Merge tag 'v3.13' into for-3.15

Linux 3.13 Conflicts: include/net/xfrm.h Simple merge where v3.13 removed 'extern' from definitions and the audit tree did s/u32/unsigned int/ to the same definitions.
author: Eric Paris <eparis@redhat.com> 2014-03-07 17:41:32 +0100
committer: Eric Paris <eparis@redhat.com> 2014-03-07 17:41:32 +0100
commit: b7d3622a39fde7658170b7f3cf6c6889bb8db30d (patch)
tree: 64f4e781ecb2a85d675e234072b988560bcd25f1 /arch/powerpc/kvm
parent: audit: whitespace fix in kernel-parameters.txt (diff)
parent: Linux 3.13 (diff)
download: linux-b7d3622a39fde7658170b7f3cf6c6889bb8db30d.tar.xz
linux-b7d3622a39fde7658170b7f3cf6c6889bb8db30d.zip
40 files changed, 2956 insertions, 1348 deletions
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 2f5c6b6d6877..93221e87b911 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -31,13 +31,13 @@
 #include "44x_tlb.h"
 #include "booke.h"
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_44x(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_booke_vcpu_load(vcpu, cpu);
 	kvmppc_44x_tlb_load(vcpu);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_44x(struct kvm_vcpu *vcpu)
 {
 	kvmppc_44x_tlb_put(vcpu);
 	kvmppc_booke_vcpu_put(vcpu);
@@ -114,29 +114,32 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_44x(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
-	kvmppc_get_sregs_ivor(vcpu, sregs);
+	return kvmppc_get_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_44x(struct kvm_vcpu *vcpu,
+				     struct kvm_sregs *sregs)
 {
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_44x(struct kvm_vcpu *vcpu, u64 id,
+				  union kvmppc_one_reg *val)
 {
 	return -EINVAL;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_44x(struct kvm_vcpu *vcpu, u64 id,
+				  union kvmppc_one_reg *val)
 {
 	return -EINVAL;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_44x(struct kvm *kvm,
+						    unsigned int id)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x;
 	struct kvm_vcpu *vcpu;
@@ -167,7 +170,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_44x(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 
@@ -176,28 +179,53 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_44x(struct kvm *kvm)
 {
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_44x(struct kvm *kvm)
 {
 }
 
+static struct kvmppc_ops kvm_ops_44x = {
+	.get_sregs = kvmppc_core_get_sregs_44x,
+	.set_sregs = kvmppc_core_set_sregs_44x,
+	.get_one_reg = kvmppc_get_one_reg_44x,
+	.set_one_reg = kvmppc_set_one_reg_44x,
+	.vcpu_load   = kvmppc_core_vcpu_load_44x,
+	.vcpu_put    = kvmppc_core_vcpu_put_44x,
+	.vcpu_create = kvmppc_core_vcpu_create_44x,
+	.vcpu_free   = kvmppc_core_vcpu_free_44x,
+	.mmu_destroy  = kvmppc_mmu_destroy_44x,
+	.init_vm = kvmppc_core_init_vm_44x,
+	.destroy_vm = kvmppc_core_destroy_vm_44x,
+	.emulate_op = kvmppc_core_emulate_op_44x,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_44x,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_44x,
+};
+
 static int __init kvmppc_44x_init(void)
 {
 	int r;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
+
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_44x.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_44x;
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_44x_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 35ec0a8547da..92c9ab4bcfec 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -91,8 +91,8 @@ static int emulate_mfdcr(struct kvm_vcpu *vcpu, int rt, int dcrn)
 	return EMULATE_DONE;
 }
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			       unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int dcrn = get_dcrn(inst);
@@ -152,7 +152,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
+int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -172,7 +172,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index ed0385448148..0deef1082e02 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -268,7 +268,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 	trace_kvm_stlb_inval(stlb_index);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	int i;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index ffaef2cb101a..141b2027189a 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -6,6 +6,7 @@ source "virt/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).
@@ -34,17 +35,20 @@ config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
 
-config KVM_BOOK3S_PR
+config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
 	select MMU_NOTIFIER
 
+config KVM_BOOK3S_HV_POSSIBLE
+	bool
+
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
-	select KVM_BOOK3S_PR
+	select KVM_BOOK3S_PR_POSSIBLE
 	---help---
 	  Support running unmodified book3s_32 guest kernels
 	  in virtual machines on book3s_32 host processors.
@@ -59,6 +63,7 @@ config KVM_BOOK3S_64
 	depends on PPC_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
+	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
@@ -69,8 +74,9 @@ config KVM_BOOK3S_64
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_HV
-	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
+	tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
 	select CMA
 	---help---
@@ -89,9 +95,20 @@ config KVM_BOOK3S_64_HV
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_PR
-	def_bool y
-	depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
-	select KVM_BOOK3S_PR
+	tristate "KVM support without using hypervisor mode in host"
+	depends on KVM_BOOK3S_64
+	select KVM_BOOK3S_PR_POSSIBLE
+	---help---
+	  Support running guest kernels in virtual machines on processors
+	  without using hypervisor mode in the host, by running the
+	  guest in user mode (problem state) and emulating all
+	  privileged instructions and registers.
+
+	  This is not as fast as using hypervisor mode, but works on
+	  machines where hypervisor mode is not available or not usable,
+	  and can emulate processors that are different from the host
+	  processor, including emulating 32-bit processors on a 64-bit
+	  host.
 
 config KVM_BOOKE_HV
 	bool
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 6646c952c5e3..ce569b6bf4d8 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -53,41 +53,51 @@ kvm-e500mc-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
-kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
-	$(KVM)/coalesced_mmio.o \
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+	book3s_64_vio_hv.o
+
+kvm-pr-y := \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s_pr.o \
 	book3s_pr_papr.o \
-	book3s_64_vio_hv.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
 	book3s_64_mmu_host.o \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
+
+ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+kvm-book3s_64-module-objs := \
+	$(KVM)/coalesced_mmio.o
+
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o
+endif
 
-kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+kvm-hv-y += \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o
+
 kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 	book3s_hv_rm_xics.o
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+
+ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
-	book3s_64_vio_hv.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
 	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
+endif
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-module-objs := \
+kvm-book3s_64-module-objs += \
 	$(KVM)/kvm_main.o \
 	$(KVM)/eventfd.o \
 	powerpc.o \
@@ -123,4 +133,7 @@ obj-$(CONFIG_KVM_E500MC) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 
+obj-$(CONFIG_KVM_BOOK3S_64_PR) += kvm-pr.o
+obj-$(CONFIG_KVM_BOOK3S_64_HV) += kvm-hv.o
+
 obj-y += $(kvm-book3s_64-builtin-objs-y)
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 700df6f1d32c..8912608b7e1b 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 
+#include "book3s.h"
 #include "trace.h"
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@@ -69,6 +70,50 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 {
 }
 
+static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
+{
+	if (!is_kvmppc_hv_enabled(vcpu->kvm))
+		return to_book3s(vcpu)->hior;
+	return 0;
+}
+
+static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
+			unsigned long pending_now, unsigned long old_pending)
+{
+	if (is_kvmppc_hv_enabled(vcpu->kvm))
+		return;
+	if (pending_now)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
+}
+
+static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
+{
+	ulong crit_raw;
+	ulong crit_r1;
+	bool crit;
+
+	if (is_kvmppc_hv_enabled(vcpu->kvm))
+		return false;
+
+	crit_raw = vcpu->arch.shared->critical;
+	crit_r1 = kvmppc_get_gpr(vcpu, 1);
+
+	/* Truncate crit indicators in 32 bit mode */
+	if (!(vcpu->arch.shared->msr & 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);
+
+	return crit;
+}
+
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
 	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
@@ -126,28 +171,32 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 	printk(KERN_INFO "Queueing interrupt %x\n", vec);
 #endif
 }
-
+EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);
 
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
 	/* might as well deliver this straight away */
 	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_program);
 
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_dec);
 
 int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
 {
 	return test_bit(BOOK3S_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_pending_dec);
 
 void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_dequeue_dec);
 
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
@@ -285,8 +334,10 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter);
 
-pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing,
+			bool *writable)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
@@ -302,20 +353,23 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 
 		pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
 		get_page(pfn_to_page(pfn));
+		if (writable)
+			*writable = true;
 		return pfn;
 	}
 
-	return gfn_to_pfn(vcpu->kvm, gfn);
+	return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
 }
+EXPORT_SYMBOL_GPL(kvmppc_gfn_to_pfn);
 
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
-			 struct kvmppc_pte *pte)
+			bool iswrite, struct kvmppc_pte *pte)
 {
 	int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
 	int r;
 
 	if (relocated) {
-		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
+		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data, iswrite);
 	} else {
 		pte->eaddr = eaddr;
 		pte->raddr = eaddr & KVM_PAM;
@@ -361,7 +415,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	vcpu->stat.st++;
 
-	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+	if (kvmppc_xlate(vcpu, *eaddr, data, true, &pte))
 		return -ENOENT;
 
 	*eaddr = pte.raddr;
@@ -374,6 +428,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	return EMULATE_DONE;
 }
+EXPORT_SYMBOL_GPL(kvmppc_st);
 
 int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		      bool data)
@@ -383,7 +438,7 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 
 	vcpu->stat.ld++;
 
-	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+	if (kvmppc_xlate(vcpu, *eaddr, data, false, &pte))
 		goto nopte;
 
 	*eaddr = pte.raddr;
@@ -404,6 +459,7 @@ nopte:
 mmio:
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_ld);
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
@@ -419,6 +475,18 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 }
 
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
+}
+
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
@@ -495,8 +563,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (size > sizeof(val))
 		return -EINVAL;
 
-	r = kvmppc_get_one_reg(vcpu, reg->id, &val);
-
+	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -528,6 +595,9 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			break;
 #endif /* CONFIG_ALTIVEC */
 		case KVM_REG_PPC_DEBUG_INST: {
 			u32 opcode = INS_TW;
@@ -572,8 +642,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
 		return -EFAULT;
 
-	r = kvmppc_set_one_reg(vcpu, reg->id, &val);
-
+	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -605,6 +674,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			break;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_KVM_XICS
 		case KVM_REG_PPC_ICP_STATE:
@@ -625,6 +701,27 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	return r;
 }
 
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
+}
+
+void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+{
+	vcpu->kvm->arch.kvm_ops->set_msr(vcpu, msr);
+}
+EXPORT_SYMBOL_GPL(kvmppc_set_msr);
+
+int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.kvm_ops->vcpu_run(kvm_run, vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                   struct kvm_translation *tr)
 {
@@ -644,3 +741,141 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_core_queue_dec(vcpu);
 	kvm_vcpu_kick(vcpu);
 }
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
+}
+
+int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
+{
+	return vcpu->kvm->arch.kvm_ops->check_requests(vcpu);
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	return kvm->arch.kvm_ops->get_dirty_log(kvm, log);
+}
+
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+			      struct kvm_memory_slot *dont)
+{
+	kvm->arch.kvm_ops->free_memslot(free, dont);
+}
+
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       unsigned long npages)
+{
+	return kvm->arch.kvm_ops->create_memslot(slot, npages);
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	kvm->arch.kvm_ops->flush_memslot(kvm, memslot);
+}
+
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
+				struct kvm_userspace_memory_region *mem)
+{
+	return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
+}
+
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
+{
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvm->arch.kvm_ops->unmap_hva(kvm, hva);
+}
+EXPORT_SYMBOL_GPL(kvm_unmap_hva);
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvm->arch.kvm_ops->age_hva(kvm, hva);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvm->arch.kvm_ops->test_age_hva(kvm, hva);
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte);
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+
+#ifdef CONFIG_PPC64
+	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
+#endif
+
+	return kvm->arch.kvm_ops->init_vm(kvm);
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvm->arch.kvm_ops->destroy_vm(kvm);
+
+#ifdef CONFIG_PPC64
+	kvmppc_rtas_tokens_free(kvm);
+	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
+#endif
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	/*
+	 * We always return 0 for book3s. We check
+	 * for compatability while loading the HV
+	 * or PR module
+	 */
+	return 0;
+}
+
+static int kvmppc_book3s_init(void)
+{
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (r)
+		return r;
+#ifdef CONFIG_KVM_BOOK3S_32
+	r = kvmppc_book3s_init_pr();
+#endif
+	return r;
+
+}
+
+static void kvmppc_book3s_exit(void)
+{
+#ifdef CONFIG_KVM_BOOK3S_32
+	kvmppc_book3s_exit_pr();
+#endif
+	kvm_exit();
+}
+
+module_init(kvmppc_book3s_init);
+module_exit(kvmppc_book3s_exit);
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
new file mode 100644
index 000000000000..4bf956cf94d6
--- /dev/null
+++ b/arch/powerpc/kvm/book3s.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+
+#ifndef __POWERPC_KVM_BOOK3S_H__
+#define __POWERPC_KVM_BOOK3S_H__
+
+extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
+					 struct kvm_memory_slot *memslot);
+extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
+				  unsigned long end);
+extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte);
+
+extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				     unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu,
+					int sprn, ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
+					int sprn, ulong *spr_val);
+extern int kvmppc_book3s_init_pr(void);
+extern void kvmppc_book3s_exit_pr(void);
+
+#endif
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index c8cefdd15fd8..76a64ce6a5b6 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -84,7 +84,8 @@ static inline bool sr_nx(u32 sr_raw)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data);
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite);
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid);
 
@@ -99,7 +100,7 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u64 vsid;
 	struct kvmppc_pte pte;
 
-	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data))
+	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data, false))
 		return pte.vpage;
 
 	kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
@@ -111,10 +112,11 @@ static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, 0);
 }
 
-static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s,
+static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu,
 				      u32 sre, gva_t eaddr,
 				      bool primary)
 {
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u32 page, hash, pteg, htabmask;
 	hva_t r;
 
@@ -132,7 +134,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 		kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
 		sr_vsid(sre));
 
-	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+	r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT);
 	if (kvm_is_error_hva(r))
 		return r;
 	return r | (pteg & ~PAGE_MASK);
@@ -145,7 +147,8 @@ static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data)
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_bat *bat;
@@ -186,8 +189,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 				printk(KERN_INFO "BAT is not readable!\n");
 				continue;
 			}
-			if (!pte->may_write) {
-				/* let's treat r/o BATs as not-readable for now */
+			if (iswrite && !pte->may_write) {
 				dprintk_pte("BAT is read-only!\n");
 				continue;
 			}
@@ -201,9 +203,8 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				     struct kvmppc_pte *pte, bool data,
-				     bool primary)
+				     bool iswrite, bool primary)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u32 sre;
 	hva_t ptegp;
 	u32 pteg[16];
@@ -218,7 +219,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
 
-	ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu_book3s, sre, eaddr, primary);
+	ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu, sre, eaddr, primary);
 	if (kvm_is_error_hva(ptegp)) {
 		printk(KERN_INFO "KVM: Invalid PTEG!\n");
 		goto no_page_found;
@@ -258,9 +259,6 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 					break;
 			}
 
-			if ( !pte->may_read )
-				continue;
-
 			dprintk_pte("MMU: Found PTE -> %x %x - %x\n",
 				    pteg[i], pteg[i+1], pp);
 			found = 1;
@@ -271,19 +269,23 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Update PTE C and A bits, so the guest's swapper knows we used the
 	   page */
 	if (found) {
-		u32 oldpte = pteg[i+1];
-
-		if (pte->may_read)
-			pteg[i+1] |= PTEG_FLAG_ACCESSED;
-		if (pte->may_write)
-			pteg[i+1] |= PTEG_FLAG_DIRTY;
-		else
-			dprintk_pte("KVM: Mapping read-only page!\n");
-
-		/* Write back into the PTEG */
-		if (pteg[i+1] != oldpte)
-			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
-
+		u32 pte_r = pteg[i+1];
+		char __user *addr = (char __user *) &pteg[i+1];
+
+		/*
+		 * Use single-byte writes to update the HPTE, to
+		 * conform to what real hardware does.
+		 */
+		if (pte->may_read && !(pte_r & PTEG_FLAG_ACCESSED)) {
+			pte_r |= PTEG_FLAG_ACCESSED;
+			put_user(pte_r >> 8, addr + 2);
+		}
+		if (iswrite && pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
+			pte_r |= PTEG_FLAG_DIRTY;
+			put_user(pte_r, addr + 3);
+		}
+		if (!pte->may_read || (iswrite && !pte->may_write))
+			return -EPERM;
 		return 0;
 	}
 
@@ -302,12 +304,14 @@ no_page_found:
 }
 
 static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				      struct kvmppc_pte *pte, bool data)
+				      struct kvmppc_pte *pte, bool data,
+				      bool iswrite)
 {
 	int r;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	pte->eaddr = eaddr;
+	pte->page_size = MMU_PAGE_4K;
 
 	/* Magic page override */
 	if (unlikely(mp_ea) &&
@@ -323,11 +327,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return 0;
 	}
 
-	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
+	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data, iswrite);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, true);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, false);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, false);
 
 	return r;
 }
@@ -347,7 +353,12 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 
 static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large)
 {
-	kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000);
+	int i;
+	struct kvm_vcpu *v;
+
+	/* flush this VA on all cpus */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvmppc_mmu_pte_flush(v, ea, 0x0FFFF000);
 }
 
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 00e619bf608e..3a0abd2e5a15 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -138,7 +138,8 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr,
 
 extern char etext[];
 
-int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
+			bool iswrite)
 {
 	pfn_t hpaddr;
 	u64 vpn;
@@ -152,9 +153,11 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	bool evict = false;
 	struct hpte_cache *pte;
 	int r = 0;
+	bool writable;
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
+	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT,
+				   iswrite, &writable);
 	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
@@ -204,7 +207,7 @@ next_pteg:
 		(primary ? 0 : PTE_SEC);
 	pteg1 = hpaddr | PTE_M | PTE_R | PTE_C;
 
-	if (orig_pte->may_write) {
+	if (orig_pte->may_write && writable) {
 		pteg1 |= PP_RWRW;
 		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
 	} else {
@@ -259,6 +262,11 @@ out:
 	return r;
 }
 
+void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	kvmppc_mmu_pte_vflush(vcpu, pte->vpage, 0xfffffffffULL);
+}
+
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
@@ -341,7 +349,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 {
 	int i;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 7e345e00661a..83da1f868fd5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -107,9 +107,20 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return kvmppc_slb_calc_vpn(slb, eaddr);
 }
 
+static int mmu_pagesize(int mmu_pg)
+{
+	switch (mmu_pg) {
+	case MMU_PAGE_64K:
+		return 16;
+	case MMU_PAGE_16M:
+		return 24;
+	}
+	return 12;
+}
+
 static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
 {
-	return slbe->large ? 24 : 12;
+	return mmu_pagesize(slbe->base_page_size);
 }
 
 static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
@@ -119,11 +130,11 @@ static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
 	return ((eaddr & kvmppc_slb_offset_mask(slbe)) >> p);
 }
 
-static hva_t kvmppc_mmu_book3s_64_get_pteg(
-				struct kvmppc_vcpu_book3s *vcpu_book3s,
+static hva_t kvmppc_mmu_book3s_64_get_pteg(struct kvm_vcpu *vcpu,
 				struct kvmppc_slb *slbe, gva_t eaddr,
 				bool second)
 {
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	u64 hash, pteg, htabsize;
 	u32 ssize;
 	hva_t r;
@@ -148,10 +159,10 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg(
 
 	/* When running a PAPR guest, SDR1 contains a HVA address instead
            of a GPA */
-	if (vcpu_book3s->vcpu.arch.papr_enabled)
+	if (vcpu->arch.papr_enabled)
 		r = pteg;
 	else
-		r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+		r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT);
 
 	if (kvm_is_error_hva(r))
 		return r;
@@ -166,18 +177,38 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr)
 	avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
 	avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p);
 
-	if (p < 24)
-		avpn >>= ((80 - p) - 56) - 8;
+	if (p < 16)
+		avpn >>= ((80 - p) - 56) - 8;	/* 16 - p */
 	else
-		avpn <<= 8;
+		avpn <<= p - 16;
 
 	return avpn;
 }
 
+/*
+ * Return page size encoded in the second word of a HPTE, or
+ * -1 for an invalid encoding for the base page size indicated by
+ * the SLB entry.  This doesn't handle mixed pagesize segments yet.
+ */
+static int decode_pagesize(struct kvmppc_slb *slbe, u64 r)
+{
+	switch (slbe->base_page_size) {
+	case MMU_PAGE_64K:
+		if ((r & 0xf000) == 0x1000)
+			return MMU_PAGE_64K;
+		break;
+	case MMU_PAGE_16M:
+		if ((r & 0xff000) == 0)
+			return MMU_PAGE_16M;
+		break;
+	}
+	return -1;
+}
+
 static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				struct kvmppc_pte *gpte, bool data)
+				      struct kvmppc_pte *gpte, bool data,
+				      bool iswrite)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_slb *slbe;
 	hva_t ptegp;
 	u64 pteg[16];
@@ -189,6 +220,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u8 pp, key = 0;
 	bool found = false;
 	bool second = false;
+	int pgsize;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -202,6 +234,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		gpte->may_execute = true;
 		gpte->may_read = true;
 		gpte->may_write = true;
+		gpte->page_size = MMU_PAGE_4K;
 
 		return 0;
 	}
@@ -222,8 +255,12 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
 		HPTE_V_SECONDARY;
 
+	pgsize = slbe->large ? MMU_PAGE_16M : MMU_PAGE_4K;
+
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
+
 do_second:
-	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
+	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu, slbe, eaddr, second);
 	if (kvm_is_error_hva(ptegp))
 		goto no_page_found;
 
@@ -240,6 +277,13 @@ do_second:
 	for (i=0; i<16; i+=2) {
 		/* Check all relevant fields of 1st dword */
 		if ((pteg[i] & 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]);
+				if (pgsize < 0)
+					continue;
+			}
 			found = true;
 			break;
 		}
@@ -256,13 +300,15 @@ do_second:
 	v = pteg[i];
 	r = pteg[i+1];
 	pp = (r & HPTE_R_PP) | key;
-	eaddr_mask = 0xFFF;
+	if (r & HPTE_R_PP0)
+		pp |= 8;
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
-	if (slbe->large)
-		eaddr_mask = 0xFFFFFF;
+
+	eaddr_mask = (1ull << mmu_pagesize(pgsize)) - 1;
 	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->page_size = pgsize;
 	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
 	gpte->may_read = false;
 	gpte->may_write = false;
@@ -277,6 +323,7 @@ do_second:
 	case 3:
 	case 5:
 	case 7:
+	case 10:
 		gpte->may_read = true;
 		break;
 	}
@@ -287,30 +334,37 @@ do_second:
 
