CLOCK_COMP:
+	case KVM_S390_INT_CPU_TIMER:
 		if (psw_extint_disabled(vcpu))
 			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
 		else
···
 	}
 }
 
+static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
+			      struct kvm_s390_pgm_info *pgm_info)
+{
+	const unsigned short table[] = { 2, 4, 4, 6 };
+	int rc = 0;
+
+	switch (pgm_info->code & ~PGM_PER) {
+	case PGM_AFX_TRANSLATION:
+	case PGM_ASX_TRANSLATION:
+	case PGM_EX_TRANSLATION:
+	case PGM_LFX_TRANSLATION:
+	case PGM_LSTE_SEQUENCE:
+	case PGM_LSX_TRANSLATION:
+	case PGM_LX_TRANSLATION:
+	case PGM_PRIMARY_AUTHORITY:
+	case PGM_SECONDARY_AUTHORITY:
+	case PGM_SPACE_SWITCH:
+		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+				  (u64 *)__LC_TRANS_EXC_CODE);
+		break;
+	case PGM_ALEN_TRANSLATION:
+	case PGM_ALE_SEQUENCE:
+	case PGM_ASTE_INSTANCE:
+	case PGM_ASTE_SEQUENCE:
+	case PGM_ASTE_VALIDITY:
+	case PGM_EXTENDED_AUTHORITY:
+		rc = put_guest_lc(vcpu, pgm_info->exc_access_id,
+				  (u8 *)__LC_EXC_ACCESS_ID);
+		break;
+	case PGM_ASCE_TYPE:
+	case PGM_PAGE_TRANSLATION:
+	case PGM_REGION_FIRST_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_SEGMENT_TRANSLATION:
+		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+				  (u64 *)__LC_TRANS_EXC_CODE);
+		rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
+				   (u8 *)__LC_EXC_ACCESS_ID);
+		rc |= put_guest_lc(vcpu, pgm_info->op_access_id,
+				   (u8 *)__LC_OP_ACCESS_ID);
+		break;
+	case PGM_MONITOR:
+		rc = put_guest_lc(vcpu, pgm_info->mon_class_nr,
+				  (u64 *)__LC_MON_CLASS_NR);
+		rc |= put_guest_lc(vcpu, pgm_info->mon_code,
+				   (u64 *)__LC_MON_CODE);
+		break;
+	case PGM_DATA:
+		rc = put_guest_lc(vcpu, pgm_info->data_exc_code,
+				  (u32 *)__LC_DATA_EXC_CODE);
+		break;
+	case PGM_PROTECTION:
+		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
+				  (u64 *)__LC_TRANS_EXC_CODE);
+		rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
+				   (u8 *)__LC_EXC_ACCESS_ID);
+		break;
+	}
+
+	if (pgm_info->code & PGM_PER) {
+		rc |= put_guest_lc(vcpu, pgm_info->per_code,
+				   (u8 *) __LC_PER_CODE);
+		rc |= put_guest_lc(vcpu, pgm_info->per_atmid,
+				   (u8 *)__LC_PER_ATMID);
+		rc |= put_guest_lc(vcpu, pgm_info->per_address,
+				   (u64 *) __LC_PER_ADDRESS);
+		rc |= put_guest_lc(vcpu, pgm_info->per_access_id,
+				   (u8 *) __LC_PER_ACCESS_ID);
+	}
+
+	switch (vcpu->arch.sie_block->icptcode) {
+	case ICPT_INST:
+	case ICPT_INSTPROGI:
+	case ICPT_OPEREXC:
+	case ICPT_PARTEXEC:
+	case ICPT_IOINST:
+		/* last instruction only stored for these icptcodes */
+		rc |= put_guest_lc(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
+				   (u16 *) __LC_PGM_ILC);
+		break;
+	case ICPT_PROGI:
+		rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->pgmilc,
+				   (u16 *) __LC_PGM_ILC);
+		break;
+	default:
+		rc |= put_guest_lc(vcpu, 0,
+				   (u16 *) __LC_PGM_ILC);
+	}
+
+	rc |= put_guest_lc(vcpu, pgm_info->code,
+			   (u16 *)__LC_PGM_INT_CODE);
+	rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
+			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+	rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
+			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+
+	return rc;
+}
+
 static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 				   struct kvm_s390_interrupt_info *inti)
 {
···
 		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,
+		rc  = put_guest_lc(vcpu, 0x1201, (u16 *)__LC_EXT_INT_CODE);
+		rc |= put_guest_lc(vcpu, inti->emerg.code,
+				   (u16 *)__LC_EXT_CPU_ADDR);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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,
+		rc  = put_guest_lc(vcpu, 0x1202, (u16 *)__LC_EXT_INT_CODE);
+		rc |= put_guest_lc(vcpu, inti->extcall.code,
+				   (u16 *)__LC_EXT_CPU_ADDR);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+				    &vcpu->arch.sie_block->gpsw,
+				    sizeof(psw_t));
+		break;
+	case KVM_S390_INT_CLOCK_COMP:
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params, 0);
+		deliver_ckc_interrupt(vcpu);
+		break;
+	case KVM_S390_INT_CPU_TIMER:
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params, 0);
+		rc  = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
+				   (u16 *)__LC_EXT_INT_CODE);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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_lc(vcpu, inti->ext.ext_params,
+				   (u32 *)__LC_EXT_PARAMS);
 		break;
 	case KVM_S390_INT_SERVICE:
 		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
···
 		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,
+		rc  = put_guest_lc(vcpu, 0x2401, (u16 *)__LC_EXT_INT_CODE);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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_lc(vcpu, inti->ext.ext_params,
+				   (u32 *)__LC_EXT_PARAMS);
 		break;
 	case KVM_S390_INT_PFAULT_INIT:
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
 						 inti->ext.ext_params2);
-		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
-		rc |= put_guest(vcpu, 0x0600, (u16 __user *) __LC_EXT_CPU_ADDR);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+		rc  = put_guest_lc(vcpu, 0x2603, (u16 *) __LC_EXT_INT_CODE);
+		rc |= put_guest_lc(vcpu, 0x0600, (u16 *) __LC_EXT_CPU_ADDR);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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_params2,
-				(u64 __user *) __LC_EXT_PARAMS2);
+		rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
+				   (u64 *) __LC_EXT_PARAMS2);
 		break;
 	case KVM_S390_INT_PFAULT_DONE:
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
 						 inti->ext.ext_params2);
-		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
-		rc |= put_guest(vcpu, 0x0680, (u16 __user *) __LC_EXT_CPU_ADDR);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+		rc  = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
+		rc |= put_guest_lc(vcpu, 0x0680, (u16 *)__LC_EXT_CPU_ADDR);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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_params2,
-				(u64 __user *) __LC_EXT_PARAMS2);
+		rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
+				   (u64 *)__LC_EXT_PARAMS2);
 		break;
 	case KVM_S390_INT_VIRTIO:
 		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
···
 		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,
+		rc  = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
+		rc |= put_guest_lc(vcpu, 0x0d00, (u16 *)__LC_EXT_CPU_ADDR);
+		rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_EXT_NEW_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);
+		rc |= put_guest_lc(vcpu, inti->ext.ext_params,
+				   (u32 *)__LC_EXT_PARAMS);
+		rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
+				   (u64 *)__LC_EXT_PARAMS2);
 		break;
 	case KVM_S390_SIGP_STOP:
 		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
···
 		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);
+		rc  = write_guest_lc(vcpu,
+				     offsetof(struct _lowcore, restart_old_psw),
+				     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
+				    &vcpu->arch.sie_block->gpsw,
+				    sizeof(psw_t));
 		break;
 	case KVM_S390_PROGRAM_INT:
 		VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
···
 		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));
+		rc = __deliver_prog_irq(vcpu, &inti->pgm);
 		break;
 
 	case KVM_S390_MCHK:
···
 						 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,
+		rc |= put_guest_lc(vcpu, inti->mchk.mcic, (u64 *)__LC_MCCK_CODE);
+		rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_MCK_NEW_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:
···
 		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));
+		rc  = put_guest_lc(vcpu, inti->io.subchannel_id,
+				   (u16 *)__LC_SUBCHANNEL_ID);
+		rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
+				   (u16 *)__LC_SUBCHANNEL_NR);
+		rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
+				   (u32 *)__LC_IO_INT_PARM);
+		rc |= put_guest_lc(vcpu, inti->io.io_int_word,
+				   (u32 *)__LC_IO_INT_WORD);
+		rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
+				     &vcpu->arch.sie_block->gpsw,
+				     sizeof(psw_t));
+		rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
+				    &vcpu->arch.sie_block->gpsw,
+				    sizeof(psw_t));
 		break;
 	}
 	default:
···
 	}
 }
 
-static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
+static void 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));
+	rc  = put_guest_lc(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
+	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
+			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
+			    &vcpu->arch.sie_block->gpsw,
+			    sizeof(psw_t));
 	if (rc) {
 		printk("kvm: The guest lowcore is not mapped during interrupt "
 			"delivery, killing userspace\n");
 		do_exit(SIGKILL);
 	}
-	return 1;
+}
+
+/* Check whether SIGP interpretation facility has an external call pending */
+int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu)
+{
+	atomic_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl;
+
+	if (!psw_extint_disabled(vcpu) &&
+	    (vcpu->arch.sie_block->gcr[0] & 0x2000ul) &&
+	    (atomic_read(sigp_ctrl) & SIGP_CTRL_C) &&
+	    (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+		return 1;
+
+	return 0;
 }
 
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
···
 		spin_unlock(&fi->lock);
 	}
 
-	if ((!rc) && (vcpu->arch.sie_block->ckc <
-		get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
-		if ((!psw_extint_disabled(vcpu)) &&
-			(vcpu->arch.sie_block->gcr[0] & 0x800ul))
-			rc = 1;
-	}
+	if (!rc && kvm_cpu_has_pending_timer(vcpu))
+		rc = 1;
+
+	if (!rc && kvm_s390_si_ext_call_pending(vcpu))
+		rc = 1;
 
 	return rc;
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return 0;
+	if (!(vcpu->arch.sie_block->ckc <
+	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
+		return 0;
+	if (!ckc_interrupts_enabled(vcpu))
+		return 0;
+	return 1;
 }
 
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
···
 		return -EOPNOTSUPP; /* disabled wait */
 	}
 
-	if (psw_extint_disabled(vcpu) ||
-	    (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
+	if (!ckc_interrupts_enabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
 		goto no_timer;
 	}
···
 	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)) {
+		!signal_pending(current) &&
+		!kvm_s390_si_ext_call_pending(vcpu)) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		spin_unlock_bh(&vcpu->arch.local_int.lock);
 		spin_unlock(&vcpu->arch.local_int.float_int->lock);
···
 	}
 	atomic_set(&li->active, 0);
 	spin_unlock_bh(&li->lock);
+
+	/* clear pending external calls set by sigp interpretation facility */
+	atomic_clear_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	atomic_clear_mask(SIGP_CTRL_C,
+			  &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl);
 }
 
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
···
 		} while (deliver);
 	}
 
-	if ((vcpu->arch.sie_block->ckc <
-		get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
-		__try_deliver_ckc_interrupt(vcpu);
+	if (kvm_cpu_has_pending_timer(vcpu))
+		deliver_ckc_interrupt(vcpu);
 
 	if (atomic_read(&fi->active)) {
 		do {
···
 
 	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;
+}
+
+int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
+			     struct kvm_s390_pgm_info *pgm_info)
+{
+	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;
+
+	VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
+		   pgm_info->code);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
+				   pgm_info->code, 0, 1);
+
+	inti->type = KVM_S390_PROGRAM_INT;
+	memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm));
 	spin_lock_bh(&li->lock);
 	list_add(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
···
 	return __inject_vm(kvm, inti);
 }
 
+void kvm_s390_reinject_io_int(struct kvm *kvm,
+			      struct kvm_s390_interrupt_info *inti)
+{
+	__inject_vm(kvm, inti);
+}
+
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 			 struct kvm_s390_interrupt *s390int)
 {
···
 		break;
 	case KVM_S390_SIGP_STOP:
 	case KVM_S390_RESTART:
+	case KVM_S390_INT_CLOCK_COMP:
+	case KVM_S390_INT_CPU_TIMER:
 		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
 		inti->type = s390int->type;
 		break;
···
 	return 0;
 }
 
-static void clear_floating_interrupts(struct kvm *kvm)
+void kvm_s390_clear_float_irqs(struct kvm *kvm)
 {
 	struct kvm_s390_float_interrupt *fi;
 	struct kvm_s390_interrupt_info	*n, *inti = NULL;
···
 		break;
 	case KVM_DEV_FLIC_CLEAR_IRQS:
 		r = 0;
-		clear_floating_interrupts(dev->kvm);
+		kvm_s390_clear_float_irqs(dev->kvm);
 		break;
 	case KVM_DEV_FLIC_APF_ENABLE:
 		dev->kvm->arch.gmap->pfault_enabled = 1;

arch/s390/kvm/kvm-s390.c

···
  *               Christian Borntraeger <[e-mail]>
  *               Heiko Carstens <[e-mail]>
  *               Christian Ehrhardt <[e-mail]>
+ *               Jason J. Herne <[e-mail]>
  */
 
