Merge branch 'kvm-ppc-next' of git://github.com/agraf/linux-2.6 into kvm-queue

Conflicts:
	arch/powerpc/kvm/book3s_hv_rmhandlers.S
	arch/powerpc/kvm/booke.c

25 files changed, 1260 insertions, 903 deletions

diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 93221e87b911..9cb4b0a36031 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -21,6 +21,8 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/export.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -231,3 +233,5 @@ static void __exit kvmppc_44x_exit(void)
 
 module_init(kvmppc_44x_init);
 module_exit(kvmppc_44x_exit);
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 8912608b7e1b..94e597e6f15c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -18,6 +18,8 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -575,10 +577,10 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = reg->id - KVM_REG_PPC_FPR0;
-			val = get_reg_val(reg->id, vcpu->arch.fpr[i]);
+			val = get_reg_val(reg->id, VCPU_FPR(vcpu, i));
 			break;
 		case KVM_REG_PPC_FPSCR:
-			val = get_reg_val(reg->id, vcpu->arch.fpscr);
+			val = get_reg_val(reg->id, vcpu->arch.fp.fpscr);
 			break;
 #ifdef CONFIG_ALTIVEC
 		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
@@ -586,19 +588,30 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0];
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
 			break;
 		case KVM_REG_PPC_VRSAVE:
 			val = get_reg_val(reg->id, vcpu->arch.vrsave);
 			break;
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
+			if (cpu_has_feature(CPU_FTR_VSX)) {
+				long int i = reg->id - KVM_REG_PPC_VSR0;
+				val.vsxval[0] = vcpu->arch.fp.fpr[i][0];
+				val.vsxval[1] = vcpu->arch.fp.fpr[i][1];
+			} else {
+				r = -ENXIO;
+			}
+			break;
+#endif /* CONFIG_VSX */
 		case KVM_REG_PPC_DEBUG_INST: {
 			u32 opcode = INS_TW;
 			r = copy_to_user((u32 __user *)(long)reg->addr,
@@ -654,10 +667,10 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = reg->id - KVM_REG_PPC_FPR0;
-			vcpu->arch.fpr[i] = set_reg_val(reg->id, val);
+			VCPU_FPR(vcpu, i) = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_FPSCR:
-			vcpu->arch.fpscr = set_reg_val(reg->id, val);
+			vcpu->arch.fp.fpscr = set_reg_val(reg->id, val);
 			break;
 #ifdef CONFIG_ALTIVEC
 		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
@@ -665,14 +678,14 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_VRSAVE:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
@@ -682,6 +695,17 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
+			if (cpu_has_feature(CPU_FTR_VSX)) {
+				long int i = reg->id - KVM_REG_PPC_VSR0;
+				vcpu->arch.fp.fpr[i][0] = val.vsxval[0];
+				vcpu->arch.fp.fpr[i][1] = val.vsxval[1];
+			} else {
+				r = -ENXIO;
+			}
+			break;
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_KVM_XICS
 		case KVM_REG_PPC_ICP_STATE:
 			if (!vcpu->arch.icp) {
@@ -879,3 +903,9 @@ static void kvmppc_book3s_exit(void)
 
 module_init(kvmppc_book3s_init);
 module_exit(kvmppc_book3s_exit);
+
+/* On 32bit this is our one and only kernel module */
+#ifdef CONFIG_KVM_BOOK3S_32
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
+#endif
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 3a0abd2e5a15..5fac89dfe4cd 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -243,6 +243,11 @@ next_pteg:
 	/* Now tell our Shadow PTE code about the new page */
 
 	pte = kvmppc_mmu_hpte_cache_next(vcpu);
+	if (!pte) {
+		kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+		r = -EAGAIN;
+		goto out;
+	}
 
 	dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n",
 		    orig_pte->may_write ? 'w' : '-',
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index c5d148434c08..303ece75b8e4 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -262,7 +262,7 @@ int kvmppc_mmu_hv_init(void)
 
 static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
 {
-	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
+	kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
 }
 
 /*
@@ -562,7 +562,7 @@ static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * we just return and retry the instruction.
 	 */
 
-	if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
+	if (instruction_is_store(kvmppc_get_last_inst(vcpu)) != !!is_store)
 		return RESUME_GUEST;
 
 	/*
diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c
index 852989a9bad3..20d4ea8e656d 100644
--- a/arch/powerpc/kvm/book3s_exports.c
+++ b/arch/powerpc/kvm/book3s_exports.c
@@ -25,9 +25,5 @@ EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline);
 #endif
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline);
-EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
-#ifdef CONFIG_ALTIVEC
-EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec);
-#endif
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3818bd95327c..17fc9496b6ac 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -31,6 +31,7 @@
 #include <linux/spinlock.h>
 #include <linux/page-flags.h>
 #include <linux/srcu.h>
+#include <linux/miscdevice.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -85,10 +86,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	/* CPU points to the first thread of the core */
 	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
+#ifdef CONFIG_KVM_XICS
 		int real_cpu = cpu + vcpu->arch.ptid;
 		if (paca[real_cpu].kvm_hstate.xics_phys)
 			xics_wake_cpu(real_cpu);
-		else if (cpu_online(cpu))
+		else
+#endif
+		if (cpu_online(cpu))
 			smp_send_reschedule(cpu);
 	}
 	put_cpu();
@@ -182,14 +186,28 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 
 		switch (arch_compat) {
 		case PVR_ARCH_205:
-			pcr = PCR_ARCH_205;
+			/*
+			 * If an arch bit is set in PCR, all the defined
+			 * higher-order arch bits also have to be set.
+			 */
+			pcr = PCR_ARCH_206 | PCR_ARCH_205;
 			break;
 		case PVR_ARCH_206:
 		case PVR_ARCH_206p:
+			pcr = PCR_ARCH_206;
+			break;
+		case PVR_ARCH_207:
 			break;
 		default:
 			return -EINVAL;
 		}
+
+		if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
+			/* POWER7 can't emulate POWER8 */
+			if (!(pcr & PCR_ARCH_206))
+				return -EINVAL;
+			pcr &= ~PCR_ARCH_206;
+		}
 	}
 
 	spin_lock(&vc->lock);
@@ -637,6 +655,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
+	case BOOK3S_INTERRUPT_H_DOORBELL:
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
@@ -673,12 +692,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* hcall - punt to userspace */
 		int i;
 
-		if (vcpu->arch.shregs.msr & MSR_PR) {
-			/* sc 1 from userspace - reflect to guest syscall */
-			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL);
-			r = RESUME_GUEST;
-			break;
-		}
+		/* hypercall with MSR_PR has already been handled in rmode,
+		 * and never reaches here.
+		 */
+
 		run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
 		for (i = 0; i < 9; ++i)
 			run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
@@ -708,7 +725,16 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * we don't emulate any guest instructions at this stage.
 	 */
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
-		kvmppc_core_queue_program(vcpu, 0x80000);
+		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+		r = RESUME_GUEST;
+		break;
+	/*
+	 * This occurs if the guest (kernel or userspace), does something that
+	 * is prohibited by HFSCR.  We just generate a program interrupt to
+	 * the guest.
+	 */
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
 		r = RESUME_GUEST;
 		break;
 	default:
@@ -766,10 +792,34 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
 
 	spin_lock(&vc->lock);
 	/*
+	 * If ILE (interrupt little-endian) has changed, update the
+	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
+	 */
+	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
+		struct kvm *kvm = vcpu->kvm;
+		struct kvm_vcpu *vcpu;
+		int i;
+
+		mutex_lock(&kvm->lock);
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (vcpu->arch.vcore != vc)
+				continue;
+			if (new_lpcr & LPCR_ILE)
+				vcpu->arch.intr_msr |= MSR_LE;
+			else
+				vcpu->arch.intr_msr &= ~MSR_LE;
+		}
+		mutex_unlock(&kvm->lock);
+	}
+
+	/*
 	 * Userspace can only modify DPFD (default prefetch depth),
 	 * ILE (interrupt little-endian) and TC (translation control).
+	 * On POWER8 userspace can also modify AIL (alt. interrupt loc.)
 	 */
 	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		mask |= LPCR_AIL;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
 }
@@ -787,6 +837,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_DABR:
 		*val = get_reg_val(id, vcpu->arch.dabr);
 		break;
+	case KVM_REG_PPC_DABRX:
+		*val = get_reg_val(id, vcpu->arch.dabrx);
+		break;
 	case KVM_REG_PPC_DSCR:
 		*val = get_reg_val(id, vcpu->arch.dscr);
 		break;
@@ -802,7 +855,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_UAMOR:
 		*val = get_reg_val(id, vcpu->arch.uamor);
 		break;
-	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
 		i = id - KVM_REG_PPC_MMCR0;
 		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
 		break;
@@ -810,33 +863,87 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		i = id - KVM_REG_PPC_PMC1;
 		*val = get_reg_val(id, vcpu->arch.pmc[i]);
 		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		*val = get_reg_val(id, vcpu->arch.spmc[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)) {
-			/* VSX => FP reg i is stored in arch.vsr[2*i] */
-			long int i = id - KVM_REG_PPC_FPR0;
-			*val = get_reg_val(id, vcpu->arch.vsr[2 * i]);
-		} else {
-			/* let generic code handle it */
-			r = -EINVAL;
-		}
+	case KVM_REG_PPC_SIER:
+		*val = get_reg_val(id, vcpu->arch.sier);
 		break;
-	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
-		if (cpu_has_feature(CPU_FTR_VSX)) {
-			long int i = id - KVM_REG_PPC_VSR0;
-			val->vsxval[0] = vcpu->arch.vsr[2 * i];
-			val->vsxval[1] = vcpu->arch.vsr[2 * i + 1];
-		} else {
-			r = -ENXIO;
-		}
+	case KVM_REG_PPC_IAMR:
+		*val = get_reg_val(id, vcpu->arch.iamr);
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case KVM_REG_PPC_TFHAR:
+		*val = get_reg_val(id, vcpu->arch.tfhar);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		*val = get_reg_val(id, vcpu->arch.tfiar);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		*val = get_reg_val(id, vcpu->arch.texasr);
+		break;
+#endif
+	case KVM_REG_PPC_FSCR:
+		*val = get_reg_val(id, vcpu->arch.fscr);
+		break;
+	case KVM_REG_PPC_PSPB:
+		*val = get_reg_val(id, vcpu->arch.pspb);
+		break;
+	case KVM_REG_PPC_EBBHR:
+		*val = get_reg_val(id, vcpu->arch.ebbhr);
+		break;
+	case KVM_REG_PPC_EBBRR:
+		*val = get_reg_val(id, vcpu->arch.ebbrr);
+		break;
+	case KVM_REG_PPC_BESCR:
+		*val = get_reg_val(id, vcpu->arch.bescr);
+		break;
+	case KVM_REG_PPC_TAR:
+		*val = get_reg_val(id, vcpu->arch.tar);
+		break;
+	case KVM_REG_PPC_DPDES:
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		break;
+	case KVM_REG_PPC_DAWR:
+		*val = get_reg_val(id, vcpu->arch.dawr);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		*val = get_reg_val(id, vcpu->arch.dawrx);
+		break;
+	case KVM_REG_PPC_CIABR:
+		*val = get_reg_val(id, vcpu->arch.ciabr);
+		break;
+	case KVM_REG_PPC_IC:
+		*val = get_reg_val(id, vcpu->arch.ic);
+		break;
+	case KVM_REG_PPC_VTB:
+		*val = get_reg_val(id, vcpu->arch.vtb);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		*val = get_reg_val(id, vcpu->arch.csigr);
+		break;
+	case KVM_REG_PPC_TACR:
+		*val = get_reg_val(id, vcpu->arch.tacr);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		*val = get_reg_val(id, vcpu->arch.tcscr);
+		break;
+	case KVM_REG_PPC_PID:
+		*val = get_reg_val(id, vcpu->arch.pid);
+		break;
+	case KVM_REG_PPC_ACOP:
+		*val = get_reg_val(id, vcpu->arch.acop);
+		break;
+	case KVM_REG_PPC_WORT:
+		*val = get_reg_val(id, vcpu->arch.wort);
 		break;
-#endif /* CONFIG_VSX */
 	case KVM_REG_PPC_VPA_ADDR:
 		spin_lock(&vcpu->arch.vpa_update_lock);
 		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
@@ -890,6 +997,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_DABR:
 		vcpu->arch.dabr = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_DABRX:
+		vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
+		break;
 	case KVM_REG_PPC_DSCR:
 		vcpu->arch.dscr = set_reg_val(id, *val);
 		break;
@@ -905,7 +1015,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_UAMOR:
 		vcpu->arch.uamor = set_reg_val(id, *val);
 		break;
-	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
 		i = id - KVM_REG_PPC_MMCR0;
 		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
 		break;
@@ -913,33 +1023,90 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		i = id - KVM_REG_PPC_PMC1;
 		vcpu->arch.pmc[i] = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		vcpu->arch.spmc[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)) {
-			/* VSX => FP reg i is stored in arch.vsr[2*i] */
-			long int i = id - KVM_REG_PPC_FPR0;
-			vcpu->arch.vsr[2 * i] = set_reg_val(id, *val);
-		} else {
-			/* let generic code handle it */
-			r = -EINVAL;
-		}
+	case KVM_REG_PPC_SIER:
+		vcpu->arch.sier = set_reg_val(id, *val);
 		break;
-	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
-		if (cpu_has_feature(CPU_FTR_VSX)) {
-			long int i = id - KVM_REG_PPC_VSR0;
-			vcpu->arch.vsr[2 * i] = val->vsxval[0];
-			vcpu->arch.vsr[2 * i + 1] = val->vsxval[1];
-		} else {
-			r = -ENXIO;
-		}
+	case KVM_REG_PPC_IAMR:
+		vcpu->arch.iamr = set_reg_val(id, *val);
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case KVM_REG_PPC_TFHAR:
+		vcpu->arch.tfhar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		vcpu->arch.tfiar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		vcpu->arch.texasr = set_reg_val(id, *val);
+		break;
+#endif
+	case KVM_REG_PPC_FSCR:
+		vcpu->arch.fscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PSPB:
+		vcpu->arch.pspb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_EBBHR:
+		vcpu->arch.ebbhr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_EBBRR:
+		vcpu->arch.ebbrr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_BESCR:
+		vcpu->arch.bescr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TAR:
+		vcpu->arch.tar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DPDES:
+		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWR:
+		vcpu->arch.dawr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+		break;
+	case KVM_REG_PPC_CIABR:
+		vcpu->arch.ciabr = set_reg_val(id, *val);
+		/* Don't allow setting breakpoints in hypervisor code */
+		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
+		break;
+	case KVM_REG_PPC_IC:
+		vcpu->arch.ic = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_VTB:
+		vcpu->arch.vtb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		vcpu->arch.csigr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TACR:
+		vcpu->arch.tacr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		vcpu->arch.tcscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PID:
+		vcpu->arch.pid = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_ACOP:
+		vcpu->arch.acop = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_WORT:
+		vcpu->arch.wort = set_reg_val(id, *val);
 		break;
-#endif /* CONFIG_VSX */
 	case KVM_REG_PPC_VPA_ADDR:
 		addr = set_reg_val(id, *val);
 		r = -EINVAL;
@@ -1017,6 +1184,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -1034,6 +1202,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
 			vcore->lpcr = kvm->arch.lpcr;
+			vcore->first_vcpuid = core * threads_per_core;
+			vcore->kvm = kvm;
 		}
 		kvm->arch.vcores[core] = vcore;
 		kvm->arch.online_vcores++;
@@ -1047,6 +1217,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	++vcore->num_threads;
 	spin_unlock(&vcore->lock);
 	vcpu->arch.vcore = vcore;
+	vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
 