 	/* Update PTE R and C bits, so the guest's swapper knows we used the
 	 * page */
-	if (gpte->may_read) {
-		/* Set the accessed flag */
+	if (gpte->may_read && !(r & HPTE_R_R)) {
+		/*
+		 * Set the accessed flag.
+		 * We have to write this back with a single byte write
+		 * because another vcpu may be accessing this on
+		 * non-PAPR platforms such as mac99, and this is
+		 * what real hardware does.
+		 */
+		char __user *addr = (char __user *) &pteg[i+1];
 		r |= HPTE_R_R;
+		put_user(r >> 8, addr + 6);
 	}
-	if (data && gpte->may_write) {
-		/* Set the dirty flag -- XXX even if not writing */
+	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];
 		r |= HPTE_R_C;
+		put_user(r, addr + 7);
 	}
 
-	/* Write back into the PTEG */
-	if (pteg[i+1] != r) {
-		pteg[i+1] = r;
-		copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
-	}
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 
-	if (!gpte->may_read)
+	if (!gpte->may_read || (iswrite && !gpte->may_write))
 		return -EPERM;
 	return 0;
 
 no_page_found:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 	return -ENOENT;
 
 no_seg_found:
-
 	dprintk("KVM MMU: Trigger segment fault\n");
 	return -EINVAL;
 }
@@ -345,6 +399,21 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe->nx    = (rs & SLB_VSID_N) ? 1 : 0;
 	slbe->class = (rs & SLB_VSID_C) ? 1 : 0;
 
+	slbe->base_page_size = MMU_PAGE_4K;
+	if (slbe->large) {
+		if (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE) {
+			switch (rs & SLB_VSID_LP) {
+			case SLB_VSID_LP_00:
+				slbe->base_page_size = MMU_PAGE_16M;
+				break;
+			case SLB_VSID_LP_01:
+				slbe->base_page_size = MMU_PAGE_64K;
+				break;
+			}
+		} else
+			slbe->base_page_size = MMU_PAGE_16M;
+	}
+
 	slbe->orige = rb & (ESID_MASK | SLB_ESID_V);
 	slbe->origv = rs;
 
@@ -460,14 +529,45 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 				       bool large)
 {
 	u64 mask = 0xFFFFFFFFFULL;
+	long i;
+	struct kvm_vcpu *v;
 
 	dprintk("KVM MMU: tlbie(0x%lx)\n", va);
 
-	if (large)
-		mask = 0xFFFFFF000ULL;
-	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
+	/*
+	 * The tlbie instruction changed behaviour starting with
+	 * POWER6.  POWER6 and later don't have the large page flag
+	 * in the instruction but in the RB value, along with bits
+	 * indicating page and segment sizes.
+	 */
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_NEW_TLBIE) {
+		/* POWER6 or later */
+		if (va & 1) {		/* L bit */
+			if ((va & 0xf000) == 0x1000)
+				mask = 0xFFFFFFFF0ULL;	/* 64k page */
+			else
+				mask = 0xFFFFFF000ULL;	/* 16M page */
+		}
+	} else {
+		/* older processors, e.g. PPC970 */
+		if (large)
+			mask = 0xFFFFFF000ULL;
+	}
+	/* flush this VA on all vcpus */
+	kvm_for_each_vcpu(i, v, vcpu->kvm)
+		kvmppc_mmu_pte_vflush(v, va >> 12, mask);
 }
 
+#ifdef CONFIG_PPC_64K_PAGES
+static int segment_contains_magic_page(struct kvm_vcpu *vcpu, ulong esid)
+{
+	ulong mp_ea = vcpu->arch.magic_page_ea;
+
+	return mp_ea && !(vcpu->arch.shared->msr & MSR_PR) &&
+		(mp_ea >> SID_SHIFT) == esid;
+}
+#endif
+
 static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid)
 {
@@ -475,11 +575,13 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	struct kvmppc_slb *slb;
 	u64 gvsid = esid;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
+	int pagesize = MMU_PAGE_64K;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
 		if (slb) {
 			gvsid = slb->vsid;
+			pagesize = slb->base_page_size;
 			if (slb->tb) {
 				gvsid <<= SID_SHIFT_1T - SID_SHIFT;
 				gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1);
@@ -490,28 +592,41 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 
 	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 	case 0:
-		*vsid = VSID_REAL | esid;
+		gvsid = VSID_REAL | esid;
 		break;
 	case MSR_IR:
-		*vsid = VSID_REAL_IR | gvsid;
+		gvsid |= VSID_REAL_IR;
 		break;
 	case MSR_DR:
-		*vsid = VSID_REAL_DR | gvsid;
+		gvsid |= VSID_REAL_DR;
 		break;
 	case MSR_DR|MSR_IR:
 		if (!slb)
 			goto no_slb;
 
-		*vsid = gvsid;
 		break;
 	default:
 		BUG();
 		break;
 	}
 
+#ifdef CONFIG_PPC_64K_PAGES
+	/*
+	 * Mark this as a 64k segment if the host is using
+	 * 64k pages, the host MMU supports 64k pages and
+	 * the guest segment page size is >= 64k,
+	 * but not if this segment contains the magic page.
+	 */
+	if (pagesize >= MMU_PAGE_64K &&
+	    mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    !segment_contains_magic_page(vcpu, esid))
+		gvsid |= VSID_64K;
+#endif
+
 	if (vcpu->arch.shared->msr & MSR_PR)
-		*vsid |= VSID_PR;
+		gvsid |= VSID_PR;
 
+	*vsid = gvsid;
 	return 0;
 
 no_slb:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index e5240524bf6c..0d513af62bba 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -27,14 +27,14 @@
 #include <asm/machdep.h>
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
-#include "trace.h"
+#include "trace_pr.h"
 
 #define PTE_SIZE 12
 
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-			       MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M,
+			       pte->pagesize, pte->pagesize, MMU_SEGSIZE_256M,
 			       false);
 }
 
@@ -78,7 +78,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	return NULL;
 }
 
-int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
+			bool iswrite)
 {
 	unsigned long vpn;
 	pfn_t hpaddr;
@@ -90,16 +91,26 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	int attempt = 0;
 	struct kvmppc_sid_map *map;
 	int r = 0;
+	int hpsize = MMU_PAGE_4K;
+	bool writable;
+	unsigned long mmu_seq;
+	struct kvm *kvm = vcpu->kvm;
+	struct hpte_cache *cpte;
+	unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT;
+	unsigned long pfn;
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (is_error_noslot_pfn(hpaddr)) {
-		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
+	pfn = kvmppc_gfn_to_pfn(vcpu, gfn, iswrite, &writable);
+	if (is_error_noslot_pfn(pfn)) {
+		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", gfn);
 		r = -EINVAL;
 		goto out;
 	}
-	hpaddr <<= PAGE_SHIFT;
-	hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
+	hpaddr = pfn << PAGE_SHIFT;
 
 	/* and write the mapping ea -> hpa into the pt */
 	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
@@ -117,20 +128,39 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 		goto out;
 	}
 
-	vsid = map->host_vsid;
-	vpn = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+	vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
-	if (!orig_pte->may_write)
-		rflags |= HPTE_R_PP;
-	else
-		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	kvm_set_pfn_accessed(pfn);
+	if (!orig_pte->may_write || !writable)
+		rflags |= PP_RXRX;
+	else {
+		mark_page_dirty(vcpu->kvm, gfn);
+		kvm_set_pfn_dirty(pfn);
+	}
 
 	if (!orig_pte->may_execute)
 		rflags |= HPTE_R_N;
 	else
-		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
+		kvmppc_mmu_flush_icache(pfn);
+
+	/*
+	 * Use 64K pages if possible; otherwise, on 64K page kernels,
+	 * we need to transfer 4 more bits from guest real to host real addr.
+	 */
+	if (vsid & VSID_64K)
+		hpsize = MMU_PAGE_64K;
+	else
+		hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
+
+	hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M);
 
-	hash = hpt_hash(vpn, PTE_SIZE, MMU_SEGSIZE_256M);
+	cpte = kvmppc_mmu_hpte_cache_next(vcpu);
+
+	spin_lock(&kvm->mmu_lock);
+	if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+		r = -EAGAIN;
+		goto out_unlock;
+	}
 
 map_again:
 	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
@@ -139,11 +169,11 @@ map_again:
 	if (attempt > 1)
 		if (ppc_md.hpte_remove(hpteg) < 0) {
 			r = -1;
-			goto out;
+			goto out_unlock;
 		}
 
 	ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
-				 MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M);
+				 hpsize, hpsize, MMU_SEGSIZE_256M);
 
 	if (ret < 0) {
 		/* If we couldn't map a primary PTE, try a secondary */
@@ -152,8 +182,6 @@ map_again:
 		attempt++;
 		goto map_again;
 	} else {
-		struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
-
 		trace_kvm_book3s_64_mmu_map(rflags, hpteg,
 					    vpn, hpaddr, orig_pte);
 
@@ -164,19 +192,37 @@ map_again:
 			hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 		}
 
-		pte->slot = hpteg + (ret & 7);
-		pte->host_vpn = vpn;
-		pte->pte = *orig_pte;
-		pte->pfn = hpaddr >> PAGE_SHIFT;
+		cpte->slot = hpteg + (ret & 7);
+		cpte->host_vpn = vpn;
+		cpte->pte = *orig_pte;
+		cpte->pfn = pfn;
+		cpte->pagesize = hpsize;
 
-		kvmppc_mmu_hpte_cache_map(vcpu, pte);
+		kvmppc_mmu_hpte_cache_map(vcpu, cpte);
+		cpte = NULL;
 	}
-	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
+	kvm_release_pfn_clean(pfn);
+	if (cpte)
+		kvmppc_mmu_hpte_cache_free(cpte);
 
 out:
 	return r;
 }
 
+void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	u64 mask = 0xfffffffffULL;
+	u64 vsid;
+
+	vcpu->arch.mmu.esid_to_vsid(vcpu, pte->eaddr >> SID_SHIFT, &vsid);
+	if (vsid & VSID_64K)
+		mask = 0xffffffff0ULL;
+	kvmppc_mmu_pte_vflush(vcpu, pte->vpage, mask);
+}
+
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
@@ -291,6 +337,12 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	slb_vsid &= ~SLB_VSID_KP;
 	slb_esid |= slb_index;
 
+#ifdef CONFIG_PPC_64K_PAGES
+	/* Set host segment base page size to 64K if possible */
+	if (gvsid & VSID_64K)
+		slb_vsid |= mmu_psize_defs[MMU_PAGE_64K].sllp;
+#endif
+
 	svcpu->slb[slb_index].esid = slb_esid;
 	svcpu->slb[slb_index].vsid = slb_vsid;
 
@@ -326,7 +378,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 	svcpu_put(svcpu);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_hpte_destroy(vcpu);
 	__destroy_context(to_book3s(vcpu)->context_id[0]);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 043eec8461e7..c5d148434c08 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -260,10 +260,6 @@ int kvmppc_mmu_hv_init(void)
 	return 0;
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
-{
-}
-
 static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 {
 	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
@@ -451,7 +447,7 @@ static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
 }
 
 static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-			struct kvmppc_pte *gpte, bool data)
+			struct kvmppc_pte *gpte, bool data, bool iswrite)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_slb *slbe;
@@ -473,11 +469,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		slb_v = vcpu->kvm->arch.vrma_slb_v;
 	}
 
+	preempt_disable();
 	/* Find the HPTE in the hash table */
 	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
 					 HPTE_V_VALID | HPTE_V_ABSENT);
-	if (index < 0)
+	if (index < 0) {
+		preempt_enable();
 		return -ENOENT;
+	}
 	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
 	v = hptep[0] & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
@@ -485,6 +484,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Unlock the HPTE */
 	asm volatile("lwsync" : : : "memory");
 	hptep[0] = v;
+	preempt_enable();
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
@@ -669,6 +669,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			return -EFAULT;
 	} else {
 		page = pages[0];
+		pfn = page_to_pfn(page);
 		if (PageHuge(page)) {
 			page = compound_head(page);
 			pte_size <<= compound_order(page);
@@ -693,7 +694,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			}
 			rcu_read_unlock_sched();
 		}
-		pfn = page_to_pfn(page);
 	}
 
 	ret = -EFAULT;
@@ -711,8 +711,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
 	}
 
-	/* Set the HPTE to point to pfn */
-	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+	/*
+	 * Set the HPTE to point to pfn.
+	 * Since the pfn is at PAGE_SIZE granularity, make sure we
+	 * don't mask out lower-order bits if psize < PAGE_SIZE.
+	 */
+	if (psize < PAGE_SIZE)
+		psize = PAGE_SIZE;
+	r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;
@@ -906,21 +912,22 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return 0;
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (kvm->arch.using_mmu_notifiers)
 		kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
 	return 0;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	if (kvm->arch.using_mmu_notifiers)
 		kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
 	return 0;
 }
 
-void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot)
 {
 	unsigned long *rmapp;
 	unsigned long gfn;
@@ -994,7 +1001,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
@@ -1032,14 +1039,14 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
 	return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return;
@@ -1512,9 +1519,8 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 
 				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
-				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-				lpcr |= senc << (LPCR_VRMASD_SH - 4);
-				kvm->arch.lpcr = lpcr;
+				lpcr = senc << (LPCR_VRMASD_SH - 4);
+				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
 				rma_setup = 1;
 			}
 			++i;
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 30c2f3b134c6..2c25f5412bdb 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -74,3 +74,4 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	/* Didn't find the liobn, punt it to userspace */
 	return H_TOO_HARD;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 360ce68c9809..99d40f8977e8 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -86,8 +86,8 @@ static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level)
 	return true;
 }
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			      unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int rt = get_rt(inst);
@@ -172,7 +172,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
-#ifdef CONFIG_KVM_BOOK3S_64_PR
+#ifdef CONFIG_PPC_BOOK3S_64
 		case OP_31_XOP_FAKE_SC1:
 		{
 			/* SC 1 papr hypercalls */
@@ -267,12 +267,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
 			if ((r == -ENOENT) || (r == -EPERM)) {
-				struct kvmppc_book3s_shadow_vcpu *svcpu;
-
-				svcpu = svcpu_get(vcpu);
 				*advance = 0;
 				vcpu->arch.shared->dar = vaddr;
-				svcpu->fault_dar = vaddr;
+				vcpu->arch.fault_dar = vaddr;
 
 				dsisr = DSISR_ISSTORE;
 				if (r == -ENOENT)
@@ -281,8 +278,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 					dsisr |= DSISR_PROTFAULT;
 
 				vcpu->arch.shared->dsisr = dsisr;
-				svcpu->fault_dsisr = dsisr;
-				svcpu_put(svcpu);
+				vcpu->arch.fault_dsisr = dsisr;
 
 				kvmppc_book3s_queue_irqprio(vcpu,
 					BOOK3S_INTERRUPT_DATA_STORAGE);
@@ -349,7 +345,7 @@ static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn)
 	return bat;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
+int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -472,7 +468,7 @@ unprivileged:
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c
index 7057a02f0906..852989a9bad3 100644
--- a/arch/powerpc/kvm/book3s_exports.c
+++ b/arch/powerpc/kvm/book3s_exports.c
@@ -20,9 +20,10 @@
 #include <linux/export.h>
 #include <asm/kvm_book3s.h>
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline);
-#else
+#endif
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline);
 EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 62a2b5ab08ed..b51d5db78068 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -52,6 +52,9 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
+#include <linux/module.h>
+
+#include "book3s.h"
 
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
@@ -66,7 +69,7 @@
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
-void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
+static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int me;
 	int cpu = vcpu->cpu;
@@ -125,11 +128,12 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
  * purely defensive; they should never fail.)
  */
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
 	    vc->preempt_tb != TB_NIL) {
 		vc->stolen_tb += mftb() - vc->preempt_tb;
@@ -140,32 +144,62 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
 		vcpu->arch.busy_preempt = TB_NIL;
 	}
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->preempt_tb = mftb();
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
 		vcpu->arch.busy_preempt = mftb();
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }
 
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	vcpu->arch.pvr = pvr;
 }
 
+int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
+{
+	unsigned long pcr = 0;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	if (arch_compat) {
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			return -EINVAL;	/* 970 has no compat mode support */
+
+		switch (arch_compat) {
+		case PVR_ARCH_205:
+			pcr = PCR_ARCH_205;
+			break;
+		case PVR_ARCH_206:
+		case PVR_ARCH_206p:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	spin_lock(&vc->lock);
+	vc->arch_compat = arch_compat;
+	vc->pcr = pcr;
+	spin_unlock(&vc->lock);
+
+	return 0;
+}
+
 void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -195,7 +229,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 		pr_err("  ESID = %.16llx VSID = %.16llx\n",
 		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
 	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
-	       vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1,
+	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
 	       vcpu->arch.last_inst);
 }
 
@@ -454,11 +488,11 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
 	 */
 	if (vc->vcore_state != VCORE_INACTIVE &&
 	    vc->runner->arch.run_task != current) {
-		spin_lock(&vc->runner->arch.tbacct_lock);
+		spin_lock_irq(&vc->runner->arch.tbacct_lock);
 		p = vc->stolen_tb;
 		if (vc->preempt_tb != TB_NIL)
 			p += now - vc->preempt_tb;
-		spin_unlock(&vc->runner->arch.tbacct_lock);
+		spin_unlock_irq(&vc->runner->arch.tbacct_lock);
 	} else {
 		p = vc->stolen_tb;
 	}
@@ -480,16 +514,16 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	core_stolen = vcore_stolen_time(vc, now);
 	stolen = core_stolen - vcpu->arch.stolen_logged;
 	vcpu->arch.stolen_logged = core_stolen;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	stolen += vcpu->arch.busy_stolen;
 	vcpu->arch.busy_stolen = 0;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	if (!dt || !vpa)
 		return;
 	memset(dt, 0, sizeof(struct dtl_entry));
 	dt->dispatch_reason = 7;
 	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
-	dt->timebase = now;
+	dt->timebase = now + vc->tb_offset;
 	dt->enqueue_to_dispatch_time = stolen;
 	dt->srr0 = kvmppc_get_pc(vcpu);
 	dt->srr1 = vcpu->arch.shregs.msr;
@@ -538,6 +572,15 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		}
 		break;
 	case H_CONFER:
+		target = kvmppc_get_gpr(vcpu, 4);
+		if (target == -1)
+			break;
+		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+		if (!tvcpu) {
+			ret = H_PARAMETER;
+			break;
+		}
+		kvm_vcpu_yield_to(tvcpu);
 		break;
 	case H_REGISTER_VPA:
 		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
@@ -548,7 +591,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
 			return RESUME_HOST;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvmppc_rtas_hcall(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		if (rc == -ENOENT)
 			return RESUME_HOST;
@@ -576,8 +621,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
-static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-			      struct task_struct *tsk)
+static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				 struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
 
@@ -671,16 +716,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
 			vcpu->arch.shregs.msr);
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
 		r = RESUME_HOST;
-		BUG();
 		break;
 	}
 
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-				  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i;
 
@@ -694,12 +739,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-				  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i, j;
 
-	kvmppc_set_pvr(vcpu, sregs->pvr);
+	kvmppc_set_pvr_hv(vcpu, sregs->pvr);
 
 	j = 0;
 	for (i = 0; i < vcpu->arch.slb_nr; i++) {
@@ -714,7 +759,23 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 mask;
+
+	spin_lock(&vc->lock);
+	/*
+	 * Userspace can only modify DPFD (default prefetch depth),
+	 * ILE (interrupt little-endian) and TC (translation control).
+	 */
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
+	spin_unlock(&vc->lock);
+}
+
+static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 	long int i;
@@ -749,6 +810,12 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		i = id - KVM_REG_PPC_PMC1;
 		*val = get_reg_val(id, vcpu->arch.pmc[i]);
 		break;
+	case KVM_REG_PPC_SIAR:
+		*val = get_reg_val(id, vcpu->arch.siar);
+		break;
+	case KVM_REG_PPC_SDAR:
+		*val = get_reg_val(id, vcpu->arch.sdar);
+		break;
 #ifdef CONFIG_VSX
 	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 		if (cpu_has_feature(CPU_FTR_VSX)) {
@@ -787,6 +854,18 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		val->vpaval.length = vcpu->arch.dtl.len;
 		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		break;
+	case KVM_REG_PPC_LPCR:
+		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+		break;
+	case KVM_REG_PPC_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr);
+		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -795,7 +874,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 	long int i;
@@ -833,6 +913,12 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		i = id - KVM_REG_PPC_PMC1;
 		vcpu->arch.pmc[i] = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_SIAR:
+		vcpu->arch.siar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SDAR:
+		vcpu->arch.sdar = set_reg_val(id, *val);
+		break;
 #ifdef CONFIG_VSX
 	case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 		if (cpu_has_feature(CPU_FTR_VSX)) {
@@ -880,6 +966,20 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		len -= len % sizeof(struct dtl_entry);
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		/* round up to multiple of 2^24 */
+		vcpu->arch.vcore->tb_offset =
+			ALIGN(set_reg_val(id, *val), 1UL << 24);
+		break;
+	case KVM_REG_PPC_LPCR:
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+		break;
+	case KVM_REG_PPC_PPR:
+		vcpu->arch.ppr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -888,14 +988,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_core_check_processor_compat(void)
-{
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		return 0;
-	return -EIO;
-}
-
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
+						   unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	int err = -EINVAL;
@@ -919,8 +1013,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.mmcr[0] = MMCR0_FC;
 	vcpu->arch.ctrl = CTRL_RUNLATCH;
 	/* default to host PVR, since we can't spoof it */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
@@ -940,6 +1033,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
+			vcore->lpcr = kvm->arch.lpcr;
 		}
 		kvm->arch.vcores[core] = vcore;
 		kvm->arch.online_vcores++;
@@ -972,7 +1066,7 @@ static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
 					vpa->dirty);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
 {
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
@@ -983,6 +1077,12 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
+static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
+{
+	/* Indicate we want to get back into the guest */
+	return 1;
+}
+
 static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 {
 	unsigned long dec_nsec, now;
@@ -1019,13 +1119,13 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	now = mftb();
 	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
 		vcpu->arch.stolen_logged;
 	vcpu->arch.busy_preempt = now;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
 	list_del(&vcpu->arch.run_list);
 }
@@ -1264,8 +1364,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 		ret = RESUME_GUEST;
 		if (vcpu->arch.trap)
-			ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
-						 vcpu->arch.run_task);
+			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+						    vcpu->arch.run_task);
 
 		vcpu->arch.ret = ret;
 		vcpu->arch.trap = 0;
@@ -1424,7 +1524,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	return vcpu->arch.ret;
 }
 