 #include <linux/compiler.h>
···
 	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
 	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
 	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
+	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
+	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
 	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
 	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
 	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
···
 	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
 	{ "instruction_stap", VCPU_STAT(instruction_stap) },
 	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
 	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
 	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
 	{ "instruction_essa", VCPU_STAT(instruction_essa) },
···
 static struct gmap_notifier gmap_notifier;
 
 /* test availability of vfacility */
-static inline int test_vfacility(unsigned long nr)
+int test_vfacility(unsigned long nr)
 {
 	return __test_facility(nr, (void *) vfacilities);
 }
···
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
+	case KVM_CAP_VM_ATTRIBUTES:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
···
 	return r;
 }
 
+static void kvm_s390_sync_dirty_log(struct kvm *kvm,
+					struct kvm_memory_slot *memslot)
+{
+	gfn_t cur_gfn, last_gfn;
+	unsigned long address;
+	struct gmap *gmap = kvm->arch.gmap;
+
+	down_read(&gmap->mm->mmap_sem);
+	/* Loop over all guest pages */
+	last_gfn = memslot->base_gfn + memslot->npages;
+	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
+		address = gfn_to_hva_memslot(memslot, cur_gfn);
+
+		if (gmap_test_and_clear_dirty(address, gmap))
+			mark_page_dirty(kvm, cur_gfn);
+	}
+	up_read(&gmap->mm->mmap_sem);
+}
+
 /* 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;
+	int r;
+	unsigned long n;
+	struct kvm_memory_slot *memslot;
+	int is_dirty = 0;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = -EINVAL;
+	if (log->slot >= KVM_USER_MEM_SLOTS)
+		goto out;
+
+	memslot = id_to_memslot(kvm->memslots, log->slot);
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
+		goto out;
+
+	kvm_s390_sync_dirty_log(kvm, memslot);
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* Clear the dirty log */
+	if (is_dirty) {
+		n = kvm_dirty_bitmap_bytes(memslot);
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
 }
 
 static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
···
 	return r;
 }
 
+static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	int ret;
+	unsigned int idx;
+	switch (attr->attr) {
+	case KVM_S390_VM_MEM_ENABLE_CMMA:
+		ret = -EBUSY;
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus) == 0) {
+			kvm->arch.use_cmma = 1;
+			ret = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		break;
+	case KVM_S390_VM_MEM_CLR_CMMA:
+		mutex_lock(&kvm->lock);
+		idx = srcu_read_lock(&kvm->srcu);
+		page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false);
+		srcu_read_unlock(&kvm->srcu, idx);
+		mutex_unlock(&kvm->lock);
+		ret = 0;
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+	return ret;
+}
+
+static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_S390_VM_MEM_CTRL:
+		ret = kvm_s390_mem_control(kvm, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+
+static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_S390_VM_MEM_CTRL:
+		switch (attr->attr) {
+		case KVM_S390_VM_MEM_ENABLE_CMMA:
+		case KVM_S390_VM_MEM_CLR_CMMA:
+			ret = 0;
+			break;
+		default:
+			ret = -ENXIO;
+			break;
+		}
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
 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;
+	struct kvm_device_attr attr;
 	int r;
 
 	switch (ioctl) {
···
 			kvm_set_irq_routing(kvm, &routing, 0, 0);
 			r = 0;
 		}
+		break;
+	}
+	case KVM_SET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+			break;
+		r = kvm_s390_vm_set_attr(kvm, &attr);
+		break;
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+			break;
+		r = kvm_s390_vm_get_attr(kvm, &attr);
+		break;
+	}
+	case KVM_HAS_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+			break;
+		r = kvm_s390_vm_has_attr(kvm, &attr);
 		break;
 	}
 	default:
···
 
 	spin_lock_init(&kvm->arch.float_int.lock);
 	INIT_LIST_HEAD(&kvm->arch.float_int.list);
+	init_waitqueue_head(&kvm->arch.ipte_wq);
 
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
···
 	kvm->arch.css_support = 0;
 	kvm->arch.use_irqchip = 0;
 
+	spin_lock_init(&kvm->arch.start_stop_lock);
+
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
···
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
+	kvm_s390_clear_local_irqs(vcpu);
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		clear_bit(63 - vcpu->vcpu_id,
···
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_free(vcpu->arch.gmap);
 
-	if (vcpu->arch.sie_block->cbrlo)
-		__free_page(__pfn_to_page(
-				vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT));
+	if (kvm_s390_cmma_enabled(vcpu->kvm))
+		kvm_s390_vcpu_unsetup_cmma(vcpu);
 	free_page((unsigned long)(vcpu->arch.sie_block));
 
 	kvm_vcpu_uninit(vcpu);
···
 	if (!kvm_is_ucontrol(kvm))
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
+	kvm_s390_clear_float_irqs(kvm);
 }
 
 /* Section: vcpu related */
···
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
-	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_vcpu_stop(vcpu);
 	kvm_s390_clear_local_irqs(vcpu);
 }
 
···
 	return 0;
 }
 
+void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
+{
+	free_page(vcpu->arch.sie_block->cbrlo);
+	vcpu->arch.sie_block->cbrlo = 0;
+}
+
+int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL);
+	if (!vcpu->arch.sie_block->cbrlo)
+		return -ENOMEM;
+
+	vcpu->arch.sie_block->ecb2 |= 0x80;
+	vcpu->arch.sie_block->ecb2 &= ~0x08;
+	return 0;
+}
+
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	struct page *cbrl;
+	int rc = 0;
 
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
···
 		vcpu->arch.sie_block->ecb |= 0x10;
 
 	vcpu->arch.sie_block->ecb2  = 8;
-	vcpu->arch.sie_block->eca   = 0xC1002001U;
+	vcpu->arch.sie_block->eca   = 0xD1002000U;
+	if (sclp_has_siif())
+		vcpu->arch.sie_block->eca |= 1;
 	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
-	if (kvm_enabled_cmma()) {
-		cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (cbrl) {
-			vcpu->arch.sie_block->ecb2 |= 0x80;
-			vcpu->arch.sie_block->ecb2 &= ~0x08;
-			vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl);
-		}
+	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
+				      ICTL_TPROT;
+
+	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
+		rc = kvm_s390_vcpu_setup_cmma(vcpu);
+		if (rc)
+			return rc;
 	}
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
···
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 	get_cpu_id(&vcpu->arch.cpu_id);
 	vcpu->arch.cpu_id.version = 0xff;
-	return 0;
+	return rc;
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
···
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		/* match against both prefix pages */
-		if (vcpu->arch.sie_block->prefix == (address & ~0x1000UL)) {
+		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
 			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
 			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 			exit_sie_sync(vcpu);
···
 	return -EINVAL; /* not implemented yet */
 }
 
+#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
+			      KVM_GUESTDBG_USE_HW_BP | \
+			      KVM_GUESTDBG_ENABLE)
+
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
-	return -EINVAL; /* not implemented yet */
+	int rc = 0;
+
+	vcpu->guest_debug = 0;
+	kvm_s390_clear_bp_data(vcpu);
+
+	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
+		return -EINVAL;
+
+	if (dbg->control & KVM_GUESTDBG_ENABLE) {
+		vcpu->guest_debug = dbg->control;
+		/* enforce guest PER */
+		atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+
+		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
+			rc = kvm_s390_import_bp_data(vcpu, dbg);
+	} else {
+		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		vcpu->arch.guestdbg.last_bp = 0;
+	}
+
+	if (rc) {
+		vcpu->guest_debug = 0;
+		kvm_s390_clear_bp_data(vcpu);
+		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+	}
+
+	return rc;
 }
 
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
···
 	return -EINVAL; /* not implemented yet */
 }
 
+bool kvm_s390_cmma_enabled(struct kvm *kvm)
+{
+	if (!MACHINE_IS_LPAR)
+		return false;
+	/* only enable for z10 and later */
+	if (!MACHINE_HAS_EDAT1)
+		return false;
+	if (!kvm->arch.use_cmma)
+		return false;
+	return true;
+}
+
+static bool ibs_enabled(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
+}
+
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
+retry:
+	s390_vcpu_unblock(vcpu);
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
···
 	 * already finished. We might race against a second unmapper that
 	 * wants to set the blocking bit. Lets just retry the request loop.
 	 */
-	while (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
+	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
 		int rc;
 		rc = gmap_ipte_notify(vcpu->arch.gmap,
-				      vcpu->arch.sie_block->prefix,
+				      kvm_s390_get_prefix(vcpu),
 				      PAGE_SIZE * 2);
 		if (rc)
 			return rc;
-		s390_vcpu_unblock(vcpu);
+		goto retry;
 	}
+
+	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
+		if (!ibs_enabled(vcpu)) {
+			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
+			atomic_set_mask(CPUSTAT_IBS,
+					&vcpu->arch.sie_block->cpuflags);
+		}
+		goto retry;
+	}
+
+	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
+		if (ibs_enabled(vcpu)) {
+			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
+			atomic_clear_mask(CPUSTAT_IBS,
+					  &vcpu->arch.sie_block->cpuflags);
+		}
+		goto retry;
+	}
+
 	return 0;
 }
 
-static long kvm_arch_fault_in_sync(struct kvm_vcpu *vcpu)
+/**
+ * kvm_arch_fault_in_page - fault-in guest page if necessary
+ * @vcpu: The corresponding virtual cpu
+ * @gpa: Guest physical address
+ * @writable: Whether the page should be writable or not
+ *
+ * Make sure that a guest page has been faulted-in on the host.
+ *
+ * Return: Zero on success, negative error code otherwise.
+ */
+long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable)
 {
-	long rc;
-	hva_t fault = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
 	struct mm_struct *mm = current->mm;
+	hva_t hva;
+	long rc;
+
+	hva = gmap_fault(gpa, vcpu->arch.gmap);
+	if (IS_ERR_VALUE(hva))
+		return (long)hva;
 	down_read(&mm->mmap_sem);
-	rc = get_user_pages(current, mm, fault, 1, 1, 0, NULL, NULL);
+	rc = get_user_pages(current, mm, hva, 1, writable, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
-	return rc;
+
+	return rc < 0 ? rc : 0;
 }
 
 static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
···
 	if (!vcpu->arch.gmap->pfault_enabled)
 		return 0;
 
-	hva = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
-	if (copy_from_guest(vcpu, &arch.pfault_token, vcpu->arch.pfault_token, 8))
+	hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr));
+	hva += current->thread.gmap_addr & ~PAGE_MASK;
+	if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8))
 		return 0;
 
 	rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
···
 	if (rc)
 		return rc;
 
+	if (guestdbg_enabled(vcpu)) {
+		kvm_s390_backup_guest_per_regs(vcpu);
+		kvm_s390_patch_guest_per_regs(vcpu);
+	}
+
 	vcpu->arch.sie_block->icptcode = 0;
 	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
···
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
 
+	if (guestdbg_enabled(vcpu))
+		kvm_s390_restore_guest_per_regs(vcpu);
+
 	if (exit_reason >= 0) {
 		rc = 0;
 	} else if (kvm_is_ucontrol(vcpu->kvm)) {
···
 	} else if (current->thread.gmap_pfault) {
 		trace_kvm_s390_major_guest_pfault(vcpu);
 		current->thread.gmap_pfault = 0;
-		if (kvm_arch_setup_async_pf(vcpu) ||
-		    (kvm_arch_fault_in_sync(vcpu) >= 0))
+		if (kvm_arch_setup_async_pf(vcpu)) {
 			rc = 0;
+		} else {
+			gpa_t gpa = current->thread.gmap_addr;
+			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
+		}
 	}
 
 	if (rc == -1) {
···
 	}
 
 	return rc;
-}
-
-bool kvm_enabled_cmma(void)
-{
-	if (!MACHINE_IS_LPAR)
-		return false;
-	/* only enable for z10 and later */
-	if (!MACHINE_HAS_EDAT1)
-		return false;
-	return true;
 }
 
 static int __vcpu_run(struct kvm_vcpu *vcpu)
···
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 		rc = vcpu_post_run(vcpu, exit_reason);
-	} while (!signal_pending(current) && !rc);
+	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	return rc;
···
 	int rc;
 	sigset_t sigsaved;
 
+	if (guestdbg_exit_pending(vcpu)) {
+		kvm_s390_prepare_debug_exit(vcpu);
+		return 0;
+	}
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_vcpu_start(vcpu);
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:
···
 	case KVM_EXIT_S390_RESET:
 	case KVM_EXIT_S390_UCONTROL:
 	case KVM_EXIT_S390_TSCH:
+	case KVM_EXIT_DEBUG:
 		break;
 	default:
 		BUG();
···
 		rc = -EINTR;
 	}
 
+	if (guestdbg_exit_pending(vcpu) && !rc)  {
+		kvm_s390_prepare_debug_exit(vcpu);
+		rc = 0;
+	}
+
 	if (rc == -EOPNOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
···
 
 	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;
+	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
 	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
 
 	if (vcpu->sigset_active)
···
 	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_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr)
+int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
-	int prefix;
+	unsigned int px;
 	u64 clkcomp;
+	int rc;
 