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
@@ -1110,7 +1281,7 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 	}
 }
 
-extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+extern void __kvmppc_vcore_entry(void);
 
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 				   struct kvm_vcpu *vcpu)
@@ -1184,13 +1355,16 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	tpaca = &paca[cpu];
 	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.kvm_vcore = vc;
-	tpaca->kvm_hstate.napping = 0;
+	tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
 	vcpu->cpu = vc->pcpu;
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
-	if (vcpu->arch.ptid) {
+	if (cpu != smp_processor_id()) {
+#ifdef CONFIG_KVM_XICS
 		xics_wake_cpu(cpu);
-		++vc->n_woken;
+#endif
+		if (vcpu->arch.ptid)
+			++vc->n_woken;
 	}
 #endif
 }
@@ -1247,10 +1421,10 @@ static int on_primary_thread(void)
  */
 static void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu, *vcpu0, *vnext;
+	struct kvm_vcpu *vcpu, *vnext;
 	long ret;
 	u64 now;
-	int ptid, i, need_vpa_update;
+	int i, need_vpa_update;
 	int srcu_idx;
 	struct kvm_vcpu *vcpus_to_update[threads_per_core];
 
@@ -1288,25 +1462,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	/*
-	 * Assign physical thread IDs, first to non-ceded vcpus
-	 * and then to ceded ones.
-	 */
-	ptid = 0;
-	vcpu0 = NULL;
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		if (!vcpu->arch.ceded) {
-			if (!ptid)
-				vcpu0 = vcpu;
-			vcpu->arch.ptid = ptid++;
-		}
-	}
-	if (!vcpu0)
-		goto out;	/* nothing to run; should never happen */
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-		if (vcpu->arch.ceded)
-			vcpu->arch.ptid = ptid++;
-
-	/*
 	 * Make sure we are running on thread 0, and that
 	 * secondary threads are offline.
 	 */
@@ -1322,15 +1477,19 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 		kvmppc_create_dtl_entry(vcpu, vc);
 	}
 
+	/* Set this explicitly in case thread 0 doesn't have a vcpu */
+	get_paca()->kvm_hstate.kvm_vcore = vc;
+	get_paca()->kvm_hstate.ptid = 0;
+
 	vc->vcore_state = VCORE_RUNNING;
 	preempt_disable();
 	spin_unlock(&vc->lock);
 
 	kvm_guest_enter();
 
-	srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
-	__kvmppc_vcore_entry(NULL, vcpu0);
+	__kvmppc_vcore_entry();
 
 	spin_lock(&vc->lock);
 	/* disable sending of IPIs on virtual external irqs */
@@ -1345,7 +1504,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
 
-	srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx);
+	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
@@ -1453,7 +1612,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (!signal_pending(current)) {
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
-			vcpu->arch.ptid = vc->n_runnable - 1;
 			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
@@ -2048,6 +2206,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 			LPCR_VPM0 | LPCR_VPM1;
 		kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
 			(VRMA_VSID << SLB_VSID_SHIFT_1T);
+		/* On POWER8 turn on online bit to enable PURR/SPURR */
+		if (cpu_has_feature(CPU_FTR_ARCH_207S))
+			lpcr |= LPCR_ONL;
 	}
 	kvm->arch.lpcr = lpcr;
 
@@ -2222,3 +2383,5 @@ static void kvmppc_book3s_exit_hv(void)
 module_init(kvmppc_book3s_init_hv);
 module_exit(kvmppc_book3s_exit_hv);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 928142c64cb0..e873796b1a29 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -35,7 +35,7 @@
  ****************************************************************************/
 
 /* Registers:
- *  r4: vcpu pointer
+ *  none
  */
 _GLOBAL(__kvmppc_vcore_entry)
 
@@ -57,9 +57,11 @@ BEGIN_FTR_SECTION
 	std	r3, HSTATE_DSCR(r13)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+BEGIN_FTR_SECTION
 	/* Save host DABR */
 	mfspr	r3, SPRN_DABR
 	std	r3, HSTATE_DABR(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 	/* Hard-disable interrupts */
 	mfmsr   r10
@@ -69,7 +71,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mtmsrd  r10,1
 
 	/* Save host PMU registers */
-	/* R4 is live here (vcpu pointer) but not r3 or r5 */
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
@@ -134,16 +135,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 * enters the guest with interrupts enabled.
 	 */
 BEGIN_FTR_SECTION
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	ld	r0, VCPU_PENDING_EXC(r4)
 	li	r7, (1 << BOOK3S_IRQPRIO_EXTERNAL)
 	oris	r7, r7, (1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
 	and.	r0, r0, r7
 	beq	32f
-	mr	r31, r4
 	lhz	r3, PACAPACAINDEX(r13)
 	bl	smp_send_reschedule
 	nop
-	mr	r4, r31
 32:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 #endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 8689e2e30857..37fb3caa4c80 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -134,7 +134,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	unlock_rmap(rmap);
 }
 
-static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,
+static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
 			      int writing, unsigned long *pte_sizep)
 {
 	pte_t *ptep;
@@ -232,7 +232,8 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 
 		/* Look up the Linux PTE for the backing page */
 		pte_size = psize;
-		pte = lookup_linux_pte(pgdir, hva, writing, &pte_size);
+		pte = lookup_linux_pte_and_update(pgdir, hva, writing,
+						  &pte_size);
 		if (pte_present(pte)) {
 			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
@@ -672,7 +673,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 			memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
 			if (memslot) {
 				hva = __gfn_to_hva_memslot(memslot, gfn);
-				pte = lookup_linux_pte(pgdir, hva, 1, &psize);
+				pte = lookup_linux_pte_and_update(pgdir, hva,
+								  1, &psize);
 				if (pte_present(pte) && !pte_write(pte))
 					r = hpte_make_readonly(r);
 			}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index be4fa04a37c9..e66d4ec04d95 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -33,6 +33,10 @@
 #error Need to fix lppaca and SLB shadow accesses in little endian mode
 #endif
 
+/* Values in HSTATE_NAPPING(r13) */
+#define NAPPING_CEDE	1
+#define NAPPING_NOVCPU	2
+
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -57,29 +61,23 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 	RFI
 
 kvmppc_call_hv_entry:
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_hv_entry
 
 	/* Back from guest - restore host state and return to caller */
 
+BEGIN_FTR_SECTION
 	/* Restore host DABR and DABRX */
 	ld	r5,HSTATE_DABR(r13)
 	li	r6,7
 	mtspr	SPRN_DABR,r5
 	mtspr	SPRN_DABRX,r6
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 	/* 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)
@@ -115,6 +113,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 23:
 
 	/*
+	 * 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
+
+	/*
 	 * 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
@@ -153,15 +160,75 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 13:	b	machine_check_fwnmi
 
+kvmppc_primary_no_guest:
+	/* We handle this much like a ceded vcpu */
+	/* set our bit in napping_threads */
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	lbz	r7, HSTATE_PTID(r13)
+	li	r0, 1
+	sld	r0, r0, r7
+	addi	r6, r5, VCORE_NAPPING_THREADS
+1:	lwarx	r3, 0, r6
+	or	r3, r3, r0
+	stwcx.	r3, 0, r6
+	bne	1b
+	/* order napping_threads update vs testing entry_exit_count */
+	isync
+	li	r12, 0
+	lwz	r7, VCORE_ENTRY_EXIT(r5)
+	cmpwi	r7, 0x100
+	bge	kvm_novcpu_exit	/* another thread already exiting */
+	li	r3, NAPPING_NOVCPU
+	stb	r3, HSTATE_NAPPING(r13)
+	li	r3, 1
+	stb	r3, HSTATE_HWTHREAD_REQ(r13)
+
+	b	kvm_do_nap
+
+kvm_novcpu_wakeup:
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	li	r0, 0
+	stb	r0, HSTATE_NAPPING(r13)
+	stb	r0, HSTATE_HWTHREAD_REQ(r13)
+
+	/* check the wake reason */
+	bl	kvmppc_check_wake_reason
+	
+	/* see if any other thread is already exiting */
+	lwz	r0, VCORE_ENTRY_EXIT(r5)
+	cmpwi	r0, 0x100
+	bge	kvm_novcpu_exit
+
+	/* clear our bit in napping_threads */
+	lbz	r7, HSTATE_PTID(r13)
+	li	r0, 1
+	sld	r0, r0, r7
+	addi	r6, r5, VCORE_NAPPING_THREADS
+4:	lwarx	r7, 0, r6
+	andc	r7, r7, r0
+	stwcx.	r7, 0, r6
+	bne	4b
+
+	/* See if the wake reason means we need to exit */
+	cmpdi	r3, 0
+	bge	kvm_novcpu_exit
+
+	/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	cmpdi	r4, 0
+	bne	kvmppc_got_guest
+
+kvm_novcpu_exit:
+	b	hdec_soon
+
 /*
- * We come in here when wakened from nap mode on a secondary hw thread.
+ * We come in here when wakened from nap mode.
  * Relocation is off and most register values are lost.
  * r13 points to the PACA.
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,STACK_FRAME_OVERHEAD
 	ld	r2,PACATOC(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
@@ -173,8 +240,13 @@ kvm_start_guest:
 
 	/* were we napping due to cede? */
 	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,0
-	bne	kvm_end_cede
+	cmpwi	r0,NAPPING_CEDE
+	beq	kvm_end_cede
+	cmpwi	r0,NAPPING_NOVCPU
+	beq	kvm_novcpu_wakeup
+
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,STACK_FRAME_OVERHEAD
 
 	/*
 	 * We weren't napping due to cede, so this must be a secondary
@@ -184,40 +256,22 @@ kvm_start_guest:
 	 */
 
 	/* Check the wake reason in SRR1 to see why we got here */
-	mfspr	r3,SPRN_SRR1
-	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
-	cmpwi	r3,4			/* was it an external interrupt? */
-	bne	27f			/* if not */
-	ld	r5,HSTATE_XICS_PHYS(r13)
-	li	r7,XICS_XIRR		/* if it was an external interrupt, */
-	lwzcix	r8,r5,r7		/* get and ack the interrupt */
-	sync
-	clrldi.	r9,r8,40		/* get interrupt source ID. */
-	beq	28f			/* none there? */
-	cmpwi	r9,XICS_IPI		/* was it an IPI? */
-	bne	29f
-	li	r0,0xff
-	li	r6,XICS_MFRR
-	stbcix	r0,r5,r6		/* clear IPI */
-	stwcix	r8,r5,r7		/* EOI the interrupt */
-	sync				/* order loading of vcpu after that */
+	bl	kvmppc_check_wake_reason
+	cmpdi	r3, 0
+	bge	kvm_no_guest
 
 	/* get vcpu pointer, NULL if we have no vcpu to run */
 	ld	r4,HSTATE_KVM_VCPU(r13)
 	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
-	b	30f
 
-27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
-	b	kvm_no_guest
-28:	/* SRR1 said external but ICP said nope?? */
-	b	kvm_no_guest
-29:	/* External non-IPI interrupt to offline secondary thread? help?? */
-	stw	r8,HSTATE_SAVED_XIRR(r13)
-	b	kvm_no_guest
+	/* Set HSTATE_DSCR(r13) to something sensible */
+	LOAD_REG_ADDR(r6, dscr_default)
+	ld	r6, 0(r6)
+	std	r6, HSTATE_DSCR(r13)
 
-30:	bl	kvmppc_hv_entry
+	bl	kvmppc_hv_entry
 
 	/* Back from the guest, go back to nap */
 	/* Clear our vcpu pointer so we don't come back in early */
@@ -229,18 +283,6 @@ kvm_start_guest:
 	 * 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)
@@ -253,6 +295,7 @@ kvm_start_guest:
 kvm_no_guest:
 	li	r0, KVM_HWTHREAD_IN_NAP
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+kvm_do_nap:
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
@@ -277,7 +320,7 @@ kvmppc_hv_entry:
 