-int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
@@ -1546,7 +1646,8 @@ static const struct file_operations kvm_rma_fops = {
 	.release	= kvm_rma_release,
 };
 
-long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
+static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
+				      struct kvm_allocate_rma *ret)
 {
 	long fd;
 	struct kvm_rma_info *ri;
@@ -1592,7 +1693,8 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
 	(*sps)++;
 }
 
-int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
 	struct kvm_ppc_one_seg_page_size *sps;
 
@@ -1613,7 +1715,8 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
 /*
  * 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)
+static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
+					 struct kvm_dirty_log *log)
 {
 	struct kvm_memory_slot *memslot;
 	int r;
@@ -1667,8 +1770,8 @@ static void unpin_slot(struct kvm_memory_slot *memslot)
 	}
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
-			      struct kvm_memory_slot *dont)
+static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
+					struct kvm_memory_slot *dont)
 {
 	if (!dont || free->arch.rmap != dont->arch.rmap) {
 		vfree(free->arch.rmap);
@@ -1681,8 +1784,8 @@ void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
-			       unsigned long npages)
+static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
+					 unsigned long npages)
 {
 	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
 	if (!slot->arch.rmap)
@@ -1692,9 +1795,9 @@ int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
 	return 0;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot,
-				      struct kvm_userspace_memory_region *mem)
+static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
+					struct kvm_memory_slot *memslot,
+					struct kvm_userspace_memory_region *mem)
 {
 	unsigned long *phys;
 
@@ -1710,9 +1813,9 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				      struct kvm_userspace_memory_region *mem,
-				      const struct kvm_memory_slot *old)
+static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 	struct kvm_memory_slot *memslot;
@@ -1729,6 +1832,37 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 	}
 }
 
+/*
+ * Update LPCR values in kvm->arch and in vcores.
+ * Caller must hold kvm->lock.
+ */
+void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
+{
+	long int i;
+	u32 cores_done = 0;
+
+	if ((kvm->arch.lpcr & mask) == lpcr)
+		return;
+
+	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i) {
+		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
+		if (!vc)
+			continue;
+		spin_lock(&vc->lock);
+		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
+		spin_unlock(&vc->lock);
+		if (++cores_done >= kvm->arch.online_vcores)
+			break;
+	}
+}
+
+static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
@@ -1737,7 +1871,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
-	unsigned long lpcr, senc;
+	unsigned long lpcr = 0, senc;
+	unsigned long lpcr_mask = 0;
 	unsigned long psize, porder;
 	unsigned long rma_size;
 	unsigned long rmls;
@@ -1802,9 +1937,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		senc = slb_pgsize_encoding(psize);
 		kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 			(VRMA_VSID << SLB_VSID_SHIFT_1T);
-		lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-		lpcr |= senc << (LPCR_VRMASD_SH - 4);
-		kvm->arch.lpcr = lpcr;
+		lpcr_mask = LPCR_VRMASD;
+		/* the -4 is to account for senc values starting at 0x10 */
+		lpcr = senc << (LPCR_VRMASD_SH - 4);
 
 		/* Create HPTEs in the hash page table for the VRMA */
 		kvmppc_map_vrma(vcpu, memslot, porder);
@@ -1825,23 +1960,21 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		kvm->arch.rma = ri;
 
 		/* Update LPCR and RMOR */
-		lpcr = kvm->arch.lpcr;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			/* PPC970; insert RMLS value (split field) in HID4 */
-			lpcr &= ~((1ul << HID4_RMLS0_SH) |
-				  (3ul << HID4_RMLS2_SH));
-			lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
+			lpcr_mask = (1ul << HID4_RMLS0_SH) |
+				(3ul << HID4_RMLS2_SH) | HID4_RMOR;
+			lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
 				((rmls & 3) << HID4_RMLS2_SH);
 			/* RMOR is also in HID4 */
 			lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
 				<< HID4_RMOR_SH;
 		} else {
 			/* POWER7 */
-			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
-			lpcr |= rmls << LPCR_RMLS_SH;
+			lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
+			lpcr = rmls << LPCR_RMLS_SH;
 			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
-		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
@@ -1860,6 +1993,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
 	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
 	smp_wmb();
 	kvm->arch.rma_setup_done = 1;
@@ -1875,7 +2010,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	goto out_srcu;
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 {
 	unsigned long lpcr, lpid;
 
@@ -1893,9 +2028,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	 */
 	cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
-	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
-
 	kvm->arch.rma = NULL;
 
 	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
@@ -1931,61 +2063,162 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_free_vcores(struct kvm *kvm)
+{
+	long int i;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i)
+		kfree(kvm->arch.vcores[i]);
+	kvm->arch.online_vcores = 0;
+}
+
+static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
 	uninhibit_secondary_onlining();
 
+	kvmppc_free_vcores(kvm);
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
 	}
 
-	kvmppc_rtas_tokens_free(kvm);
-
 	kvmppc_free_hpt(kvm);
-	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 }
 
-/* These are stubs for now */
-void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
+/* We don't need to emulate any privileged instructions or dcbz */
+static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				     unsigned int inst, int *advance)
 {
+	return EMULATE_FAIL;
 }
 
-/* We don't need to emulate any privileged instructions or dcbz */
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
+static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong *spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+static int kvmppc_core_check_processor_compat_hv(void)
 {
-	return EMULATE_FAIL;
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EIO;
+	return 0;
 }
 
-static int kvmppc_book3s_hv_init(void)
+static long kvm_arch_vm_ioctl_hv(struct file *filp,
+				 unsigned int ioctl, unsigned long arg)
 {
-	int r;
+	struct kvm *kvm __maybe_unused = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r;
 
-	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	switch (ioctl) {
 
-	if (r)
+	case KVM_ALLOCATE_RMA: {
+		struct kvm_allocate_rma rma;
+		struct kvm *kvm = filp->private_data;
+
+		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
+		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
+			r = -EFAULT;
+		break;
+	}
+
+	case KVM_PPC_ALLOCATE_HTAB: {
+		u32 htab_order;
+
+		r = -EFAULT;
+		if (get_user(htab_order, (u32 __user *)argp))
+			break;
+		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (put_user(htab_order, (u32 __user *)argp))
+			break;
+		r = 0;
+		break;
+	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm_get_htab_fd ghf;
+
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
+
+	default:
+		r = -ENOTTY;
+	}
+
+	return r;
+}
+
+static struct kvmppc_ops kvm_ops_hv = {
+	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
+	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
+	.get_one_reg = kvmppc_get_one_reg_hv,
+	.set_one_reg = kvmppc_set_one_reg_hv,
+	.vcpu_load   = kvmppc_core_vcpu_load_hv,
+	.vcpu_put    = kvmppc_core_vcpu_put_hv,
+	.set_msr     = kvmppc_set_msr_hv,
+	.vcpu_run    = kvmppc_vcpu_run_hv,
+	.vcpu_create = kvmppc_core_vcpu_create_hv,
+	.vcpu_free   = kvmppc_core_vcpu_free_hv,
+	.check_requests = kvmppc_core_check_requests_hv,
+	.get_dirty_log  = kvm_vm_ioctl_get_dirty_log_hv,
+	.flush_memslot  = kvmppc_core_flush_memslot_hv,
+	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
+	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
+	.unmap_hva = kvm_unmap_hva_hv,
+	.unmap_hva_range = kvm_unmap_hva_range_hv,
+	.age_hva  = kvm_age_hva_hv,
+	.test_age_hva = kvm_test_age_hva_hv,
+	.set_spte_hva = kvm_set_spte_hva_hv,
+	.mmu_destroy  = kvmppc_mmu_destroy_hv,
+	.free_memslot = kvmppc_core_free_memslot_hv,
+	.create_memslot = kvmppc_core_create_memslot_hv,
+	.init_vm =  kvmppc_core_init_vm_hv,
+	.destroy_vm = kvmppc_core_destroy_vm_hv,
+	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
+	.emulate_op = kvmppc_core_emulate_op_hv,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
+	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
+	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
+};
+
+static int kvmppc_book3s_init_hv(void)
+{
+	int r;
+	/*
+	 * FIXME!! Do we need to check on all cpus ?
+	 */
+	r = kvmppc_core_check_processor_compat_hv();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hv_init();
+	kvm_ops_hv.owner = THIS_MODULE;
+	kvmppc_hv_ops = &kvm_ops_hv;
 
+	r = kvmppc_mmu_hv_init();
 	return r;
 }
 
-static void kvmppc_book3s_hv_exit(void)
+static void kvmppc_book3s_exit_hv(void)
 {
-	kvm_exit();
+	kvmppc_hv_ops = NULL;
 }
 
-module_init(kvmppc_book3s_hv_init);
-module_exit(kvmppc_book3s_hv_exit);
+module_init(kvmppc_book3s_init_hv);
+module_exit(kvmppc_book3s_exit_hv);
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 37f1cc417ca0..928142c64cb0 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -158,9 +158,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
  * Interrupts are enabled again at this point.
  */
 
-.global kvmppc_handler_highmem
-kvmppc_handler_highmem:
-
 	/*
 	 * Register usage at this point:
 	 *
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9c515440ad1a..8689e2e30857 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -225,6 +225,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		is_io = pa & (HPTE_R_I | HPTE_R_W);
 		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
 		pa &= PAGE_MASK;
+		pa |= gpa & ~PAGE_MASK;
 	} else {
 		/* Translate to host virtual address */
 		hva = __gfn_to_hva_memslot(memslot, gfn);
@@ -238,13 +239,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 				ptel = hpte_make_readonly(ptel);
 			is_io = hpte_cache_bits(pte_val(pte));
 			pa = pte_pfn(pte) << PAGE_SHIFT;
+			pa |= hva & (pte_size - 1);
+			pa |= gpa & ~PAGE_MASK;
 		}
 	}
 
 	if (pte_size < psize)
 		return H_PARAMETER;
-	if (pa && pte_size > psize)
-		pa |= gpa & (pte_size - 1);
 
 	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
@@ -749,6 +750,10 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
 long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			      unsigned long valid)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c71103b8a748..be4fa04a37c9 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -33,30 +33,6 @@
 #error Need to fix lppaca and SLB shadow accesses in little endian mode
 #endif
 
-/*****************************************************************************
- *                                                                           *
- *        Real Mode handlers that need to be in the linear mapping           *
- *                                                                           *
- ****************************************************************************/
-
-	.globl	kvmppc_skip_interrupt
-kvmppc_skip_interrupt:
-	mfspr	r13,SPRN_SRR0
-	addi	r13,r13,4
-	mtspr	SPRN_SRR0,r13
-	GET_SCRATCH0(r13)
-	rfid
-	b	.
-
-	.globl	kvmppc_skip_Hinterrupt
-kvmppc_skip_Hinterrupt:
-	mfspr	r13,SPRN_HSRR0
-	addi	r13,r13,4
-	mtspr	SPRN_HSRR0,r13
-	GET_SCRATCH0(r13)
-	hrfid
-	b	.
-
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -66,8 +42,11 @@ kvmppc_skip_Hinterrupt:
  * LR = return address to continue at after eventually re-enabling MMU
  */
 _GLOBAL(kvmppc_hv_entry_trampoline)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 	mfmsr	r10
-	LOAD_REG_ADDR(r5, kvmppc_hv_entry)
+	LOAD_REG_ADDR(r5, kvmppc_call_hv_entry)
 	li	r0,MSR_RI
 	andc	r0,r10,r0
 	li	r6,MSR_IR | MSR_DR
@@ -77,11 +56,102 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 	mtsrr1	r6
 	RFI
 
-/******************************************************************************
- *                                                                            *
- *                               Entry code                                   *
- *                                                                            *
- *****************************************************************************/
+kvmppc_call_hv_entry:
+	bl	kvmppc_hv_entry
+
+	/* Back from guest - restore host state and return to caller */
+
+	/* Restore host DABR and DABRX */
+	ld	r5,HSTATE_DABR(r13)
+	li	r6,7
+	mtspr	SPRN_DABR,r5
+	mtspr	SPRN_DABRX,r6
+
+	/* Restore SPRG3 */
+	ld	r3,PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3,r3
+
+	/*
+	 * Reload DEC.  HDEC interrupts were disabled when
+	 * we reloaded the host's LPCR value.
+	 */
+	ld	r3, HSTATE_DECEXP(r13)
+	mftb	r4
+	subf	r4, r4, r3
+	mtspr	SPRN_DEC, r4
+
+	/* Reload the host's PMU registers */
+	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
+	lbz	r4, LPPACA_PMCINUSE(r3)
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+	lwz	r3, HSTATE_PMC(r13)
+	lwz	r4, HSTATE_PMC + 4(r13)
+	lwz	r5, HSTATE_PMC + 8(r13)
+	lwz	r6, HSTATE_PMC + 12(r13)
+	lwz	r8, HSTATE_PMC + 16(r13)
+	lwz	r9, HSTATE_PMC + 20(r13)
+BEGIN_FTR_SECTION
+	lwz	r10, HSTATE_PMC + 24(r13)
+	lwz	r11, HSTATE_PMC + 28(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PMC7, r10
+	mtspr	SPRN_PMC8, r11
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	ld	r3, HSTATE_MMCR(r13)
+	ld	r4, HSTATE_MMCR + 8(r13)
+	ld	r5, HSTATE_MMCR + 16(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_MMCR0, r3
+	isync
+23:
+
+	/*
+	 * For external and machine check interrupts, we need
+	 * to call the Linux handler to process the interrupt.
+	 * We do that by jumping to absolute address 0x500 for
+	 * external interrupts, or the machine_check_fwnmi label
+	 * for machine checks (since firmware might have patched
+	 * the vector area at 0x200).  The [h]rfid at the end of the
+	 * handler will return to the book3s_hv_interrupts.S code.
+	 * For other interrupts we do the rfid to get back
+	 * to the book3s_hv_interrupts.S code here.
+	 */
+	ld	r8, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	ld	r7, HSTATE_HOST_MSR(r13)
+
+	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+BEGIN_FTR_SECTION
+	beq	11f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+	/* RFI into the highmem handler, or branch to interrupt handler */
+	mfmsr	r6
+	li	r0, MSR_RI
+	andc	r6, r6, r0
+	mtmsrd	r6, 1			/* Clear RI in MSR */
+	mtsrr0	r8
+	mtsrr1	r7
+	beqa	0x500			/* external interrupt (PPC970) */
+	beq	cr1, 13f		/* machine check */
+	RFI
+
+	/* On POWER7, we have external interrupts set to use HSRR0/1 */
+11:	mtspr	SPRN_HSRR0, r8
+	mtspr	SPRN_HSRR1, r7
+	ba	0x500
+
+13:	b	machine_check_fwnmi
 
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
@@ -137,7 +207,7 @@ kvm_start_guest:
 	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
-	b	kvmppc_hv_entry
+	b	30f
 
 27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
 	b	kvm_no_guest
@@ -147,6 +217,61 @@ kvm_start_guest:
 	stw	r8,HSTATE_SAVED_XIRR(r13)
 	b	kvm_no_guest
 
+30:	bl	kvmppc_hv_entry
+
+	/* Back from the guest, go back to nap */
+	/* Clear our vcpu pointer so we don't come back in early */
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+	/*
+	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+	 * the nap_count, because once the increment to nap_count is
+	 * visible we could be given another vcpu.
+	 */
+	lwsync
+	/* Clear any pending IPI - we're an offline thread */
+	ld	r5, HSTATE_XICS_PHYS(r13)
+	li	r7, XICS_XIRR
+	lwzcix	r3, r5, r7		/* ack any pending interrupt */
+	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
+	beq	37f
+	sync
+	li	r0, 0xff
+	li	r6, XICS_MFRR
+	stbcix	r0, r5, r6		/* clear the IPI */
+	stwcix	r3, r5, r7		/* EOI it */
+37:	sync
+
+	/* increment the nap count and then go to nap mode */
+	ld	r4, HSTATE_KVM_VCORE(r13)
+	addi	r4, r4, VCORE_NAP_COUNT
+51:	lwarx	r3, 0, r4
+	addi	r3, r3, 1
+	stwcx.	r3, 0, r4
+	bne	51b
+
+kvm_no_guest:
+	li	r0, KVM_HWTHREAD_IN_NAP
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	li	r3, LPCR_PECE0
+	mfspr	r4, SPRN_LPCR
+	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
+	mtspr	SPRN_LPCR, r4
+	isync
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
 
@@ -159,7 +284,8 @@ kvmppc_hv_entry:
 	 * all other volatile GPRS = free
 	 */
 	mflr	r0
-	std	r0, HSTATE_VMHANDLER(r13)
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -112(r1)
 
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -200,8 +326,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	ld	r3, VCPU_MMCR(r4)
 	ld	r5, VCPU_MMCR + 8(r4)
 	ld	r6, VCPU_MMCR + 16(r4)
+	ld	r7, VCPU_SIAR(r4)
+	ld	r8, VCPU_SDAR(r4)
 	mtspr	SPRN_MMCR1, r5
 	mtspr	SPRN_MMCRA, r6
+	mtspr	SPRN_SIAR, r7
+	mtspr	SPRN_SDAR, r8
 	mtspr	SPRN_MMCR0, r3
 	isync
 
@@ -254,22 +384,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
 
-	/* Increment yield count if they have a VPA */
-	ld	r3, VCPU_VPA(r4)
-	cmpdi	r3, 0
-	beq	25f
-	lwz	r5, LPPACA_YIELDCOUNT(r3)
-	addi	r5, r5, 1
-	stw	r5, LPPACA_YIELDCOUNT(r3)
-	li	r6, 1
-	stb	r6, VCPU_VPA_DIRTY(r4)
-25:
 	/* Load up DAR and DSISR */
 	ld	r5, VCPU_DAR(r4)
 	lwz	r6, VCPU_DSISR(r4)
 	mtspr	SPRN_DAR, r5
 	mtspr	SPRN_DSISR, r6
 
+	li	r6, KVM_GUEST_MODE_HOST_HV
+	stb	r6, HSTATE_IN_GUEST(r13)
+
 BEGIN_FTR_SECTION
 	/* Restore AMR and UAMOR, set AMOR to all 1s */
 	ld	r5,VCPU_AMR(r4)
@@ -343,7 +466,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	bdnz	28b
 	ptesync
 
-22:	li	r0,1
+	/* Add timebase offset onto timebase */
+22:	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	37f
+	mftb	r6		/* current host timebase */
+	add	r8,r8,r6
+	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
+	mftb	r7		/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	37f
+	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+	/* Load guest PCR value to select appropriate compat mode */
+37:	ld	r7, VCORE_PCR(r5)
+	cmpdi	r7, 0
+	beq	38f
+	mtspr	SPRN_PCR, r7
+38:
+	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -353,12 +497,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	beq	20b
 
 	/* Set LPCR and RMOR. */
-10:	ld	r8,KVM_LPCR(r9)
+10:	ld	r8,VCORE_LPCR(r5)
 	mtspr	SPRN_LPCR,r8
 	ld	r8,KVM_RMOR(r9)
 	mtspr	SPRN_RMOR,r8
 	isync
 
+	/* Increment yield count if they have a VPA */
+	ld	r3, VCPU_VPA(r4)
+	cmpdi	r3, 0
+	beq	25f
+	lwz	r5, LPPACA_YIELDCOUNT(r3)
+	addi	r5, r5, 1
+	stw	r5, LPPACA_YIELDCOUNT(r3)
+	li	r6, 1
+	stb	r6, VCPU_VPA_DIRTY(r4)
+25:
 	/* Check if HDEC expires soon */
 	mfspr	r3,SPRN_HDEC
 	cmpwi	r3,10
@@ -405,7 +559,8 @@ toc_tlbie_lock:
 	bne	24b
 	isync
 
-	ld	r7,KVM_LPCR(r9)		/* use kvm->arch.lpcr to store HID4 */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r7,VCORE_LPCR(r5)	/* use vcore->lpcr to store HID4 */
 	li	r0,0x18f
 	rotldi	r0,r0,HID4_LPID5_SH	/* all lpid bits in HID4 = 1 */
 	or	r0,r7,r0
@@ -541,7 +696,7 @@ fast_guest_return:
 	mtspr	SPRN_HSRR1,r11
 
 	/* Activate guest mode, so faults get handled by KVM */
-	li	r9, KVM_GUEST_MODE_GUEST
+	li	r9, KVM_GUEST_MODE_GUEST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
 
 	/* Enter guest */
@@ -550,13 +705,15 @@ BEGIN_FTR_SECTION
 	ld	r5, VCPU_CFAR(r4)
 	mtspr	SPRN_CFAR, r5
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r0, VCPU_PPR(r4)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r5, VCPU_LR(r4)
 	lwz	r6, VCPU_CR(r4)
 	mtlr	r5
 	mtcr	r6
 
-	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r1, VCPU_GPR(R1)(r4)
 	ld	r2, VCPU_GPR(R2)(r4)
 	ld	r3, VCPU_GPR(R3)(r4)
@@ -570,6 +727,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r12, VCPU_GPR(R12)(r4)
 	ld	r13, VCPU_GPR(R13)(r4)
 