-	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
-		if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
+	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
+		if (write_guest_abs(vcpu, 163, &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))
+		gpa = SAVE_AREA_BASE;
+	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
+		if (write_guest_real(vcpu, 163, &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->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;
-
+		gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
+	}
+	rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
+			     vcpu->arch.guest_fpregs.fprs, 128);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
+			      vcpu->run->s.regs.gprs, 128);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
+			      &vcpu->arch.sie_block->gpsw, 16);
+	px = kvm_s390_get_prefix(vcpu);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
+			      &px, 4);
+	rc |= write_guest_abs(vcpu,
+			      gpa + offsetof(struct save_area, fp_ctrl_reg),
+			      &vcpu->arch.guest_fpregs.fpc, 4);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
+			      &vcpu->arch.sie_block->todpr, 4);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
+			      &vcpu->arch.sie_block->cputm, 8);
 	clkcomp = vcpu->arch.sie_block->ckc >> 8;
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
-			&clkcomp, 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;
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
+			      &clkcomp, 8);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
+			      &vcpu->run->s.regs.acrs, 64);
+	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
+			      &vcpu->arch.sie_block->gcr, 128);
+	return rc ? -EFAULT : 0;
 }
 
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
···
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
+}
+
+static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
+}
+
+static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
+{
+	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
+	kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu);
+	exit_sie_sync(vcpu);
+}
+
+static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
+{
+	unsigned int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		__disable_ibs_on_vcpu(vcpu);
+	}
+}
+
+static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
+{
+	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
+	kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu);
+	exit_sie_sync(vcpu);
+}
+
+void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
+{
+	int i, online_vcpus, started_vcpus = 0;
+
+	if (!is_vcpu_stopped(vcpu))
+		return;
+
+	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
+	/* Only one cpu at a time may enter/leave the STOPPED state. */
+	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
+
+	for (i = 0; i < online_vcpus; i++) {
+		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
+			started_vcpus++;
+	}
+
+	if (started_vcpus == 0) {
+		/* we're the only active VCPU -> speed it up */
+		__enable_ibs_on_vcpu(vcpu);
+	} else if (started_vcpus == 1) {
+		/*
+		 * As we are starting a second VCPU, we have to disable
+		 * the IBS facility on all VCPUs to remove potentially
+		 * oustanding ENABLE requests.
+		 */
+		__disable_ibs_on_all_vcpus(vcpu->kvm);
+	}
+
+	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	/*
+	 * Another VCPU might have used IBS while we were offline.
+	 * Let's play safe and flush the VCPU at startup.
+	 */
+	vcpu->arch.sie_block->ihcpu  = 0xffff;
+	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+	return;
+}
+
+void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
+{
+	int i, online_vcpus, started_vcpus = 0;
+	struct kvm_vcpu *started_vcpu = NULL;
+
+	if (is_vcpu_stopped(vcpu))
+		return;
+
+	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
+	/* Only one cpu at a time may enter/leave the STOPPED state. */
+	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
+
+	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	__disable_ibs_on_vcpu(vcpu);
+
+	for (i = 0; i < online_vcpus; i++) {
+		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
+			started_vcpus++;
+			started_vcpu = vcpu->kvm->vcpus[i];
+		}
+	}
+
+	if (started_vcpus == 1) {
+		/*
+		 * As we only have one VCPU left, we want to enable the
+		 * IBS facility for that VCPU to speed it up.
+		 */
+		__enable_ibs_on_vcpu(started_vcpu);
+	}
+
+	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+	return;
 }
 
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,

arch/s390/kvm/kvm-s390.h

···
 
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & 0x10))
-#define TDB_ADDR		0x1800UL
 #define TDB_FORMAT1		1
 #define IS_ITDB_VALID(vcpu)	((*(char *)vcpu->arch.sie_block->itdba == TDB_FORMAT1))
 
···
 #endif
 }
 
+#define GUEST_PREFIX_SHIFT 13
+static inline u32 kvm_s390_get_prefix(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.sie_block->prefix << GUEST_PREFIX_SHIFT;
+}
+
 static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 {
-	vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u;
+	vcpu->arch.sie_block->prefix = prefix >> GUEST_PREFIX_SHIFT;
 	vcpu->arch.sie_block->ihcpu  = 0xffff;
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 }
···
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
 void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu);
+void kvm_s390_clear_float_irqs(struct kvm *kvm);
 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,
···
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 cr6, u64 schid);
+void kvm_s390_reinject_io_int(struct kvm *kvm,
+			      struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in priv.c */
+int is_valid_psw(psw_t *psw);
 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_stctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
+long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
 void s390_vcpu_block(struct kvm_vcpu *vcpu);
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
 void exit_sie_sync(struct kvm_vcpu *vcpu);
-/* are we going to support cmma? */
-bool kvm_enabled_cmma(void);
+int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
+/* is cmma enabled */
+bool kvm_s390_cmma_enabled(struct kvm *kvm);
+int test_vfacility(unsigned long nr);
+
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+/* implemented in interrupt.c */
+int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
+			     struct kvm_s390_pgm_info *pgm_info);
+
+/**
+ * kvm_s390_inject_prog_cond - conditionally inject a program check
+ * @vcpu: virtual cpu
+ * @rc: original return/error code
+ *
+ * This function is supposed to be used after regular guest access functions
+ * failed, to conditionally inject a program check to a vcpu. The typical
+ * pattern would look like
+ *
+ * rc = write_guest(vcpu, addr, data, len);
+ * if (rc)
+ *	return kvm_s390_inject_prog_cond(vcpu, rc);
+ *
+ * A negative return code from guest access functions implies an internal error
+ * like e.g. out of memory. In these cases no program check should be injected
+ * to the guest.
+ * A positive value implies that an exception happened while accessing a guest's
+ * memory. In this case all data belonging to the corresponding program check
+ * has been stored in vcpu->arch.pgm and can be injected with
+ * kvm_s390_inject_prog_irq().
+ *
+ * Returns: - the original @rc value if @rc was negative (internal error)
+ *	    - zero if @rc was already zero
+ *	    - zero or error code from injecting if @rc was positive
+ *	      (program check injected to @vcpu)
+ */
+static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc)
+{
+	if (rc <= 0)
+		return rc;
+	return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+}
 
 /* implemented in interrupt.c */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);
 void kvm_s390_destroy_adapters(struct kvm *kvm);
+int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu);
+
+/* implemented in guestdbg.c */
+void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
+void kvm_s390_restore_guest_per_regs(struct kvm_vcpu *vcpu);
+void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu);
+int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
+			    struct kvm_guest_debug *dbg);
+void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
+void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
+void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
 #endif

arch/s390/kvm/priv.c

···
 {
 	struct kvm_vcpu *cpup;
 	s64 hostclk, val;
+	int i, rc;
 	u64 op2;
-	int i;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
···
 	op2 = kvm_s390_get_base_disp_s(vcpu);
 	if (op2 & 7)	/* Operand must be on a doubleword boundary */
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	if (get_guest(vcpu, val, (u64 __user *) op2))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = read_guest(vcpu, op2, &val, sizeof(val));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 
 	if (store_tod_clock(&hostclk)) {
 		kvm_s390_set_psw_cc(vcpu, 3);
···
 static int handle_set_prefix(struct kvm_vcpu *vcpu)
 {
 	u64 operand2;
-	u32 address = 0;
-	u8 tmp;
+	u32 address;
+	int rc;
 
 	vcpu->stat.instruction_spx++;
 
···
 		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);
+	rc = read_guest(vcpu, operand2, &address, sizeof(address));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	address = address & 0x7fffe000u;
+	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)))
+	/*
+	 * Make sure the new value is valid memory. We only need to check the
+	 * first page, since address is 8k aligned and memory pieces are always
+	 * at least 1MB aligned and have at least a size of 1MB.
+	 */
+	if (kvm_is_error_gpa(vcpu->kvm, address))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 	kvm_s390_set_prefix(vcpu, address);
···
 {
 	u64 operand2;
 	u32 address;
+	int rc;
 
 	vcpu->stat.instruction_stpx++;
 
···
 	if (operand2 & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	address = vcpu->arch.sie_block->prefix;
-	address = address & 0x7fffe000u;
+	address = kvm_s390_get_prefix(vcpu);
 
 	/* get the value */
-	if (put_guest(vcpu, address, (u32 __user *)operand2))
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = write_guest(vcpu, operand2, &address, sizeof(address));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 
 	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
 	trace_kvm_s390_handle_prefix(vcpu, 0, address);
···
 
 static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 {
-	u64 useraddr;
+	u16 vcpu_id = vcpu->vcpu_id;
+	u64 ga;
+	int rc;
 
 	vcpu->stat.instruction_stap++;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	useraddr = kvm_s390_get_base_disp_s(vcpu);
+	ga = kvm_s390_get_base_disp_s(vcpu);
 
-	if (useraddr & 1)
+	if (ga & 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);
+	rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr);
-	trace_kvm_s390_handle_stap(vcpu, useraddr);
+	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", ga);
+	trace_kvm_s390_handle_stap(vcpu, ga);
 	return 0;
 }
 
+static void __skey_check_enable(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)))
+		return;
+
+	s390_enable_skey();
+	trace_kvm_s390_skey_related_inst(vcpu);
+	vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
+}
+
+
 static int handle_skey(struct kvm_vcpu *vcpu)
 {
+	__skey_check_enable(vcpu);
+
 	vcpu->stat.instruction_storage_key++;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
···
 	return 0;
 }
 
+static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
+{
+	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+
+	vcpu->stat.instruction_ipte_interlock++;
+	if (psw_bits(*psw).p)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+	wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
+	psw->addr = __rewind_psw(*psw, 4);
+	VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
+	return 0;
+}
+
 static int handle_test_block(struct kvm_vcpu *vcpu)
 {
-	unsigned long hva;
 	gpa_t addr;
 	int reg2;
 
···
 
 	kvm_s390_get_regs_rre(vcpu, NULL, &reg2);
 	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	addr = kvm_s390_logical_to_effective(vcpu, addr);
+	if (kvm_s390_check_low_addr_protection(vcpu, addr))
+		return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
 	addr = kvm_s390_real_to_abs(vcpu, addr);
 
-	hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(hva))
+	if (kvm_is_error_gpa(vcpu->kvm, addr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 	/*
 	 * We don't expect errors on modern systems, and do not care
 	 * about storage keys (yet), so let's just clear the page.
 	 */
-	if (clear_user((void __user *)hva, PAGE_SIZE) != 0)
+	if (kvm_clear_guest(vcpu->kvm, addr, PAGE_SIZE))
 		return -EFAULT;
 	kvm_s390_set_psw_cc(vcpu, 0);
 	vcpu->run->s.regs.gprs[0] = 0;
···
 static int handle_tpi(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_interrupt_info *inti;
+	unsigned long len;
+	u32 tpi_data[3];
+	int cc, rc;
 	u64 addr;
-	int cc;
 
+	rc = 0;
 	addr = kvm_s390_get_base_disp_s(vcpu);
 	if (addr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
···
 	if (!inti)
 		goto no_interrupt;
 	cc = 1;
+	tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr;
+	tpi_data[1] = inti->io.io_int_parm;
+	tpi_data[2] = inti->io.io_int_word;
 	if (addr) {
 		/*
 		 * Store the two-word I/O interruption code into the
 		 * provided area.
 		 */
-		if (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)))
-			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		len = sizeof(tpi_data) - 4;
+		rc = write_guest(vcpu, addr, &tpi_data, len);
+		if (rc)
+			return kvm_s390_inject_prog_cond(vcpu, rc);
 	} 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);
+		len = sizeof(tpi_data);
+		if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len))
+			rc = -EFAULT;
 	}
-	kfree(inti);
+	/*
+	 * If we encounter a problem storing the interruption code, the
+	 * instruction is suppressed from the guest's view: reinject the
+	 * interrupt.
+	 */
+	if (!rc)
+		kfree(inti);
+	else
+		kvm_s390_reinject_io_int(vcpu->kvm, inti);
 no_interrupt:
 	/* Set condition code and we're done. */
-	kvm_s390_set_psw_cc(vcpu, cc);
-	return 0;
+	if (!rc)
+		kvm_s390_set_psw_cc(vcpu, cc);
+	return rc ? -EFAULT : 0;
 }
 
 static int handle_tsch(struct kvm_vcpu *vcpu)
···
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
-			   vfacilities, 4);
+	rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+			    vfacilities, 4);
 	if (rc)
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		return rc;
 	VCPU_EVENT(vcpu, 5, "store facility list value %x",
 		   *(unsigned int *) vfacilities);
 	trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities);
···
 #define PSW_ADDR_24 0x0000000000ffffffUL
 #define PSW_ADDR_31 0x000000007fffffffUL
 
-static int is_valid_psw(psw_t *psw) {
+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) {
···
 		return 0;
 	if ((psw->mask & PSW_MASK_ADDR_MODE) ==  PSW_MASK_EA)
 		return 0;
+	if (psw->addr & 1)
+		return 0;
 	return 1;
 }
 
···
 	psw_t *gpsw = &vcpu->arch.sie_block->gpsw;
 	psw_compat_t new_psw;
 	u64 addr;
+	int rc;
 
 	if (gpsw->mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
···
 	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);
+
+	rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 	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;
···
 {
 	psw_t new_psw;
 	u64 addr;
+	int rc;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
···
 	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);
+	rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 	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);
···
 
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
+	u64 stidp_data = vcpu->arch.stidp_data;
 	u64 operand2;
+	int rc;
 
 	vcpu->stat.instruction_stidp++;
 
···
 	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);
+	rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
 
 	VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
 	return 0;
···
 		break;
 	}
 