 	/* Required state:
 	 *
-	 * R4 = vcpu pointer
+	 * R4 = vcpu pointer (or NULL)
 	 * MSR = ~IR|DR
 	 * R13 = PACA
 	 * R1 = host R1
@@ -287,122 +330,12 @@ kvmppc_hv_entry:
 	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 */
-	li	r5,3
-	ld	r6,VCPU_DABR(r4)
-	mtspr	SPRN_DABRX,r5
-	mtspr	SPRN_DABR,r6
-BEGIN_FTR_SECTION
-	isync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* Load guest PMU registers */
-	/* R4 is live here (vcpu pointer) */
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	isync
-	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
-	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
-	lwz	r6, VCPU_PMC + 8(r4)
-	lwz	r7, VCPU_PMC + 12(r4)
-	lwz	r8, VCPU_PMC + 16(r4)
-	lwz	r9, VCPU_PMC + 20(r4)
-BEGIN_FTR_SECTION
-	lwz	r10, VCPU_PMC + 24(r4)
-	lwz	r11, VCPU_PMC + 28(r4)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r5
-	mtspr	SPRN_PMC3, r6
-	mtspr	SPRN_PMC4, r7
-	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, 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
-
-	/* Load up FP, VMX and VSX registers */
-	bl	kvmppc_load_fp
-
-	ld	r14, VCPU_GPR(R14)(r4)
-	ld	r15, VCPU_GPR(R15)(r4)
-	ld	r16, VCPU_GPR(R16)(r4)
-	ld	r17, VCPU_GPR(R17)(r4)
-	ld	r18, VCPU_GPR(R18)(r4)
-	ld	r19, VCPU_GPR(R19)(r4)
-	ld	r20, VCPU_GPR(R20)(r4)
-	ld	r21, VCPU_GPR(R21)(r4)
-	ld	r22, VCPU_GPR(R22)(r4)
-	ld	r23, VCPU_GPR(R23)(r4)
-	ld	r24, VCPU_GPR(R24)(r4)
-	ld	r25, VCPU_GPR(R25)(r4)
-	ld	r26, VCPU_GPR(R26)(r4)
-	ld	r27, VCPU_GPR(R27)(r4)
-	ld	r28, VCPU_GPR(R28)(r4)
-	ld	r29, VCPU_GPR(R29)(r4)
-	ld	r30, VCPU_GPR(R30)(r4)
-	ld	r31, VCPU_GPR(R31)(r4)
-
-BEGIN_FTR_SECTION
-	/* Switch DSCR to guest value */
-	ld	r5, VCPU_DSCR(r4)
-	mtspr	SPRN_DSCR, r5
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/*
-	 * Set the decrementer to the guest decrementer.
-	 */
-	ld	r8,VCPU_DEC_EXPIRES(r4)
-	mftb	r7
-	subf	r3,r7,r8
-	mtspr	SPRN_DEC,r3
-	stw	r3,VCPU_DEC(r4)
-
-	ld	r5, VCPU_SPRG0(r4)
-	ld	r6, VCPU_SPRG1(r4)
-	ld	r7, VCPU_SPRG2(r4)
-	ld	r8, VCPU_SPRG3(r4)
-	mtspr	SPRN_SPRG0, r5
-	mtspr	SPRN_SPRG1, r6
-	mtspr	SPRN_SPRG2, r7
-	mtspr	SPRN_SPRG3, r8
-
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
 
-	/* 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)
-	ld	r6,VCPU_UAMOR(r4)
-	li	r7,-1
-	mtspr	SPRN_AMR,r5
-	mtspr	SPRN_UAMOR,r6
-	mtspr	SPRN_AMOR,r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
 	/* Clear out SLB */
 	li	r6,0
 	slbmte	r6,r6
@@ -428,8 +361,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	bne	21b
 
 	/* Primary thread switches to guest partition. */
-	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
-	lwz	r6,VCPU_PTID(r4)
+	ld	r9,VCORE_KVM(r5)	/* pointer to struct kvm */
+	lbz	r6,HSTATE_PTID(r13)
 	cmpwi	r6,0
 	bne	20f
 	ld	r6,KVM_SDR1(r9)
@@ -457,7 +390,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	andc	r7,r7,r0
 	stdcx.	r7,0,r6
 	bne	23b
-	li	r6,128			/* and flush the TLB */
+	/* Flush the TLB of any entries for this LPID */
+	/* use arch 2.07S as a proxy for POWER8 */
+BEGIN_FTR_SECTION
+	li	r6,512			/* POWER8 has 512 sets */
+FTR_SECTION_ELSE
+	li	r6,128			/* POWER7 has 128 sets */
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
 	mtctr	r6
 	li	r7,0x800		/* IS field = 0b10 */
 	ptesync
@@ -487,6 +426,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	beq	38f
 	mtspr	SPRN_PCR, r7
 38:
+
+BEGIN_FTR_SECTION
+	/* DPDES is shared between threads */
+	ld	r8, VCORE_DPDES(r5)
+	mtspr	SPRN_DPDES, r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
@@ -503,32 +449,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	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
+	cmpwi	r3,512		/* 1 microsecond */
 	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-	mr	r9,r4
 	blt	hdec_soon
-
-	/* Save purr/spurr */
-	mfspr	r5,SPRN_PURR
-	mfspr	r6,SPRN_SPURR
-	std	r5,HSTATE_PURR(r13)
-	std	r6,HSTATE_SPURR(r13)
-	ld	r7,VCPU_PURR(r4)
-	ld	r8,VCPU_SPURR(r4)
-	mtspr	SPRN_PURR,r7
-	mtspr	SPRN_SPURR,r8
 	b	31f
 
 	/*
@@ -539,7 +464,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 * We also have to invalidate the TLB since its
 	 * entries aren't tagged with the LPID.
 	 */
-30:	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
+30:	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r9,VCORE_KVM(r5)	/* pointer to struct kvm */
 
 	/* first take native_tlbie_lock */
 	.section ".toc","aw"
@@ -604,7 +530,6 @@ toc_tlbie_lock:
 	mfspr	r3,SPRN_HDEC
 	cmpwi	r3,10
 	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-	mr	r9,r4
 	blt	hdec_soon
 
 	/* Enable HDEC interrupts */
@@ -619,9 +544,14 @@ toc_tlbie_lock:
 	mfspr	r0,SPRN_HID0
 	mfspr	r0,SPRN_HID0
 	mfspr	r0,SPRN_HID0
+31:
+	/* Do we have a guest vcpu to run? */
+	cmpdi	r4, 0
+	beq	kvmppc_primary_no_guest
+kvmppc_got_guest:
 
 	/* Load up guest SLB entries */
-31:	lwz	r5,VCPU_SLB_MAX(r4)
+	lwz	r5,VCPU_SLB_MAX(r4)
 	cmpwi	r5,0
 	beq	9f
 	mtctr	r5
@@ -632,6 +562,209 @@ toc_tlbie_lock:
 	addi	r6,r6,VCPU_SLB_SIZE
 	bdnz	1b
 9:
+	/* 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:
+
+BEGIN_FTR_SECTION
+	/* Save purr/spurr */
+	mfspr	r5,SPRN_PURR
+	mfspr	r6,SPRN_SPURR
+	std	r5,HSTATE_PURR(r13)
+	std	r6,HSTATE_SPURR(r13)
+	ld	r7,VCPU_PURR(r4)
+	ld	r8,VCPU_SPURR(r4)
+	mtspr	SPRN_PURR,r7
+	mtspr	SPRN_SPURR,r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+	/* Set partition DABR */
+	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
+	lwz	r5,VCPU_DABRX(r4)
+	ld	r6,VCPU_DABR(r4)
+	mtspr	SPRN_DABRX,r5
+	mtspr	SPRN_DABR,r6
+ BEGIN_FTR_SECTION_NESTED(89)
+	isync
+ END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+
+	/* Load guest PMU registers */
+	/* R4 is live here (vcpu pointer) */
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	isync
+	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
+	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
+	lwz	r6, VCPU_PMC + 8(r4)
+	lwz	r7, VCPU_PMC + 12(r4)
+	lwz	r8, VCPU_PMC + 16(r4)
+	lwz	r9, VCPU_PMC + 20(r4)
+BEGIN_FTR_SECTION
+	lwz	r10, VCPU_PMC + 24(r4)
+	lwz	r11, VCPU_PMC + 28(r4)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r5
+	mtspr	SPRN_PMC3, r6
+	mtspr	SPRN_PMC4, r7
+	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, 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
+BEGIN_FTR_SECTION
+	ld	r5, VCPU_MMCR + 24(r4)
+	ld	r6, VCPU_SIER(r4)
+	lwz	r7, VCPU_PMC + 24(r4)
+	lwz	r8, VCPU_PMC + 28(r4)
+	ld	r9, VCPU_MMCR + 32(r4)
+	mtspr	SPRN_MMCR2, r5
+	mtspr	SPRN_SIER, r6
+	mtspr	SPRN_SPMC1, r7
+	mtspr	SPRN_SPMC2, r8
+	mtspr	SPRN_MMCRS, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mtspr	SPRN_MMCR0, r3
+	isync
+
+	/* Load up FP, VMX and VSX registers */
+	bl	kvmppc_load_fp
+
+	ld	r14, VCPU_GPR(R14)(r4)
+	ld	r15, VCPU_GPR(R15)(r4)
+	ld	r16, VCPU_GPR(R16)(r4)
+	ld	r17, VCPU_GPR(R17)(r4)
+	ld	r18, VCPU_GPR(R18)(r4)
+	ld	r19, VCPU_GPR(R19)(r4)
+	ld	r20, VCPU_GPR(R20)(r4)
+	ld	r21, VCPU_GPR(R21)(r4)
+	ld	r22, VCPU_GPR(R22)(r4)
+	ld	r23, VCPU_GPR(R23)(r4)
+	ld	r24, VCPU_GPR(R24)(r4)
+	ld	r25, VCPU_GPR(R25)(r4)
+	ld	r26, VCPU_GPR(R26)(r4)
+	ld	r27, VCPU_GPR(R27)(r4)
+	ld	r28, VCPU_GPR(R28)(r4)
+	ld	r29, VCPU_GPR(R29)(r4)
+	ld	r30, VCPU_GPR(R30)(r4)
+	ld	r31, VCPU_GPR(R31)(r4)
+
+BEGIN_FTR_SECTION
+	/* Switch DSCR to guest value */
+	ld	r5, VCPU_DSCR(r4)
+	mtspr	SPRN_DSCR, r5
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+	/* Skip next section on POWER7 or PPC970 */
+	b	8f
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	/* Load up POWER8-specific registers */
+	ld	r5, VCPU_IAMR(r4)
+	lwz	r6, VCPU_PSPB(r4)
+	ld	r7, VCPU_FSCR(r4)
+	mtspr	SPRN_IAMR, r5
+	mtspr	SPRN_PSPB, r6
+	mtspr	SPRN_FSCR, r7
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
+	mtspr	SPRN_DAWR, r5
+	mtspr	SPRN_DAWRX, r6
+	mtspr	SPRN_CIABR, r7
+	mtspr	SPRN_TAR, r8
+	ld	r5, VCPU_IC(r4)
+	ld	r6, VCPU_VTB(r4)
+	mtspr	SPRN_IC, r5
+	mtspr	SPRN_VTB, r6
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+#endif
+	ld	r8, VCPU_EBBHR(r4)
+	mtspr	SPRN_EBBHR, r8
+	ld	r5, VCPU_EBBRR(r4)
+	ld	r6, VCPU_BESCR(r4)
+	ld	r7, VCPU_CSIGR(r4)
+	ld	r8, VCPU_TACR(r4)
+	mtspr	SPRN_EBBRR, r5
+	mtspr	SPRN_BESCR, r6
+	mtspr	SPRN_CSIGR, r7
+	mtspr	SPRN_TACR, r8
+	ld	r5, VCPU_TCSCR(r4)
+	ld	r6, VCPU_ACOP(r4)
+	lwz	r7, VCPU_GUEST_PID(r4)
+	ld	r8, VCPU_WORT(r4)
+	mtspr	SPRN_TCSCR, r5
+	mtspr	SPRN_ACOP, r6
+	mtspr	SPRN_PID, r7
+	mtspr	SPRN_WORT, r8
+8:
+
+	/*
+	 * Set the decrementer to the guest decrementer.
+	 */
+	ld	r8,VCPU_DEC_EXPIRES(r4)
+	mftb	r7
+	subf	r3,r7,r8
+	mtspr	SPRN_DEC,r3
+	stw	r3,VCPU_DEC(r4)
+
+	ld	r5, VCPU_SPRG0(r4)
+	ld	r6, VCPU_SPRG1(r4)
+	ld	r7, VCPU_SPRG2(r4)
+	ld	r8, VCPU_SPRG3(r4)
+	mtspr	SPRN_SPRG0, r5
+	mtspr	SPRN_SPRG1, r6
+	mtspr	SPRN_SPRG2, r7
+	mtspr	SPRN_SPRG3, r8
+
+	/* Load up DAR and DSISR */
+	ld	r5, VCPU_DAR(r4)
+	lwz	r6, VCPU_DSISR(r4)
+	mtspr	SPRN_DAR, r5
+	mtspr	SPRN_DSISR, r6
+
+BEGIN_FTR_SECTION
+	/* Restore AMR and UAMOR, set AMOR to all 1s */
+	ld	r5,VCPU_AMR(r4)
+	ld	r6,VCPU_UAMOR(r4)
+	li	r7,-1
+	mtspr	SPRN_AMR,r5
+	mtspr	SPRN_UAMOR,r6
+	mtspr	SPRN_AMOR,r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 	/* Restore state of CTRL run bit; assume 1 on entry */
 	lwz	r5,VCPU_CTRL(r4)
@@ -647,48 +780,53 @@ toc_tlbie_lock:
 	mtctr	r6
 	mtxer	r7
 