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PPR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 
 	hrfid
@@ -584,8 +745,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 /*
  * We come here from the first-level interrupt handlers.
  */
-	.globl	kvmppc_interrupt
-kvmppc_interrupt:
+	.globl	kvmppc_interrupt_hv
+kvmppc_interrupt_hv:
 	/*
 	 * Register contents:
 	 * R12		= interrupt vector
@@ -593,8 +754,20 @@ kvmppc_interrupt:
 	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
-	std	r9, HSTATE_HOST_R2(r13)
+	std	r9, HSTATE_SCRATCH2(r13)
+
+	lbz	r9, HSTATE_IN_GUEST(r13)
+	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
+	beq	kvmppc_bad_host_intr
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	cmpwi	r9, KVM_GUEST_MODE_GUEST
+	ld	r9, HSTATE_SCRATCH2(r13)
+	beq	kvmppc_interrupt_pr
+#endif
+	/* We're now back in the host but in guest MMU context */
+	li	r9, KVM_GUEST_MODE_HOST_HV
+	stb	r9, HSTATE_IN_GUEST(r13)
+
 	ld	r9, HSTATE_KVM_VCPU(r13)
 
 	/* Save registers */
@@ -608,7 +781,7 @@ kvmppc_interrupt:
 	std	r6, VCPU_GPR(R6)(r9)
 	std	r7, VCPU_GPR(R7)(r9)
 	std	r8, VCPU_GPR(R8)(r9)
-	ld	r0, HSTATE_HOST_R2(r13)
+	ld	r0, HSTATE_SCRATCH2(r13)
 	std	r0, VCPU_GPR(R9)(r9)
 	std	r10, VCPU_GPR(R10)(r9)
 	std	r11, VCPU_GPR(R11)(r9)
@@ -620,6 +793,10 @@ BEGIN_FTR_SECTION
 	ld	r3, HSTATE_CFAR(r13)
 	std	r3, VCPU_CFAR(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r4, HSTATE_PPR(r13)
+	std	r4, VCPU_PPR(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	/* Restore R1/R2 so we can handle faults */
 	ld	r1, HSTATE_HOST_R1(r13)
@@ -642,10 +819,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	std	r3, VCPU_GPR(R13)(r9)
 	std	r4, VCPU_LR(r9)
 
-	/* Unset guest mode */
-	li	r0, KVM_GUEST_MODE_NONE
-	stb	r0, HSTATE_IN_GUEST(r13)
-
 	stw	r12,VCPU_TRAP(r9)
 
 	/* Save HEIR (HV emulation assist reg) in last_inst
@@ -696,46 +869,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * set, we know the host wants us out so let's do it now
 	 */
 do_ext_interrupt:
-	lbz	r0, HSTATE_HOST_IPI(r13)
-	cmpwi	r0, 0
-	bne	ext_interrupt_to_host
-
-	/* Now read the interrupt from the ICP */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r7, XICS_XIRR
-	cmpdi	r5, 0
-	beq-	ext_interrupt_to_host
-	lwzcix	r3, r5, r7
-	rlwinm.	r0, r3, 0, 0xffffff
-	sync
-	beq	3f		/* if nothing pending in the ICP */
-
-	/* We found something in the ICP...
-	 *
-	 * If it's not an IPI, stash it in the PACA and return to
-	 * the host, we don't (yet) handle directing real external
-	 * interrupts directly to the guest
-	 */
-	cmpwi	r0, XICS_IPI
-	bne	ext_stash_for_host
-
-	/* It's an IPI, clear the MFRR and EOI it */
-	li	r0, 0xff
-	li	r6, XICS_MFRR
-	stbcix	r0, r5, r6		/* clear the IPI */
-	stwcix	r3, r5, r7		/* EOI it */
-	sync
-
-	/* We need to re-check host IPI now in case it got set in the
-	 * meantime. If it's clear, we bounce the interrupt to the
-	 * guest
-	 */
-	lbz	r0, HSTATE_HOST_IPI(r13)
-	cmpwi	r0, 0
-	bne-	1f
+	bl	kvmppc_read_intr
+	cmpdi	r3, 0
+	bgt	ext_interrupt_to_host
 
 	/* Allright, looks like an IPI for the guest, we need to set MER */
-3:
 	/* Check if any CPU is heading out to the host, if so head out too */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	lwz	r0, VCORE_ENTRY_EXIT(r5)
@@ -764,27 +902,9 @@ do_ext_interrupt:
 	mtspr	SPRN_LPCR, r8
 	b	fast_guest_return
 
-	/* We raced with the host, we need to resend that IPI, bummer */
-1:	li	r0, IPI_PRIORITY
-	stbcix	r0, r5, r6		/* set the IPI */
-	sync
-	b	ext_interrupt_to_host
-
-ext_stash_for_host:
-	/* It's not an IPI and it's for the host, stash it in the PACA
-	 * before exit, it will be picked up by the host ICP driver
-	 */
-	stw	r3, HSTATE_SAVED_XIRR(r13)
 ext_interrupt_to_host:
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
 	/* Save more register state  */
 	mfdar	r6
 	mfdsisr	r7
@@ -872,14 +992,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 */
 	/* Increment the threads-exiting-guest count in the 0xff00
 	   bits of vcore->entry_exit_count */
-	lwsync
 	ld	r5,HSTATE_KVM_VCORE(r13)
 	addi	r6,r5,VCORE_ENTRY_EXIT
 41:	lwarx	r3,0,r6
 	addi	r0,r3,0x100
 	stwcx.	r0,0,r6
 	bne	41b
-	lwsync
+	isync		/* order stwcx. vs. reading napping_threads */
 
 	/*
 	 * At this point we have an interrupt that we have to pass
@@ -912,6 +1031,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
 	beq	43f
+	/* Order entry/exit update vs. IPIs */
+	sync
 	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
 	subf	r6,r4,r13
 42:	andi.	r0,r3,1
@@ -954,7 +1075,30 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
-	li	r0,0
+
+	/* Subtract timebase offset from timebase */
+	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	17f
+	mftb	r6			/* current host timebase */
+	subf	r8,r8,r6
+	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
+	mftb	r7			/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	17f
+	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+	/* Reset PCR */
+17:	ld	r0, VCORE_PCR(r5)
+	cmpdi	r0, 0
+	beq	18f
+	li	r0, 0
+	mtspr	SPRN_PCR, r0
+18:
+	/* Signal secondary CPUs to continue */
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
@@ -1052,6 +1196,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 1:	addi	r8,r8,16
 	.endr
 
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR
@@ -1062,6 +1213,10 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_AMR,r6
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+	/* Unset guest mode */
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+
 	/* Switch DSCR back to host value */
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
@@ -1134,9 +1289,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
 	b	22f
 21:	mfspr	r5, SPRN_MMCR1
+	mfspr	r7, SPRN_SIAR
+	mfspr	r8, SPRN_SDAR
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
 	std	r6, VCPU_MMCR + 16(r9)
+	std	r7, VCPU_SIAR(r9)
+	std	r8, VCPU_SDAR(r9)
 	mfspr	r3, SPRN_PMC1
 	mfspr	r4, SPRN_PMC2
 	mfspr	r5, SPRN_PMC3
@@ -1158,103 +1317,30 @@ BEGIN_FTR_SECTION
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 22:
+	ld	r0, 112+PPC_LR_STKOFF(r1)
+	addi	r1, r1, 112
+	mtlr	r0
+	blr
+secondary_too_late:
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	HMT_LOW
+13:	lbz	r3,VCORE_IN_GUEST(r5)
+	cmpwi	r3,0
+	bne	13b
+	HMT_MEDIUM
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+	ld	r11,PACA_SLBSHADOWPTR(r13)
 
-	/* Secondary threads go off to take a nap on POWER7 */
-BEGIN_FTR_SECTION
-	lwz	r0,VCPU_PTID(r9)
-	cmpwi	r0,0
-	bne	secondary_nap
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* Restore host DABR and DABRX */
-	ld	r5,HSTATE_DABR(r13)
-	li	r6,7
-	mtspr	SPRN_DABR,r5
-	mtspr	SPRN_DABRX,r6
-
-	/* Restore SPRG3 */
-	ld	r3,PACA_SPRG3(r13)
-	mtspr	SPRN_SPRG3,r3
-
-	/*
-	 * Reload DEC.  HDEC interrupts were disabled when
-	 * we reloaded the host's LPCR value.
-	 */
-	ld	r3, HSTATE_DECEXP(r13)
-	mftb	r4
-	subf	r4, r4, r3
-	mtspr	SPRN_DEC, r4
-
-	/* Reload the host's PMU registers */
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r4, LPPACA_PMCINUSE(r3)
-	cmpwi	r4, 0
-	beq	23f			/* skip if not */
-	lwz	r3, HSTATE_PMC(r13)
-	lwz	r4, HSTATE_PMC + 4(r13)
-	lwz	r5, HSTATE_PMC + 8(r13)
-	lwz	r6, HSTATE_PMC + 12(r13)
-	lwz	r8, HSTATE_PMC + 16(r13)
-	lwz	r9, HSTATE_PMC + 20(r13)
-BEGIN_FTR_SECTION
-	lwz	r10, HSTATE_PMC + 24(r13)
-	lwz	r11, HSTATE_PMC + 28(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r4
-	mtspr	SPRN_PMC3, r5
-	mtspr	SPRN_PMC4, r6
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-BEGIN_FTR_SECTION
-	mtspr	SPRN_PMC7, r10
-	mtspr	SPRN_PMC8, r11
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	ld	r3, HSTATE_MMCR(r13)
-	ld	r4, HSTATE_MMCR + 8(r13)
-	ld	r5, HSTATE_MMCR + 16(r13)
-	mtspr	SPRN_MMCR1, r4
-	mtspr	SPRN_MMCRA, r5
-	mtspr	SPRN_MMCR0, r3
-	isync
-23:
-	/*
-	 * For external and machine check interrupts, we need
-	 * to call the Linux handler to process the interrupt.
-	 * We do that by jumping to absolute address 0x500 for
-	 * external interrupts, or the machine_check_fwnmi label
-	 * for machine checks (since firmware might have patched
-	 * the vector area at 0x200).  The [h]rfid at the end of the
-	 * handler will return to the book3s_hv_interrupts.S code.
-	 * For other interrupts we do the rfid to get back
-	 * to the book3s_hv_interrupts.S code here.
-	 */
-	ld	r8, HSTATE_VMHANDLER(r13)
-	ld	r7, HSTATE_HOST_MSR(r13)
-
-	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-BEGIN_FTR_SECTION
-	beq	11f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* RFI into the highmem handler, or branch to interrupt handler */
-	mfmsr	r6
-	li	r0, MSR_RI
-	andc	r6, r6, r0
-	mtmsrd	r6, 1			/* Clear RI in MSR */
-	mtsrr0	r8
-	mtsrr1	r7
-	beqa	0x500			/* external interrupt (PPC970) */
-	beq	cr1, 13f		/* machine check */
-	RFI
-
-	/* On POWER7, we have external interrupts set to use HSRR0/1 */
-11:	mtspr	SPRN_HSRR0, r8
-	mtspr	SPRN_HSRR1, r7
-	ba	0x500
-
-13:	b	machine_check_fwnmi
+	.rept	SLB_NUM_BOLTED
+	ld	r5,SLBSHADOW_SAVEAREA(r11)
+	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r11,r11,16
+	.endr
+	b	22b
 
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
@@ -1333,7 +1419,7 @@ fast_interrupt_c_return:
 	stw	r8, VCPU_LAST_INST(r9)
 
 	/* Unset guest mode. */
-	li	r0, KVM_GUEST_MODE_NONE
+	li	r0, KVM_GUEST_MODE_HOST_HV
 	stb	r0, HSTATE_IN_GUEST(r13)
 	b	guest_exit_cont
 
@@ -1555,10 +1641,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
+	/* order napping_threads update vs testing entry_exit_count */
+	isync
 	li	r0,1
 	stb	r0,HSTATE_NAPPING(r13)
-	/* order napping_threads update vs testing entry_exit_count */
-	lwsync
 	mr	r4,r3
 	lwz	r7,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r7,0x100
@@ -1701,67 +1787,70 @@ machine_check_realmode:
 	rotldi	r11, r11, 63
 	b	fast_interrupt_c_return
 
-secondary_too_late:
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	HMT_LOW
-13:	lbz	r3,VCORE_IN_GUEST(r5)
-	cmpwi	r3,0
-	bne	13b
-	HMT_MEDIUM
-	ld	r11,PACA_SLBSHADOWPTR(r13)
-
-	.rept	SLB_NUM_BOLTED
-	ld	r5,SLBSHADOW_SAVEAREA(r11)
-	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
-	andis.	r7,r5,SLB_ESID_V@h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r11,r11,16
-	.endr
+/*
+ * Determine what sort of external interrupt is pending (if any).
+ * Returns:
+ *	0 if no interrupt is pending
+ *	1 if an interrupt is pending that needs to be handled by the host
+ *	-1 if there was a guest wakeup IPI (which has now been cleared)
+ */
+kvmppc_read_intr:
+	/* see if a host IPI is pending */
+	li	r3, 1
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
+	bne	1f
 
-secondary_nap:
-	/* Clear our vcpu pointer so we don't come back in early */
-	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
-	lwsync
-	/* Clear any pending IPI - assume we're a secondary thread */
-	ld	r5, HSTATE_XICS_PHYS(r13)
+	/* Now read the interrupt from the ICP */
+	ld	r6, HSTATE_XICS_PHYS(r13)
 	li	r7, XICS_XIRR
-	lwzcix	r3, r5, r7		/* ack any pending interrupt */
-	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
-	beq	37f
+	cmpdi	r6, 0
+	beq-	1f
+	lwzcix	r0, r6, r7
+	rlwinm.	r3, r0, 0, 0xffffff
 	sync
-	li	r0, 0xff
-	li	r6, XICS_MFRR
-	stbcix	r0, r5, r6		/* clear the IPI */
-	stwcix	r3, r5, r7		/* EOI it */
-37:	sync
+	beq	1f			/* if nothing pending in the ICP */
 
-	/* increment the nap count and then go to nap mode */
-	ld	r4, HSTATE_KVM_VCORE(r13)
-	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
-51:	lwarx	r3, 0, r4
-	addi	r3, r3, 1
-	stwcx.	r3, 0, r4
-	bne	51b
+	/* We found something in the ICP...
+	 *
+	 * If it's not an IPI, stash it in the PACA and return to
+	 * the host, we don't (yet) handle directing real external
+	 * interrupts directly to the guest
+	 */
+	cmpwi	r3, XICS_IPI		/* if there is, is it an IPI? */
+	li	r3, 1
+	bne	42f
 
-kvm_no_guest:
-	li	r0, KVM_HWTHREAD_IN_NAP
-	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	/* It's an IPI, clear the MFRR and EOI it */
+	li	r3, 0xff
+	li	r8, XICS_MFRR
+	stbcix	r3, r6, r8		/* clear the IPI */
+	stwcix	r0, r6, r7		/* EOI it */
+	sync
 
-	li	r3, LPCR_PECE0
-	mfspr	r4, SPRN_LPCR
-	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
-	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
+	/* We need to re-check host IPI now in case it got set in the
+	 * meantime. If it's clear, we bounce the interrupt to the
+	 * guest
+	 */
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
+	bne-	43f
+
+	/* OK, it's an IPI for us */
+	li	r3, -1
+1:	blr
+
+42:	/* It's not an IPI and it's for the host, stash it in the PACA
+	 * before exit, it will be picked up by the host ICP driver
+	 */
+	stw	r0, HSTATE_SAVED_XIRR(r13)
+	b	1b
+
+43:	/* We raced with the host, we need to resend that IPI, bummer */
+	li	r0, IPI_PRIORITY
+	stbcix	r0, r6, r8		/* set the IPI */
+	sync
+	b	1b
 
 /*
  * Save away FP, VMX and VSX registers.
@@ -1879,3 +1968,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	lwz	r7,VCPU_VRSAVE(r4)
 	mtspr	SPRN_VRSAVE,r7
 	blr
+
+/*
+ * We come here if we get any exception or interrupt while we are
+ * executing host real mode code while in guest MMU context.
+ * For now just spin, but we should do something better.
+ */
+kvmppc_bad_host_intr:
+	b	.
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 17cfae5497a3..f779450cb07c 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -26,8 +26,12 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 #define FUNC(name) 		GLUE(.,name)
+#define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
+
 #elif defined(CONFIG_PPC_BOOK3S_32)
 #define FUNC(name)		name
+#define GET_SHADOW_VCPU(reg)	lwz     reg, (THREAD + THREAD_KVM_SVCPU)(r2)
+
 #endif /* CONFIG_PPC_BOOK3S_XX */
 
 #define VCPU_LOAD_NVGPRS(vcpu) \
@@ -87,8 +91,14 @@ kvm_start_entry:
 	VCPU_LOAD_NVGPRS(r4)
 
 kvm_start_lightweight:
+	/* Copy registers into shadow vcpu so we can access them in real mode */
+	GET_SHADOW_VCPU(r3)
+	bl	FUNC(kvmppc_copy_to_svcpu)
+	nop
+	REST_GPR(4, r1)
 
 #ifdef CONFIG_PPC_BOOK3S_64
+	/* Get the dcbz32 flag */
 	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
 	stb	r3, HSTATE_RESTORE_HID5(r13)
@@ -111,9 +121,6 @@ kvm_start_lightweight:
  *
  */
 
-.global kvmppc_handler_highmem
-kvmppc_handler_highmem:
-
 	/*
 	 * Register usage at this point:
 	 *
@@ -122,11 +129,24 @@ kvmppc_handler_highmem:
 	 * R12      = exit handler id
 	 * R13      = PACA
 	 * SVCPU.*  = guest *
+	 * MSR.EE   = 1
 	 *
 	 */
 
-	/* R7 = vcpu */
-	PPC_LL	r7, GPR4(r1)
+	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
+	/*
+	 * kvmppc_copy_from_svcpu can clobber volatile registers, save
+	 * the exit handler id to the vcpu and restore it from there later.
+	 */
+	stw	r12, VCPU_TRAP(r3)
+
+	/* Transfer reg values from shadow vcpu back to vcpu struct */
+	/* On 64-bit, interrupts are still off at this point */
+
+	GET_SHADOW_VCPU(r4)
+	bl	FUNC(kvmppc_copy_from_svcpu)
+	nop
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
@@ -137,6 +157,9 @@ kvmppc_handler_highmem:
 	mtspr	SPRN_SPRG3, r3
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+	/* R7 = vcpu */
+	PPC_LL	r7, GPR4(r1)
+
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
 	PPC_STL	r16, VCPU_GPR(R16)(r7)
@@ -157,11 +180,11 @@ kvmppc_handler_highmem:
 	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	mr	r5, r12
+	lwz	r5, VCPU_TRAP(r7)
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
-	bl	FUNC(kvmppc_handle_exit)
+	bl	FUNC(kvmppc_handle_exit_pr)
 
 	/* If RESUME_GUEST, get back in the loop */
 	cmpwi	r3, RESUME_GUEST
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index da8b13c4b776..5a1ab1250a05 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -28,7 +28,7 @@
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
 
-#include "trace.h"
+#include "trace_pr.h"
 
 #define PTE_SIZE	12
 
@@ -56,6 +56,14 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage)
 		       HPTEG_HASH_BITS_VPTE_LONG);
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline u64 kvmppc_mmu_hash_vpte_64k(u64 vpage)
+{
+	return hash_64((vpage & 0xffffffff0ULL) >> 4,
+		       HPTEG_HASH_BITS_VPTE_64K);
+}
+#endif
+
 void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
@@ -83,6 +91,15 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_add_head_rcu(&pte->list_vpte_long,
 			   &vcpu3s->hpte_hash_vpte_long[index]);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Add to vPTE_64k list */
+	index = kvmppc_mmu_hash_vpte_64k(pte->pte.vpage);
+	hlist_add_head_rcu(&pte->list_vpte_64k,
+			   &vcpu3s->hpte_hash_vpte_64k[index]);
+#endif
+
+	vcpu3s->hpte_cache_count++;
+
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
@@ -113,10 +130,13 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	hlist_del_init_rcu(&pte->list_pte_long);
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
+#ifdef CONFIG_PPC_BOOK3S_64
+	hlist_del_init_rcu(&pte->list_vpte_64k);
+#endif
+	vcpu3s->hpte_cache_count--;
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
-	vcpu3s->hpte_cache_count--;
 	call_rcu(&pte->rcu_head, free_pte_rcu);
 }
 
@@ -219,6 +239,29 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Flush with mask 0xffffffff0 */
+static void kvmppc_mmu_pte_vflush_64k(struct kvm_vcpu *vcpu, u64 guest_vp)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	struct hlist_head *list;
+	struct hpte_cache *pte;
+	u64 vp_mask = 0xffffffff0ULL;
+
+	list = &vcpu3s->hpte_hash_vpte_64k[
+		kvmppc_mmu_hash_vpte_64k(guest_vp)];
+
+	rcu_read_lock();
+
+	/* Check the list for matching entries and invalidate */
+	hlist_for_each_entry_rcu(pte, list, list_vpte_64k)
+		if ((pte->pte.vpage & vp_mask) == guest_vp)
+			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
+}
+#endif
+
 /* Flush with mask 0xffffff000 */
 static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
@@ -249,6 +292,11 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 	case 0xfffffffffULL:
 		kvmppc_mmu_pte_vflush_short(vcpu, guest_vp);
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case 0xffffffff0ULL:
+		kvmppc_mmu_pte_vflush_64k(vcpu, guest_vp);
+		break;
+#endif
 	case 0xffffff000ULL:
 		kvmppc_mmu_pte_vflush_long(vcpu, guest_vp);
 		break;
@@ -285,15 +333,19 @@ struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hpte_cache *pte;
 
-	pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL);
-	vcpu3s->hpte_cache_count++;
-
 	if (vcpu3s->hpte_cache_count == HPTEG_CACHE_NUM)
 		kvmppc_mmu_pte_flush_all(vcpu);
 
+	pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL);
+
 	return pte;
 }
 
+void kvmppc_mmu_hpte_cache_free(struct hpte_cache *pte)
+{
+	kmem_cache_free(hpte_cache, pte);
+}
+
 void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
@@ -320,6 +372,10 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte));
 	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long,
 				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long));
+#ifdef CONFIG_PPC_BOOK3S_64
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_64k,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_64k));
+#endif
 
 	spin_lock_init(&vcpu3s->mmu_lock);
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 27db1e665959..5b9e9063cfaf 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -40,8 +40,12 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
+#include <linux/module.h>
 
-#include "trace.h"
+#include "book3s.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace_pr.h"
 