-	if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
-		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		goto out_exception;
+	rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE);
+	if (rc) {
+		rc = kvm_s390_inject_prog_cond(vcpu, rc);
+		goto out;
 	}
 	trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
 	free_page(mem);
···
 	return 0;
 out_no_data:
 	kvm_s390_set_psw_cc(vcpu, 3);
-out_exception:
+out:
 	free_page(mem);
 	return rc;
 }
···
 	[0x10] = handle_set_prefix,
 	[0x11] = handle_store_prefix,
 	[0x12] = handle_store_cpu_address,
+	[0x21] = handle_ipte_interlock,
 	[0x29] = handle_skey,
 	[0x2a] = handle_skey,
 	[0x2b] = handle_skey,
···
 	[0x3a] = handle_io_inst,
 	[0x3b] = handle_io_inst,
 	[0x3c] = handle_io_inst,
+	[0x50] = handle_ipte_interlock,
 	[0x5f] = handle_io_inst,
 	[0x74] = handle_io_inst,
 	[0x76] = handle_io_inst,
···
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
+		if (kvm_s390_check_low_addr_protection(vcpu, start))
+			return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+	}
+
 	switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 	case 0x00000000:
 		end = (start + (1UL << 12)) & ~((1UL << 12) - 1);
···
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	}
 	while (start < end) {
-		unsigned long useraddr;
+		unsigned long useraddr, abs_addr;
 
-		useraddr = gmap_translate(start, vcpu->arch.gmap);
-		if (IS_ERR((void *)useraddr))
+		/* Translate guest address to host address */
+		if ((vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) == 0)
+			abs_addr = kvm_s390_real_to_abs(vcpu, start);
+		else
+			abs_addr = start;
+		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(abs_addr));
+		if (kvm_is_error_hva(useraddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
···
 		}
 
 		if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) {
+			__skey_check_enable(vcpu);
 			if (set_guest_storage_key(current->mm, useraddr,
 					vcpu->run->s.regs.gprs[reg1] & PFMF_KEY,
 					vcpu->run->s.regs.gprs[reg1] & PFMF_NQ))
···
 	VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
 	gmap = vcpu->arch.gmap;
 	vcpu->stat.instruction_essa++;
-	if (!kvm_enabled_cmma() || !vcpu->arch.sie_block->cbrlo)
+	if (!kvm_s390_cmma_enabled(vcpu->kvm))
 		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
···
 }
 
 static const intercept_handler_t b9_handlers[256] = {
+	[0x8a] = handle_ipte_interlock,
 	[0x8d] = handle_epsw,
+	[0x8e] = handle_ipte_interlock,
+	[0x8f] = handle_ipte_interlock,
 	[0xab] = handle_essa,
 	[0xaf] = handle_pfmf,
 };
···
 {
 	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;
+	u64 ga;
 
 	vcpu->stat.instruction_lctl++;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	useraddr = kvm_s390_get_base_disp_rs(vcpu);
+	ga = kvm_s390_get_base_disp_rs(vcpu);
 
-	if (useraddr & 3)
+	if (ga & 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);
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
 
 	reg = reg1;
 	do {
-		rc = get_guest(vcpu, val, (u32 __user *) useraddr);
+		rc = read_guest(vcpu, ga, &val, sizeof(val));
 		if (rc)
-			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			return kvm_s390_inject_prog_cond(vcpu, rc);
 		vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
 		vcpu->arch.sie_block->gcr[reg] |= val;
-		useraddr += 4;
+		ga += 4;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+
+	return 0;
+}
+
+int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u64 ga;
+	u32 val;
+	int reg, rc;
+
+	vcpu->stat.instruction_stctl++;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	ga = kvm_s390_get_base_disp_rs(vcpu);
+
+	if (ga & 3)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	VCPU_EVENT(vcpu, 5, "stctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga);
+
+	reg = reg1;
+	do {
+		val = vcpu->arch.sie_block->gcr[reg] &  0x00000000fffffffful;
+		rc = write_guest(vcpu, ga, &val, sizeof(val));
+		if (rc)
+			return kvm_s390_inject_prog_cond(vcpu, rc);
+		ga += 4;
 		if (reg == reg3)
 			break;
 		reg = (reg + 1) % 16;
···
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	u64 useraddr;
+	u64 ga, val;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctlg++;
···
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
+	ga = kvm_s390_get_base_disp_rsy(vcpu);
 
-	if (useraddr & 7)
+	if (ga & 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);
+	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
 
 	do {
-		rc = get_guest(vcpu, vcpu->arch.sie_block->gcr[reg],
-			       (u64 __user *) useraddr);
+		rc = read_guest(vcpu, ga, &val, sizeof(val));
 		if (rc)
-			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		useraddr += 8;
+			return kvm_s390_inject_prog_cond(vcpu, rc);
+		vcpu->arch.sie_block->gcr[reg] = val;
+		ga += 8;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+
+	return 0;
+}
+
+static int handle_stctg(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u64 ga, val;
+	int reg, rc;
+
+	vcpu->stat.instruction_stctg++;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	ga = kvm_s390_get_base_disp_rsy(vcpu);
+
+	if (ga & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	reg = reg1;
+
+	VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
+	trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga);
+
+	do {
+		val = vcpu->arch.sie_block->gcr[reg];
+		rc = write_guest(vcpu, ga, &val, sizeof(val));
+		if (rc)
+			return kvm_s390_inject_prog_cond(vcpu, rc);
+		ga += 8;
 		if (reg == reg3)
 			break;
 		reg = (reg + 1) % 16;
···
 
 static const intercept_handler_t eb_handlers[256] = {
 	[0x2f] = handle_lctlg,
+	[0x25] = handle_stctg,
 };
 
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
···
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
 	u64 address1, address2;
-	struct vm_area_struct *vma;
-	unsigned long user_address;
+	unsigned long hva, gpa;
+	int ret = 0, cc = 0;
+	bool writable;
 
 	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;
+		ipte_lock(vcpu);
+	ret = guest_translate_address(vcpu, address1, &gpa, 1);
+	if (ret == PGM_PROTECTION) {
+		/* Write protected? Try again with read-only... */
+		cc = 1;
+		ret = guest_translate_address(vcpu, address1, &gpa, 0);
+	}
+	if (ret) {
+		if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) {
+			ret = kvm_s390_inject_program_int(vcpu, ret);
+		} else if (ret > 0) {
+			/* Translation not available */
+			kvm_s390_set_psw_cc(vcpu, 3);
+			ret = 0;
+		}
+		goto out_unlock;
+	}
 
-	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);
+	hva = gfn_to_hva_prot(vcpu->kvm, gpa_to_gfn(gpa), &writable);
+	if (kvm_is_error_hva(hva)) {
+		ret = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	} else {
+		if (!writable)
+			cc = 1;		/* Write not permitted ==> read-only */
+		kvm_s390_set_psw_cc(vcpu, cc);
+		/* Note: CC2 only occurs for storage keys (not supported yet) */
+	}
+out_unlock:
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
+		ipte_unlock(vcpu);
+	return ret;
 }
 
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)

arch/s390/kvm/sigp.c

···
 
 static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct kvm_s390_local_interrupt *li;
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt s390int = {
+		.type = KVM_S390_INT_EMERGENCY,
+		.parm = vcpu->vcpu_id,
+	};
 	struct kvm_vcpu *dst_vcpu = NULL;
+	int rc = 0;
 
 	if (cpu_addr < KVM_MAX_VCPUS)
 		dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return -ENOMEM;
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
+	if (!rc)
+		VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
 
-	inti->type = KVM_S390_INT_EMERGENCY;
-	inti->emerg.code = vcpu->vcpu_id;
-
-	li = &dst_vcpu->arch.local_int;
-	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);
-	VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
-
-	return SIGP_CC_ORDER_CODE_ACCEPTED;
+	return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
···
 
 static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct kvm_s390_local_interrupt *li;
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt s390int = {
+		.type = KVM_S390_INT_EXTERNAL_CALL,
+		.parm = vcpu->vcpu_id,
+	};
 	struct kvm_vcpu *dst_vcpu = NULL;
+	int rc;
 
 	if (cpu_addr < KVM_MAX_VCPUS)
 		dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return -ENOMEM;
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
+	if (!rc)
+		VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
 
-	inti->type = KVM_S390_INT_EXTERNAL_CALL;
-	inti->extcall.code = vcpu->vcpu_id;
-
-	li = &dst_vcpu->arch.local_int;
-	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);
-	VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
-
-	return SIGP_CC_ORDER_CODE_ACCEPTED;
+	return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
···
 	struct kvm_vcpu *dst_vcpu = NULL;
 	struct kvm_s390_interrupt_info *inti;
 	int rc;
-	u8 tmp;
 
 	if (cpu_addr < KVM_MAX_VCPUS)
 		dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
···
 		return SIGP_CC_NOT_OPERATIONAL;
 	li = &dst_vcpu->arch.local_int;
 
-	/* 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)) {
+	/*
+	 * Make sure the new value is valid memory. We only need to check the
+	 * first page, since address is 8k aligned and memory pieces are always
+	 * at least 1MB aligned and have at least a size of 1MB.
+	 */
+	address &= 0x7fffe000u;
+	if (kvm_is_error_gpa(vcpu->kvm, address)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INVALID_PARAMETER;
 		return SIGP_CC_STATUS_STORED;
···
 
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
+}
+
+/*
+ * Handle SIGP partial execution interception.
+ *
+ * This interception will occur at the source cpu when a source cpu sends an
+ * external call to a target cpu and the target cpu has the WAIT bit set in
+ * its cpuflags. Interception will occurr after the interrupt indicator bits at
+ * the target cpu have been set. All error cases will lead to instruction
+ * interception, therefore nothing is to be checked or prepared.
+ */
+int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
+{
+	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
+	struct kvm_vcpu *dest_vcpu;
+	u8 order_code = kvm_s390_get_base_disp_rs(vcpu);
+
+	trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
+
+	if (order_code == SIGP_EXTERNAL_CALL) {
+		dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+		BUG_ON(dest_vcpu == NULL);
+
+		spin_lock_bh(&dest_vcpu->arch.local_int.lock);
+		if (waitqueue_active(&dest_vcpu->wq))
+			wake_up_interruptible(&dest_vcpu->wq);
+		dest_vcpu->preempted = true;
+		spin_unlock_bh(&dest_vcpu->arch.local_int.lock);
+
+		kvm_s390_set_psw_cc(vcpu, SIGP_CC_ORDER_CODE_ACCEPTED);
+		return 0;
+	}
+
+	return -EOPNOTSUPP;
 }

arch/s390/kvm/trace-s390.h

···
 	);
 
 /*
+ * Trace point for start and stop of vpcus.
+ */
+TRACE_EVENT(kvm_s390_vcpu_start_stop,
+	    TP_PROTO(unsigned int id, int state),
+	    TP_ARGS(id, state),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    __field(int, state)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->state = state;
+		    ),
+
+	    TP_printk("%s cpu %d", __entry->state ? "starting" : "stopping",
+		      __entry->id)
+	);
+
+/*
  * Trace points for injection of interrupts, either per machine or
  * per vcpu.
  */
···
 
 	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
 		      __entry->kvm)
+	);
+
+/*
+ * Trace point for enabling and disabling interlocking-and-broadcasting
+ * suppression.
+ */
+TRACE_EVENT(kvm_s390_enable_disable_ibs,
+	    TP_PROTO(unsigned int id, int state),
+	    TP_ARGS(id, state),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    __field(int, state)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->state = state;
+		    ),
+
+	    TP_printk("%s ibs on cpu %d",
+		      __entry->state ? "enabling" : "disabling", __entry->id)
 	);
 
 

arch/s390/kvm/trace.h

···
 #define _TRACE_KVM_H
 
 #include <linux/tracepoint.h>
-#include <asm/sigp.h>
+#include <asm/sie.h>
 #include <asm/debug.h>
 #include <asm/dis.h>
 
···
 #define VCPU_TP_PRINTK(p_str, p_args...)				\
 	TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id,		\
 		  __entry->pswmask, __entry->pswaddr, p_args)
+
+TRACE_EVENT(kvm_s390_skey_related_inst,
+	    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", "first instruction related to skeys on vcpu")
+	);
 
 TRACE_EVENT(kvm_s390_major_guest_pfault,
 	    TP_PROTO(VCPU_PROTO_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(__u64, instruction)
-		    __field(char, insn[8])
 		    ),
 
 	    TP_fast_assign(
···
 
 	    VCPU_TP_PRINTK("intercepted instruction %016llx (%s)",
 			   __entry->instruction,
-			   insn_to_mnemonic((unsigned char *)
-					    &__entry->instruction,
-					 __entry->insn, sizeof(__entry->insn)) ?
-			   "unknown" : __entry->insn)
+			   __print_symbolic(icpt_insn_decoder(__entry->instruction),
+					    icpt_insn_codes))
 	);
 
 /*
···
  * 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_STORE_STATUS_AT_ADDRESS, "store status at addr"},	\
-	{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),
···
 			   __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_sigp_pei,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u8, order_code)
+		    __field(__u16, cpu_addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->order_code = order_code;
+		    __entry->cpu_addr = cpu_addr;
+		    ),
+
+	    VCPU_TP_PRINTK("handle sigp pei order %02x (%s), cpu address %04x",
+			   __entry->order_code,
+			   __print_symbolic(__entry->order_code,
+					    sigp_order_codes),
+			   __entry->cpu_addr)
+	);
 