+kvmppc_cede_reentry:		/* r4 = vcpu, r13 = paca */
 	ld	r10, VCPU_PC(r4)
 	ld	r11, VCPU_MSR(r4)
-kvmppc_cede_reentry:		/* r4 = vcpu, r13 = paca */
 	ld	r6, VCPU_SRR0(r4)
 	ld	r7, VCPU_SRR1(r4)
+	mtspr	SPRN_SRR0, r6
+	mtspr	SPRN_SRR1, r7
 
+deliver_guest_interrupt:
 	/* r11 = vcpu->arch.msr & ~MSR_HV */
 	rldicl	r11, r11, 63 - MSR_HV_LG, 1
 	rotldi	r11, r11, 1 + MSR_HV_LG
 	ori	r11, r11, MSR_ME
 
 	/* Check if we can deliver an external or decrementer interrupt now */
-	ld	r0,VCPU_PENDING_EXC(r4)
-	lis	r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
-	and	r0,r0,r8
-	cmpdi	cr1,r0,0
-	andi.	r0,r11,MSR_EE
-	beq	cr1,11f
+	ld	r0, VCPU_PENDING_EXC(r4)
+	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
+	cmpdi	cr1, r0, 0
+	andi.	r8, r11, MSR_EE
 BEGIN_FTR_SECTION
-	mfspr	r8,SPRN_LPCR
-	ori	r8,r8,LPCR_MER
-	mtspr	SPRN_LPCR,r8
+	mfspr	r8, SPRN_LPCR
+	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
+	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
+	mtspr	SPRN_LPCR, r8
 	isync
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	beq	5f
-	li	r0,BOOK3S_INTERRUPT_EXTERNAL
-12:	mr	r6,r10
-	mr	r10,r0
-	mr	r7,r11
-	li	r11,(MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
-	rotldi	r11,r11,63
-	b	5f
-11:	beq	5f
-	mfspr	r0,SPRN_DEC
-	cmpwi	r0,0
-	li	r0,BOOK3S_INTERRUPT_DECREMENTER
-	blt	12b
+	li	r0, BOOK3S_INTERRUPT_EXTERNAL
+	bne	cr1, 12f
+	mfspr	r0, SPRN_DEC
+	cmpwi	r0, 0
+	li	r0, BOOK3S_INTERRUPT_DECREMENTER
+	bge	5f
 
-	/* Move SRR0 and SRR1 into the respective regs */
-5:	mtspr	SPRN_SRR0, r6
-	mtspr	SPRN_SRR1, r7
+12:	mtspr	SPRN_SRR0, r10
+	mr	r10,r0
+	mtspr	SPRN_SRR1, r11
+	ld	r11, VCPU_INTR_MSR(r4)
+5:
 
+/*
+ * Required state:
+ * R4 = vcpu
+ * R10: value for HSRR0
+ * R11: value for HSRR1
+ * R13 = PACA
+ */
 fast_guest_return:
 	li	r0,0
 	stb	r0,VCPU_CEDED(r4)	/* cancel cede */
@@ -868,39 +1006,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	/* External interrupt, first check for host_ipi. If this is
 	 * set, we know the host wants us out so let's do it now
 	 */
-do_ext_interrupt:
 	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 */
 	/* 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)
 	cmpwi	r0, 0x100
 	bge	ext_interrupt_to_host
 
-	/* See if there is a pending interrupt for the guest */
-	mfspr	r8, SPRN_LPCR
-	ld	r0, VCPU_PENDING_EXC(r9)
-	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
-	rldicl.	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
-	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
-	beq	2f
-
-	/* And if the guest EE is set, we can deliver immediately, else
-	 * we return to the guest with MER set
-	 */
-	andi.	r0, r11, MSR_EE
-	beq	2f
-	mtspr	SPRN_SRR0, r10
-	mtspr	SPRN_SRR1, r11
-	li	r10, BOOK3S_INTERRUPT_EXTERNAL
-	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
-	rotldi	r11, r11, 63
-2:	mr	r4, r9
-	mtspr	SPRN_LPCR, r8
-	b	fast_guest_return
+	/* Return to guest after delivering any pending interrupt */
+	mr	r4, r9
+	b	deliver_guest_interrupt
 
 ext_interrupt_to_host:
 
@@ -975,13 +1093,194 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_SPURR,r4
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
 
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
+BEGIN_FTR_SECTION
+	b	8f
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	/* Save POWER8-specific registers */
+	mfspr	r5, SPRN_IAMR
+	mfspr	r6, SPRN_PSPB
+	mfspr	r7, SPRN_FSCR
+	std	r5, VCPU_IAMR(r9)
+	stw	r6, VCPU_PSPB(r9)
+	std	r7, VCPU_FSCR(r9)
+	mfspr	r5, SPRN_IC
+	mfspr	r6, SPRN_VTB
+	mfspr	r7, SPRN_TAR
+	std	r5, VCPU_IC(r9)
+	std	r6, VCPU_VTB(r9)
+	std	r7, VCPU_TAR(r9)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+#endif
+	mfspr	r8, SPRN_EBBHR
+	std	r8, VCPU_EBBHR(r9)
+	mfspr	r5, SPRN_EBBRR
+	mfspr	r6, SPRN_BESCR
+	mfspr	r7, SPRN_CSIGR
+	mfspr	r8, SPRN_TACR
+	std	r5, VCPU_EBBRR(r9)
+	std	r6, VCPU_BESCR(r9)
+	std	r7, VCPU_CSIGR(r9)
+	std	r8, VCPU_TACR(r9)
+	mfspr	r5, SPRN_TCSCR
+	mfspr	r6, SPRN_ACOP
+	mfspr	r7, SPRN_PID
+	mfspr	r8, SPRN_WORT
+	std	r5, VCPU_TCSCR(r9)
+	std	r6, VCPU_ACOP(r9)
+	stw	r7, VCPU_GUEST_PID(r9)
+	std	r8, VCPU_WORT(r9)
+8:
+
+	/* Save and reset AMR and UAMOR before turning on the MMU */
+BEGIN_FTR_SECTION
+	mfspr	r5,SPRN_AMR
+	mfspr	r6,SPRN_UAMOR
+	std	r5,VCPU_AMR(r9)
+	std	r6,VCPU_UAMOR(r9)
+	li	r6,0
+	mtspr	SPRN_AMR,r6
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+	/* Switch DSCR back to host value */
+BEGIN_FTR_SECTION
+	mfspr	r8, SPRN_DSCR
+	ld	r7, HSTATE_DSCR(r13)
+	std	r8, VCPU_DSCR(r9)
+	mtspr	SPRN_DSCR, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+	/* Save non-volatile GPRs */
+	std	r14, VCPU_GPR(R14)(r9)
+	std	r15, VCPU_GPR(R15)(r9)
+	std	r16, VCPU_GPR(R16)(r9)
+	std	r17, VCPU_GPR(R17)(r9)
+	std	r18, VCPU_GPR(R18)(r9)
+	std	r19, VCPU_GPR(R19)(r9)
+	std	r20, VCPU_GPR(R20)(r9)
+	std	r21, VCPU_GPR(R21)(r9)
+	std	r22, VCPU_GPR(R22)(r9)
+	std	r23, VCPU_GPR(R23)(r9)
+	std	r24, VCPU_GPR(R24)(r9)
+	std	r25, VCPU_GPR(R25)(r9)
+	std	r26, VCPU_GPR(R26)(r9)
+	std	r27, VCPU_GPR(R27)(r9)
+	std	r28, VCPU_GPR(R28)(r9)
+	std	r29, VCPU_GPR(R29)(r9)
+	std	r30, VCPU_GPR(R30)(r9)
+	std	r31, VCPU_GPR(R31)(r9)
+
+	/* Save SPRGs */
+	mfspr	r3, SPRN_SPRG0
+	mfspr	r4, SPRN_SPRG1
+	mfspr	r5, SPRN_SPRG2
+	mfspr	r6, SPRN_SPRG3
+	std	r3, VCPU_SPRG0(r9)
+	std	r4, VCPU_SPRG1(r9)
+	std	r5, VCPU_SPRG2(r9)
+	std	r6, VCPU_SPRG3(r9)
+
+	/* save FP state */
+	mr	r3, r9
+	bl	kvmppc_save_fp
+
+	/* Increment yield count if they have a VPA */
+	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
+	cmpdi	r8, 0
+	beq	25f
+	lwz	r3, LPPACA_YIELDCOUNT(r8)
+	addi	r3, r3, 1
+	stw	r3, LPPACA_YIELDCOUNT(r8)
+	li	r3, 1
+	stb	r3, VCPU_VPA_DIRTY(r9)
+25:
+	/* Save PMU registers if requested */
+	/* r8 and cr0.eq are live here */
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	mfspr	r6, SPRN_MMCRA
+BEGIN_FTR_SECTION
+	/* On P7, clear MMCRA in order to disable SDAR updates */
+	li	r7, 0
+	mtspr	SPRN_MMCRA, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+	isync
+	beq	21f			/* if no VPA, save PMU stuff anyway */
+	lbz	r7, LPPACA_PMCINUSE(r8)
+	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
+	bne	21f
+	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
+	mfspr	r6, SPRN_PMC4
+	mfspr	r7, SPRN_PMC5
+	mfspr	r8, SPRN_PMC6
+BEGIN_FTR_SECTION
+	mfspr	r10, SPRN_PMC7
+	mfspr	r11, SPRN_PMC8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+	stw	r3, VCPU_PMC(r9)
+	stw	r4, VCPU_PMC + 4(r9)
+	stw	r5, VCPU_PMC + 8(r9)
+	stw	r6, VCPU_PMC + 12(r9)
+	stw	r7, VCPU_PMC + 16(r9)
+	stw	r8, VCPU_PMC + 20(r9)
+BEGIN_FTR_SECTION
+	stw	r10, VCPU_PMC + 24(r9)
+	stw	r11, VCPU_PMC + 28(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+BEGIN_FTR_SECTION
+	mfspr	r4, SPRN_MMCR2
+	mfspr	r5, SPRN_SIER
+	mfspr	r6, SPRN_SPMC1
+	mfspr	r7, SPRN_SPMC2
+	mfspr	r8, SPRN_MMCRS
+	std	r4, VCPU_MMCR + 24(r9)
+	std	r5, VCPU_SIER(r9)
+	stw	r6, VCPU_PMC + 24(r9)
+	stw	r7, VCPU_PMC + 28(r9)
+	std	r8, VCPU_MMCR + 32(r9)
+	lis	r4, 0x8000
+	mtspr	SPRN_MMCRS, r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+22:
 	/* Clear out SLB */
 	li	r5,0
 	slbmte	r5,r5
 	slbia
 	ptesync
 
-hdec_soon:			/* r9 = vcpu, r12 = trap, r13 = paca */
+hdec_soon:			/* r12 = trap, r13 = paca */
 BEGIN_FTR_SECTION
 	b	32f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
@@ -1014,8 +1313,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 */
 	cmpwi	r3,0x100	/* Are we the first here? */
 	bge	43f
-	cmpwi	r3,1		/* Are any other threads in the guest? */
-	ble	43f
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	beq	40f
 	li	r0,0
@@ -1026,7 +1323,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 * doesn't wake CPUs up from nap.
 	 */
 	lwz	r3,VCORE_NAPPING_THREADS(r5)
-	lwz	r4,VCPU_PTID(r9)
+	lbz	r4,HSTATE_PTID(r13)
 	li	r0,1
 	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
@@ -1045,10 +1342,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	addi	r6,r6,PACA_SIZE
 	bne	42b
 
+secondary_too_late:
 	/* Secondary threads wait for primary to do partition switch */
-43:	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	lwz	r3,VCPU_PTID(r9)
+43:	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
+	lbz	r3,HSTATE_PTID(r13)
 	cmpwi	r3,0
 	beq	15f
 	HMT_LOW
@@ -1076,6 +1374,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_LPID,r7
 	isync
 
+BEGIN_FTR_SECTION
+	/* DPDES is shared between threads */
+	mfspr	r7, SPRN_DPDES
+	std	r7, VCORE_DPDES(r5)
+	/* clear DPDES so we don't get guest doorbells in the host */
+	li	r8, 0
+	mtspr	SPRN_DPDES, r8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	/* Subtract timebase offset from timebase */
 	ld	r8,VCORE_TB_OFFSET(r5)
 	cmpdi	r8,0
@@ -1113,7 +1420,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 * We have to lock against concurrent tlbies, and
 	 * we have to flush the whole TLB.
 	 */
-32:	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
+32:	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
 
 	/* Take the guest's tlbie_lock */
 #ifdef __BIG_ENDIAN__
@@ -1203,6 +1511,56 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	add	r5,r5,r6
 	std	r5,VCPU_DEC_EXPIRES(r9)
 