 /* #define EXIT_DEBUG */
 /* #define DEBUG_EXT */
@@ -56,29 +60,29 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define HW_PAGE_SIZE PAGE_SIZE
 #endif
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
-	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->in_use = 0;
 	svcpu_put(svcpu);
 #endif
 	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
-	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
+	current->thread.kvm_shadow_vcpu = vcpu->arch.shadow_vcpu;
 #endif
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	if (svcpu->in_use) {
+		kvmppc_copy_from_svcpu(vcpu, svcpu);
+	}
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
-	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
 #endif
@@ -87,7 +91,79 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 }
 
-int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
+/* Copy data needed by real-mode code from vcpu to shadow vcpu */
+void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+			  struct kvm_vcpu *vcpu)
+{
+	svcpu->gpr[0] = vcpu->arch.gpr[0];
+	svcpu->gpr[1] = vcpu->arch.gpr[1];
+	svcpu->gpr[2] = vcpu->arch.gpr[2];
+	svcpu->gpr[3] = vcpu->arch.gpr[3];
+	svcpu->gpr[4] = vcpu->arch.gpr[4];
+	svcpu->gpr[5] = vcpu->arch.gpr[5];
+	svcpu->gpr[6] = vcpu->arch.gpr[6];
+	svcpu->gpr[7] = vcpu->arch.gpr[7];
+	svcpu->gpr[8] = vcpu->arch.gpr[8];
+	svcpu->gpr[9] = vcpu->arch.gpr[9];
+	svcpu->gpr[10] = vcpu->arch.gpr[10];
+	svcpu->gpr[11] = vcpu->arch.gpr[11];
+	svcpu->gpr[12] = vcpu->arch.gpr[12];
+	svcpu->gpr[13] = vcpu->arch.gpr[13];
+	svcpu->cr  = vcpu->arch.cr;
+	svcpu->xer = vcpu->arch.xer;
+	svcpu->ctr = vcpu->arch.ctr;
+	svcpu->lr  = vcpu->arch.lr;
+	svcpu->pc  = vcpu->arch.pc;
+	svcpu->in_use = true;
+}
+
+/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
+void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+			    struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+	/*
+	 * vcpu_put would just call us again because in_use hasn't
+	 * been updated yet.
+	 */
+	preempt_disable();
+
+	/*
+	 * Maybe we were already preempted and synced the svcpu from
+	 * our preempt notifiers. Don't bother touching this svcpu then.
+	 */
+	if (!svcpu->in_use)
+		goto out;
+
+	vcpu->arch.gpr[0] = svcpu->gpr[0];
+	vcpu->arch.gpr[1] = svcpu->gpr[1];
+	vcpu->arch.gpr[2] = svcpu->gpr[2];
+	vcpu->arch.gpr[3] = svcpu->gpr[3];
+	vcpu->arch.gpr[4] = svcpu->gpr[4];
+	vcpu->arch.gpr[5] = svcpu->gpr[5];
+	vcpu->arch.gpr[6] = svcpu->gpr[6];
+	vcpu->arch.gpr[7] = svcpu->gpr[7];
+	vcpu->arch.gpr[8] = svcpu->gpr[8];
+	vcpu->arch.gpr[9] = svcpu->gpr[9];
+	vcpu->arch.gpr[10] = svcpu->gpr[10];
+	vcpu->arch.gpr[11] = svcpu->gpr[11];
+	vcpu->arch.gpr[12] = svcpu->gpr[12];
+	vcpu->arch.gpr[13] = svcpu->gpr[13];
+	vcpu->arch.cr  = svcpu->cr;
+	vcpu->arch.xer = svcpu->xer;
+	vcpu->arch.ctr = svcpu->ctr;
+	vcpu->arch.lr  = svcpu->lr;
+	vcpu->arch.pc  = svcpu->pc;
+	vcpu->arch.shadow_srr1 = svcpu->shadow_srr1;
+	vcpu->arch.fault_dar   = svcpu->fault_dar;
+	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
+	vcpu->arch.last_inst   = svcpu->last_inst;
+	svcpu->in_use = false;
+
+out:
+	preempt_enable();
+}
+
+static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
 {
 	int r = 1; /* Indicate we want to get back into the guest */
 
@@ -100,44 +176,69 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 }
 
 /************* MMU Notifiers *************/
+static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start,
+			     unsigned long end)
+{
+	long i;
+	struct kvm_vcpu *vcpu;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		unsigned long hva_start, hva_end;
+		gfn_t gfn, gfn_end;
+
+		hva_start = max(start, memslot->userspace_addr);
+		hva_end = min(end, memslot->userspace_addr +
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn, gfn+1, ..., gfn_end-1}.
+		 */
+		gfn = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, gfn << PAGE_SHIFT,
+					      gfn_end << PAGE_SHIFT);
+	}
+}
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_unmap_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	trace_kvm_unmap_hva(hva);
 
-	/*
-	 * Flush all shadow tlb entries everywhere. This is slow, but
-	 * we are 100% sure that we catch the to be unmapped page
-	 */
-	kvm_flush_remote_tlbs(kvm);
+	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
 
 	return 0;
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
+				  unsigned long end)
 {
-	/* kvm_unmap_hva flushes everything anyways */
-	kvm_unmap_hva(kvm, start);
+	do_kvm_unmap_hva(kvm, start, end);
 
 	return 0;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_age_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	/* XXX could be more clever ;) */
 	return 0;
 }
 
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+static int kvm_test_age_hva_pr(struct kvm *kvm, unsigned long hva)
 {
 	/* XXX could be more clever ;) */
 	return 0;
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+static void kvm_set_spte_hva_pr(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	/* The page will get remapped properly on its next fault */
-	kvm_unmap_hva(kvm, hva);
+	do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE);
 }
 
 /*****************************************/
@@ -159,7 +260,7 @@ static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 	vcpu->arch.shadow_msr = smsr;
 }
 
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 {
 	ulong old_msr = vcpu->arch.shared->msr;
 
@@ -219,7 +320,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 }
 
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	u32 host_pvr;
 
@@ -256,6 +357,23 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
 		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
 
+	/*
+	 * If they're asking for POWER6 or later, set the flag
+	 * indicating that we can do multiple large page sizes
+	 * and 1TB segments.
+	 * Also set the flag that indicates that tlbie has the large
+	 * page bit in the RB operand instead of the instruction.
+	 */
+	switch (PVR_VER(pvr)) {
+	case PVR_POWER6:
+	case PVR_POWER7:
+	case PVR_POWER7p:
+	case PVR_POWER8:
+		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
+			BOOK3S_HFLAG_NEW_TLBIE;
+		break;
+	}
+
 #ifdef CONFIG_PPC_BOOK3S_32
 	/* 32 bit Book3S always has 32 byte dcbz */
 	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
@@ -334,6 +452,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			    ulong eaddr, int vec)
 {
 	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
+	bool iswrite = false;
 	int r = RESUME_GUEST;
 	int relocated;
 	int page_found = 0;
@@ -344,10 +463,12 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	u64 vsid;
 
 	relocated = data ? dr : ir;
+	if (data && (vcpu->arch.fault_dsisr & DSISR_ISSTORE))
+		iswrite = true;
 
 	/* Resolve real address if translation turned on */
 	if (relocated) {
-		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
+		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data, iswrite);
 	} else {
 		pte.may_execute = true;
 		pte.may_read = true;
@@ -355,6 +476,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.raddr = eaddr & KVM_PAM;
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
+		pte.page_size = MMU_PAGE_64K;
 	}
 
 	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
@@ -388,22 +510,18 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = svcpu->fault_dsisr;
+		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr;
 		vcpu->arch.shared->msr |=
-			(svcpu->shadow_srr1 & 0x00000000f8000000ULL);
-		svcpu_put(svcpu);
+			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
 		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
 		vcpu->arch.shared->msr |=
-			svcpu->shadow_srr1 & 0x00000000f8000000ULL;
-		svcpu_put(svcpu);
+			vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL;
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -411,12 +529,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
 	} else if (!is_mmio &&
 		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
+		if (data && !(vcpu->arch.fault_dsisr & DSISR_NOHPTE)) {
+			/*
+			 * There is already a host HPTE there, presumably
+			 * a read-only one for a page the guest thinks
+			 * is writable, so get rid of it first.
+			 */
+			kvmppc_mmu_unmap_page(vcpu, &pte);
+		}
 		/* The guest's PTE is not mapped yet. Map on the host */
-		kvmppc_mmu_map_page(vcpu, &pte);
+		kvmppc_mmu_map_page(vcpu, &pte, iswrite);
 		if (data)
 			vcpu->stat.sp_storage++;
 		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
-			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
+			 (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
 			kvmppc_patch_dcbz(vcpu, &pte);
 	} else {
 		/* MMIO */
@@ -444,7 +570,7 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 #ifdef CONFIG_VSX
 	u64 *vcpu_vsx = vcpu->arch.vsr;
 #endif
-	u64 *thread_fpr = (u64*)t->fpr;
+	u64 *thread_fpr = &t->fp_state.fpr[0][0];
 	int i;
 
 	/*
@@ -466,14 +592,14 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 		/*
 		 * Note that on CPUs with VSX, giveup_fpu stores
 		 * both the traditional FP registers and the added VSX
-		 * registers into thread.fpr[].
+		 * registers into thread.fp_state.fpr[].
 		 */
 		if (current->thread.regs->msr & MSR_FP)
 			giveup_fpu(current);
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
 
-		vcpu->arch.fpscr = t->fpscr.val;
+		vcpu->arch.fpscr = t->fp_state.fpscr;
 
 #ifdef CONFIG_VSX
 		if (cpu_has_feature(CPU_FTR_VSX))
@@ -486,8 +612,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 	if (msr & MSR_VEC) {
 		if (current->thread.regs->msr & MSR_VEC)
 			giveup_altivec(current);
-		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
-		vcpu->arch.vscr = t->vscr;
+		memcpy(vcpu->arch.vr, t->vr_state.vr, sizeof(vcpu->arch.vr));
+		vcpu->arch.vscr = t->vr_state.vscr;
 	}
 #endif
 
@@ -539,7 +665,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #ifdef CONFIG_VSX
 	u64 *vcpu_vsx = vcpu->arch.vsr;
 #endif
-	u64 *thread_fpr = (u64*)t->fpr;
+	u64 *thread_fpr = &t->fp_state.fpr[0][0];
 	int i;
 
 	/* When we have paired singles, we emulate in software */
@@ -584,15 +710,15 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
 			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
 #endif
-		t->fpscr.val = vcpu->arch.fpscr;
+		t->fp_state.fpscr = vcpu->arch.fpscr;
 		t->fpexc_mode = 0;
 		kvmppc_load_up_fpu();
 	}
 
 	if (msr & MSR_VEC) {
 #ifdef CONFIG_ALTIVEC
-		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
-		t->vscr = vcpu->arch.vscr;
+		memcpy(t->vr_state.vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
+		t->vr_state.vscr = vcpu->arch.vscr;
 		t->vrsave = -1;
 		kvmppc_load_up_altivec();
 #endif
@@ -619,13 +745,15 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 
 	if (lost_ext & MSR_FP)
 		kvmppc_load_up_fpu();
+#ifdef CONFIG_ALTIVEC
 	if (lost_ext & MSR_VEC)
 		kvmppc_load_up_altivec();
+#endif
 	current->thread.regs->msr |= lost_ext;
 }
 
-int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int exit_nr)
+int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			  unsigned int exit_nr)
 {
 	int r = RESUME_HOST;
 	int s;
@@ -643,25 +771,32 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
 	{
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		ulong shadow_srr1 = svcpu->shadow_srr1;
+		ulong shadow_srr1 = vcpu->arch.shadow_srr1;
 		vcpu->stat.pf_instruc++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
-			r = RESUME_GUEST;
+		{
+			struct kvmppc_book3s_shadow_vcpu *svcpu;
+			u32 sr;
+
+			svcpu = svcpu_get(vcpu);
+			sr = svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT];
 			svcpu_put(svcpu);
-			break;
+			if (sr == SR_INVALID) {
+				kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+				r = RESUME_GUEST;
+				break;
+			}
 		}
 #endif
-		svcpu_put(svcpu);
 
 		/* only care about PTEG not found errors, but leave NX alone */
 		if (shadow_srr1 & 0x40000000) {
+			int idx = srcu_read_lock(&vcpu->kvm->srcu);
 			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
 			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
@@ -682,25 +817,36 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_DATA_STORAGE:
 	{
 		ulong dar = kvmppc_get_fault_dar(vcpu);
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		u32 fault_dsisr = svcpu->fault_dsisr;
+		u32 fault_dsisr = vcpu->arch.fault_dsisr;
 		vcpu->stat.pf_storage++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, dar);
-			r = RESUME_GUEST;
+		{
+			struct kvmppc_book3s_shadow_vcpu *svcpu;
+			u32 sr;
+
+			svcpu = svcpu_get(vcpu);
+			sr = svcpu->sr[dar >> SID_SHIFT];
 			svcpu_put(svcpu);
-			break;
+			if (sr == SR_INVALID) {
+				kvmppc_mmu_map_segment(vcpu, dar);
+				r = RESUME_GUEST;
+				break;
+			}
 		}
 #endif
-		svcpu_put(svcpu);
 
-		/* The only case we need to handle is missing shadow PTEs */
-		if (fault_dsisr & DSISR_NOHPTE) {
+		/*
+		 * We need to handle missing shadow PTEs, and
+		 * protection faults due to us mapping a page read-only
+		 * when the guest thinks it is writable.
+		 */
+		if (fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT)) {
+			int idx = srcu_read_lock(&vcpu->kvm->srcu);
 			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;
@@ -743,13 +889,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
 	{
 		enum emulation_result er;
-		struct kvmppc_book3s_shadow_vcpu *svcpu;
 		ulong flags;
 
 program_interrupt:
-		svcpu = svcpu_get(vcpu);
-		flags = svcpu->shadow_srr1 & 0x1f0000ull;
-		svcpu_put(svcpu);
+		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
 
 		if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -798,7 +941,7 @@ program_interrupt:
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
 			int i;
 
-#ifdef CONFIG_KVM_BOOK3S_64_PR
+#ifdef CONFIG_PPC_BOOK3S_64
 			if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
 				r = RESUME_GUEST;
 				break;
@@ -881,9 +1024,7 @@ program_interrupt:
 		break;
 	default:
 	{
-		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
-		ulong shadow_srr1 = svcpu->shadow_srr1;
-		svcpu_put(svcpu);
+		ulong shadow_srr1 = vcpu->arch.shadow_srr1;
 		/* Ugh - bork here! What did we get? */
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
 			exit_nr, kvmppc_get_pc(vcpu), shadow_srr1);
@@ -920,8 +1061,8 @@ program_interrupt:
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_get_sregs_pr(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
@@ -947,13 +1088,13 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_set_sregs_pr(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
-	kvmppc_set_pvr(vcpu, sregs->pvr);
+	kvmppc_set_pvr_pr(vcpu, sregs->pvr);
 
 	vcpu3s->sdr1 = sregs->u.s.sdr1;
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
@@ -983,7 +1124,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 
@@ -1012,7 +1154,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
 {
 	int r = 0;
 
@@ -1042,28 +1185,30 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	return r;
 }
 
-int kvmppc_core_check_processor_compat(void)
-{
-	return 0;
-}
-
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
+						   unsigned int id)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	struct kvm_vcpu *vcpu;
 	int err = -ENOMEM;
 	unsigned long p;
 
-	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
-	if (!vcpu_book3s)
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu)
 		goto out;
 
-	vcpu_book3s->shadow_vcpu =
-		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
-	if (!vcpu_book3s->shadow_vcpu)
+	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
+	if (!vcpu_book3s)
 		goto free_vcpu;
+	vcpu->arch.book3s = vcpu_book3s;
+
+#ifdef CONFIG_KVM_BOOK3S_32
+	vcpu->arch.shadow_vcpu =
+		kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL);
+	if (!vcpu->arch.shadow_vcpu)
+		goto free_vcpu3s;
+#endif
 
-	vcpu = &vcpu_book3s->vcpu;
 	err = kvm_vcpu_init(vcpu, kvm, id);
 	if (err)
 		goto free_shadow_vcpu;
@@ -1076,13 +1221,19 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* default to book3s_64 (970fx) */
+	/*
+	 * Default to the same as the host if we're on sufficiently
+	 * recent machine that we have 1TB segments;
+	 * otherwise default to PPC970FX.
+	 */
 	vcpu->arch.pvr = 0x3C0301;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		vcpu->arch.pvr = mfspr(SPRN_PVR);
 #else
 	/* default to book3s_32 (750) */
 	vcpu->arch.pvr = 0x84202;
 #endif
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr);
 	vcpu->arch.slb_nr = 64;
 
 	vcpu->arch.shadow_msr = MSR_USER64;
@@ -1096,32 +1247,37 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
-	kfree(vcpu_book3s->shadow_vcpu);
-free_vcpu:
+#ifdef CONFIG_KVM_BOOK3S_32
+	kfree(vcpu->arch.shadow_vcpu);
+free_vcpu3s:
+#endif
 	vfree(vcpu_book3s);
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu_book3s->shadow_vcpu);
+#ifdef CONFIG_KVM_BOOK3S_32
+	kfree(vcpu->arch.shadow_vcpu);
+#endif
 	vfree(vcpu_book3s);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
-int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
-	double fpr[32][TS_FPRWIDTH];
-	unsigned int fpscr;
+	struct thread_fp_state fp;
 	int fpexc_mode;
 #ifdef CONFIG_ALTIVEC
-	vector128 vr[32];
-	vector128 vscr;
+	struct thread_vr_state vr;
 	unsigned long uninitialized_var(vrsave);
 	int used_vr;
 #endif
@@ -1153,8 +1309,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* Save FPU state in stack */
 	if (current->thread.regs->msr & MSR_FP)
 		giveup_fpu(current);
-	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
-	fpscr = current->thread.fpscr.val;
+	fp = current->thread.fp_state;
 	fpexc_mode = current->thread.fpexc_mode;
 
 #ifdef CONFIG_ALTIVEC
@@ -1163,8 +1318,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (used_vr) {
 		if (current->thread.regs->msr & MSR_VEC)
 			giveup_altivec(current);
-		memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
-		vscr = current->thread.vscr;
+		vr = current->thread.vr_state;
 		vrsave = current->thread.vrsave;
 	}
 #endif
@@ -1196,15 +1350,13 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	current->thread.regs->msr = ext_msr;
 
 	/* Restore FPU/VSX state from stack */
-	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
-	current->thread.fpscr.val = fpscr;
+	current->thread.fp_state = fp;
 	current->thread.fpexc_mode = fpexc_mode;
 
 #ifdef CONFIG_ALTIVEC
 	/* Restore Altivec state from stack */
 	if (used_vr && current->thread.used_vr) {
-		memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
-		current->thread.vscr = vscr;
+		current->thread.vr_state = vr;
 		current->thread.vrsave = vrsave;
 	}
 	current->thread.used_vr = used_vr;
@@ -1222,8 +1374,8 @@ out:
 /*
  * 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)
+static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
+					 struct kvm_dirty_log *log)
 {
 	struct kvm_memory_slot *memslot;
 	struct kvm_vcpu *vcpu;
@@ -1258,67 +1410,100 @@ out:
 	return r;
 }
 
-#ifdef CONFIG_PPC64
-int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+static void kvmppc_core_flush_memslot_pr(struct kvm *kvm,
+					 struct kvm_memory_slot *memslot)
 {
-	info->flags = KVM_PPC_1T_SEGMENTS;
-
-	/* SLB is always 64 entries */
-	info->slb_size = 64;
-
-	/* Standard 4k base page size segment */
-	info->sps[0].page_shift = 12;
-	info->sps[0].slb_enc = 0;
-	info->sps[0].enc[0].page_shift = 12;
-	info->sps[0].enc[0].pte_enc = 0;
-
-	/* Standard 16M large page size segment */
-	info->sps[1].page_shift = 24;
-	info->sps[1].slb_enc = SLB_VSID_L;
-	info->sps[1].enc[0].page_shift = 24;
-	info->sps[1].enc[0].pte_enc = 0;
+	return;
+}
 
+static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
+					struct kvm_memory_slot *memslot,
+					struct kvm_userspace_memory_region *mem)
+{
 	return 0;
 }
-#endif /* CONFIG_PPC64 */
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
-			      struct kvm_memory_slot *dont)
+static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
 {
+	return;
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
-			       unsigned long npages)
+static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free,
+					struct kvm_memory_slot *dont)
 {
-	return 0;
+	return;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot,
-				      struct kvm_userspace_memory_region *mem)
+static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot,
+					 unsigned long npages)
 {
 	return 0;
 }
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
+
+#ifdef CONFIG_PPC64
+static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
-}
+	long int i;
+	struct kvm_vcpu *vcpu;
+
+	info->flags = 0;
+
+	/* SLB is always 64 entries */
+	info->slb_size = 64;
 
-void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+	/* Standard 4k base page size segment */
+	info->sps[0].page_shift = 12;
+	info->sps[0].slb_enc = 0;
+	info->sps[0].enc[0].page_shift = 12;
+	info->sps[0].enc[0].pte_enc = 0;
+
+	/*
+	 * 64k large page size.
+	 * We only want to put this in if the CPUs we're emulating
+	 * support it, but unfortunately we don't have a vcpu easily
+	 * to hand here to test.  Just pick the first vcpu, and if
+	 * that doesn't exist yet, report the minimum capability,
+	 * i.e., no 64k pages.
+	 * 1T segment support goes along with 64k pages.
+	 */
+	i = 1;
+	vcpu = kvm_get_vcpu(kvm, 0);
+	if (vcpu && (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) {
+		info->flags = KVM_PPC_1T_SEGMENTS;
+		info->sps[i].page_shift = 16;
+		info->sps[i].slb_enc = SLB_VSID_L | SLB_VSID_LP_01;
+		info->sps[i].enc[0].page_shift = 16;
+		info->sps[i].enc[0].pte_enc = 1;
+		++i;
+	}
+
+	/* Standard 16M large page size segment */
+	info->sps[i].page_shift = 24;
+	info->sps[i].slb_enc = SLB_VSID_L;
+	info->sps[i].enc[0].page_shift = 24;
+	info->sps[i].enc[0].pte_enc = 0;
+
+	return 0;
+}
+#else
+static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
+	/* We should not get called */
+	BUG();
 }
+#endif /* CONFIG_PPC64 */
 
 static unsigned int kvm_global_user_count = 0;
 static DEFINE_SPINLOCK(kvm_global_user_count_lock);
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_pr(struct kvm *kvm)
 {
-#ifdef CONFIG_PPC64
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
-	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
-#endif
+	mutex_init(&kvm->arch.hpt_mutex);
 