 TRACE_EVENT(kvm_s390_handle_diag,
 	    TP_PROTO(VCPU_PROTO_COMMON, __u16 code),
···
 
 	    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_stctl,
+	    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: storing cr %x-%x to %016llx",
+			   __entry->g ? "stctg" : "stctl",
 			   __entry->reg1, __entry->reg3, __entry->addr)
 	);
 

arch/s390/mm/pgtable.c

···
 	}
 	spin_unlock(&gmap_notifier_lock);
 }
+EXPORT_SYMBOL_GPL(gmap_do_ipte_notify);
 
 static inline int page_table_with_pgste(struct page *page)
 {
···
 	atomic_set(&page->_mapcount, 0);
 	table = (unsigned long *) page_to_phys(page);
 	clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
-	clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT,
-		    PAGE_SIZE/2);
+	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
 	return table;
 }
 
···
 	__free_page(page);
 }
 
-static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
-			pmd_t *pmd, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pte(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	pte_t *start_pte, *pte;
 	spinlock_t *ptl;
···
 	do {
 		pgste = pgste_get_lock(pte);
 		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		if (init_skey) {
+			unsigned long address;
+
+			pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
+					      PGSTE_GR_BIT | PGSTE_GC_BIT);
+
+			/* skip invalid and not writable pages */
+			if (pte_val(*pte) & _PAGE_INVALID ||
+			    !(pte_val(*pte) & _PAGE_WRITE)) {
+				pgste_set_unlock(pte, pgste);
+				continue;
+			}
+
+			address = pte_val(*pte) & PAGE_MASK;
+			page_set_storage_key(address, PAGE_DEFAULT_KEY, 1);
+		}
 		pgste_set_unlock(pte, pgste);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap_unlock(start_pte, ptl);
···
 	return addr;
 }
 
-static inline unsigned long page_table_reset_pmd(struct mm_struct *mm,
-			pud_t *pud, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pmd(struct mm_struct *mm, pud_t *pud,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	unsigned long next;
 	pmd_t *pmd;
···
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		next = page_table_reset_pte(mm, pmd, addr, next);
+		next = page_table_reset_pte(mm, pmd, addr, next, init_skey);
 	} while (pmd++, addr = next, addr != end);
 
 	return addr;
 }
 
-static inline unsigned long page_table_reset_pud(struct mm_struct *mm,
-			pgd_t *pgd, unsigned long addr, unsigned long end)
+static inline unsigned long page_table_reset_pud(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end, bool init_skey)
 {
 	unsigned long next;
 	pud_t *pud;
···
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		next = page_table_reset_pmd(mm, pud, addr, next);
+		next = page_table_reset_pmd(mm, pud, addr, next, init_skey);
 	} while (pud++, addr = next, addr != end);
 
 	return addr;
 }
 
-void page_table_reset_pgste(struct mm_struct *mm,
-			unsigned long start, unsigned long end)
+void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
+			    unsigned long end, bool init_skey)
 {
 	unsigned long addr, next;
 	pgd_t *pgd;
 
+	down_write(&mm->mmap_sem);
+	if (init_skey && mm_use_skey(mm))
+		goto out_up;
 	addr = start;
-	down_read(&mm->mmap_sem);
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		next = page_table_reset_pud(mm, pgd, addr, next);
+		next = page_table_reset_pud(mm, pgd, addr, next, init_skey);
 	} while (pgd++, addr = next, addr != end);
-	up_read(&mm->mmap_sem);
+	if (init_skey)
+		current->mm->context.use_skey = 1;
+out_up:
+	up_write(&mm->mmap_sem);
 }
 EXPORT_SYMBOL(page_table_reset_pgste);
 
···
 	/* changing the guest storage key is considered a change of the page */
 	if ((pgste_val(new) ^ pgste_val(old)) &
 	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
-		pgste_val(new) |= PGSTE_HC_BIT;
+		pgste_val(new) |= PGSTE_UC_BIT;
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(*ptep, ptl);
···
 						    unsigned long vmaddr)
 {
 	return NULL;
+}
+
+void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
+			    unsigned long end, bool init_skey)
+{
 }
 
 static inline void page_table_free_pgste(unsigned long *table)
···
 	return mm->context.has_pgste ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
+
+/*
+ * Enable storage key handling from now on and initialize the storage
+ * keys with the default key.
+ */
+void s390_enable_skey(void)
+{
+	page_table_reset_pgste(current->mm, 0, TASK_SIZE, true);
+}
+EXPORT_SYMBOL_GPL(s390_enable_skey);
+
+/*
+ * Test and reset if a guest page is dirty
+ */
+bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+	bool dirty = false;
+
+	pte = get_locked_pte(gmap->mm, address, &ptl);
+	if (unlikely(!pte))
+		return false;
+
+	if (ptep_test_and_clear_user_dirty(gmap->mm, address, pte))
+		dirty = true;
+
+	spin_unlock(ptl);
+	return dirty;
+}
+EXPORT_SYMBOL_GPL(gmap_test_and_clear_dirty);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,

arch/x86/include/asm/kvm_emulate.h

···
 	void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
 	ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
 	int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
-	void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val);
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);

arch/x86/include/asm/kvm_host.h

···
 			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
 			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
 
-#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
-#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
-#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL
-#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
-				  0xFFFFFF0000000000ULL)
+#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
···
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
 	VCPU_EXREG_CR3,
 	VCPU_EXREG_RFLAGS,
-	VCPU_EXREG_CPL,
 	VCPU_EXREG_SEGMENTS,
 };
 

arch/x86/include/asm/traps.h

···
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
 #ifdef CONFIG_TRACING
 dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long);
+#else
+static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error)
+{
+	do_page_fault(regs, error);
+}
 #endif
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
 dotraplinkage void do_coprocessor_error(struct pt_regs *, long);

arch/x86/kernel/kvm.c

···
 
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
-		do_page_fault(regs, error_code);
+		trace_do_page_fault(regs, error_code);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */

arch/x86/kvm/cpuid.c

···
 		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
 	/* cpuid 1.ecx */
 	const u32 kvm_supported_word4_x86_features =
+		/* NOTE: MONITOR (and MWAIT) are emulated as NOP,
+		 * but *not* advertised to guests via CPUID ! */
 		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
 		0 /* DS-CPL, VMX, SMX, EST */ |
 		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
···
 		entry->ecx &= kvm_supported_word6_x86_features;
 		cpuid_mask(&entry->ecx, 6);
 		break;
+	case 0x80000007: /* Advanced power management */
+		/* invariant TSC is CPUID.80000007H:EDX[8] */
+		entry->edx &= (1 << 8);
+		/* mask against host */
+		entry->edx &= boot_cpu_data.x86_power;
+		entry->eax = entry->ebx = entry->ecx = 0;
+		break;
 	case 0x80000008: {
 		unsigned g_phys_as = (entry->eax >> 16) & 0xff;
 		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
···
 	case 3: /* Processor serial number */
 	case 5: /* MONITOR/MWAIT */
 	case 6: /* Thermal management */
-	case 0x80000007: /* Advanced power management */
 	case 0xC0000002:
 	case 0xC0000003:
 	case 0xC0000004:
···
 not_found:
 	return 36;
 }
+EXPORT_SYMBOL_GPL(cpuid_maxphyaddr);
 
 /*
  * If no match is found, check whether we exceed the vCPU's limit

arch/x86/kvm/cpuid.h

···
 	return best && (best->ecx & bit(X86_FEATURE_X2APIC));
 }
 
+static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_GBPAGES));
+}
 #endif

arch/x86/kvm/emulate.c

···
 #define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
+#define NoMod	    ((u64)1 << 47)  /* Mod field is ignored */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
···
 	ctxt->modrm_rm |= (ctxt->modrm & 0x07);
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
-	if (ctxt->modrm_mod == 3) {
+	if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) {
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
 		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
···
 		rc->end = n * size;
 	}
 
-	if (ctxt->rep_prefix && !(ctxt->eflags & EFLG_DF)) {
+	if (ctxt->rep_prefix && (ctxt->d & String) &&
+	    !(ctxt->eflags & EFLG_DF)) {
 		ctxt->dst.data = rc->data + rc->pos;
 		ctxt->dst.type = OP_MEM_STR;
 		ctxt->dst.count = (rc->end - rc->pos) / size;
···
 }
 
 /* Does not support long mode */
-static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
-				   u16 selector, int seg)
+static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				     u16 selector, int seg, u8 cpl, bool in_task_switch)
 {
 	struct desc_struct seg_desc, old_desc;
-	u8 dpl, rpl, cpl;
+	u8 dpl, rpl;
 	unsigned err_vec = GP_VECTOR;
 	u32 err_code = 0;
 	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
···
 	}
 
 	rpl = selector & 3;
-	cpl = ctxt->ops->cpl(ctxt);
 
 	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
 	if ((seg == VCPU_SREG_CS
···
 			goto exception;
 		break;
 	case VCPU_SREG_CS:
+		if (in_task_switch && rpl != dpl)
+			goto exception;
+
 		if (!(seg_desc.type & 8))
 			goto exception;
 
···
 exception:
 	emulate_exception(ctxt, err_vec, err_code, true);
 	return X86EMUL_PROPAGATE_FAULT;
+}
+
+static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   u16 selector, int seg)
+{
+	u8 cpl = ctxt->ops->cpl(ctxt);
+	return __load_segment_descriptor(ctxt, selector, seg, cpl, false);
 }
 
 static void write_register_operand(struct operand *op)
···
 				 struct tss_segment_16 *tss)
 {
 	int ret;
+	u8 cpl;
 
 	ctxt->_eip = tss->ip;
 	ctxt->eflags = tss->flag | 2;
···
 	set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS);
 	set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
 
+	cpl = tss->cs & 3;
+
 	/*
 	 * Now load segment descriptors. If fault happens at this stage
 	 * it is handled in a context of new task
 	 */
-	ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR);
+	ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES);
+	ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS);
+	ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS);
+	ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS);
+	ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
···
 static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
 				struct tss_segment_32 *tss)
 {
-	tss->cr3 = ctxt->ops->get_cr(ctxt, 3);
+	/* CR3 and ldt selector are not saved intentionally */
 	tss->eip = ctxt->_eip;
 	tss->eflags = ctxt->eflags;
 	tss->eax = reg_read(ctxt, VCPU_REGS_RAX);
···
 	tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS);
 	tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS);
 	tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS);
-	tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR);
 }
 
 static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 				 struct tss_segment_32 *tss)
 {
 	int ret;
+	u8 cpl;
 
 	if (ctxt->ops->set_cr(ctxt, 3, tss->cr3))
 		return emulate_gp(ctxt, 0);
···
 
 	/*
 	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
+	 * descriptors.  This is important because CPL checks will
+	 * use CS.RPL.
 	 */
 	set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR);
 	set_segment_selector(ctxt, tss->es, VCPU_SREG_ES);
···
 	 * If we're switching between Protected Mode and VM86, we need to make
 	 * sure to update the mode before loading the segment descriptors so
 	 * that the selectors are interpreted correctly.
-	 *
-	 * Need to get rflags to the vcpu struct immediately because it
-	 * influences the CPL which is checked at least when loading the segment
-	 * descriptors and when pushing an error code to the new kernel stack.
-	 *
-	 * TODO Introduce a separate ctxt->ops->set_cpl callback
 	 */
-	if (ctxt->eflags & X86_EFLAGS_VM)
+	if (ctxt->eflags & X86_EFLAGS_VM) {
 		ctxt->mode = X86EMUL_MODE_VM86;
-	else
+		cpl = 3;
+	} else {
 		ctxt->mode = X86EMUL_MODE_PROT32;
-
-	ctxt->ops->set_rflags(ctxt, ctxt->eflags);
+		cpl = tss->cs & 3;
+	}
 
 	/*
 	 * Now load segment descriptors. If fault happenes at this stage
 	 * it is handled in a context of new task
 	 */
-	ret = load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR);
+	ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES);
+	ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS);
+	ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS);
+	ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS);
+	ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS);
+	ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS);
+	ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
···
 	struct tss_segment_32 tss_seg;
 	int ret;
 	u32 new_tss_base = get_desc_base(new_desc);
+	u32 eip_offset = offsetof(struct tss_segment_32, eip);
+	u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector);
 
 	ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
 			    &ctxt->exception);
···
 
 	save_state_to_tss32(ctxt, &tss_seg);
 
-	ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
-			     &ctxt->exception);
+	/* Only GP registers and segment selectors are saved */
+	ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip,
+			     ldt_sel_offset - eip_offset, &ctxt->exception);
 	if (ret != X86EMUL_CONTINUE)
 		/* FIXME: need to provide precise fault address */
 		return ret;
···
 		ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 		if (efer & EFER_LMA)
 			rsvd = CR3_L_MODE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE)
-			rsvd = CR3_PAE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG)
-			rsvd = CR3_NONPAE_RESERVED_BITS;
 
 		if (new_val & rsvd)
 			return emulate_gp(ctxt, 0);
···
 	N, N, N, N, N, N, N, N,
 	D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
 	/* 0x20 - 0x2F */
-	DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
-	DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
-	IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write),
-	IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write),
+	DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read),
+	DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read),
+	IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_cr_write, cr_write,
+						check_cr_write),
+	IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write,
+						check_dr_write),
 	N, N, N, N,
 	GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
 	GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),

arch/x86/kvm/irq.c

···
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
 }
+EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {

arch/x86/kvm/lapic.c

···
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
 		++apic->isr_count;
 	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
···
 	apic->highest_isr_cache = vec;
 }
 