+BEGIN_FTR_SECTION
+	b	8f
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	/* Save POWER8-specific registers */
+	mfspr	r5, SPRN_IAMR
+	mfspr	r6, SPRN_PSPB
+	mfspr	r7, SPRN_FSCR
+	std	r5, VCPU_IAMR(r9)
+	stw	r6, VCPU_PSPB(r9)
+	std	r7, VCPU_FSCR(r9)
+	mfspr	r5, SPRN_IC
+	mfspr	r6, SPRN_VTB
+	mfspr	r7, SPRN_TAR
+	std	r5, VCPU_IC(r9)
+	std	r6, VCPU_VTB(r9)
+	std	r7, VCPU_TAR(r9)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+#endif
+	mfspr	r8, SPRN_EBBHR
+	std	r8, VCPU_EBBHR(r9)
+	mfspr	r5, SPRN_EBBRR
+	mfspr	r6, SPRN_BESCR
+	mfspr	r7, SPRN_CSIGR
+	mfspr	r8, SPRN_TACR
+	std	r5, VCPU_EBBRR(r9)
+	std	r6, VCPU_BESCR(r9)
+	std	r7, VCPU_CSIGR(r9)
+	std	r8, VCPU_TACR(r9)
+	mfspr	r5, SPRN_TCSCR
+	mfspr	r6, SPRN_ACOP
+	mfspr	r7, SPRN_PID
+	mfspr	r8, SPRN_WORT
+	std	r5, VCPU_TCSCR(r9)
+	std	r6, VCPU_ACOP(r9)
+	stw	r7, VCPU_GUEST_PID(r9)
+	std	r8, VCPU_WORT(r9)
+8:
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR
@@ -1217,130 +1575,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	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
-	ld	r7, HSTATE_DSCR(r13)
-	std	r8, VCPU_DSCR(r9)
-	mtspr	SPRN_DSCR, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
-	/* Save non-volatile GPRs */
-	std	r14, VCPU_GPR(R14)(r9)
-	std	r15, VCPU_GPR(R15)(r9)
-	std	r16, VCPU_GPR(R16)(r9)
-	std	r17, VCPU_GPR(R17)(r9)
-	std	r18, VCPU_GPR(R18)(r9)
-	std	r19, VCPU_GPR(R19)(r9)
-	std	r20, VCPU_GPR(R20)(r9)
-	std	r21, VCPU_GPR(R21)(r9)
-	std	r22, VCPU_GPR(R22)(r9)
-	std	r23, VCPU_GPR(R23)(r9)
-	std	r24, VCPU_GPR(R24)(r9)
-	std	r25, VCPU_GPR(R25)(r9)
-	std	r26, VCPU_GPR(R26)(r9)
-	std	r27, VCPU_GPR(R27)(r9)
-	std	r28, VCPU_GPR(R28)(r9)
-	std	r29, VCPU_GPR(R29)(r9)
-	std	r30, VCPU_GPR(R30)(r9)
-	std	r31, VCPU_GPR(R31)(r9)
-
-	/* Save SPRGs */
-	mfspr	r3, SPRN_SPRG0
-	mfspr	r4, SPRN_SPRG1
-	mfspr	r5, SPRN_SPRG2
-	mfspr	r6, SPRN_SPRG3
-	std	r3, VCPU_SPRG0(r9)
-	std	r4, VCPU_SPRG1(r9)
-	std	r5, VCPU_SPRG2(r9)
-	std	r6, VCPU_SPRG3(r9)
-
-	/* save FP state */
-	mr	r3, r9
-	bl	.kvmppc_save_fp
-
-	/* Increment yield count if they have a VPA */
-	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
-	cmpdi	r8, 0
-	beq	25f
-	lwz	r3, LPPACA_YIELDCOUNT(r8)
-	addi	r3, r3, 1
-	stw	r3, LPPACA_YIELDCOUNT(r8)
-	li	r3, 1
-	stb	r3, VCPU_VPA_DIRTY(r9)
-25:
-	/* Save PMU registers if requested */
-	/* r8 and cr0.eq are live here */
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	mfspr	r6, SPRN_MMCRA
-BEGIN_FTR_SECTION
-	/* On P7, clear MMCRA in order to disable SDAR updates */
-	li	r7, 0
-	mtspr	SPRN_MMCRA, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-	isync
-	beq	21f			/* if no VPA, save PMU stuff anyway */
-	lbz	r7, LPPACA_PMCINUSE(r8)
-	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
-	bne	21f
-	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
-	mfspr	r6, SPRN_PMC4
-	mfspr	r7, SPRN_PMC5
-	mfspr	r8, SPRN_PMC6
-BEGIN_FTR_SECTION
-	mfspr	r10, SPRN_PMC7
-	mfspr	r11, SPRN_PMC8
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-	stw	r3, VCPU_PMC(r9)
-	stw	r4, VCPU_PMC + 4(r9)
-	stw	r5, VCPU_PMC + 8(r9)
-	stw	r6, VCPU_PMC + 12(r9)
-	stw	r7, VCPU_PMC + 16(r9)
-	stw	r8, VCPU_PMC + 20(r9)
-BEGIN_FTR_SECTION
-	stw	r10, VCPU_PMC + 24(r9)
-	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)
-
-	.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.
@@ -1386,8 +1624,7 @@ kvmppc_hdsi:
 	mtspr	SPRN_SRR0, r10
 	mtspr	SPRN_SRR1, r11
 	li	r10, BOOK3S_INTERRUPT_DATA_STORAGE
-	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
-	rotldi	r11, r11, 63
+	ld	r11, VCPU_INTR_MSR(r9)
 fast_interrupt_c_return:
 6:	ld	r7, VCPU_CTR(r9)
 	lwz	r8, VCPU_XER(r9)
@@ -1456,8 +1693,7 @@ kvmppc_hisi:
 1:	mtspr	SPRN_SRR0, r10
 	mtspr	SPRN_SRR1, r11
 	li	r10, BOOK3S_INTERRUPT_INST_STORAGE
-	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
-	rotldi	r11, r11, 63
+	ld	r11, VCPU_INTR_MSR(r9)
 	b	fast_interrupt_c_return
 
 3:	ld	r6, VCPU_KVM(r9)	/* not relocated, use VRMA */
@@ -1474,7 +1710,8 @@ kvmppc_hisi:
 hcall_try_real_mode:
 	ld	r3,VCPU_GPR(R3)(r9)
 	andi.	r0,r11,MSR_PR
-	bne	guest_exit_cont
+	/* sc 1 from userspace - reflect to guest syscall */
+	bne	sc_1_fast_return
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
@@ -1495,6 +1732,14 @@ hcall_try_real_mode:
 	ld	r11,VCPU_MSR(r4)
 	b	fast_guest_return
 
+sc_1_fast_return:
+	mtspr	SPRN_SRR0,r10
+	mtspr	SPRN_SRR1,r11
+	li	r10, BOOK3S_INTERRUPT_SYSCALL
+	ld	r11, VCPU_INTR_MSR(r9)
+	mr	r4,r9
+	b	fast_guest_return
+
 	/* We've attempted a real mode hcall, but it's punted it back
 	 * to userspace.  We need to restore some clobbered volatiles
 	 * before resuming the pass-it-to-qemu path */
@@ -1588,14 +1833,34 @@ hcall_real_table:
 	.long	0		/* 0x11c */
 	.long	0		/* 0x120 */
 	.long	.kvmppc_h_bulk_remove - hcall_real_table
+	.long	0		/* 0x128 */
+	.long	0		/* 0x12c */
+	.long	0		/* 0x130 */
+	.long	.kvmppc_h_set_xdabr - hcall_real_table
 hcall_real_table_end:
 
 ignore_hdec:
 	mr	r4,r9
 	b	fast_guest_return
 
+_GLOBAL(kvmppc_h_set_xdabr)
+	andi.	r0, r5, DABRX_USER | DABRX_KERNEL
+	beq	6f
+	li	r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI
+	andc.	r0, r5, r0
+	beq	3f
+6:	li	r3, H_PARAMETER
+	blr
+
 _GLOBAL(kvmppc_h_set_dabr)
+	li	r5, DABRX_USER | DABRX_KERNEL
+3:
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	std	r4,VCPU_DABR(r3)
+	stw	r5, VCPU_DABRX(r3)
+	mtspr	SPRN_DABRX, r5
 	/* Work around P7 bug where DABR can get corrupted on mtspr */
 1:	mtspr	SPRN_DABR,r4
 	mfspr	r5, SPRN_DABR
@@ -1605,6 +1870,17 @@ _GLOBAL(kvmppc_h_set_dabr)
 	li	r3,0
 	blr
 
+	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
+2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
+	rlwimi	r5, r4, 1, DAWRX_WT
+	clrrdi	r4, r4, 3
+	std	r4, VCPU_DAWR(r3)
+	std	r5, VCPU_DAWRX(r3)
+	mtspr	SPRN_DAWR, r4
+	mtspr	SPRN_DAWRX, r5
+	li	r3, 0
+	blr
+
 _GLOBAL(kvmppc_h_cede)
 	ori	r11,r11,MSR_EE
 	std	r11,VCPU_MSR(r3)
@@ -1628,7 +1904,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * up to the host.
 	 */
 	ld	r5,HSTATE_KVM_VCORE(r13)
-	lwz	r6,VCPU_PTID(r3)
+	lbz	r6,HSTATE_PTID(r13)
 	lwz	r8,VCORE_ENTRY_EXIT(r5)
 	clrldi	r8,r8,56
 	li	r0,1
@@ -1643,9 +1919,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	bne	31b
 	/* order napping_threads update vs testing entry_exit_count */
 	isync
-	li	r0,1
+	li	r0,NAPPING_CEDE
 	stb	r0,HSTATE_NAPPING(r13)
-	mr	r4,r3
 	lwz	r7,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r7,0x100
 	bge	33f		/* another thread already exiting */
@@ -1677,16 +1952,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	std	r31, VCPU_GPR(R31)(r3)
 
 	/* save FP state */
-	bl	.kvmppc_save_fp
+	bl	kvmppc_save_fp
 
 	/*
-	 * Take a nap until a decrementer or external interrupt occurs,
-	 * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
+	 * Take a nap until a decrementer or external or doobell interrupt
+	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR
 	 */
 	li	r0,1
 	stb	r0,HSTATE_HWTHREAD_REQ(r13)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
+BEGIN_FTR_SECTION
+	oris	r5,r5,LPCR_PECEDP@h
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_LPCR,r5
 	isync
 	li	r0, 0
@@ -1698,6 +1976,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	nap
 	b	.
 
+33:	mr	r4, r3
+	li	r3, 0
+	li	r12, 0
+	b	34f
+
 kvm_end_cede:
 	/* get vcpu pointer */
 	ld	r4, HSTATE_KVM_VCPU(r13)
@@ -1727,12 +2010,15 @@ kvm_end_cede:
 	ld	r29, VCPU_GPR(R29)(r4)
 	ld	r30, VCPU_GPR(R30)(r4)
 	ld	r31, VCPU_GPR(R31)(r4)
+ 
+	/* Check the wake reason in SRR1 to see why we got here */
+	bl	kvmppc_check_wake_reason
 
 	/* clear our bit in vcore->napping_threads */
-33:	ld	r5,HSTATE_KVM_VCORE(r13)
-	lwz	r3,VCPU_PTID(r4)
+34:	ld	r5,HSTATE_KVM_VCORE(r13)
+	lbz	r7,HSTATE_PTID(r13)
 	li	r0,1
-	sld	r0,r0,r3
+	sld	r0,r0,r7
 	addi	r6,r5,VCORE_NAPPING_THREADS
 32:	lwarx	r7,0,r6
 	andc	r7,r7,r0
@@ -1741,23 +2027,18 @@ kvm_end_cede:
 	li	r0,0
 	stb	r0,HSTATE_NAPPING(r13)
 
-	/* Check the wake reason in SRR1 to see why we got here */
-	mfspr	r3, SPRN_SRR1
-	rlwinm	r3, r3, 44-31, 0x7	/* extract wake reason field */
-	cmpwi	r3, 4			/* was it an external interrupt? */
-	li	r12, BOOK3S_INTERRUPT_EXTERNAL
+	/* See if the wake reason means we need to exit */
+	stw	r12, VCPU_TRAP(r4)
 	mr	r9, r4
-	ld	r10, VCPU_PC(r9)
-	ld	r11, VCPU_MSR(r9)
-	beq	do_ext_interrupt	/* if so */
+	cmpdi	r3, 0
+	bgt	guest_exit_cont
 
 	/* see if any other thread is already exiting */
 	lwz	r0,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r0,0x100
-	blt	kvmppc_cede_reentry	/* if not go back to guest */
+	bge	guest_exit_cont
 
-	/* some threads are exiting, so go to the guest exit path */
-	b	hcall_real_fallback
+	b	kvmppc_cede_reentry	/* if not go back to guest */
 
 	/* cede when already previously prodded case */
 kvm_cede_prodded:
@@ -1783,11 +2064,48 @@ machine_check_realmode:
 	beq	mc_cont
 	/* If not, deliver a machine check.  SRR0/1 are already set */
 	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
-	rotldi	r11, r11, 63
+	ld	r11, VCPU_INTR_MSR(r9)
 	b	fast_interrupt_c_return
 
 /*
+ * Check the reason we woke from nap, and take appropriate action.
+ * Returns:
+ *	0 if nothing needs to be done
+ *	1 if something happened that needs to be handled by the host
+ *	-1 if there was a guest wakeup (IPI)
+ *
+ * Also sets r12 to the interrupt vector for any interrupt that needs
+ * to be handled now by the host (0x500 for external interrupt), or zero.
+ */
+kvmppc_check_wake_reason:
+	mfspr	r6, SPRN_SRR1
+BEGIN_FTR_SECTION
+	rlwinm	r6, r6, 45-31, 0xf	/* extract wake reason field (P8) */
+FTR_SECTION_ELSE
+	rlwinm	r6, r6, 45-31, 0xe	/* P7 wake reason field is 3 bits */
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
+	cmpwi	r6, 8			/* was it an external interrupt? */
+	li	r12, BOOK3S_INTERRUPT_EXTERNAL
+	beq	kvmppc_read_intr	/* if so, see what it was */
+	li	r3, 0
+	li	r12, 0
+	cmpwi	r6, 6			/* was it the decrementer? */
+	beq	0f
+BEGIN_FTR_SECTION
+	cmpwi	r6, 5			/* privileged doorbell? */
+	beq	0f
+	cmpwi	r6, 3			/* hypervisor doorbell? */
+	beq	3f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	li	r3, 1			/* anything else, return 1 */
+0:	blr
+
+	/* hypervisor doorbell */
+3:	li	r12, BOOK3S_INTERRUPT_H_DOORBELL
+	li	r3, 1
+	blr
+
+/*
  * Determine what sort of external interrupt is pending (if any).
  * Returns:
  *	0 if no interrupt is pending
@@ -1818,7 +2136,6 @@ kvmppc_read_intr:
 	 * interrupts directly to the guest
 	 */
 	cmpwi	r3, XICS_IPI		/* if there is, is it an IPI? */
-	li	r3, 1
 	bne	42f
 