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		spin_lock(&kvm_global_user_count_lock);
@@ -1329,7 +1514,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_pr(struct kvm *kvm)
 {
 #ifdef CONFIG_PPC64
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
@@ -1344,26 +1529,81 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 	}
 }
 
-static int kvmppc_book3s_init(void)
+static int kvmppc_core_check_processor_compat_pr(void)
 {
-	int r;
+	/* we are always compatible */
+	return 0;
+}
+
+static long kvm_arch_vm_ioctl_pr(struct file *filp,
+				 unsigned int ioctl, unsigned long arg)
+{
+	return -ENOTTY;
+}
 
-	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
-		     THIS_MODULE);
+static struct kvmppc_ops kvm_ops_pr = {
+	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
+	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
+	.get_one_reg = kvmppc_get_one_reg_pr,
+	.set_one_reg = kvmppc_set_one_reg_pr,
+	.vcpu_load   = kvmppc_core_vcpu_load_pr,
+	.vcpu_put    = kvmppc_core_vcpu_put_pr,
+	.set_msr     = kvmppc_set_msr_pr,
+	.vcpu_run    = kvmppc_vcpu_run_pr,
+	.vcpu_create = kvmppc_core_vcpu_create_pr,
+	.vcpu_free   = kvmppc_core_vcpu_free_pr,
+	.check_requests = kvmppc_core_check_requests_pr,
+	.get_dirty_log = kvm_vm_ioctl_get_dirty_log_pr,
+	.flush_memslot = kvmppc_core_flush_memslot_pr,
+	.prepare_memory_region = kvmppc_core_prepare_memory_region_pr,
+	.commit_memory_region = kvmppc_core_commit_memory_region_pr,
+	.unmap_hva = kvm_unmap_hva_pr,
+	.unmap_hva_range = kvm_unmap_hva_range_pr,
+	.age_hva  = kvm_age_hva_pr,
+	.test_age_hva = kvm_test_age_hva_pr,
+	.set_spte_hva = kvm_set_spte_hva_pr,
+	.mmu_destroy  = kvmppc_mmu_destroy_pr,
+	.free_memslot = kvmppc_core_free_memslot_pr,
+	.create_memslot = kvmppc_core_create_memslot_pr,
+	.init_vm = kvmppc_core_init_vm_pr,
+	.destroy_vm = kvmppc_core_destroy_vm_pr,
+	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr,
+	.emulate_op = kvmppc_core_emulate_op_pr,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_pr,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_pr,
+	.fast_vcpu_kick = kvm_vcpu_kick,
+	.arch_vm_ioctl  = kvm_arch_vm_ioctl_pr,
+};
+
+
+int kvmppc_book3s_init_pr(void)
+{
+	int r;
 
-	if (r)
+	r = kvmppc_core_check_processor_compat_pr();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hpte_sysinit();
+	kvm_ops_pr.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_pr;
 
+	r = kvmppc_mmu_hpte_sysinit();
 	return r;
 }
 
-static void kvmppc_book3s_exit(void)
+void kvmppc_book3s_exit_pr(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_mmu_hpte_sysexit();
-	kvm_exit();
 }
 
-module_init(kvmppc_book3s_init);
-module_exit(kvmppc_book3s_exit);
+/*
+ * We only support separate modules for book3s 64
+ */
+#ifdef CONFIG_PPC_BOOK3S_64
+
+module_init(kvmppc_book3s_init_pr);
+module_exit(kvmppc_book3s_exit_pr);
+
+MODULE_LICENSE("GPL");
+#endif
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index da0e0bc268bd..5efa97b993d8 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -21,6 +21,8 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#define HPTE_SIZE	16		/* bytes per HPT entry */
+
 static unsigned long get_pteg_addr(struct kvm_vcpu *vcpu, long pte_index)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
@@ -40,32 +42,41 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
 	long pte_index = kvmppc_get_gpr(vcpu, 5);
 	unsigned long pteg[2 * 8];
 	unsigned long pteg_addr, i, *hpte;
+	long int ret;
 
+	i = pte_index & 7;
 	pte_index &= ~7UL;
 	pteg_addr = get_pteg_addr(vcpu, pte_index);
 
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
 	hpte = pteg;
 
+	ret = H_PTEG_FULL;
 	if (likely((flags & H_EXACT) == 0)) {
-		pte_index &= ~7UL;
 		for (i = 0; ; ++i) {
 			if (i == 8)
-				return H_PTEG_FULL;
+				goto done;
 			if ((*hpte & HPTE_V_VALID) == 0)
 				break;
 			hpte += 2;
 		}
 	} else {
-		i = kvmppc_get_gpr(vcpu, 5) & 7UL;
 		hpte += i * 2;
+		if (*hpte & HPTE_V_VALID)
+			goto done;
 	}
 
 	hpte[0] = kvmppc_get_gpr(vcpu, 6);
 	hpte[1] = kvmppc_get_gpr(vcpu, 7);
-	copy_to_user((void __user *)pteg_addr, pteg, sizeof(pteg));
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+	pteg_addr += i * HPTE_SIZE;
+	copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
 	kvmppc_set_gpr(vcpu, 4, pte_index | i);
+	ret = H_SUCCESS;
+
+ done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
+	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
 }
@@ -77,26 +88,31 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
 	unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
 	unsigned long v = 0, pteg, rb;
 	unsigned long pte[2];
+	long int ret;
 
 	pteg = get_pteg_addr(vcpu, pte_index);
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
 
+	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
 	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn) ||
-	    ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) {
-		kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
-		return EMULATE_DONE;
-	}
+	    ((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
+		goto done;
 
 	copy_to_user((void __user *)pteg, &v, sizeof(v));
 
 	rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
 
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+	ret = H_SUCCESS;
 	kvmppc_set_gpr(vcpu, 4, pte[0]);
 	kvmppc_set_gpr(vcpu, 5, pte[1]);
 
+ done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
+	kvmppc_set_gpr(vcpu, 3, ret);
+
 	return EMULATE_DONE;
 }
 
@@ -124,6 +140,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 	int paramnr = 4;
 	int ret = H_SUCCESS;
 
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) {
 		unsigned long tsh = kvmppc_get_gpr(vcpu, paramnr+(2*i));
 		unsigned long tsl = kvmppc_get_gpr(vcpu, paramnr+(2*i)+1);
@@ -172,6 +189,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
 		}
 		kvmppc_set_gpr(vcpu, paramnr+(2*i), tsh);
 	}
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
 	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
@@ -184,15 +202,16 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
 	unsigned long rb, pteg, r, v;
 	unsigned long pte[2];
+	long int ret;
 
 	pteg = get_pteg_addr(vcpu, pte_index);
+	mutex_lock(&vcpu->kvm->arch.hpt_mutex);
 	copy_from_user(pte, (void __user *)pteg, sizeof(pte));
 
+	ret = H_NOT_FOUND;
 	if ((pte[0] & HPTE_V_VALID) == 0 ||
-	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) {
-		kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
-		return EMULATE_DONE;
-	}
+	    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn))
+		goto done;
 
 	v = pte[0];
 	r = pte[1];
@@ -207,8 +226,11 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	rb = compute_tlbie_rb(v, r, pte_index);
 	vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
 	copy_to_user((void __user *)pteg, pte, sizeof(pte));
+	ret = H_SUCCESS;
 
-	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+ done:
+	mutex_unlock(&vcpu->kvm->arch.hpt_mutex);
+	kvmppc_set_gpr(vcpu, 3, ret);
 
 	return EMULATE_DONE;
 }
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 8f7633e3afb8..c3c5231adade 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -38,32 +38,6 @@
 
 #define FUNC(name) 		GLUE(.,name)
 
-	.globl	kvmppc_skip_interrupt
-kvmppc_skip_interrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_SRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_SRR0, r13
-	GET_SCRATCH0(r13)
-	rfid
-	b	.
-
-	.globl	kvmppc_skip_Hinterrupt
-kvmppc_skip_Hinterrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_HSRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_HSRR0, r13
-	GET_SCRATCH0(r13)
-	hrfid
-	b	.
-
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
 #define FUNC(name)		name
@@ -181,7 +155,7 @@ _GLOBAL(kvmppc_entry_trampoline)
 	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
 	/*
 	 * Set EE in HOST_MSR so that it's enabled when we get into our
-	 * C exit handler function
+	 * C exit handler function.
 	 */
 	ori	r5, r5, MSR_EE
 	mtsrr0	r7
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 3219ba895246..cf95cdef73c9 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -260,6 +260,7 @@ fail:
 	 */
 	return rc;
 }
+EXPORT_SYMBOL_GPL(kvmppc_rtas_hcall);
 
 void kvmppc_rtas_tokens_free(struct kvm *kvm)
 {
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 1abe4788191a..bc50c97751d3 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -161,8 +161,8 @@ kvmppc_handler_trampoline_enter_end:
 .global kvmppc_handler_trampoline_exit
 kvmppc_handler_trampoline_exit:
 
-.global kvmppc_interrupt
-kvmppc_interrupt:
+.global kvmppc_interrupt_pr
+kvmppc_interrupt_pr:
 
 	/* Register usage at this point:
 	 *
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index a3a5cb8ee7ea..02a17dcf1610 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	}
 
 	/* Check for real mode returning too hard */
-	if (xics->real_mode)
+	if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm))
 		return kvmppc_xics_rm_complete(vcpu, req);
 
 	switch (req) {
@@ -840,6 +840,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(kvmppc_xics_hcall);
 
 
 /* -- Initialisation code etc. -- */
@@ -1250,13 +1251,13 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 
 	xics_debugfs_init(xics);
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
 		/* Enable real mode support */
 		xics->real_mode = ENABLE_REALMODE;
 		xics->real_mode_dbg = DEBUG_REALMODE;
 	}
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 17722d82f1d1..0591e05db74b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -40,7 +40,9 @@
 
 #include "timing.h"
 #include "booke.h"
-#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace_booke.h"
 
 unsigned long kvmppc_booke_handlers;
 
@@ -133,6 +135,29 @@ static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static void kvmppc_vcpu_sync_debug(struct kvm_vcpu *vcpu)
+{
+	/* Synchronize guest's desire to get debug interrupts into shadow MSR */
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr &= ~MSR_DE;
+	vcpu->arch.shadow_msr |= vcpu->arch.shared->msr & MSR_DE;
+#endif
+
+	/* Force enable debug interrupts when user space wants to debug */
+	if (vcpu->guest_debug) {
+#ifdef CONFIG_KVM_BOOKE_HV
+		/*
+		 * Since there is no shadow MSR, sync MSR_DE into the guest
+		 * visible MSR.
+		 */
+		vcpu->arch.shared->msr |= MSR_DE;
+#else
+		vcpu->arch.shadow_msr |= MSR_DE;
+		vcpu->arch.shared->msr &= ~MSR_DE;
+#endif
+	}
+}
+
 /*
  * Helper function for "full" MSR writes.  No need to call this if only
  * EE/CE/ME/DE/RI are changing.
@@ -150,6 +175,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
 	kvmppc_vcpu_sync_spe(vcpu);
 	kvmppc_vcpu_sync_fpu(vcpu);
+	kvmppc_vcpu_sync_debug(vcpu);
 }
 
 static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
@@ -655,10 +681,10 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
+	struct debug_reg debug;
 #ifdef CONFIG_PPC_FPU
-	unsigned int fpscr;
+	struct thread_fp_state fp;
 	int fpexc_mode;
-	u64 fpr[32];
 #endif
 
 	if (!vcpu->arch.sane) {
@@ -677,13 +703,13 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #ifdef CONFIG_PPC_FPU
 	/* Save userspace FPU state in stack */
 	enable_kernel_fp();
-	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
-	fpscr = current->thread.fpscr.val;
+	fp = current->thread.fp_state;
 	fpexc_mode = current->thread.fpexc_mode;
 
 	/* Restore guest FPU state to thread */
-	memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
-	current->thread.fpscr.val = vcpu->arch.fpscr;
+	memcpy(current->thread.fp_state.fpr, vcpu->arch.fpr,
+	       sizeof(vcpu->arch.fpr));
+	current->thread.fp_state.fpscr = vcpu->arch.fpscr;
 
 	/*
 	 * Since we can't trap on MSR_FP in GS-mode, we consider the guest
@@ -696,6 +722,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+	/* Switch to guest debug context */
+	debug = vcpu->arch.shadow_dbg_reg;
+	switch_booke_debug_regs(&debug);
+	debug = current->thread.debug;
+	current->thread.debug = vcpu->arch.shadow_dbg_reg;
+
 	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -703,18 +735,22 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* No need for kvm_guest_exit. It's done in handle_exit.
 	   We also get here with interrupts enabled. */
 
+	/* Switch back to user space debug context */
+	switch_booke_debug_regs(&debug);
+	current->thread.debug = debug;
+
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
 
 	vcpu->fpu_active = 0;
 
 	/* Save guest FPU state from thread */
-	memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
-	vcpu->arch.fpscr = current->thread.fpscr.val;
+	memcpy(vcpu->arch.fpr, current->thread.fp_state.fpr,
+	       sizeof(vcpu->arch.fpr));
+	vcpu->arch.fpscr = current->thread.fp_state.fpscr;
 
 	/* Restore userspace FPU state from stack */
-	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
-	current->thread.fpscr.val = fpscr;
+	current->thread.fp_state = fp;
 	current->thread.fpexc_mode = fpexc_mode;
 #endif
 
@@ -758,6 +794,30 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 }
 
+static int kvmppc_handle_debug(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	struct debug_reg *dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+	u32 dbsr = vcpu->arch.dbsr;
+
+	run->debug.arch.status = 0;
+	run->debug.arch.address = vcpu->arch.pc;
+
+	if (dbsr & (DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4)) {
+		run->debug.arch.status |= KVMPPC_DEBUG_BREAKPOINT;
+	} else {
+		if (dbsr & (DBSR_DAC1W | DBSR_DAC2W))
+			run->debug.arch.status |= KVMPPC_DEBUG_WATCH_WRITE;
+		else if (dbsr & (DBSR_DAC1R | DBSR_DAC2R))
+			run->debug.arch.status |= KVMPPC_DEBUG_WATCH_READ;
+		if (dbsr & (DBSR_DAC1R | DBSR_DAC1W))
+			run->debug.arch.address = dbg_reg->dac1;
+		else if (dbsr & (DBSR_DAC2R | DBSR_DAC2W))
+			run->debug.arch.address = dbg_reg->dac2;
+	}
+
+	return RESUME_HOST;
+}
+
 static void kvmppc_fill_pt_regs(struct pt_regs *regs)
 {
 	ulong r1, ip, msr, lr;
@@ -818,6 +878,11 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_CRITICAL:
 		unknown_exception(&regs);
 		break;
+	case BOOKE_INTERRUPT_DEBUG:
+		/* Save DBSR before preemption is enabled */
+		vcpu->arch.dbsr = mfspr(SPRN_DBSR);
+		kvmppc_clear_dbsr();
+		break;
 	}
 }
 
@@ -1135,18 +1200,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	case BOOKE_INTERRUPT_DEBUG: {
-		u32 dbsr;
-
-		vcpu->arch.pc = mfspr(SPRN_CSRR0);
-
-		/* clear IAC events in DBSR register */
-		dbsr = mfspr(SPRN_DBSR);
-		dbsr &= DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4;
-		mtspr(SPRN_DBSR, dbsr);
-
-		run->exit_reason = KVM_EXIT_DEBUG;
+		r = kvmppc_handle_debug(run, vcpu);
+		if (r == RESUME_HOST)
+			run->exit_reason = KVM_EXIT_DEBUG;
 		kvmppc_account_exit(vcpu, DEBUG_EXITS);
-		r = RESUME_HOST;
 		break;
 	}
 
@@ -1197,7 +1254,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, 0);
 
 #ifndef CONFIG_KVM_BOOKE_HV
-	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
+	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
 	vcpu->arch.shadow_pid = 1;
 	vcpu->arch.shared->msr = 0;
 #endif
@@ -1359,7 +1416,7 @@ static int set_sregs_arch206(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+int kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	sregs->u.e.features |= KVM_SREGS_E_IVOR;
 
@@ -1379,6 +1436,7 @@ void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
 	sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
 	sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+	return 0;
 }
 
 int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -1413,8 +1471,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 	get_sregs_base(vcpu, sregs);
 	get_sregs_arch206(vcpu, sregs);
-	kvmppc_core_get_sregs(vcpu, sregs);
-	return 0;
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
@@ -1433,7 +1490,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (ret < 0)
 		return ret;
 
-	return kvmppc_core_set_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
@@ -1441,7 +1498,6 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	int r = 0;
 	union kvmppc_one_reg val;
 	int size;
-	long int i;
 
 	size = one_reg_size(reg->id);
 	if (size > sizeof(val))
@@ -1449,16 +1505,24 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 	switch (reg->id) {
 	case KVM_REG_PPC_IAC1:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac1);
+		break;
 	case KVM_REG_PPC_IAC2:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac2);
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac3);
+		break;
 	case KVM_REG_PPC_IAC4:
-		i = reg->id - KVM_REG_PPC_IAC1;
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac[i]);
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac4);
 		break;
+#endif
 	case KVM_REG_PPC_DAC1:
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac1);
+		break;
 	case KVM_REG_PPC_DAC2:
-		i = reg->id - KVM_REG_PPC_DAC1;
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac[i]);
+		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac2);
 		break;
 	case KVM_REG_PPC_EPR: {
 		u32 epr = get_guest_epr(vcpu);
@@ -1477,10 +1541,13 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		val = get_reg_val(reg->id, vcpu->arch.tsr);
 		break;
 	case KVM_REG_PPC_DEBUG_INST:
-		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV);
+		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV_DEBUG);
+		break;
+	case KVM_REG_PPC_VRSAVE:
+		val = get_reg_val(reg->id, vcpu->arch.vrsave);
 		break;
 	default:
-		r = kvmppc_get_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1498,7 +1565,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	int r = 0;
 	union kvmppc_one_reg val;
 	int size;
-	long int i;
 
 	size = one_reg_size(reg->id);
 	if (size > sizeof(val))
@@ -1509,16 +1575,24 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 	switch (reg->id) {
 	case KVM_REG_PPC_IAC1:
+		vcpu->arch.dbg_reg.iac1 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_IAC2:
+		vcpu->arch.dbg_reg.iac2 = set_reg_val(reg->id, val);
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
+		vcpu->arch.dbg_reg.iac3 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_IAC4:
-		i = reg->id - KVM_REG_PPC_IAC1;
-		vcpu->arch.dbg_reg.iac[i] = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac4 = set_reg_val(reg->id, val);
 		break;
+#endif
 	case KVM_REG_PPC_DAC1:
+		vcpu->arch.dbg_reg.dac1 = set_reg_val(reg->id, val);
+		break;
 	case KVM_REG_PPC_DAC2:
-		i = reg->id - KVM_REG_PPC_DAC1;
-		vcpu->arch.dbg_reg.dac[i] = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.dac2 = set_reg_val(reg->id, val);
 		break;
 	case KVM_REG_PPC_EPR: {
 		u32 new_epr = set_reg_val(reg->id, val);
@@ -1552,20 +1626,17 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		kvmppc_set_tcr(vcpu, tcr);
 		break;
 	}
+	case KVM_REG_PPC_VRSAVE:
+		vcpu->arch.vrsave = set_reg_val(reg->id, val);
+		break;
 	default:
-		r = kvmppc_set_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-					 struct kvm_guest_debug *dbg)
-{
-	return -EINVAL;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -ENOTSUPP;
@@ -1590,12 +1661,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
 	return 0;
@@ -1671,6 +1742,157 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
+static int kvmppc_booke_add_breakpoint(struct debug_reg *dbg_reg,
+				       uint64_t addr, int index)
+{
+	switch (index) {
+	case 0:
+		dbg_reg->dbcr0 |= DBCR0_IAC1;
+		dbg_reg->iac1 = addr;
+		break;
+	case 1:
+		dbg_reg->dbcr0 |= DBCR0_IAC2;
+		dbg_reg->iac2 = addr;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case 2:
+		dbg_reg->dbcr0 |= DBCR0_IAC3;
+		dbg_reg->iac3 = addr;
+		break;
+	case 3:
+		dbg_reg->dbcr0 |= DBCR0_IAC4;
+		dbg_reg->iac4 = addr;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	dbg_reg->dbcr0 |= DBCR0_IDM;
+	return 0;
+}
+
+static int kvmppc_booke_add_watchpoint(struct debug_reg *dbg_reg, uint64_t addr,
+				       int type, int index)
+{
+	switch (index) {
+	case 0:
+		if (type & KVMPPC_DEBUG_WATCH_READ)
+			dbg_reg->dbcr0 |= DBCR0_DAC1R;
+		if (type & KVMPPC_DEBUG_WATCH_WRITE)
+			dbg_reg->dbcr0 |= DBCR0_DAC1W;
+		dbg_reg->dac1 = addr;
+		break;
+	case 1:
+		if (type & KVMPPC_DEBUG_WATCH_READ)
+			dbg_reg->dbcr0 |= DBCR0_DAC2R;
+		if (type & KVMPPC_DEBUG_WATCH_WRITE)
+			dbg_reg->dbcr0 |= DBCR0_DAC2W;
+		dbg_reg->dac2 = addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dbg_reg->dbcr0 |= DBCR0_IDM;
+	return 0;
+}
+void kvm_guest_protect_msr(struct kvm_vcpu *vcpu, ulong prot_bitmap, bool set)
+{
+	/* XXX: Add similar MSR protection for BookE-PR */
+#ifdef CONFIG_KVM_BOOKE_HV
+	BUG_ON(prot_bitmap & ~(MSRP_UCLEP | MSRP_DEP | MSRP_PMMP));
+	if (set) {
+		if (prot_bitmap & MSR_UCLE)
+			vcpu->arch.shadow_msrp |= MSRP_UCLEP;
+		if (prot_bitmap & MSR_DE)
+			vcpu->arch.shadow_msrp |= MSRP_DEP;
+		if (prot_bitmap & MSR_PMM)
+			vcpu->arch.shadow_msrp |= MSRP_PMMP;
+	} else {
+		if (prot_bitmap & MSR_UCLE)
+			vcpu->arch.shadow_msrp &= ~MSRP_UCLEP;
+		if (prot_bitmap & MSR_DE)
+			vcpu->arch.shadow_msrp &= ~MSRP_DEP;
+		if (prot_bitmap & MSR_PMM)
+			vcpu->arch.shadow_msrp &= ~MSRP_PMMP;
+	}
+#endif
+}
+
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					 struct kvm_guest_debug *dbg)
+{
+	struct debug_reg *dbg_reg;
+	int n, b = 0, w = 0;
+
+	if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
+		vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
+		vcpu->guest_debug = 0;
+		kvm_guest_protect_msr(vcpu, MSR_DE, false);
+		return 0;
+	}
+
+	kvm_guest_protect_msr(vcpu, MSR_DE, true);
+	vcpu->guest_debug = dbg->control;
+	vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
+	/* Set DBCR0_EDM in guest visible DBCR0 register. */
+	vcpu->arch.dbg_reg.dbcr0 = DBCR0_EDM;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vcpu->arch.shadow_dbg_reg.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+
+	/* Code below handles only HW breakpoints */
+	dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/*
+	 * On BookE-HV (e500mc) the guest is always executed with MSR.GS=1
+	 * DBCR1 and DBCR2 are set to trigger debug events when MSR.PR is 0
+	 */
+	dbg_reg->dbcr1 = 0;
+	dbg_reg->dbcr2 = 0;
+#else
+	/*
+	 * On BookE-PR (e500v2) the guest is always executed with MSR.PR=1
+	 * We set DBCR1 and DBCR2 to only trigger debug events when MSR.PR
+	 * is set.
+	 */
+	dbg_reg->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | DBCR1_IAC3US |
+			  DBCR1_IAC4US;
+	dbg_reg->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US;
+#endif
+
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+		return 0;
+
+	for (n = 0; n < (KVMPPC_BOOKE_IAC_NUM + KVMPPC_BOOKE_DAC_NUM); n++) {
+		uint64_t addr = dbg->arch.bp[n].addr;
+		uint32_t type = dbg->arch.bp[n].type;
+
+		if (type == KVMPPC_DEBUG_NONE)
+			continue;
+
+		if (type & !(KVMPPC_DEBUG_WATCH_READ |
+			     KVMPPC_DEBUG_WATCH_WRITE |
+			     KVMPPC_DEBUG_BREAKPOINT))
+			return -EINVAL;
+
+		if (type & KVMPPC_DEBUG_BREAKPOINT) {
+			/* Setting H/W breakpoint */
+			if (kvmppc_booke_add_breakpoint(dbg_reg, addr, b++))
+				return -EINVAL;
+		} else {
+			/* Setting H/W watchpoint */
+			if (kvmppc_booke_add_watchpoint(dbg_reg, addr,
+							type, w++))
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = smp_processor_id();
@@ -1681,6 +1903,44 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	current->thread.kvm_vcpu = NULL;
 	vcpu->cpu = -1;
+
+	/* Clear pending debug event in DBSR */
+	kvmppc_clear_dbsr();
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return kvm->arch.kvm_ops->init_vm(kvm);
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvm->arch.kvm_ops->destroy_vm(kvm);
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
 }
 