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
+	/*
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
+	 */
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
+}
+
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
···
 		return;
 	}
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
-}
-
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
 }
 
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
···
 {
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	/* Note that we never get here with APIC virtualization enabled.  */
 
 	if (vector == -1)
 		return -1;

arch/x86/kvm/mmu.c

···
 #include "mmu.h"
 #include "x86.h"
 #include "kvm_cache_regs.h"
+#include "cpuid.h"
 
 #include <linux/kvm_host.h>
 #include <linux/types.h>
···
 	 * we always atomicly update it, see the comments in
 	 * spte_has_volatile_bits().
 	 */
-	if (is_writable_pte(old_spte) && !is_writable_pte(new_spte))
+	if (spte_is_locklessly_modifiable(old_spte) &&
+	      !is_writable_pte(new_spte))
 		ret = true;
 
 	if (!shadow_accessed_mask)
···
 
 /*
  * Write-protect on the specified @sptep, @pt_protect indicates whether
- * spte writ-protection is caused by protecting shadow page table.
- * @flush indicates whether tlb need be flushed.
+ * spte write-protection is caused by protecting shadow page table.
  *
  * Note: write protection is difference between drity logging and spte
  * protection:
···
  * - for spte protection, the spte can be writable only after unsync-ing
  *   shadow page.
  *
- * Return true if the spte is dropped.
+ * Return true if tlb need be flushed.
  */
-static bool
-spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
+static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect)
 {
 	u64 spte = *sptep;
 
···
 
 	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
 
-	if (__drop_large_spte(kvm, sptep)) {
-		*flush |= true;
-		return true;
-	}
-
 	if (pt_protect)
 		spte &= ~SPTE_MMU_WRITEABLE;
 	spte = spte & ~PT_WRITABLE_MASK;
 
-	*flush |= mmu_spte_update(sptep, spte);
-	return false;
+	return mmu_spte_update(sptep, spte);
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
···
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		if (spte_write_protect(kvm, sptep, &flush, pt_protect)) {
-			sptep = rmap_get_first(*rmapp, &iter);
-			continue;
-		}
 
+		flush |= spte_write_protect(kvm, sptep, pt_protect);
 		sptep = rmap_get_next(&iter);
 	}
 
···
 }
 
 static bool
-fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte)
+fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+			u64 *sptep, u64 spte)
 {
-	struct kvm_mmu_page *sp = page_header(__pa(sptep));
 	gfn_t gfn;
 
 	WARN_ON(!sp->role.direct);
···
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
+	struct kvm_mmu_page *sp;
 	bool ret = false;
 	u64 spte = 0ull;
 
···
 		goto exit;
 	}
 
-	if (!is_last_spte(spte, level))
+	sp = page_header(__pa(iterator.sptep));
+	if (!is_last_spte(spte, sp->role.level))
 		goto exit;
 
 	/*
···
 		goto exit;
 
 	/*
+	 * Do not fix write-permission on the large spte since we only dirty
+	 * the first page into the dirty-bitmap in fast_pf_fix_direct_spte()
+	 * that means other pages are missed if its slot is dirty-logged.
+	 *
+	 * Instead, we let the slow page fault path create a normal spte to
+	 * fix the access.
+	 *
+	 * See the comments in kvm_arch_commit_memory_region().
+	 */
+	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+		goto exit;
+
+	/*
 	 * Currently, fast page fault only works for direct mapping since
 	 * the gfn is not stable for indirect shadow page.
 	 * See Documentation/virtual/kvm/locking.txt to get more detail.
 	 */
-	ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte);
+	ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte);
 exit:
 	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
 			      spte, ret);
···
 {
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
+	u64 gbpages_bit_rsvd = 0;
 
 	context->bad_mt_xwr = 0;
 
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
+	if (!guest_cpuid_has_gbpages(vcpu))
+		gbpages_bit_rsvd = rsvd_bits(7, 7);
 	switch (context->root_level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
···
 	case PT32E_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][2] =
 			rsvd_bits(maxphyaddr, 63) |
-			rsvd_bits(7, 8) | rsvd_bits(1, 2);	/* PDPTE */
+			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
 		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62);	/* PDE */
 		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
···
 		break;
 	case PT64_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
 		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
 		context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) |
+			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 29);
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
···
 			if (*rmapp)
 				__rmap_write_protect(kvm, rmapp, false);
 
-			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
-				kvm_flush_remote_tlbs(kvm);
+			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
 				cond_resched_lock(&kvm->mmu_lock);
-			}
 		}
 	}
 
-	kvm_flush_remote_tlbs(kvm);
 	spin_unlock(&kvm->mmu_lock);
+
+	/*
+	 * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log()
+	 * which do tlb flush out of mmu-lock should be serialized by
+	 * kvm->slots_lock otherwise tlb flush would be missed.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * We can flush all the TLBs out of the mmu lock without TLB
+	 * corruption since we just change the spte from writable to
+	 * readonly so that we only need to care the case of changing
+	 * spte from present to present (changing the spte from present
+	 * to nonpresent will flush all the TLBs immediately), in other
+	 * words, the only case we care is mmu_spte_update() where we
+	 * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
+	 * instead of PT_WRITABLE_MASK, that means it does not depend
+	 * on PT_WRITABLE_MASK anymore.
+	 */
+	kvm_flush_remote_tlbs(kvm);
 }
 
 #define BATCH_ZAP_PAGES	10

arch/x86/kvm/mmu.h

···
 	return pte & PT_PRESENT_MASK;
 }
 
+/*
+ * Currently, we have two sorts of write-protection, a) the first one
+ * write-protects guest page to sync the guest modification, b) another one is
+ * used to sync dirty bitmap when we do KVM_GET_DIRTY_LOG. The differences
+ * between these two sorts are:
+ * 1) the first case clears SPTE_MMU_WRITEABLE bit.
+ * 2) the first case requires flushing tlb immediately avoiding corrupting
+ *    shadow page table between all vcpus so it should be in the protection of
+ *    mmu-lock. And the another case does not need to flush tlb until returning
+ *    the dirty bitmap to userspace since it only write-protects the page
+ *    logged in the bitmap, that means the page in the dirty bitmap is not
+ *    missed, so it can flush tlb out of mmu-lock.
+ *
+ * So, there is the problem: the first case can meet the corrupted tlb caused
+ * by another case which write-protects pages but without flush tlb
+ * immediately. In order to making the first case be aware this problem we let
+ * it flush tlb if we try to write-protect a spte whose SPTE_MMU_WRITEABLE bit
+ * is set, it works since another case never touches SPTE_MMU_WRITEABLE bit.
+ *
+ * Anyway, whenever a spte is updated (only permission and status bits are
+ * changed) we need to check whether the spte with SPTE_MMU_WRITEABLE becomes
+ * readonly, if that happens, we need to flush tlb. Fortunately,
+ * mmu_spte_update() has already handled it perfectly.
+ *
+ * The rules to use SPTE_MMU_WRITEABLE and PT_WRITABLE_MASK:
+ * - if we want to see if it has writable tlb entry or if the spte can be
+ *   writable on the mmu mapping, check SPTE_MMU_WRITEABLE, this is the most
+ *   case, otherwise
+ * - if we fix page fault on the spte or do write-protection by dirty logging,
+ *   check PT_WRITABLE_MASK.
+ *
+ * TODO: introduce APIs to split these two cases.
+ */
 static inline int is_writable_pte(unsigned long pte)
 {
 	return pte & PT_WRITABLE_MASK;

arch/x86/kvm/paging_tmpl.h

···
  *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
  *   used by guest then tlbs are not flushed, so guest is allowed to access the
  *   freed pages.
- *   We set tlbs_dirty to let the notifier know this change and delay the flush
- *   until such a case actually happens.
+ *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
···
 			return -EINVAL;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			vcpu->kvm->tlbs_dirty = true;
+			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
···
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			vcpu->kvm->tlbs_dirty = true;
+			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 

arch/x86/kvm/pmu.c

···
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-	__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+	}
 }
 
 static void kvm_perf_overflow_intr(struct perf_event *perf_event,
···
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
 	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
-		kvm_perf_overflow(perf_event, data, regs);
+		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 		/*
 		 * Inject PMI. If vcpu was in a guest mode during NMI PMI

arch/x86/kvm/svm.c

···
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 }
 
-static void svm_update_cpl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int cpl;
-
-	if (!is_protmode(vcpu))
-		cpl = 0;
-	else if (svm->vmcb->save.rflags & X86_EFLAGS_VM)
-		cpl = 3;
-	else
-		cpl = svm->vmcb->save.cs.selector & 0x3;
-
-	svm->vmcb->save.cpl = cpl;
-}
-
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 {
 	return to_svm(vcpu)->vmcb->save.rflags;
···
 
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags;
-
+       /*
+        * Any change of EFLAGS.VM is accompained by a reload of SS
+        * (caused by either a task switch or an inter-privilege IRET),
+        * so we do not need to update the CPL here.
+        */
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
-	if ((old_rflags ^ rflags) & X86_EFLAGS_VM)
-		svm_update_cpl(vcpu);
 }
 
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
···
 		s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
 		s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
 	}
-	if (seg == VCPU_SREG_CS)
-		svm_update_cpl(vcpu);
+
+	/*
+	 * This is always accurate, except if SYSRET returned to a segment
+	 * with SS.DPL != 3.  Intel does not have this quirk, and always
+	 * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it
+	 * would entail passing the CPL to userspace and back.
+	 */
+	if (seg == VCPU_SREG_SS)
+		svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
 
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }
···
 	return 1;
 }
 
-static int invalid_op_interception(struct vcpu_svm *svm)
-{
-	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
-	return 1;
-}
-
 static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
···
 	return 1;
 }
 
+static int nop_interception(struct vcpu_svm *svm)
+{
+	skip_emulated_instruction(&(svm->vcpu));
+	return 1;
+}
+
+static int monitor_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
+static int mwait_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
 static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
···
 	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= skinit_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
-	[SVM_EXIT_MONITOR]			= invalid_op_interception,
-	[SVM_EXIT_MWAIT]			= invalid_op_interception,
+	[SVM_EXIT_MONITOR]			= monitor_interception,
+	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 };

arch/x86/kvm/trace.h

···
 /*
  * Tracepoint for PIO.
  */
+
+#define KVM_PIO_IN   0
+#define KVM_PIO_OUT  1
+
 TRACE_EVENT(kvm_pio,
 	TP_PROTO(unsigned int rw, unsigned int port, unsigned int size,
-		 unsigned int count),
-	TP_ARGS(rw, port, size, count),
+		 unsigned int count, void *data),
+	TP_ARGS(rw, port, size, count, data),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int, 	rw		)
 		__field(	unsigned int, 	port		)
 		__field(	unsigned int, 	size		)
 		__field(	unsigned int,	count		)
+		__field(	unsigned int,	val		)
 	),
 
 	TP_fast_assign(
···
 		__entry->port		= port;
 		__entry->size		= size;
 		__entry->count		= count;
+		if (size == 1)
+			__entry->val	= *(unsigned char *)data;
+		else if (size == 2)
+			__entry->val	= *(unsigned short *)data;
+		else
+			__entry->val	= *(unsigned int *)data;
 	),
 
-	TP_printk("pio_%s at 0x%x size %d count %d",
+	TP_printk("pio_%s at 0x%x size %d count %d val 0x%x %s",
 		  __entry->rw ? "write" : "read",
-		  __entry->port, __entry->size, __entry->count)
+		  __entry->port, __entry->size, __entry->count, __entry->val,
+		  __entry->count > 1 ? "(...)" : "")
 );
 
 /*

arch/x86/kvm/vmx.c

···
 struct nested_vmx {
 	/* Has the level1 guest done vmxon? */
 	bool vmxon;
+	gpa_t vmxon_ptr;
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
···
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
 	u8                    fail;
-	u8                    cpl;
 	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
···
 	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
 		nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
 	nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
-	/* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
+
 	nested_vmx_exit_ctls_high &=
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
···
 		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
 	nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
-		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
+
 	if (vmx_mpx_supported())
 		nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
···
 			 VMX_EPT_INVEPT_BIT;
 		nested_vmx_ept_caps &= vmx_capability.ept;
 		/*
-		 * Since invept is completely emulated we support both global
-		 * and context invalidation independent of what host cpu
-		 * supports
+		 * For nested guests, we don't do anything specific
+		 * for single context invalidation. Hence, only advertise
+		 * support for global context invalidation.
 		 */
-		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
-			VMX_EPT_EXTENT_CONTEXT_BIT;
+		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT;
 	} else
 		nested_vmx_ept_caps = 0;
 
···
 	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-
-	/* CPL is always 0 when CPU enters protected mode */
-	__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-	vmx->cpl = 0;
 }
 
 static void fix_rmode_seg(int seg, struct kvm_segment *save)
···
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!is_protmode(vcpu))
+	if (unlikely(vmx->rmode.vm86_active))
 		return 0;
-
-	if (!is_long_mode(vcpu)
-	    && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
-		return 3;
-
-	if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-		vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3;
+	else {
+		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+		return AR_DPL(ar);
 	}
-
-	return vmx->cpl;
 }
-
 