 	/* It's an IPI, clear the MFRR and EOI it */
@@ -1844,19 +2161,25 @@ kvmppc_read_intr:
 	 * before exit, it will be picked up by the host ICP driver
 	 */
 	stw	r0, HSTATE_SAVED_XIRR(r13)
+	li	r3, 1
 	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
+	li	r3, 1
 	b	1b
 
 /*
  * Save away FP, VMX and VSX registers.
  * r3 = vcpu pointer
+ * N.B. r30 and r31 are volatile across this function,
+ * thus it is not callable from C.
  */
-_GLOBAL(kvmppc_save_fp)
+kvmppc_save_fp:
+	mflr	r30
+	mr	r31,r3
 	mfmsr	r5
 	ori	r8,r5,MSR_FP
 #ifdef CONFIG_ALTIVEC
@@ -1871,42 +2194,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
 	mtmsrd	r8
 	isync
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	reg = 0
-	.rept	32
-	li	r6,reg*16+VCPU_VSRS
-	STXVD2X(reg,R6,R3)
-	reg = reg + 1
-	.endr
-FTR_SECTION_ELSE
-#endif
-	reg = 0
-	.rept	32
-	stfd	reg,reg*8+VCPU_FPRS(r3)
-	reg = reg + 1
-	.endr
-#ifdef CONFIG_VSX
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
-#endif
-	mffs	fr0
-	stfd	fr0,VCPU_FPSCR(r3)
-
+	addi	r3,r3,VCPU_FPRS
+	bl	.store_fp_state
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
-	reg = 0
-	.rept	32
-	li	r6,reg*16+VCPU_VRS
-	stvx	reg,r6,r3
-	reg = reg + 1
-	.endr
-	mfvscr	vr0
-	li	r6,VCPU_VSCR
-	stvx	vr0,r6,r3
+	addi	r3,r31,VCPU_VRS
+	bl	.store_vr_state
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	mfspr	r6,SPRN_VRSAVE
 	stw	r6,VCPU_VRSAVE(r3)
+	mtlr	r30
 	mtmsrd	r5
 	isync
 	blr
@@ -1914,9 +2212,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 /*
  * Load up FP, VMX and VSX registers
  * r4 = vcpu pointer
+ * N.B. r30 and r31 are volatile across this function,
+ * thus it is not callable from C.
  */
-	.globl	kvmppc_load_fp
 kvmppc_load_fp:
+	mflr	r30
+	mr	r31,r4
 	mfmsr	r9
 	ori	r8,r9,MSR_FP
 #ifdef CONFIG_ALTIVEC
@@ -1931,42 +2232,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
 	mtmsrd	r8
 	isync
-	lfd	fr0,VCPU_FPSCR(r4)
-	MTFSF_L(fr0)
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	reg = 0
-	.rept	32
-	li	r7,reg*16+VCPU_VSRS
-	LXVD2X(reg,R7,R4)
-	reg = reg + 1
-	.endr
-FTR_SECTION_ELSE
-#endif
-	reg = 0
-	.rept	32
-	lfd	reg,reg*8+VCPU_FPRS(r4)
-	reg = reg + 1
-	.endr
-#ifdef CONFIG_VSX
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
-#endif
-
+	addi	r3,r4,VCPU_FPRS
+	bl	.load_fp_state
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
-	li	r7,VCPU_VSCR
-	lvx	vr0,r7,r4
-	mtvscr	vr0
-	reg = 0
-	.rept	32
-	li	r7,reg*16+VCPU_VRS
-	lvx	reg,r7,r4
-	reg = reg + 1
-	.endr
+	addi	r3,r31,VCPU_VRS
+	bl	.load_vr_state
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	lwz	r7,VCPU_VRSAVE(r4)
 	mtspr	SPRN_VRSAVE,r7
+	mtlr	r30
+	mr	r4,r31
 	blr
 
 /*
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index a59a25a13218..c1abd95063f4 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -160,7 +160,7 @@
 
 static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
 {
-	kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt]);
+	kvm_cvt_df(&VCPU_FPR(vcpu, rt), &vcpu->arch.qpr[rt]);
 }
 
 static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
@@ -207,11 +207,11 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* put in registers */
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs]);
+		kvm_cvt_fd((u32*)tmp, &VCPU_FPR(vcpu, rs));
 		vcpu->arch.qpr[rs] = *((u32*)tmp);
 		break;
 	case FPU_LS_DOUBLE:
-		vcpu->arch.fpr[rs] = *((u64*)tmp);
+		VCPU_FPR(vcpu, rs) = *((u64*)tmp);
 		break;
 	}
 
@@ -233,18 +233,18 @@ static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp);
+		kvm_cvt_df(&VCPU_FPR(vcpu, rs), (u32*)tmp);
 		val = *((u32*)tmp);
 		len = sizeof(u32);
 		break;
 	case FPU_LS_SINGLE_LOW:
-		*((u32*)tmp) = vcpu->arch.fpr[rs];
-		val = vcpu->arch.fpr[rs] & 0xffffffff;
+		*((u32*)tmp) = VCPU_FPR(vcpu, rs);
+		val = VCPU_FPR(vcpu, rs) & 0xffffffff;
 		len = sizeof(u32);
 		break;
 	case FPU_LS_DOUBLE:
-		*((u64*)tmp) = vcpu->arch.fpr[rs];
-		val = vcpu->arch.fpr[rs];
+		*((u64*)tmp) = VCPU_FPR(vcpu, rs);
+		val = VCPU_FPR(vcpu, rs);
 		len = sizeof(u64);
 		break;
 	default:
@@ -301,7 +301,7 @@ static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	emulated = EMULATE_DONE;
 
 	/* put in registers */
-	kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs]);
+	kvm_cvt_fd(&tmp[0], &VCPU_FPR(vcpu, rs));
 	vcpu->arch.qpr[rs] = tmp[1];
 
 	dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0],
@@ -319,7 +319,7 @@ static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	u32 tmp[2];
 	int len = w ? sizeof(u32) : sizeof(u64);
 
-	kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0]);
+	kvm_cvt_df(&VCPU_FPR(vcpu, rs), &tmp[0]);
 	tmp[1] = vcpu->arch.qpr[rs];
 
 	r = kvmppc_st(vcpu, &addr, len, tmp, true);
@@ -512,7 +512,6 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
 						 u32 *src2, u32 *src3))
 {
 	u32 *qpr = vcpu->arch.qpr;
-	u64 *fpr = vcpu->arch.fpr;
 	u32 ps0_out;
 	u32 ps0_in1, ps0_in2, ps0_in3;
 	u32 ps1_in1, ps1_in2, ps1_in3;
@@ -521,20 +520,20 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
-	kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
-	kvm_cvt_df(&fpr[reg_in3], &ps0_in3);
+	kvm_cvt_df(&VCPU_FPR(vcpu, reg_in1), &ps0_in1);
+	kvm_cvt_df(&VCPU_FPR(vcpu, reg_in2), &ps0_in2);
+	kvm_cvt_df(&VCPU_FPR(vcpu, reg_in3), &ps0_in3);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
 
-	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3);
+	func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3);
 
 	dprintk(KERN_INFO "PS3 ps0 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n",
 			  ps0_in1, ps0_in2, ps0_in3, ps0_out);
 
 	if (!(scalar & SCALAR_NO_PS0))
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
+		kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out));
 
 	/* PS1 */
 	ps1_in1 = qpr[reg_in1];
@@ -545,7 +544,7 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
 		ps1_in2 = ps0_in2;
 
 	if (!(scalar & SCALAR_NO_PS1))
-		func(&vcpu->arch.fpscr, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3);
+		func(&vcpu->arch.fp.fpscr, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3);
 
 	dprintk(KERN_INFO "PS3 ps1 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n",
 			  ps1_in1, ps1_in2, ps1_in3, qpr[reg_out]);
@@ -561,7 +560,6 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
 						 u32 *src2))
 {
 	u32 *qpr = vcpu->arch.qpr;
-	u64 *fpr = vcpu->arch.fpr;
 	u32 ps0_out;
 	u32 ps0_in1, ps0_in2;
 	u32 ps1_out;
@@ -571,20 +569,20 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
+	kvm_cvt_df(&VCPU_FPR(vcpu, reg_in1), &ps0_in1);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
 	else
-		kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
+		kvm_cvt_df(&VCPU_FPR(vcpu, reg_in2), &ps0_in2);
 
-	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2);
+	func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in1, &ps0_in2);
 
 	if (!(scalar & SCALAR_NO_PS0)) {
 		dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n",
 				  ps0_in1, ps0_in2, ps0_out);
 
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
+		kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out));
 	}
 
 	/* PS1 */
@@ -594,7 +592,7 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
 	if (scalar & SCALAR_HIGH)
 		ps1_in2 = ps0_in2;
 
-	func(&vcpu->arch.fpscr, &ps1_out, &ps1_in1, &ps1_in2);
+	func(&vcpu->arch.fp.fpscr, &ps1_out, &ps1_in1, &ps1_in2);
 
 	if (!(scalar & SCALAR_NO_PS1)) {
 		qpr[reg_out] = ps1_out;
@@ -612,7 +610,6 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc,
 						 u32 *dst, u32 *src1))
 {
 	u32 *qpr = vcpu->arch.qpr;
-	u64 *fpr = vcpu->arch.fpr;
 	u32 ps0_out, ps0_in;
 	u32 ps1_in;
 
@@ -620,17 +617,17 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in], &ps0_in);
-	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in);
+	kvm_cvt_df(&VCPU_FPR(vcpu, reg_in), &ps0_in);
+	func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in);
 
 	dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n",
 			  ps0_in, ps0_out);
 
-	kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
+	kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out));
 
 	/* PS1 */
 	ps1_in = qpr[reg_in];
-	func(&vcpu->arch.fpscr, &qpr[reg_out], &ps1_in);
+	func(&vcpu->arch.fp.fpscr, &qpr[reg_out], &ps1_in);
 
 	dprintk(KERN_INFO "PS1 ps1 -> f(0x%x) = 0x%x\n",
 			  ps1_in, qpr[reg_out]);
@@ -649,10 +646,10 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	int ax_rc = inst_get_field(inst, 21, 25);
 	short full_d = inst_get_field(inst, 16, 31);
 
-	u64 *fpr_d = &vcpu->arch.fpr[ax_rd];
-	u64 *fpr_a = &vcpu->arch.fpr[ax_ra];
-	u64 *fpr_b = &vcpu->arch.fpr[ax_rb];
-	u64 *fpr_c = &vcpu->arch.fpr[ax_rc];
+	u64 *fpr_d = &VCPU_FPR(vcpu, ax_rd);
+	u64 *fpr_a = &VCPU_FPR(vcpu, ax_ra);
+	u64 *fpr_b = &VCPU_FPR(vcpu, ax_rb);
+	u64 *fpr_c = &VCPU_FPR(vcpu, ax_rc);
 
 	bool rcomp = (inst & 1) ? true : false;
 	u32 cr = kvmppc_get_cr(vcpu);
@@ -674,11 +671,11 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	/* Do we need to clear FE0 / FE1 here? Don't think so. */
 
 #ifdef DEBUG
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fp.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
+		kvm_cvt_df(&VCPU_FPR(vcpu, i), &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx    QPR[%d] = 0x%x\n",
-			i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]);
+			i, f, VCPU_FPR(vcpu, i), i, vcpu->arch.qpr[i]);
 	}
 #endif
 
@@ -764,8 +761,8 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 		}
 		case OP_4X_PS_NEG:
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
-			vcpu->arch.fpr[ax_rd] ^= 0x8000000000000000ULL;
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb);
+			VCPU_FPR(vcpu, ax_rd) ^= 0x8000000000000000ULL;
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			vcpu->arch.qpr[ax_rd] ^= 0x80000000;
 			break;
@@ -775,7 +772,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 		case OP_4X_PS_MR:
 			WARN_ON(rcomp);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb);
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			break;
 		case OP_4X_PS_CMPO1:
@@ -784,44 +781,44 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 		case OP_4X_PS_NABS:
 			WARN_ON(rcomp);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
-			vcpu->arch.fpr[ax_rd] |= 0x8000000000000000ULL;
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb);
+			VCPU_FPR(vcpu, ax_rd) |= 0x8000000000000000ULL;
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			vcpu->arch.qpr[ax_rd] |= 0x80000000;
 			break;
 		case OP_4X_PS_ABS:
 			WARN_ON(rcomp);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
-			vcpu->arch.fpr[ax_rd] &= ~0x8000000000000000ULL;
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb);
+			VCPU_FPR(vcpu, ax_rd) &= ~0x8000000000000000ULL;
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			vcpu->arch.qpr[ax_rd] &= ~0x80000000;
 			break;
 		case OP_4X_PS_MERGE00:
 			WARN_ON(rcomp);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
-			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
-			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_ra);
+			/* vcpu->arch.qpr[ax_rd] = VCPU_FPR(vcpu, ax_rb); */
+			kvm_cvt_df(&VCPU_FPR(vcpu, ax_rb),
 				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE01:
 			WARN_ON(rcomp);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_ra);
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			break;
 		case OP_4X_PS_MERGE10:
 			WARN_ON(rcomp);
-			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
+			/* VCPU_FPR(vcpu, ax_rd) = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd]);
-			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
-			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
+				   &VCPU_FPR(vcpu, ax_rd));
+			/* vcpu->arch.qpr[ax_rd] = VCPU_FPR(vcpu, ax_rb); */
+			kvm_cvt_df(&VCPU_FPR(vcpu, ax_rb),
 				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE11:
 			WARN_ON(rcomp);
-			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
+			/* VCPU_FPR(vcpu, ax_rd) = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd]);
+				   &VCPU_FPR(vcpu, ax_rd));
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			break;
 		}
@@ -856,7 +853,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		case OP_4A_PS_SUM1:
 			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
 					ax_rb, ax_ra, SCALAR_NO_PS0 | SCALAR_HIGH, fps_fadds);
-			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rc];
+			VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rc);
 			break;
 		case OP_4A_PS_SUM0:
 			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
@@ -1106,45 +1103,45 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case 59:
 		switch (inst_get_field(inst, 21, 30)) {
 		case OP_59_FADDS:
-			fpd_fadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FSUBS:
-			fpd_fsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FDIVS:
-			fpd_fdivs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fdivs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FRES:
-			fpd_fres(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fres(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FRSQRTES:
-			fpd_frsqrtes(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_frsqrtes(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		}
 		switch (inst_get_field(inst, 26, 30)) {
 		case OP_59_FMULS:
-			fpd_fmuls(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c);
+			fpd_fmuls(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FMSUBS:
-			fpd_fmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fmsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FMADDS:
-			fpd_fmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fmadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FNMSUBS:
-			fpd_fnmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fnmsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_59_FNMADDS:
-			fpd_fnmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fnmadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		}
@@ -1159,12 +1156,12 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 		case OP_63_MFFS:
 			/* XXX missing CR */
-			*fpr_d = vcpu->arch.fpscr;
+			*fpr_d = vcpu->arch.fp.fpscr;
 			break;
 		case OP_63_MTFSF:
 			/* XXX missing fm bits */
 			/* XXX missing CR */
-			vcpu->arch.fpscr = *fpr_b;
+			vcpu->arch.fp.fpscr = *fpr_b;
 			break;
 		case OP_63_FCMPU:
 		{
@@ -1172,7 +1169,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			u32 cr0_mask = 0xf0000000;
 			u32 cr_shift = inst_get_field(inst, 6, 8) * 4;
 