 int __init kvmppc_booke_init(void)
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 5fd1ba693579..09bfd9bc7cf8 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -99,6 +99,30 @@ enum int_class {
 
 void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
 
+extern void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				      unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn,
+					 ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn,
+					 ulong *spr_val);
+extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
+				       struct kvm_vcpu *vcpu,
+				       unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong *spr_val);
+extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
+				       struct kvm_vcpu *vcpu,
+				       unsigned int inst, int *advance);
+extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong spr_val);
+extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
+					  ulong *spr_val);
+
 /*
  * Load up guest vcpu FP state if it's needed.
  * It also set the MSR_FP in thread so that host know
@@ -129,4 +153,9 @@ static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
 		giveup_fpu(current);
 #endif
 }
+
+static inline void kvmppc_clear_dbsr(void)
+{
+	mtspr(SPRN_DBSR, mfspr(SPRN_DBSR));
+}
 #endif /* __KVM_BOOKE_H__ */
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index ce6b73c29612..497b142f651c 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -305,7 +305,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_booke_vcpu_load(vcpu, cpu);
 
@@ -313,7 +313,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_SPE
 	if (vcpu->arch.shadow_msr & MSR_SPE)
@@ -367,7 +367,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -388,9 +389,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 
 	kvmppc_get_sregs_ivor(vcpu, sregs);
 	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
+	return 0;
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_e500(struct kvm_vcpu *vcpu,
+				      struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int ret;
@@ -425,21 +428,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
+				   union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
+						     unsigned int id)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
 	struct kvm_vcpu *vcpu;
@@ -481,7 +485,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -492,15 +496,32 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_e500(struct kvm *kvm)
 {
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_e500(struct kvm *kvm)
 {
 }
 
+static struct kvmppc_ops kvm_ops_e500 = {
+	.get_sregs = kvmppc_core_get_sregs_e500,
+	.set_sregs = kvmppc_core_set_sregs_e500,
+	.get_one_reg = kvmppc_get_one_reg_e500,
+	.set_one_reg = kvmppc_set_one_reg_e500,
+	.vcpu_load   = kvmppc_core_vcpu_load_e500,
+	.vcpu_put    = kvmppc_core_vcpu_put_e500,
+	.vcpu_create = kvmppc_core_vcpu_create_e500,
+	.vcpu_free   = kvmppc_core_vcpu_free_e500,
+	.mmu_destroy  = kvmppc_mmu_destroy_e500,
+	.init_vm = kvmppc_core_init_vm_e500,
+	.destroy_vm = kvmppc_core_destroy_vm_e500,
+	.emulate_op = kvmppc_core_emulate_op_e500,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_e500,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_e500,
+};
+
 static int __init kvmppc_e500_init(void)
 {
 	int r, i;
@@ -512,11 +533,11 @@ static int __init kvmppc_e500_init(void)
 
 	r = kvmppc_core_check_processor_compat();
 	if (r)
-		return r;
+		goto err_out;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
 
 	/* copy extra E500 exception handlers */
 	ivor[0] = mfspr(SPRN_IVOR32);
@@ -534,11 +555,19 @@ static int __init kvmppc_e500_init(void)
 	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
 			   ivor[max_ivor] + handler_len);
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_e500.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500;
+
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_e500_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index c2e5e98453a6..4fd9650eb018 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -117,7 +117,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
 #define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
 #define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
 #define MAS2_ATTRIB_MASK \
-	  (MAS2_X0 | MAS2_X1)
+	  (MAS2_X0 | MAS2_X1 | MAS2_E | MAS2_G)
 #define MAS3_ATTRIB_MASK \
 	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
 	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index b10a01243abd..89b7f821f6c4 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -26,6 +26,7 @@
 #define XOP_TLBRE   946
 #define XOP_TLBWE   978
 #define XOP_TLBILX  18
+#define XOP_EHPRIV  270
 
 #ifdef CONFIG_KVM_E500MC
 static int dbell2prio(ulong param)
@@ -82,8 +83,28 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb)
 }
 #endif
 
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+static int kvmppc_e500_emul_ehpriv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (get_oc(inst)) {
+	case EHPRIV_OC_DEBUG:
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.address = vcpu->arch.pc;
+		run->debug.arch.status = 0;
+		kvmppc_account_exit(vcpu, DEBUG_EXITS);
+		emulated = EMULATE_EXIT_USER;
+		*advance = 0;
+		break;
+	default:
+		emulated = EMULATE_FAIL;
+	}
+	return emulated;
+}
+
+int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
 	int ra = get_ra(inst);
@@ -130,6 +151,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			emulated = kvmppc_e500_emul_tlbivax(vcpu, ea);
 			break;
 
+		case XOP_EHPRIV:
+			emulated = kvmppc_e500_emul_ehpriv(run, vcpu, inst,
+							   advance);
+			break;
+
 		default:
 			emulated = EMULATE_FAIL;
 		}
@@ -146,7 +172,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
+int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
@@ -237,7 +263,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
+int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 6d6f153b6c1d..ebca6b88ea5e 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -32,7 +32,7 @@
 #include <asm/kvm_ppc.h>
 
 #include "e500.h"
-#include "trace.h"
+#include "trace_booke.h"
 #include "timing.h"
 #include "e500_mmu_host.h"
 
@@ -536,7 +536,7 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
 	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu)
 {
 }
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index c65593abae8e..ecf2247b13be 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -32,10 +32,11 @@
 #include <asm/kvm_ppc.h>
 
 #include "e500.h"
-#include "trace.h"
 #include "timing.h"
 #include "e500_mmu_host.h"
 
+#include "trace_booke.h"
+
 #define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
 static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
@@ -253,6 +254,9 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 	ref->pfn = pfn;
 	ref->flags |= E500_TLB_VALID;
 
+	/* Mark the page accessed */
+	kvm_set_pfn_accessed(pfn);
+
 	if (tlbe_is_writable(gtlbe))
 		kvm_set_pfn_dirty(pfn);
 }
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 19c8379575f7..4132cd2fc171 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -110,7 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
 
 static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu);
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -147,7 +147,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvmppc_load_guest_fp(vcpu);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.eplc = mfspr(SPRN_EPLC);
 	vcpu->arch.epsc = mfspr(SPRN_EPSC);
@@ -204,7 +204,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_get_sregs_e500mc(struct kvm_vcpu *vcpu,
+					struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -224,10 +225,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.ivor_high[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
 	sregs->u.e.ivor_high[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
 
-	kvmppc_get_sregs_ivor(vcpu, sregs);
+	return kvmppc_get_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static int kvmppc_core_set_sregs_e500mc(struct kvm_vcpu *vcpu,
+					struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int ret;
@@ -260,21 +262,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	return kvmppc_set_sregs_ivor(vcpu, sregs);
 }
 
-int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
-			union kvmppc_one_reg *val)
+static int kvmppc_get_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
+			      union kvmppc_one_reg *val)
 {
 	int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
-		       union kvmppc_one_reg *val)
+static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
+			      union kvmppc_one_reg *val)
 {
 	int r = kvmppc_set_one_reg_e500_tlb(vcpu, id, val);
 	return r;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
+						       unsigned int id)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
 	struct kvm_vcpu *vcpu;
@@ -315,7 +318,7 @@ out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
@@ -325,7 +328,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_e500mc(struct kvm *kvm)
 {
 	int lpid;
 
@@ -337,27 +340,52 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_e500mc(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
 }
 
+static struct kvmppc_ops kvm_ops_e500mc = {
+	.get_sregs = kvmppc_core_get_sregs_e500mc,
+	.set_sregs = kvmppc_core_set_sregs_e500mc,
+	.get_one_reg = kvmppc_get_one_reg_e500mc,
+	.set_one_reg = kvmppc_set_one_reg_e500mc,
+	.vcpu_load   = kvmppc_core_vcpu_load_e500mc,
+	.vcpu_put    = kvmppc_core_vcpu_put_e500mc,
+	.vcpu_create = kvmppc_core_vcpu_create_e500mc,
+	.vcpu_free   = kvmppc_core_vcpu_free_e500mc,
+	.mmu_destroy  = kvmppc_mmu_destroy_e500,
+	.init_vm = kvmppc_core_init_vm_e500mc,
+	.destroy_vm = kvmppc_core_destroy_vm_e500mc,
+	.emulate_op = kvmppc_core_emulate_op_e500,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_e500,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_e500,
+};
+
 static int __init kvmppc_e500mc_init(void)
 {
 	int r;
 
 	r = kvmppc_booke_init();
 	if (r)
-		return r;
+		goto err_out;
 
 	kvmppc_init_lpid(64);
 	kvmppc_claim_lpid(0); /* host */
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_e500mc.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500mc;
+
+err_out:
+	return r;
 }
 
 static void __exit kvmppc_e500mc_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 751cd45f65a0..2f9a0873b44f 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -130,8 +130,8 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_PIR: break;
 
 	default:
-		emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
-						     spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mtspr(vcpu, sprn,
+								  spr_val);
 		if (emulated == EMULATE_FAIL)
 			printk(KERN_INFO "mtspr: unknown spr "
 				"0x%x\n", sprn);
@@ -191,8 +191,8 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		spr_val = kvmppc_get_dec(vcpu, get_tb());
 		break;
 	default:
-		emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
-						     &spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mfspr(vcpu, sprn,
+								  &spr_val);
 		if (unlikely(emulated == EMULATE_FAIL)) {
 			printk(KERN_INFO "mfspr: unknown spr "
 				"0x%x\n", sprn);
@@ -464,7 +464,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	if (emulated == EMULATE_FAIL) {
-		emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_op(run, vcpu, inst,
+							       &advance);
 		if (emulated == EMULATE_AGAIN) {
 			advance = 0;
 		} else if (emulated == EMULATE_FAIL) {
@@ -483,3 +484,4 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	return emulated;
 }
+EXPORT_SYMBOL_GPL(kvmppc_emulate_instruction);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 07c0106fab76..9ae97686e9f4 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/module.h>
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
@@ -39,6 +40,12 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
+struct kvmppc_ops *kvmppc_hv_ops;
+EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
+struct kvmppc_ops *kvmppc_pr_ops;
+EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
+
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	return !!(v->arch.pending_exceptions) ||
@@ -50,7 +57,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-#ifndef CONFIG_KVM_BOOK3S_64_HV
 /*
  * Common checks before entering the guest world.  Call with interrupts
  * disabled.
@@ -125,7 +131,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	return r;
 }
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
@@ -179,6 +185,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvmppc_kvm_pv);
 
 int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 {
@@ -192,11 +199,9 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 	if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
 		goto out;
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
 	/* HV KVM can only do PAPR mode for now */
-	if (!vcpu->arch.papr_enabled)
+	if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm))
 		goto out;
-#endif
 
 #ifdef CONFIG_KVM_BOOKE_HV
 	if (!cpu_has_feature(CPU_FTR_EMB_HV))
@@ -209,6 +214,7 @@ out:
 	vcpu->arch.sane = r;
 	return r ? 0 : -EINVAL;
 }
+EXPORT_SYMBOL_GPL(kvmppc_sanity_check);
 
 int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
@@ -243,6 +249,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);
 
 int kvm_arch_hardware_enable(void *garbage)
 {
@@ -269,10 +276,35 @@ void kvm_arch_check_processor_compat(void *rtn)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	if (type)
-		return -EINVAL;
-
+	struct kvmppc_ops *kvm_ops = NULL;
+	/*
+	 * if we have both HV and PR enabled, default is HV
+	 */
+	if (type == 0) {
+		if (kvmppc_hv_ops)
+			kvm_ops = kvmppc_hv_ops;
+		else
+			kvm_ops = kvmppc_pr_ops;
+		if (!kvm_ops)
+			goto err_out;
+	} else	if (type == KVM_VM_PPC_HV) {
+		if (!kvmppc_hv_ops)
+			goto err_out;
+		kvm_ops = kvmppc_hv_ops;
+	} else if (type == KVM_VM_PPC_PR) {
+		if (!kvmppc_pr_ops)
+			goto err_out;
+		kvm_ops = kvmppc_pr_ops;
+	} else
+		goto err_out;
+
+	if (kvm_ops->owner && !try_module_get(kvm_ops->owner))
+		return -ENOENT;
+
+	kvm->arch.kvm_ops = kvm_ops;
 	return kvmppc_core_init_vm(kvm);
+err_out:
+	return -EINVAL;
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -292,6 +324,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvmppc_core_destroy_vm(kvm);
 
 	mutex_unlock(&kvm->lock);
+
+	/* drop the module reference */
+	module_put(kvm->arch.kvm_ops->owner);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
@@ -301,6 +336,10 @@ void kvm_arch_sync_events(struct kvm *kvm)
 int kvm_dev_ioctl_check_extension(long ext)
 {
 	int r;
+	/* FIXME!!
+	 * Should some of this be vm ioctl ? is it possible now ?
+	 */
+	int hv_enabled = kvmppc_hv_ops ? 1 : 0;
 
 	switch (ext) {
 #ifdef CONFIG_BOOKE
@@ -320,22 +359,26 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_DEVICE_CTRL:
 		r = 1;
 		break;
-#ifndef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
 #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB:
 #endif
-#ifdef CONFIG_KVM_MPIC
-	case KVM_CAP_IRQ_MPIC:
-#endif
-		r = 1;
+		/* We support this only for PR */
+		r = !hv_enabled;
 		break;
+#ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
 #endif
+#ifdef CONFIG_KVM_MPIC
+	case KVM_CAP_IRQ_MPIC:
+		r = 1;
+		break;
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_PPC_ALLOC_HTAB:
@@ -346,32 +389,37 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
-		r = threads_per_core;
+		if (hv_enabled)
+			r = threads_per_core;
+		else
+			r = 0;
 		break;
 	case KVM_CAP_PPC_RMA:
-		r = 1;
+		r = hv_enabled;
 		/* PPC970 requires an RMA */
-		if (cpu_has_feature(CPU_FTR_ARCH_201))
+		if (r && cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
-		r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		if (hv_enabled)
+			r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+		else
+			r = 0;
 #elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 		r = 1;
 #else
 		r = 0;
-		break;
 #endif
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+		break;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
-		r = 1;
+		r = hv_enabled;
 		break;
 #endif
-		break;
 	case KVM_CAP_NR_VCPUS:
 		/*
 		 * Recommending a number of CPUs is somewhat arbitrary; we
@@ -379,11 +427,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 		 * will have secondary threads "offline"), and for other KVM
 		 * implementations just count online CPUs.
 		 */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
-		r = num_present_cpus();
-#else
-		r = num_online_cpus();
-#endif
+		if (hv_enabled)
+			r = num_present_cpus();
+		else
+			r = num_online_cpus();
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
@@ -407,15 +454,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
-	kvmppc_core_free_memslot(free, dont);
+	kvmppc_core_free_memslot(kvm, free, dont);
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
-	return kvmppc_core_create_memslot(slot, npages);
+	return kvmppc_core_create_memslot(kvm, slot, npages);
 }
 
 void kvm_arch_memslots_updated(struct kvm *kvm)
@@ -659,6 +707,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_handle_load);
 
 /* Same as above, but sign extends */
 int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
@@ -720,6 +769,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	return EMULATE_DO_MMIO;
 }
+EXPORT_SYMBOL_GPL(kvmppc_handle_store);
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
@@ -1024,52 +1074,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
 		goto out;
 	}
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-#ifdef CONFIG_KVM_BOOK3S_64_HV
-	case KVM_ALLOCATE_RMA: {
-		struct kvm_allocate_rma rma;
-		struct kvm *kvm = filp->private_data;
-
-		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
-		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
-			r = -EFAULT;
-		break;
-	}
-
-	case KVM_PPC_ALLOCATE_HTAB: {
-		u32 htab_order;
-
-		r = -EFAULT;
-		if (get_user(htab_order, (u32 __user *)argp))
-			break;
-		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
-		if (r)
-			break;
-		r = -EFAULT;
-		if (put_user(htab_order, (u32 __user *)argp))
-			break;
-		r = 0;
-		break;
-	}
-
-	case KVM_PPC_GET_HTAB_FD: {
-		struct kvm_get_htab_fd ghf;
-
-		r = -EFAULT;
-		if (copy_from_user(&ghf, argp, sizeof(ghf)))
-			break;
-		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
-		break;
-	}
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
-
-#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_PPC_GET_SMMU_INFO: {
 		struct kvm_ppc_smmu_info info;
+		struct kvm *kvm = filp->private_data;
 
 		memset(&info, 0, sizeof(info));
-		r = kvm_vm_ioctl_get_smmu_info(kvm, &info);
+		r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info);
 		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
 			r = -EFAULT;
 		break;
@@ -1080,11 +1090,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
 		break;
 	}
-#endif /* CONFIG_PPC_BOOK3S_64 */
+	default: {
+		struct kvm *kvm = filp->private_data;
+		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
+	}
+#else /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
+#endif
 	}
-
 out:
 	return r;
 }
@@ -1106,22 +1120,26 @@ long kvmppc_alloc_lpid(void)
 
 	return lpid;
 }
+EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid);
 
 void kvmppc_claim_lpid(long lpid)
 {
 	set_bit(lpid, lpid_inuse);
 }
+EXPORT_SYMBOL_GPL(kvmppc_claim_lpid);
 
 void kvmppc_free_lpid(long lpid)
 {
 	clear_bit(lpid, lpid_inuse);
 }
+EXPORT_SYMBOL_GPL(kvmppc_free_lpid);
 
 void kvmppc_init_lpid(unsigned long nr_lpids_param)
 {
 	nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
 	memset(lpid_inuse, 0, sizeof(lpid_inuse));
 }
+EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
 
 int kvm_arch_init(void *opaque)
 {
@@ -1130,4 +1148,5 @@ int kvm_arch_init(void *opaque)
 
 void kvm_arch_exit(void)
 {
+
 }
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index e326489a5420..2e0e67ef3544 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -31,126 +31,6 @@ TRACE_EVENT(kvm_ppc_instr,
 		  __entry->inst, __entry->pc, __entry->emulate)
 );
 