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
···
 	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 
 	vmx_segment_cache_clear(vmx);
-	if (seg == VCPU_SREG_CS)
-		__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 
 	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
 		vmx->rmode.segs[seg] = *var;
···
 		PIN_BASED_EXT_INTR_MASK;
 }
 
+/*
+ * In nested virtualization, check if L1 has set
+ * VM_EXIT_ACK_INTR_ON_EXIT
+ */
+static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->vm_exit_controls &
+		VM_EXIT_ACK_INTR_ON_EXIT;
+}
+
 static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
 {
 	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
···
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
 			vcpu->arch.dr6 |= dr6;
+			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+				skip_emulated_instruction(vcpu);
+
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			return 1;
 		}
···
 			return 1;
 		kvm_register_write(vcpu, reg, val);
 	} else
-		if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]))
+		if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)))
 			return 1;
 
 	skip_emulated_instruction(vcpu);
···
 	}
 
 	/* clear all local breakpoint enable flags */
-	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55);
 
 	/*
 	 * TODO: What about debug traps on tss switch?
···
 	gpa_t gpa;
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+	if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		skip_emulated_instruction(vcpu);
+		return 1;
+	}
 
 	ret = handle_mmio_page_fault_common(vcpu, gpa, true);
 	if (likely(ret == RET_MMIO_PF_EMULATE))
···
 	return 1;
 }
 
-static int handle_invalid_op(struct kvm_vcpu *vcpu)
+static int handle_nop(struct kvm_vcpu *vcpu)
 {
-	kvm_queue_exception(vcpu, UD_VECTOR);
+	skip_emulated_instruction(vcpu);
 	return 1;
+}
+
+static int handle_mwait(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_monitor(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
 }
 
 /*
···
 }
 
 /*
+ * Decode the memory-address operand of a vmx instruction, as recorded on an
+ * exit caused by such an instruction (run by a guest hypervisor).
+ * On success, returns 0. When the operand is invalid, returns 1 and throws
+ * #UD or #GP.
+ */
+static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
+				 unsigned long exit_qualification,
+				 u32 vmx_instruction_info, gva_t *ret)
+{
+	/*
+	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
+	 * Execution", on an exit, vmx_instruction_info holds most of the
+	 * addressing components of the operand. Only the displacement part
+	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
+	 * For how an actual address is calculated from all these components,
+	 * refer to Vol. 1, "Operand Addressing".
+	 */
+	int  scaling = vmx_instruction_info & 3;
+	int  addr_size = (vmx_instruction_info >> 7) & 7;
+	bool is_reg = vmx_instruction_info & (1u << 10);
+	int  seg_reg = (vmx_instruction_info >> 15) & 7;
+	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
+	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
+	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
+	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
+
+	if (is_reg) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* Addr = segment_base + offset */
+	/* offset = base + [index * scale] + displacement */
+	*ret = vmx_get_segment_base(vcpu, seg_reg);
+	if (base_is_valid)
+		*ret += kvm_register_read(vcpu, base_reg);
+	if (index_is_valid)
+		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
+	*ret += exit_qualification; /* holds the displacement */
+
+	if (addr_size == 1) /* 32 bit */
+		*ret &= 0xffffffff;
+
+	/*
+	 * TODO: throw #GP (and return 1) in various cases that the VM*
+	 * instructions require it - e.g., offset beyond segment limit,
+	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
+	 * address, and so on. Currently these are not checked.
+	 */
+	return 0;
+}
+
+/*
+ * This function performs the various checks including
+ * - if it's 4KB aligned
+ * - No bits beyond the physical address width are set
+ * - Returns 0 on success or else 1
+ * (Intel SDM Section 30.3)
+ */
+static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
+				  gpa_t *vmpointer)
+{
+	gva_t gva;
+	gpa_t vmptr;
+	struct x86_exception e;
+	struct page *page;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+		return 1;
+
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
+				sizeof(vmptr), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (exit_reason) {
+	case EXIT_REASON_VMON:
+		/*
+		 * SDM 3: 24.11.5
+		 * The first 4 bytes of VMXON region contain the supported
+		 * VMCS revision identifier
+		 *
+		 * Note - IA32_VMX_BASIC[48] will never be 1
+		 * for the nested case;
+		 * which replaces physical address width with 32
+		 *
+		 */
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failInvalid(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		page = nested_get_page(vcpu, vmptr);
+		if (page == NULL ||
+		    *(u32 *)kmap(page) != VMCS12_REVISION) {
+			nested_vmx_failInvalid(vcpu);
+			kunmap(page);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		kunmap(page);
+		vmx->nested.vmxon_ptr = vmptr;
+		break;
+	case EXIT_REASON_VMCLEAR:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	case EXIT_REASON_VMPTRLD:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMPTRLD_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	default:
+		return 1; /* shouldn't happen */
+	}
+
+	if (vmpointer)
+		*vmpointer = vmptr;
+	return 0;
+}
+
+/*
  * Emulate the VMXON instruction.
  * Currently, we just remember that VMX is active, and do not save or even
  * inspect the argument to VMXON (the so-called "VMXON pointer") because we
···
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
+
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+		return 1;
+
 	if (vmx->nested.vmxon) {
 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
 		skip_emulated_instruction(vcpu);
···
 	return 1;
 }
 
-/*
- * Decode the memory-address operand of a vmx instruction, as recorded on an
- * exit caused by such an instruction (run by a guest hypervisor).
- * On success, returns 0. When the operand is invalid, returns 1 and throws
- * #UD or #GP.
- */
-static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
-				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, gva_t *ret)
-{
-	/*
-	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
-	 * Execution", on an exit, vmx_instruction_info holds most of the
-	 * addressing components of the operand. Only the displacement part
-	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
-	 * For how an actual address is calculated from all these components,
-	 * refer to Vol. 1, "Operand Addressing".
-	 */
-	int  scaling = vmx_instruction_info & 3;
-	int  addr_size = (vmx_instruction_info >> 7) & 7;
-	bool is_reg = vmx_instruction_info & (1u << 10);
-	int  seg_reg = (vmx_instruction_info >> 15) & 7;
-	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
-	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
-	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
-	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
-
-	if (is_reg) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	/* Addr = segment_base + offset */
-	/* offset = base + [index * scale] + displacement */
-	*ret = vmx_get_segment_base(vcpu, seg_reg);
-	if (base_is_valid)
-		*ret += kvm_register_read(vcpu, base_reg);
-	if (index_is_valid)
-		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
-	*ret += exit_qualification; /* holds the displacement */
-
-	if (addr_size == 1) /* 32 bit */
-		*ret &= 0xffffffff;
-
-	/*
-	 * TODO: throw #GP (and return 1) in various cases that the VM*
-	 * instructions require it - e.g., offset beyond segment limit,
-	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
-	 * address, and so on. Currently these are not checked.
-	 */
-	return 0;
-}
-
 /* Emulate the VMCLEAR instruction */
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
 	struct vmcs12 *vmcs12;
 	struct page *page;
-	struct x86_exception e;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
 		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
-		return 1;
-	}
 
 	if (vmptr == vmx->nested.current_vmptr) {
 		nested_release_vmcs12(vmx);
···
 static int handle_vmptrld(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
-	struct x86_exception e;
 	u32 exec_control;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
 		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
-		return 1;
-	}
 
 	if (vmx->nested.current_vmptr != vmptr) {
 		struct vmcs12 *new_vmcs12;
···
 	struct {
 		u64 eptp, gpa;
 	} operand;
-	u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK;
 
 	if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
 	    !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
···
 	}
 
 	switch (type) {
-	case VMX_EPT_EXTENT_CONTEXT:
-		if ((operand.eptp & eptp_mask) !=
-				(nested_ept_get_cr3(vcpu) & eptp_mask))
-			break;
 	case VMX_EPT_EXTENT_GLOBAL:
 		kvm_mmu_sync_roots(vcpu);
 		kvm_mmu_flush_tlb(vcpu);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
+		/* Trap single context invalidation invept calls */
 		BUG_ON(1);
 		break;
 	}
···
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
-	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
-	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
···
 
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
 				  | (1 << VCPU_EXREG_RFLAGS)
-				  | (1 << VCPU_EXREG_CPL)
 				  | (1 << VCPU_EXREG_PDPTR)
 				  | (1 << VCPU_EXREG_SEGMENTS)
 				  | (1 << VCPU_EXREG_CR3));
···
 	leave_guest_mode(vcpu);
 	prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
 		       exit_qualification);
+
+	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+	    && nested_exit_intr_ack_set(vcpu)) {
+		int irq = kvm_cpu_get_interrupt(vcpu);
+		WARN_ON(irq < 0);
+		vmcs12->vm_exit_intr_info = irq |
+			INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
+	}
 
 	trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
 				       vmcs12->exit_qualification,

arch/x86/kvm/x86.c

···
 	}
 
 	if (is_long_mode(vcpu)) {
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) {
-			if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS)
-				return 1;
-		} else
-			if (cr3 & CR3_L_MODE_RESERVED_BITS)
-				return 1;
-	} else {
-		if (is_pae(vcpu)) {
-			if (cr3 & CR3_PAE_RESERVED_BITS)
-				return 1;
-			if (is_paging(vcpu) &&
-			    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
-				return 1;
-		}
-		/*
-		 * We don't check reserved bits in nonpae mode, because
-		 * this isn't enforced, and VMware depends on this.
-		 */
-	}
+		if (cr3 & CR3_L_MODE_RESERVED_BITS)
+			return 1;
+	} else if (is_pae(vcpu) && is_paging(vcpu) &&
+		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+		return 1;
 
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
···
 
 		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
 			vcpu->arch.hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+				return 1;
 			break;
 		}
 		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
···
 			return 1;
 		vcpu->arch.hv_vapic = data;
 		mark_page_dirty(vcpu->kvm, gfn);
+		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+			return 1;
 		break;
 	}
 	case HV_X64_MSR_EOI:
···
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
···
 		offset = i * BITS_PER_LONG;
 		kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
 	}
-	if (is_dirty)
-		kvm_flush_remote_tlbs(kvm);
 
 	spin_unlock(&kvm->mmu_lock);
+
+	/* See the comments in kvm_mmu_slot_remove_write_access(). */
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * All the TLBs can be flushed out of mmu lock, see the comments in
+	 * kvm_mmu_slot_remove_write_access().
+	 */
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
 
 	r = -EFAULT;
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
···
 			       unsigned short port, void *val,
 			       unsigned int count, bool in)
 {
-	trace_kvm_pio(!in, port, size, count);
-
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = in;
 	vcpu->arch.pio.count  = count;
···
 	if (ret) {
 data_avail:
 		memcpy(val, vcpu->arch.pio_data, size * count);
+		trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
 		vcpu->arch.pio.count = 0;
 		return 1;
 	}
···
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 
 	memcpy(vcpu->arch.pio_data, val, size * count);
+	trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
 	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
 }
 
···
 	}
 
 	return res;
-}
-
-static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
-{
-	kvm_set_rflags(emul_to_vcpu(ctxt), val);
 }
 
 static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
···
 	.set_idt	     = emulator_set_idt,
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
-	.set_rflags          = emulator_set_rflags,
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,
···
 	ctxt->eip = kvm_rip_read(vcpu);
 	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
 		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
-		     cs_l				? X86EMUL_MODE_PROT64 :
+		     (cs_l && is_long_mode(vcpu))	? X86EMUL_MODE_PROT64 :
 		     cs_db				? X86EMUL_MODE_PROT32 :
 							  X86EMUL_MODE_PROT16;
 	ctxt->guest_mode = is_guest_mode(vcpu);
···
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
 	/*
 	 * Write protect all pages for dirty logging.
-	 * Existing largepage mappings are destroyed here and new ones will
-	 * not be created until the end of the logging.
+	 *
+	 * All the sptes including the large sptes which point to this
+	 * slot are set to readonly. We can not create any new large
+	 * spte on this slot until the end of the logging.
+	 *
+	 * See the comments in fast_page_fault().
 	 */
 	if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
 		kvm_mmu_slot_remove_write_access(kvm, mem->slot);

drivers/s390/char/sclp_early.c

···
 	u8	rnsize;			/* 10 */
 	u8	_reserved0[16 - 11];	/* 11-15 */
 	u16	ncpurl;			/* 16-17 */
-	u8	_reserved7[24 - 18];	/* 18-23 */
+	u16	cpuoff;			/* 18-19 */
+	u8	_reserved7[24 - 20];	/* 20-23 */
 	u8	loadparm[8];		/* 24-31 */
 	u8	_reserved1[48 - 32];	/* 32-47 */
 	u64	facilities;		/* 48-55 */
-	u8	_reserved2[84 - 56];	/* 56-83 */
+	u8	_reserved2a[76 - 56];	/* 56-75 */
+	u32	ibc;			/* 76-79 */
+	u8	_reserved2b[84 - 80];	/* 80-83 */
 	u8	fac84;			/* 84 */
 	u8	fac85;			/* 85 */
 	u8	_reserved3[91 - 86];	/* 86-90 */
···
 static unsigned long sclp_hsa_size;
 static unsigned int sclp_max_cpu;
 static struct sclp_ipl_info sclp_ipl_info;
+static unsigned char sclp_siif;
+static u32 sclp_ibc;
 
 u64 sclp_facilities;
 u8 sclp_fac84;
···
 
 static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 {
+	struct sclp_cpu_entry *cpue;
+	u16 boot_cpu_address, cpu;
+
 	if (sclp_read_info_early(sccb))
 		return;
 