-			fpd_fcmpu(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b);
+			fpd_fcmpu(&vcpu->arch.fp.fpscr, &tmp_cr, fpr_a, fpr_b);
 			cr &= ~(cr0_mask >> cr_shift);
 			cr |= (cr & cr0_mask) >> cr_shift;
 			break;
@@ -1183,40 +1180,40 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			u32 cr0_mask = 0xf0000000;
 			u32 cr_shift = inst_get_field(inst, 6, 8) * 4;
 
-			fpd_fcmpo(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b);
+			fpd_fcmpo(&vcpu->arch.fp.fpscr, &tmp_cr, fpr_a, fpr_b);
 			cr &= ~(cr0_mask >> cr_shift);
 			cr |= (cr & cr0_mask) >> cr_shift;
 			break;
 		}
 		case OP_63_FNEG:
-			fpd_fneg(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fneg(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			break;
 		case OP_63_FMR:
 			*fpr_d = *fpr_b;
 			break;
 		case OP_63_FABS:
-			fpd_fabs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fabs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			break;
 		case OP_63_FCPSGN:
-			fpd_fcpsgn(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fcpsgn(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			break;
 		case OP_63_FDIV:
-			fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fdiv(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			break;
 		case OP_63_FADD:
-			fpd_fadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			break;
 		case OP_63_FSUB:
-			fpd_fsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			fpd_fsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b);
 			break;
 		case OP_63_FCTIW:
-			fpd_fctiw(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fctiw(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			break;
 		case OP_63_FCTIWZ:
-			fpd_fctiwz(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fctiwz(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			break;
 		case OP_63_FRSP:
-			fpd_frsp(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_frsp(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			kvmppc_sync_qpr(vcpu, ax_rd);
 			break;
 		case OP_63_FRSQRTE:
@@ -1224,39 +1221,39 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			double one = 1.0f;
 
 			/* fD = sqrt(fB) */
-			fpd_fsqrt(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			fpd_fsqrt(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b);
 			/* fD = 1.0f / fD */
-			fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, (u64*)&one, fpr_d);
+			fpd_fdiv(&vcpu->arch.fp.fpscr, &cr, fpr_d, (u64*)&one, fpr_d);
 			break;
 		}
 		}
 		switch (inst_get_field(inst, 26, 30)) {
 		case OP_63_FMUL:
-			fpd_fmul(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c);
+			fpd_fmul(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c);
 			break;
 		case OP_63_FSEL:
-			fpd_fsel(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fsel(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			break;
 		case OP_63_FMSUB:
-			fpd_fmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fmsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			break;
 		case OP_63_FMADD:
-			fpd_fmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fmadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			break;
 		case OP_63_FNMSUB:
-			fpd_fnmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fnmsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			break;
 		case OP_63_FNMADD:
-			fpd_fnmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			fpd_fnmadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
 			break;
 		}
 		break;
 	}
 
 #ifdef DEBUG
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fp.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
+		kvm_cvt_df(&VCPU_FPR(vcpu, i), &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f);
 	}
 #endif
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 5b9e9063cfaf..c5c052a9729c 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -41,6 +41,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/miscdevice.h>
 
 #include "book3s.h"
 
@@ -566,12 +567,6 @@ static inline int get_fpr_index(int i)
 void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 {
 	struct thread_struct *t = &current->thread;
-	u64 *vcpu_fpr = vcpu->arch.fpr;
-#ifdef CONFIG_VSX
-	u64 *vcpu_vsx = vcpu->arch.vsr;
-#endif
-	u64 *thread_fpr = &t->fp_state.fpr[0][0];
-	int i;
 
 	/*
 	 * VSX instructions can access FP and vector registers, so if
@@ -594,26 +589,16 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 		 * both the traditional FP registers and the added VSX
 		 * registers into thread.fp_state.fpr[].
 		 */
-		if (current->thread.regs->msr & MSR_FP)
+		if (t->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->fp_state.fpscr;
-
-#ifdef CONFIG_VSX
-		if (cpu_has_feature(CPU_FTR_VSX))
-			for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
-				vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
-#endif
+		t->fp_save_area = NULL;
 	}
 
 #ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
 		if (current->thread.regs->msr & MSR_VEC)
 			giveup_altivec(current);
-		memcpy(vcpu->arch.vr, t->vr_state.vr, sizeof(vcpu->arch.vr));
-		vcpu->arch.vscr = t->vr_state.vscr;
+		t->vr_save_area = NULL;
 	}
 #endif
 
@@ -661,12 +646,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 			     ulong msr)
 {
 	struct thread_struct *t = &current->thread;
-	u64 *vcpu_fpr = vcpu->arch.fpr;
-#ifdef CONFIG_VSX
-	u64 *vcpu_vsx = vcpu->arch.vsr;
-#endif
-	u64 *thread_fpr = &t->fp_state.fpr[0][0];
-	int i;
 
 	/* When we have paired singles, we emulate in software */
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
@@ -704,27 +683,20 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #endif
 
 	if (msr & MSR_FP) {
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
-			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
-#ifdef CONFIG_VSX
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
-			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
-#endif
-		t->fp_state.fpscr = vcpu->arch.fpscr;
-		t->fpexc_mode = 0;
-		kvmppc_load_up_fpu();
+		enable_kernel_fp();
+		load_fp_state(&vcpu->arch.fp);
+		t->fp_save_area = &vcpu->arch.fp;
 	}
 
 	if (msr & MSR_VEC) {
 #ifdef CONFIG_ALTIVEC
-		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();
+		enable_kernel_altivec();
+		load_vr_state(&vcpu->arch.vr);
+		t->vr_save_area = &vcpu->arch.vr;
 #endif
 	}
 
-	current->thread.regs->msr |= msr;
+	t->regs->msr |= msr;
 	vcpu->arch.guest_owned_ext |= msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
@@ -743,11 +715,15 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
 	if (!lost_ext)
 		return;
 
-	if (lost_ext & MSR_FP)
-		kvmppc_load_up_fpu();
+	if (lost_ext & MSR_FP) {
+		enable_kernel_fp();
+		load_fp_state(&vcpu->arch.fp);
+	}
 #ifdef CONFIG_ALTIVEC
-	if (lost_ext & MSR_VEC)
-		kvmppc_load_up_altivec();
+	if (lost_ext & MSR_VEC) {
+		enable_kernel_altivec();
+		load_vr_state(&vcpu->arch.vr);
+	}
 #endif
 	current->thread.regs->msr |= lost_ext;
 }
@@ -873,6 +849,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* We're good on these - the host merely wanted to get our attention */
 	case BOOK3S_INTERRUPT_DECREMENTER:
 	case BOOK3S_INTERRUPT_HV_DECREMENTER:
+	case BOOK3S_INTERRUPT_DOORBELL:
 		vcpu->stat.dec_exits++;
 		r = RESUME_GUEST;
 		break;
@@ -1045,14 +1022,14 @@ program_interrupt:
 		 * and if we really did time things so badly, then we just exit
 		 * again due to a host external interrupt.
 		 */
-		local_irq_disable();
 		s = kvmppc_prepare_to_enter(vcpu);
-		if (s <= 0) {
-			local_irq_enable();
+		if (s <= 0)
 			r = s;
-		} else {
+		else {
+			/* interrupts now hard-disabled */
 			kvmppc_fix_ee_before_entry();
 		}
+
 		kvmppc_handle_lost_ext(vcpu);
 	}
 
@@ -1133,19 +1110,6 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_HIOR:
 		*val = get_reg_val(id, to_book3s(vcpu)->hior);
 		break;
-#ifdef CONFIG_VSX
-	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
-		long int i = id - KVM_REG_PPC_VSR0;
-
-		if (!cpu_has_feature(CPU_FTR_VSX)) {
-			r = -ENXIO;
-			break;
-		}
-		val->vsxval[0] = vcpu->arch.fpr[i];
-		val->vsxval[1] = vcpu->arch.vsr[i];
-		break;
-	}
-#endif /* CONFIG_VSX */
 	default:
 		r = -EINVAL;
 		break;
@@ -1164,19 +1128,6 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 		to_book3s(vcpu)->hior = set_reg_val(id, *val);
 		to_book3s(vcpu)->hior_explicit = true;
 		break;
-#ifdef CONFIG_VSX
-	case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
-		long int i = id - KVM_REG_PPC_VSR0;
-
-		if (!cpu_has_feature(CPU_FTR_VSX)) {
-			r = -ENXIO;
-			break;
-		}
-		vcpu->arch.fpr[i] = val->vsxval[0];
-		vcpu->arch.vsr[i] = val->vsxval[1];
-		break;
-	}
-#endif /* CONFIG_VSX */
 	default:
 		r = -EINVAL;
 		break;
@@ -1274,17 +1225,9 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
-	struct thread_fp_state fp;
-	int fpexc_mode;
 #ifdef CONFIG_ALTIVEC
-	struct thread_vr_state vr;
 	unsigned long uninitialized_var(vrsave);
-	int used_vr;
 #endif
-#ifdef CONFIG_VSX
-	int used_vsr;
-#endif
-	ulong ext_msr;
 
 	/* Check if we can run the vcpu at all */
 	if (!vcpu->arch.sane) {
@@ -1299,40 +1242,27 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * really did time things so badly, then we just exit again due to
 	 * a host external interrupt.
 	 */
-	local_irq_disable();
 	ret = kvmppc_prepare_to_enter(vcpu);
-	if (ret <= 0) {
-		local_irq_enable();
+	if (ret <= 0)
 		goto out;
-	}
+	/* interrupts now hard-disabled */
 
-	/* Save FPU state in stack */
+	/* Save FPU state in thread_struct */
 	if (current->thread.regs->msr & MSR_FP)
 		giveup_fpu(current);
-	fp = current->thread.fp_state;
-	fpexc_mode = current->thread.fpexc_mode;
 
 #ifdef CONFIG_ALTIVEC
-	/* Save Altivec state in stack */
-	used_vr = current->thread.used_vr;
-	if (used_vr) {
-		if (current->thread.regs->msr & MSR_VEC)
-			giveup_altivec(current);
-		vr = current->thread.vr_state;
-		vrsave = current->thread.vrsave;
-	}
+	/* Save Altivec state in thread_struct */
+	if (current->thread.regs->msr & MSR_VEC)
+		giveup_altivec(current);
 #endif
 
 #ifdef CONFIG_VSX
-	/* Save VSX state in stack */
-	used_vsr = current->thread.used_vsr;
-	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
+	/* Save VSX state in thread_struct */
+	if (current->thread.regs->msr & MSR_VSX)
 		__giveup_vsx(current);
 #endif
 
-	/* Remember the MSR with disabled extensions */
-	ext_msr = current->thread.regs->msr;
-
 	/* Preload FPU if it's enabled */
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
@@ -1347,25 +1277,6 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* Make sure we save the guest FPU/Altivec/VSX state */
 	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
 
-	current->thread.regs->msr = ext_msr;
-
-	/* Restore FPU/VSX state from stack */
-	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) {
-		current->thread.vr_state = vr;
-		current->thread.vrsave = vrsave;
-	}
-	current->thread.used_vr = used_vr;
-#endif
-
-#ifdef CONFIG_VSX
-	current->thread.used_vsr = used_vsr;
-#endif
-
 out:
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	return ret;
@@ -1606,4 +1517,6 @@ module_init(kvmppc_book3s_init_pr);
 module_exit(kvmppc_book3s_exit_pr);
 
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
 #endif
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index c3c5231adade..9eec675220e6 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -162,51 +162,4 @@ _GLOBAL(kvmppc_entry_trampoline)
 	mtsrr1	r6
 	RFI
 