-#ifdef CONFIG_PPC_BOOK3S
-#define kvm_trace_symbol_exit \
-	{0x100, "SYSTEM_RESET"}, \
-	{0x200, "MACHINE_CHECK"}, \
-	{0x300, "DATA_STORAGE"}, \
-	{0x380, "DATA_SEGMENT"}, \
-	{0x400, "INST_STORAGE"}, \
-	{0x480, "INST_SEGMENT"}, \
-	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
-	{0x502, "EXTERNAL_HV"}, \
-	{0x600, "ALIGNMENT"}, \
-	{0x700, "PROGRAM"}, \
-	{0x800, "FP_UNAVAIL"}, \
-	{0x900, "DECREMENTER"}, \
-	{0x980, "HV_DECREMENTER"}, \
-	{0xc00, "SYSCALL"}, \
-	{0xd00, "TRACE"}, \
-	{0xe00, "H_DATA_STORAGE"}, \
-	{0xe20, "H_INST_STORAGE"}, \
-	{0xe40, "H_EMUL_ASSIST"}, \
-	{0xf00, "PERFMON"}, \
-	{0xf20, "ALTIVEC"}, \
-	{0xf40, "VSX"}
-#else
-#define kvm_trace_symbol_exit \
-	{0, "CRITICAL"}, \
-	{1, "MACHINE_CHECK"}, \
-	{2, "DATA_STORAGE"}, \
-	{3, "INST_STORAGE"}, \
-	{4, "EXTERNAL"}, \
-	{5, "ALIGNMENT"}, \
-	{6, "PROGRAM"}, \
-	{7, "FP_UNAVAIL"}, \
-	{8, "SYSCALL"}, \
-	{9, "AP_UNAVAIL"}, \
-	{10, "DECREMENTER"}, \
-	{11, "FIT"}, \
-	{12, "WATCHDOG"}, \
-	{13, "DTLB_MISS"}, \
-	{14, "ITLB_MISS"}, \
-	{15, "DEBUG"}, \
-	{32, "SPE_UNAVAIL"}, \
-	{33, "SPE_FP_DATA"}, \
-	{34, "SPE_FP_ROUND"}, \
-	{35, "PERFORMANCE_MONITOR"}, \
-	{36, "DOORBELL"}, \
-	{37, "DOORBELL_CRITICAL"}, \
-	{38, "GUEST_DBELL"}, \
-	{39, "GUEST_DBELL_CRIT"}, \
-	{40, "HV_SYSCALL"}, \
-	{41, "HV_PRIV"}
-#endif
-
-TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
-	TP_ARGS(exit_nr, vcpu),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	exit_nr		)
-		__field(	unsigned long,	pc		)
-		__field(	unsigned long,	msr		)
-		__field(	unsigned long,	dar		)
-#ifdef CONFIG_KVM_BOOK3S_PR
-		__field(	unsigned long,	srr1		)
-#endif
-		__field(	unsigned long,	last_inst	)
-	),
-
-	TP_fast_assign(
-#ifdef CONFIG_KVM_BOOK3S_PR
-		struct kvmppc_book3s_shadow_vcpu *svcpu;
-#endif
-		__entry->exit_nr	= exit_nr;
-		__entry->pc		= kvmppc_get_pc(vcpu);
-		__entry->dar		= kvmppc_get_fault_dar(vcpu);
-		__entry->msr		= vcpu->arch.shared->msr;
-#ifdef CONFIG_KVM_BOOK3S_PR
-		svcpu = svcpu_get(vcpu);
-		__entry->srr1		= svcpu->shadow_srr1;
-		svcpu_put(svcpu);
-#endif
-		__entry->last_inst	= vcpu->arch.last_inst;
-	),
-
-	TP_printk("exit=%s"
-		" | pc=0x%lx"
-		" | msr=0x%lx"
-		" | dar=0x%lx"
-#ifdef CONFIG_KVM_BOOK3S_PR
-		" | srr1=0x%lx"
-#endif
-		" | last_inst=0x%lx"
-		,
-		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
-		__entry->pc,
-		__entry->msr,
-		__entry->dar,
-#ifdef CONFIG_KVM_BOOK3S_PR
-		__entry->srr1,
-#endif
-		__entry->last_inst
-		)
-);
-
-TRACE_EVENT(kvm_unmap_hva,
-	TP_PROTO(unsigned long hva),
-	TP_ARGS(hva),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long,	hva		)
-	),
-
-	TP_fast_assign(
-		__entry->hva		= hva;
-	),
-
-	TP_printk("unmap hva 0x%lx\n", __entry->hva)
-);
-
 TRACE_EVENT(kvm_stlb_inval,
 	TP_PROTO(unsigned int stlb_index),
 	TP_ARGS(stlb_index),
@@ -236,315 +116,6 @@ TRACE_EVENT(kvm_check_requests,
 		__entry->cpu_nr, __entry->requests)
 );
 
-
-/*************************************************************************
- *                         Book3S trace points                           *
- *************************************************************************/
-
-#ifdef CONFIG_KVM_BOOK3S_PR
-
-TRACE_EVENT(kvm_book3s_reenter,
-	TP_PROTO(int r, struct kvm_vcpu *vcpu),
-	TP_ARGS(r, vcpu),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	r		)
-		__field(	unsigned long,	pc		)
-	),
-
-	TP_fast_assign(
-		__entry->r		= r;
-		__entry->pc		= kvmppc_get_pc(vcpu);
-	),
-
-	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
-);
-
-#ifdef CONFIG_PPC_BOOK3S_64
-
-TRACE_EVENT(kvm_book3s_64_mmu_map,
-	TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
-		 struct kvmppc_pte *orig_pte),
-	TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
-
-	TP_STRUCT__entry(
-		__field(	unsigned char,		flag_w		)
-		__field(	unsigned char,		flag_x		)
-		__field(	unsigned long,		eaddr		)
-		__field(	unsigned long,		hpteg		)
-		__field(	unsigned long,		va		)
-		__field(	unsigned long long,	vpage		)
-		__field(	unsigned long,		hpaddr		)
-	),
-
-	TP_fast_assign(
-		__entry->flag_w	= ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
-		__entry->flag_x	= (rflags & HPTE_R_N) ? '-' : 'x';
-		__entry->eaddr	= orig_pte->eaddr;
-		__entry->hpteg	= hpteg;
-		__entry->va	= va;
-		__entry->vpage	= orig_pte->vpage;
-		__entry->hpaddr	= hpaddr;
-	),
-
-	TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
-		  __entry->flag_w, __entry->flag_x, __entry->eaddr,
-		  __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
-);
-
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-TRACE_EVENT(kvm_book3s_mmu_map,
-	TP_PROTO(struct hpte_cache *pte),
-	TP_ARGS(pte),
-
-	TP_STRUCT__entry(
-		__field(	u64,		host_vpn	)
-		__field(	u64,		pfn		)
-		__field(	ulong,		eaddr		)
-		__field(	u64,		vpage		)
-		__field(	ulong,		raddr		)
-		__field(	int,		flags		)
-	),
-
-	TP_fast_assign(
-		__entry->host_vpn	= pte->host_vpn;
-		__entry->pfn		= pte->pfn;
-		__entry->eaddr		= pte->pte.eaddr;
-		__entry->vpage		= pte->pte.vpage;
-		__entry->raddr		= pte->pte.raddr;
-		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
-					  (pte->pte.may_write ? 0x2 : 0) |
-					  (pte->pte.may_execute ? 0x1 : 0);
-	),
-
-	TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
-		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
-		  __entry->vpage, __entry->raddr, __entry->flags)
-);
-
-TRACE_EVENT(kvm_book3s_mmu_invalidate,
-	TP_PROTO(struct hpte_cache *pte),
-	TP_ARGS(pte),
-
-	TP_STRUCT__entry(
-		__field(	u64,		host_vpn	)
-		__field(	u64,		pfn		)
-		__field(	ulong,		eaddr		)
-		__field(	u64,		vpage		)
-		__field(	ulong,		raddr		)
-		__field(	int,		flags		)
-	),
-
-	TP_fast_assign(
-		__entry->host_vpn	= pte->host_vpn;
-		__entry->pfn		= pte->pfn;
-		__entry->eaddr		= pte->pte.eaddr;
-		__entry->vpage		= pte->pte.vpage;
-		__entry->raddr		= pte->pte.raddr;
-		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
-					  (pte->pte.may_write ? 0x2 : 0) |
-					  (pte->pte.may_execute ? 0x1 : 0);
-	),
-
-	TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
-		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
-		  __entry->vpage, __entry->raddr, __entry->flags)
-);
-
-TRACE_EVENT(kvm_book3s_mmu_flush,
-	TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
-		 unsigned long long p2),
-	TP_ARGS(type, vcpu, p1, p2),
-
-	TP_STRUCT__entry(
-		__field(	int,			count		)
-		__field(	unsigned long long,	p1		)
-		__field(	unsigned long long,	p2		)
-		__field(	const char *,		type		)
-	),
-
-	TP_fast_assign(
-		__entry->count		= to_book3s(vcpu)->hpte_cache_count;
-		__entry->p1		= p1;
-		__entry->p2		= p2;
-		__entry->type		= type;
-	),
-
-	TP_printk("Flush %d %sPTEs: %llx - %llx",
-		  __entry->count, __entry->type, __entry->p1, __entry->p2)
-);
-
-TRACE_EVENT(kvm_book3s_slb_found,
-	TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
-	TP_ARGS(gvsid, hvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long long,	gvsid		)
-		__field(	unsigned long long,	hvsid		)
-	),
-
-	TP_fast_assign(
-		__entry->gvsid		= gvsid;
-		__entry->hvsid		= hvsid;
-	),
-
-	TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
-);
-
-TRACE_EVENT(kvm_book3s_slb_fail,
-	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
-	TP_ARGS(sid_map_mask, gvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned short,		sid_map_mask	)
-		__field(	unsigned long long,	gvsid		)
-	),
-
-	TP_fast_assign(
-		__entry->sid_map_mask	= sid_map_mask;
-		__entry->gvsid		= gvsid;
-	),
-
-	TP_printk("%x/%x: %llx", __entry->sid_map_mask,
-		  SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
-);
-
-TRACE_EVENT(kvm_book3s_slb_map,
-	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
-		 unsigned long long hvsid),
-	TP_ARGS(sid_map_mask, gvsid, hvsid),
-
-	TP_STRUCT__entry(
-		__field(	unsigned short,		sid_map_mask	)
-		__field(	unsigned long long,	guest_vsid	)
-		__field(	unsigned long long,	host_vsid	)
-	),
-
-	TP_fast_assign(
-		__entry->sid_map_mask	= sid_map_mask;
-		__entry->guest_vsid	= gvsid;
-		__entry->host_vsid	= hvsid;
-	),
-
-	TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
-		  __entry->guest_vsid, __entry->host_vsid)
-);
-
-TRACE_EVENT(kvm_book3s_slbmte,
-	TP_PROTO(u64 slb_vsid, u64 slb_esid),
-	TP_ARGS(slb_vsid, slb_esid),
-
-	TP_STRUCT__entry(
-		__field(	u64,	slb_vsid	)
-		__field(	u64,	slb_esid	)
-	),
-
-	TP_fast_assign(
-		__entry->slb_vsid	= slb_vsid;
-		__entry->slb_esid	= slb_esid;
-	),
-
-	TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
-);
-
-#endif /* CONFIG_PPC_BOOK3S */
-
-
-/*************************************************************************
- *                         Book3E trace points                           *
- *************************************************************************/
-
-#ifdef CONFIG_BOOKE
-
-TRACE_EVENT(kvm_booke206_stlb_write,
-	TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
-	TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	mas0		)
-		__field(	__u32,	mas8		)
-		__field(	__u32,	mas1		)
-		__field(	__u64,	mas2		)
-		__field(	__u64,	mas7_3		)
-	),
-
-	TP_fast_assign(
-		__entry->mas0		= mas0;
-		__entry->mas8		= mas8;
-		__entry->mas1		= mas1;
-		__entry->mas2		= mas2;
-		__entry->mas7_3		= mas7_3;
-	),
-
-	TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
-		__entry->mas0, __entry->mas8, __entry->mas1,
-		__entry->mas2, __entry->mas7_3)
-);
-
-TRACE_EVENT(kvm_booke206_gtlb_write,
-	TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
-	TP_ARGS(mas0, mas1, mas2, mas7_3),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	mas0		)
-		__field(	__u32,	mas1		)
-		__field(	__u64,	mas2		)
-		__field(	__u64,	mas7_3		)
-	),
-
-	TP_fast_assign(
-		__entry->mas0		= mas0;
-		__entry->mas1		= mas1;
-		__entry->mas2		= mas2;
-		__entry->mas7_3		= mas7_3;
-	),
-
-	TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
-		__entry->mas0, __entry->mas1,
-		__entry->mas2, __entry->mas7_3)
-);
-
-TRACE_EVENT(kvm_booke206_ref_release,
-	TP_PROTO(__u64 pfn, __u32 flags),
-	TP_ARGS(pfn, flags),
-
-	TP_STRUCT__entry(
-		__field(	__u64,	pfn		)
-		__field(	__u32,	flags		)
-	),
-
-	TP_fast_assign(
-		__entry->pfn		= pfn;
-		__entry->flags		= flags;
-	),
-
-	TP_printk("pfn=%llx flags=%x",
-		__entry->pfn, __entry->flags)
-);
-
-TRACE_EVENT(kvm_booke_queue_irqprio,
-	TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority),
-	TP_ARGS(vcpu, priority),
-
-	TP_STRUCT__entry(
-		__field(	__u32,	cpu_nr		)
-		__field(	__u32,	priority		)
-		__field(	unsigned long,	pending		)
-	),
-
-	TP_fast_assign(
-		__entry->cpu_nr		= vcpu->vcpu_id;
-		__entry->priority	= priority;
-		__entry->pending	= vcpu->arch.pending_exceptions;
-	),
-
-	TP_printk("vcpu=%x prio=%x pending=%lx",
-		__entry->cpu_nr, __entry->priority, __entry->pending)
-);
-
-#endif
-
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h
new file mode 100644
index 000000000000..f7537cf26ce7
--- /dev/null
+++ b/arch/powerpc/kvm/trace_booke.h
@@ -0,0 +1,177 @@
+#if !defined(_TRACE_KVM_BOOKE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_BOOKE_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm_booke
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_booke
+
+#define kvm_trace_symbol_exit \
+	{0, "CRITICAL"}, \
+	{1, "MACHINE_CHECK"}, \
+	{2, "DATA_STORAGE"}, \
+	{3, "INST_STORAGE"}, \
+	{4, "EXTERNAL"}, \
+	{5, "ALIGNMENT"}, \
+	{6, "PROGRAM"}, \
+	{7, "FP_UNAVAIL"}, \
+	{8, "SYSCALL"}, \
+	{9, "AP_UNAVAIL"}, \
+	{10, "DECREMENTER"}, \
+	{11, "FIT"}, \
+	{12, "WATCHDOG"}, \
+	{13, "DTLB_MISS"}, \
+	{14, "ITLB_MISS"}, \
+	{15, "DEBUG"}, \
+	{32, "SPE_UNAVAIL"}, \
+	{33, "SPE_FP_DATA"}, \
+	{34, "SPE_FP_ROUND"}, \
+	{35, "PERFORMANCE_MONITOR"}, \
+	{36, "DOORBELL"}, \
+	{37, "DOORBELL_CRITICAL"}, \
+	{38, "GUEST_DBELL"}, \
+	{39, "GUEST_DBELL_CRIT"}, \
+	{40, "HV_SYSCALL"}, \
+	{41, "HV_PRIV"}
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+		__field(	unsigned long,	last_inst	)
+	),
+
+	TP_fast_assign(
+		__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->last_inst	= vcpu->arch.last_inst;
+	),
+
+	TP_printk("exit=%s"
+		" | pc=0x%lx"
+		" | msr=0x%lx"
+		" | dar=0x%lx"
+		" | last_inst=0x%lx"
+		,
+		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
+		__entry->pc,
+		__entry->msr,
+		__entry->dar,
+		__entry->last_inst
+		)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("unmap hva 0x%lx\n", __entry->hva)
+);
+
+TRACE_EVENT(kvm_booke206_stlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas8		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas8		= mas8;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas8, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_gtlb_write,
+	TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
+	TP_ARGS(mas0, mas1, mas2, mas7_3),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	mas0		)
+		__field(	__u32,	mas1		)
+		__field(	__u64,	mas2		)
+		__field(	__u64,	mas7_3		)
+	),
+
+	TP_fast_assign(
+		__entry->mas0		= mas0;
+		__entry->mas1		= mas1;
+		__entry->mas2		= mas2;
+		__entry->mas7_3		= mas7_3;
+	),
+
+	TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
+		__entry->mas0, __entry->mas1,
+		__entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_ref_release,
+	TP_PROTO(__u64 pfn, __u32 flags),
+	TP_ARGS(pfn, flags),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	pfn		)
+		__field(	__u32,	flags		)
+	),
+
+	TP_fast_assign(
+		__entry->pfn		= pfn;
+		__entry->flags		= flags;
+	),
+
+	TP_printk("pfn=%llx flags=%x",
+		__entry->pfn, __entry->flags)
+);
+
+TRACE_EVENT(kvm_booke_queue_irqprio,
+	TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority),
+	TP_ARGS(vcpu, priority),
+
+	TP_STRUCT__entry(
+		__field(	__u32,	cpu_nr		)
+		__field(	__u32,	priority		)
+		__field(	unsigned long,	pending		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu_nr		= vcpu->vcpu_id;
+		__entry->priority	= priority;
+		__entry->pending	= vcpu->arch.pending_exceptions;
+	),
+
+	TP_printk("vcpu=%x prio=%x pending=%lx",
+		__entry->cpu_nr, __entry->priority, __entry->pending)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h
new file mode 100644
index 000000000000..8b22e4748344
--- /dev/null
+++ b/arch/powerpc/kvm/trace_pr.h
@@ -0,0 +1,297 @@
+
+#if !defined(_TRACE_KVM_PR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_PR_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm_pr
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_pr
+
+#define kvm_trace_symbol_exit \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+
+TRACE_EVENT(kvm_book3s_reenter,
+	TP_PROTO(int r, struct kvm_vcpu *vcpu),
+	TP_ARGS(r, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	r		)
+		__field(	unsigned long,	pc		)
+	),
+
+	TP_fast_assign(
+		__entry->r		= r;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+	),
+
+	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
+);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+
+TRACE_EVENT(kvm_book3s_64_mmu_map,
+	TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
+		 struct kvmppc_pte *orig_pte),
+	TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
+
+	TP_STRUCT__entry(
+		__field(	unsigned char,		flag_w		)
+		__field(	unsigned char,		flag_x		)
+		__field(	unsigned long,		eaddr		)
+		__field(	unsigned long,		hpteg		)
+		__field(	unsigned long,		va		)
+		__field(	unsigned long long,	vpage		)
+		__field(	unsigned long,		hpaddr		)
+	),
+
+	TP_fast_assign(
+		__entry->flag_w	= ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
+		__entry->flag_x	= (rflags & HPTE_R_N) ? '-' : 'x';
+		__entry->eaddr	= orig_pte->eaddr;
+		__entry->hpteg	= hpteg;
+		__entry->va	= va;
+		__entry->vpage	= orig_pte->vpage;
+		__entry->hpaddr	= hpaddr;
+	),
+
+	TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
+		  __entry->flag_w, __entry->flag_x, __entry->eaddr,
+		  __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
+);
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+TRACE_EVENT(kvm_book3s_mmu_map,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_vpn	)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_vpn	= pte->host_vpn;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_invalidate,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_vpn	)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_vpn	= pte->host_vpn;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_vpn, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
+TRACE_EVENT(kvm_book3s_mmu_flush,
+	TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
+		 unsigned long long p2),
+	TP_ARGS(type, vcpu, p1, p2),
+
+	TP_STRUCT__entry(
+		__field(	int,			count		)
+		__field(	unsigned long long,	p1		)
+		__field(	unsigned long long,	p2		)
+		__field(	const char *,		type		)
+	),
+
+	TP_fast_assign(
+		__entry->count		= to_book3s(vcpu)->hpte_cache_count;
+		__entry->p1		= p1;
+		__entry->p2		= p2;
+		__entry->type		= type;
+	),
+
+	TP_printk("Flush %d %sPTEs: %llx - %llx",
+		  __entry->count, __entry->type, __entry->p1, __entry->p2)
+);
+
+TRACE_EVENT(kvm_book3s_slb_found,
+	TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
+	TP_ARGS(gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long long,	gvsid		)
+		__field(	unsigned long long,	hvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->gvsid		= gvsid;
+		__entry->hvsid		= hvsid;
+	),
+
+	TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_fail,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
+	TP_ARGS(sid_map_mask, gvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	gvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->gvsid		= gvsid;
+	),
+
+	TP_printk("%x/%x: %llx", __entry->sid_map_mask,
+		  SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_map,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
+		 unsigned long long hvsid),
+	TP_ARGS(sid_map_mask, gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	guest_vsid	)
+		__field(	unsigned long long,	host_vsid	)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->guest_vsid	= gvsid;
+		__entry->host_vsid	= hvsid;
+	),
+
+	TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
+		  __entry->guest_vsid, __entry->host_vsid)
+);
+
+TRACE_EVENT(kvm_book3s_slbmte,
+	TP_PROTO(u64 slb_vsid, u64 slb_esid),
+	TP_ARGS(slb_vsid, slb_esid),
+
+	TP_STRUCT__entry(
+		__field(	u64,	slb_vsid	)
+		__field(	u64,	slb_esid	)
+	),
+
+	TP_fast_assign(
+		__entry->slb_vsid	= slb_vsid;
+		__entry->slb_esid	= slb_esid;
+	),
+
+	TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
+);
+
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+		__field(	unsigned long,	srr1		)
+		__field(	unsigned long,	last_inst	)
+	),
+
+	TP_fast_assign(
+		__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->srr1		= vcpu->arch.shadow_srr1;
+		__entry->last_inst	= vcpu->arch.last_inst;
+	),
+
+	TP_printk("exit=%s"
+		" | pc=0x%lx"
+		" | msr=0x%lx"
+		" | dar=0x%lx"
+		" | srr1=0x%lx"
+		" | last_inst=0x%lx"
+		,
+		__print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit),
+		__entry->pc,
+		__entry->msr,
+		__entry->dar,
+		__entry->srr1,
+		__entry->last_inst
+		)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("unmap hva 0x%lx\n", __entry->hva)
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
author	Eric Paris <eparis@redhat.com>	2014-03-07 17:41:32 +0100
committer	Eric Paris <eparis@redhat.com>	2014-03-07 17:41:32 +0100
commit	b7d3622a39fde7658170b7f3cf6c6889bb8db30d (patch)
tree	64f4e781ecb2a85d675e234072b988560bcd25f1 /arch/powerpc/kvm
parent	audit: whitespace fix in kernel-parameters.txt (diff)
parent	Linux 3.13 (diff)
download	linux-b7d3622a39fde7658170b7f3cf6c6889bb8db30d.tar.xz linux-b7d3622a39fde7658170b7f3cf6c6889bb8db30d.zip