···
 	sclp_rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
 	sclp_rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2;
 	sclp_rzm <<= 20;
+	sclp_ibc = sccb->ibc;
 
 	if (!sccb->hcpua) {
 		if (MACHINE_IS_VM)
···
 			sclp_max_cpu = sccb->ncpurl;
 	} else {
 		sclp_max_cpu = sccb->hcpua + 1;
+	}
+
+	boot_cpu_address = stap();
+	cpue = (void *)sccb + sccb->cpuoff;
+	for (cpu = 0; cpu < sccb->ncpurl; cpue++, cpu++) {
+		if (boot_cpu_address != cpue->address)
+			continue;
+		sclp_siif = cpue->siif;
+		break;
 	}
 
 	/* Save IPL information */
···
 {
 	return sclp_max_cpu;
 }
+
+int sclp_has_siif(void)
+{
+	return sclp_siif;
+}
+EXPORT_SYMBOL(sclp_has_siif);
+
+unsigned int sclp_get_ibc(void)
+{
+	return sclp_ibc;
+}
+EXPORT_SYMBOL(sclp_get_ibc);
 
 /*
  * This function will be called after sclp_facilities_detect(), which gets

include/linux/kvm_host.h

···
 #define KVM_REQ_EPR_EXIT          20
 #define KVM_REQ_SCAN_IOAPIC       21
 #define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
+#define KVM_REQ_ENABLE_IBS        23
+#define KVM_REQ_DISABLE_IBS       24
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
···
 	KVM_MMIO_BUS,
 	KVM_PIO_BUS,
 	KVM_VIRTIO_CCW_NOTIFY_BUS,
+	KVM_FAST_MMIO_BUS,
 	KVM_NR_BUSES
 };
 
···
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots;
 	struct srcu_struct srcu;
+	struct srcu_struct irq_srcu;
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	u32 bsp_vcpu_id;
 #endif
···
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
 #endif
-	/* Protected by mmu_lock */
-	bool tlbs_dirty;
-
+	long tlbs_dirty;
 	struct list_head devices;
 };
 
···
 static inline hpa_t pfn_to_hpa(pfn_t pfn)
 {
 	return (hpa_t)pfn << PAGE_SHIFT;
+}
+
+static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+{
+	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	return kvm_is_error_hva(hva);
 }
 
 static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)

include/uapi/linux/Kbuild

···
 header-y += ppp_defs.h
 header-y += pps.h
 header-y += prctl.h
+header-y += psci.h
 header-y += ptp_clock.h
 header-y += ptrace.h
 header-y += qnx4_fs.h

include/uapi/linux/kvm.h

···
 #define KVM_EXIT_WATCHDOG         21
 #define KVM_EXIT_S390_TSCH        22
 #define KVM_EXIT_EPR              23
+#define KVM_EXIT_SYSTEM_EVENT     24
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
···
 		struct {
 			__u32 epr;
 		} epr;
+		/* KVM_EXIT_SYSTEM_EVENT */
+		struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+			__u32 type;
+			__u64 flags;
+		} system_event;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
···
 #define KVM_S390_INT_PFAULT_INIT	0xfffe0004u
 #define KVM_S390_INT_PFAULT_DONE	0xfffe0005u
 #define KVM_S390_MCHK			0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP		0xffff1004u
+#define KVM_S390_INT_CPU_TIMER		0xffff1005u
 #define KVM_S390_INT_VIRTIO		0xffff2603u
 #define KVM_S390_INT_SERVICE		0xffff2401u
 #define KVM_S390_INT_EMERGENCY		0xffff1201u
···
 	kvm_ioeventfd_flag_nr_pio,
 	kvm_ioeventfd_flag_nr_deassign,
 	kvm_ioeventfd_flag_nr_virtio_ccw_notify,
+	kvm_ioeventfd_flag_nr_fast_mmio,
 	kvm_ioeventfd_flag_nr_max,
 };
 
···
 struct kvm_ioeventfd {
 	__u64 datamatch;
 	__u64 addr;        /* legal pio/mmio address */
-	__u32 len;         /* 1, 2, 4, or 8 bytes    */
+	__u32 len;         /* 1, 2, 4, or 8 bytes; or 0 to ignore length */
 	__s32 fd;
 	__u32 flags;
 	__u8  pad[36];
···
 #define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
 #define KVM_CAP_ENABLE_CAP_VM 98
 #define KVM_CAP_S390_IRQCHIP 99
+#define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_PPC_FIXUP_HCALL 103
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

include/uapi/linux/psci.h

···
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <[e-mail]>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE			0x84000000
+#define PSCI_0_2_FN(n)				(PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT				0x40000000
+#define PSCI_0_2_FN64_BASE			\
+					(PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n)			(PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION		PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND			PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF			PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON			PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO		PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE			PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE		PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU		PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF			PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET		PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND		PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON			PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO		PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE			PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT		0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT		16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK		\
+				(0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT		24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK		\
+				(0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON		0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF		1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING	2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE			0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE		1
+#define PSCI_0_2_TOS_MP				2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT		16
+#define PSCI_VERSION_MINOR_MASK			\
+		((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK			~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver)			\
+		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver)			\
+		((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS			0
+#define PSCI_RET_NOT_SUPPORTED			-1
+#define PSCI_RET_INVALID_PARAMS			-2
+#define PSCI_RET_DENIED				-3
+#define PSCI_RET_ALREADY_ON			-4
+#define PSCI_RET_ON_PENDING			-5
+#define PSCI_RET_INTERNAL_FAILURE		-6
+#define PSCI_RET_NOT_PRESENT			-7
+#define PSCI_RET_DISABLED			-8
+
+#endif /* _UAPI_LINUX_PSCI_H */

virt/kvm/async_pf.c

···
 
 	might_sleep();
 
-	use_mm(mm);
 	down_read(&mm->mmap_sem);
-	get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
+	get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
 	kvm_async_page_present_sync(vcpu, apf);
-	unuse_mm(mm);
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);

virt/kvm/eventfd.c

···
 #include <linux/list.h>
 #include <linux/eventfd.h>
 #include <linux/kernel.h>
+#include <linux/srcu.h>
 #include <linux/slab.h>
 
 #include "iodev.h"
···
 irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
 {
 	struct _irqfd_resampler *resampler;
+	struct kvm *kvm;
 	struct _irqfd *irqfd;
+	int idx;
 
 	resampler = container_of(kian, struct _irqfd_resampler, notifier);
+	kvm = resampler->kvm;
 
-	kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
 		    resampler->notifier.gsi, 0, false);
 
-	rcu_read_lock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
 
 	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
 		eventfd_signal(irqfd->resamplefd, 1);
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 static void
···
 	mutex_lock(&kvm->irqfds.resampler_lock);
 
 	list_del_rcu(&irqfd->resampler_link);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 
 	if (list_empty(&resampler->list)) {
 		list_del(&resampler->link);
···
 	unsigned long flags = (unsigned long)key;
 	struct kvm_kernel_irq_routing_entry *irq;
 	struct kvm *kvm = irqfd->kvm;
+	int idx;
 
 	if (flags & POLLIN) {
-		rcu_read_lock();
-		irq = rcu_dereference(irqfd->irq_entry);
+		idx = srcu_read_lock(&kvm->irq_srcu);
+		irq = srcu_dereference(irqfd->irq_entry, &kvm->irq_srcu);
 		/* An event has been signaled, inject an interrupt */
 		if (irq)
 			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
 					false);
 		else
 			schedule_work(&irqfd->inject);
-		rcu_read_unlock();
+		srcu_read_unlock(&kvm->irq_srcu, idx);
 	}
 
 	if (flags & POLLHUP) {
···
 		}
 
 		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
-		synchronize_rcu();
+		synchronize_srcu(&kvm->irq_srcu);
 
 		mutex_unlock(&kvm->irqfds.resampler_lock);
 	}
···
 			 * another thread calls kvm_irq_routing_update before
 			 * we flush workqueue below (we synchronize with
 			 * kvm_irq_routing_update using irqfds.lock).
-			 * It is paired with synchronize_rcu done by caller
+			 * It is paired with synchronize_srcu done by caller
 			 * of that function.
 			 */
 			rcu_assign_pointer(irqfd->irq_entry, NULL);
···
 
 /*
  * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
  */
 void kvm_irq_routing_update(struct kvm *kvm,
 			    struct kvm_irq_routing_table *irq_rt)
···
 {
 	u64 _val;
 
-	if (!(addr == p->addr && len == p->length))
+	if (addr != p->addr)
+		/* address must be precise for a hit */
+		return false;
+
+	if (!p->length)
+		/* length = 0 means only look at the address, so always a hit */
+		return true;
+
+	if (len != p->length)
 		/* address-range must be precise for a hit */
 		return false;
 
···
 
 	list_for_each_entry(_p, &kvm->ioeventfds, list)
 		if (_p->bus_idx == p->bus_idx &&
-		    _p->addr == p->addr && _p->length == p->length &&
-		    (_p->wildcard || p->wildcard ||
-		     _p->datamatch == p->datamatch))
+		    _p->addr == p->addr &&
+		    (!_p->length || !p->length ||
+		     (_p->length == p->length &&
+		      (_p->wildcard || p->wildcard ||
+		       _p->datamatch == p->datamatch))))
 			return true;
 
 	return false;
···
 	int                       ret;
 
 	bus_idx = ioeventfd_bus_from_flags(args->flags);
-	/* must be natural-word sized */
+	/* must be natural-word sized, or 0 to ignore length */
 	switch (args->len) {
+	case 0:
 	case 1:
 	case 2:
 	case 4:
···
 
 	/* check for extra flags that we don't understand */
 	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
+		return -EINVAL;
+
+	/* ioeventfd with no length can't be combined with DATAMATCH */
+	if (!args->len &&
+	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+			   KVM_IOEVENTFD_FLAG_DATAMATCH))
 		return -EINVAL;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
···
 	if (ret < 0)
 		goto unlock_fail;
 
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
+		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
+					      p->addr, 0, &p->dev);
+		if (ret < 0)
+			goto register_fail;
+	}
+
 	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
···
 
 	return 0;
 
+register_fail:
+	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
···
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+		if (!p->length) {
+			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
+						  &p->dev);
+		}
 		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;

virt/kvm/irq_comm.c

···
 	struct kvm_kernel_irq_routing_entry *e;
 	int ret = -EINVAL;
 	struct kvm_irq_routing_table *irq_rt;
+	int idx;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
···
 	 * Since there's no easy way to do this, we only support injecting MSI
 	 * which is limited to 1:1 GSI mapping.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	if (irq < irq_rt->nr_rt_entries)
 		hlist_for_each_entry(e, &irq_rt->map[irq], link) {
 			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
···
 				ret = -EWOULDBLOCK;
 			break;
 		}
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
 }
 
···
 	mutex_lock(&kvm->irq_lock);
 	hlist_del_rcu(&kimn->link);
 	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask)
 {
 	struct kvm_irq_mask_notifier *kimn;
-	int gsi;
+	int idx, gsi;
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
 			if (kimn->irq == gsi)
 				kimn->func(kimn, mask);
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,

virt/kvm/irqchip.c

···
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/export.h>
 #include <trace/events/kvm.h>
 #include "irq.h"
···
 bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-	int gsi;
+	int gsi, idx;
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
 			if (kian->gsi == gsi) {
-				rcu_read_unlock();
+				srcu_read_unlock(&kvm->irq_srcu, idx);
 				return true;
 			}
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	return false;
 }
···
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-	int gsi;
+	int gsi, idx;
 
 	trace_kvm_ack_irq(irqchip, pin);
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu)->chip[irqchip][pin];
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
 					 link)
 			if (kian->gsi == gsi)
 				kian->irq_acked(kian);
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
···
 	mutex_lock(&kvm->irq_lock);
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 #ifdef __KVM_HAVE_IOAPIC
 	kvm_vcpu_request_scan_ioapic(kvm);
 #endif
···
 		bool line_status)
 {
 	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
-	int ret = -1, i = 0;
+	int ret = -1, i = 0, idx;
 	struct kvm_irq_routing_table *irq_rt;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
···
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
 	if (irq < irq_rt->nr_rt_entries)
 		hlist_for_each_entry(e, &irq_rt->map[irq], link)
 			irq_set[i++] = *e;
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	while(i--) {
 		int r;
···
 	kvm_irq_routing_update(kvm, new);
 	mutex_unlock(&kvm->irq_lock);
 
-	synchronize_rcu();
+	synchronize_srcu_expedited(&kvm->irq_srcu);
 
 	new = old;
 	r = 0;

virt/kvm/kvm_main.c

···
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
+	long dirty_count = kvm->tlbs_dirty;
+
+	smp_mb();
 	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
-	kvm->tlbs_dirty = false;
+	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
···
 
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 	r = hardware_enable_all();
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
···
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
 	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
 					GFP_KERNEL);
···
 	return kvm;
 
 out_err:
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
 	hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
 	kfree(kvm->memslots);
···
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
 	hardware_disable_all();
···
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
-#ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
 	memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-#endif /* !CONFIG_S390 */
 	return 0;
 }
 
···
 
 	return -EOPNOTSUPP;
 }
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
 
 /* kvm_io_bus_read - called under kvm->slots_lock */
 int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,