-#if defined(CONFIG_PPC_BOOK3S_32)
-#define STACK_LR	INT_FRAME_SIZE+4
-
-/* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */
-#define MSR_EXT_START						\
-	PPC_STL	r20, _NIP(r1);					\
-	mfmsr	r20;						\
-	LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE);			\
-	andc	r3,r20,r3;		/* Disable DR,EE */	\
-	mtmsr	r3;						\
-	sync
-
-#define MSR_EXT_END						\
-	mtmsr	r20;			/* Enable DR,EE */	\
-	sync;							\
-	PPC_LL	r20, _NIP(r1)
-
-#elif defined(CONFIG_PPC_BOOK3S_64)
-#define STACK_LR	_LINK
-#define MSR_EXT_START
-#define MSR_EXT_END
-#endif
-
-/*
- * Activate current's external feature (FPU/Altivec/VSX)
- */
-#define define_load_up(what) 					\
-								\
-_GLOBAL(kvmppc_load_up_ ## what);				\
-	PPC_STLU r1, -INT_FRAME_SIZE(r1);			\
-	mflr	r3;						\
-	PPC_STL	r3, STACK_LR(r1);				\
-	MSR_EXT_START;						\
-								\
-	bl	FUNC(load_up_ ## what);				\
-								\
-	MSR_EXT_END;						\
-	PPC_LL	r3, STACK_LR(r1);				\
-	mtlr	r3;						\
-	addi	r1, r1, INT_FRAME_SIZE;				\
-	blr
-
-define_load_up(fpu)
-#ifdef CONFIG_ALTIVEC
-define_load_up(altivec)
-#endif
-
 #include "book3s_segment.S"
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index bc50c97751d3..1e0cc2adfd40 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -361,6 +361,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	beqa	BOOK3S_INTERRUPT_DECREMENTER
 	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
 	beqa	BOOK3S_INTERRUPT_PERFMON
+	cmpwi	r12, BOOK3S_INTERRUPT_DOORBELL
+	beqa	BOOK3S_INTERRUPT_DOORBELL
 
 	RFI
 kvmppc_handler_trampoline_exit_end:
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 02a17dcf1610..d1acd32a64c0 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1246,8 +1246,10 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 		kvm->arch.xics = xics;
 	mutex_unlock(&kvm->lock);
 
-	if (ret)
+	if (ret) {
+		kfree(xics);
 		return ret;
+	}
 
 	xics_debugfs_init(xics);
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 0591e05db74b..ab62109fdfa3 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -643,7 +643,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 		local_irq_enable();
 		kvm_vcpu_block(vcpu);
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
-		local_irq_disable();
+		hard_irq_disable();
 
 		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
 		r = 1;
@@ -682,34 +682,22 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
 	struct debug_reg debug;
-#ifdef CONFIG_PPC_FPU
-	struct thread_fp_state fp;
-	int fpexc_mode;
-#endif
 
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
-	local_irq_disable();
 	s = kvmppc_prepare_to_enter(vcpu);
 	if (s <= 0) {
-		local_irq_enable();
 		ret = s;
 		goto out;
 	}
+	/* interrupts now hard-disabled */
 
 #ifdef CONFIG_PPC_FPU
 	/* Save userspace FPU state in stack */
 	enable_kernel_fp();
-	fp = current->thread.fp_state;
-	fpexc_mode = current->thread.fpexc_mode;
-
-	/* Restore guest FPU state to thread */
-	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
@@ -728,6 +716,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.shadow_dbg_reg;
 
+	vcpu->arch.pgdir = current->mm->pgd;
 	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -743,15 +732,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_save_guest_fp(vcpu);
 
 	vcpu->fpu_active = 0;
-
-	/* Save guest FPU state from thread */
-	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 */
-	current->thread.fp_state = fp;
-	current->thread.fpexc_mode = fpexc_mode;
 #endif
 
 out:
@@ -898,17 +878,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int s;
 	int idx;
 
-#ifdef CONFIG_PPC64
-	WARN_ON(local_paca->irq_happened != 0);
-#endif
-
-	/*
-	 * We enter with interrupts disabled in hardware, but
-	 * we need to call hard_irq_disable anyway to ensure that
-	 * the software state is kept in sync.
-	 */
-	hard_irq_disable();
-
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
 
@@ -1217,12 +1186,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * aren't already exiting to userspace for some other reason.
 	 */
 	if (!(r & RESUME_HOST)) {
-		local_irq_disable();
 		s = kvmppc_prepare_to_enter(vcpu);
-		if (s <= 0) {
-			local_irq_enable();
+		if (s <= 0)
 			r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
-		} else {
+		else {
+			/* interrupts now hard-disabled */
 			kvmppc_fix_ee_before_entry();
 		}
 	}
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 09bfd9bc7cf8..b632cd35919b 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -136,7 +136,9 @@ static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_FPU
 	if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) {
-		load_up_fpu();
+		enable_kernel_fp();
+		load_fp_state(&vcpu->arch.fp);
+		current->thread.fp_save_area = &vcpu->arch.fp;
 		current->thread.regs->msr |= MSR_FP;
 	}
 #endif
@@ -151,6 +153,7 @@ static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_PPC_FPU
 	if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP))
 		giveup_fpu(current);
+	current->thread.fp_save_area = NULL;
 #endif
 }
 
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index e8ed7d659c55..be3de1dd7bb3 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -33,6 +33,8 @@
 
 #ifdef CONFIG_64BIT
 #include <asm/exception-64e.h>
+#include <asm/hw_irq.h>
+#include <asm/irqflags.h>
 #else
 #include "../kernel/head_booke.h" /* for THREAD_NORMSAVE() */
 #endif
@@ -465,6 +467,15 @@ _GLOBAL(kvmppc_resume_host)
 	mtspr	SPRN_EPCR, r3
 	isync
 
+#ifdef CONFIG_64BIT
+	/*
+	 * We enter with interrupts disabled in hardware, but
+	 * we need to call RECONCILE_IRQ_STATE to ensure
+	 * that the software state is kept in sync.
+	 */
+	RECONCILE_IRQ_STATE(r3,r5)
+#endif
+
 	/* Switch to kernel stack and jump to handler. */
 	PPC_LL	r3, HOST_RUN(r1)
 	mr	r5, r14 /* intno */
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 497b142f651c..2e02ed849f36 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -16,6 +16,8 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/export.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -573,3 +575,5 @@ static void __exit kvmppc_e500_exit(void)
 
 module_init(kvmppc_e500_init);
 module_exit(kvmppc_e500_exit);
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 4fd9650eb018..a326178bdea5 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -31,11 +31,13 @@ enum vcpu_ftr {
 #define E500_TLB_NUM   2
 
 /* entry is mapped somewhere in host TLB */
-#define E500_TLB_VALID		(1 << 0)
+#define E500_TLB_VALID		(1 << 31)
 /* TLB1 entry is mapped by host TLB1, tracked by bitmaps */
-#define E500_TLB_BITMAP		(1 << 1)
+#define E500_TLB_BITMAP		(1 << 30)
 /* TLB1 entry is mapped by host TLB0 */
-#define E500_TLB_TLB0		(1 << 2)
+#define E500_TLB_TLB0		(1 << 29)
+/* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */
+#define E500_TLB_MAS2_ATTR	(0x7f)
 
 struct tlbe_ref {
 	pfn_t pfn;		/* valid only for TLB0, except briefly */
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index ebca6b88ea5e..50860e919cb8 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -127,7 +127,7 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 }
 
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
-		unsigned int eaddr, int as)
+		gva_t eaddr, int as)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	unsigned int victim, tsized;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index ecf2247b13be..dd2cc03f406f 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -65,15 +65,6 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
 	return mas3;
 }
 
-static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
-{
-#ifdef CONFIG_SMP
-	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
-#else
-	return mas2 & MAS2_ATTRIB_MASK;
-#endif
-}
-
 /*
  * writing shadow tlb entry to host TLB
  */
@@ -231,15 +222,15 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 		ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
 	}
 
-	/* Already invalidated in between */
-	if (!(ref->flags & E500_TLB_VALID))
-		return;
-
-	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
-	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
+	/*
+	 * If TLB entry is still valid then it's a TLB0 entry, and thus
+	 * backed by at most one host tlbe per shadow pid
+	 */
+	if (ref->flags & E500_TLB_VALID)
+		kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
 
 	/* Mark the TLB as not backed by the host anymore */
-	ref->flags &= ~E500_TLB_VALID;
+	ref->flags = 0;
 }
 
 static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
@@ -249,10 +240,13 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 
 static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 pfn_t pfn)
+					 pfn_t pfn, unsigned int wimg)
 {
 	ref->pfn = pfn;
-	ref->flags |= E500_TLB_VALID;
+	ref->flags = E500_TLB_VALID;
+
+	/* Use guest supplied MAS2_G and MAS2_E */
+	ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
 
 	/* Mark the page accessed */
 	kvm_set_pfn_accessed(pfn);
@@ -316,8 +310,7 @@ static void kvmppc_e500_setup_stlbe(
 
 	/* Force IPROT=0 for all guest mappings. */
 	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN) |
-		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
+	stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
 			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
 
@@ -339,6 +332,10 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	int ret = 0;
 	unsigned long mmu_seq;
 	struct kvm *kvm = vcpu_e500->vcpu.kvm;
+	unsigned long tsize_pages = 0;
+	pte_t *ptep;
+	unsigned int wimg = 0;
+	pgd_t *pgdir;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -405,7 +402,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 			 */
 
 			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
-				unsigned long gfn_start, gfn_end, tsize_pages;
+				unsigned long gfn_start, gfn_end;
 				tsize_pages = 1 << (tsize - 2);
 
 				gfn_start = gfn & ~(tsize_pages - 1);
@@ -447,11 +444,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	if (likely(!pfnmap)) {
-		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
+		tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
 		pfn = gfn_to_pfn_memslot(slot, gfn);
 		if (is_error_noslot_pfn(pfn)) {
-			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
-					(long)gfn);
+			if (printk_ratelimit())
+				pr_err("%s: real page not found for gfn %lx\n",
+				       __func__, (long)gfn);
 			return -EINVAL;
 		}
 
@@ -466,7 +464,18 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		goto out;
 	}
 
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
+
+	pgdir = vcpu_e500->vcpu.arch.pgdir;
+	ptep = lookup_linux_ptep(pgdir, hva, &tsize_pages);
+	if (pte_present(*ptep))
+		wimg = (*ptep >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
+	else {
+		if (printk_ratelimit())
+			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
+				__func__, (long)gfn, pfn);
+		return -EINVAL;
+	}
+	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
 				ref, gvaddr, stlbe);
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 4132cd2fc171..17e456279224 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -16,6 +16,8 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/export.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -391,3 +393,5 @@ static void __exit kvmppc_e500mc_exit(void)
 
 module_init(kvmppc_e500mc_init);
 module_exit(kvmppc_e500mc_exit);
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 2f9a0873b44f..c2b887be2c29 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -219,7 +219,6 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
  * lmw
  * stmw
  *
- * XXX is_bigendian should depend on MMU mapping or MSR[LE]
  */
 /* XXX Should probably auto-generate instruction decoding for a particular core
  * from opcode tables in the future. */
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index 2861ae9eaae6..efbd9962a209 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -1635,6 +1635,7 @@ static void mpic_destroy(struct kvm_device *dev)
 
 	dev->kvm->arch.mpic = NULL;
 	kfree(opp);
+	kfree(dev);
 }
 
 static int mpic_set_default_irq_routing(struct openpic *opp)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9ae97686e9f4..3cf541a53e2a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -68,14 +68,16 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
  */
 int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
-	int r = 1;
+	int r;
+
+	WARN_ON(irqs_disabled());
+	hard_irq_disable();
 
-	WARN_ON_ONCE(!irqs_disabled());
 	while (true) {
 		if (need_resched()) {
 			local_irq_enable();
 			cond_resched();
-			local_irq_disable();
+			hard_irq_disable();
 			continue;
 		}
 
@@ -101,7 +103,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			local_irq_enable();
 			trace_kvm_check_requests(vcpu);
 			r = kvmppc_core_check_requests(vcpu);
-			local_irq_disable();
+			hard_irq_disable();
 			if (r > 0)
 				continue;
 			break;
@@ -113,22 +115,12 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-#ifdef CONFIG_PPC64
-		/* lazy EE magic */
-		hard_irq_disable();
-		if (lazy_irq_pending()) {
-			/* Got an interrupt in between, try again */
-			local_irq_enable();
-			local_irq_disable();
-			kvm_guest_exit();
-			continue;
-		}
-#endif
-
 		kvm_guest_enter();
-		break;
+		return 1;
 	}
 
+	/* return to host */
+	local_irq_enable();
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
@@ -656,14 +648,14 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 		kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 		break;
 	case KVM_MMIO_REG_FPR:
-		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
+		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
 		break;
 #ifdef CONFIG_PPC_BOOK3S
 	case KVM_MMIO_REG_QPR:
 		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 	case KVM_MMIO_REG_FQPR:
-		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
+		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
 		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 #endif
@@ -673,9 +665,19 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 }
 
 int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int rt, unsigned int bytes, int is_bigendian)
+		       unsigned int rt, unsigned int bytes,
+		       int is_default_endian)
 {
 	int idx, ret;
+	int is_bigendian;
+
+	if (kvmppc_need_byteswap(vcpu)) {
+		/* Default endianness is "little endian". */
+		is_bigendian = !is_default_endian;
+	} else {
+		/* Default endianness is "big endian". */
+		is_bigendian = is_default_endian;
+	}
 
 	if (bytes > sizeof(run->mmio.data)) {
 		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
@@ -711,21 +713,31 @@ EXPORT_SYMBOL_GPL(kvmppc_handle_load);
 
 /* Same as above, but sign extends */
 int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                        unsigned int rt, unsigned int bytes, int is_bigendian)
+			unsigned int rt, unsigned int bytes,
+			int is_default_endian)
 {
 	int r;
 
 	vcpu->arch.mmio_sign_extend = 1;
-	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian);
+	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian);
 
 	return r;
 }
 
 int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                        u64 val, unsigned int bytes, int is_bigendian)
+			u64 val, unsigned int bytes, int is_default_endian)
 {
 	void *data = run->mmio.data;
 	int idx, ret;
+	int is_bigendian;
+
+	if (kvmppc_need_byteswap(vcpu)) {
+		/* Default endianness is "little endian". */
+		is_bigendian = !is_default_endian;
+	} else {
+		/* Default endianness is "big endian". */
+		is_bigendian = is_default_endian;
+	}
 
 	if (bytes > sizeof(run->mmio.data)) {
 		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,