Merge tag 'kvm-3.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "KVM updates for the 3.9 merge window, including x86 real mode
  emulation fixes, stronger memory slot interface restrictions, mmu_lock
  spinlock hold time reduction, improved handling of large page faults
  on shadow, initial APICv HW acceleration support, s390 channel IO
  based virtio, amongst others"

* tag 'kvm-3.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (143 commits)
  Revert "KVM: MMU: lazily drop large spte"
  x86: pvclock kvm: align allocation size to page size
  KVM: nVMX: Remove redundant get_vmcs12 from nested_vmx_exit_handled_msr
  x86 emulator: fix parity calculation for AAD instruction
  KVM: PPC: BookE: Handle alignment interrupts
  booke: Added DBCR4 SPR number
  KVM: PPC: booke: Allow multiple exception types
  KVM: PPC: booke: use vcpu reference from thread_struct
  KVM: Remove user_alloc from struct kvm_memory_slot
  KVM: VMX: disable apicv by default
  KVM: s390: Fix handling of iscs.
  KVM: MMU: cleanup __direct_map
  KVM: MMU: remove pt_access in mmu_set_spte
  KVM: MMU: cleanup mapping-level
  KVM: MMU: lazily drop large spte
  KVM: VMX: cleanup vmx_set_cr0().
  KVM: VMX: add missing exit names to VMX_EXIT_REASONS array
  KVM: VMX: disable SMEP feature when guest is in non-paging mode
  KVM: Remove duplicate text in api.txt
  Revert "KVM: MMU: split kvm_mmu_free_page"
  ...

15 files changed, 910 insertions, 674 deletions

diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 1e473d4..b772ede 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -10,7 +10,8 @@ common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o \
 						eventfd.o)
 
 CFLAGS_44x_tlb.o  := -I.
-CFLAGS_e500_tlb.o := -I.
+CFLAGS_e500_mmu.o := -I.
+CFLAGS_e500_mmu_host.o := -I.
 CFLAGS_emulate.o  := -I.
 
 common-objs-y += powerpc.o emulate.o
@@ -35,7 +36,8 @@ kvm-e500-objs := \
 	booke_emulate.o \
 	booke_interrupts.o \
 	e500.o \
-	e500_tlb.o \
+	e500_mmu.o \
+	e500_mmu_host.o \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500V2) := $(kvm-e500-objs)
 
@@ -45,7 +47,8 @@ kvm-e500mc-objs := \
 	booke_emulate.o \
 	bookehv_interrupts.o \
 	e500mc.o \
-	e500_tlb.o \
+	e500_mmu.o \
+	e500_mmu_host.o \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index d31a716..836c569 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -34,6 +34,8 @@
 #define OP_31_XOP_MTSRIN	242
 #define OP_31_XOP_TLBIEL	274
 #define OP_31_XOP_TLBIE		306
+/* Opcode is officially reserved, reuse it as sc 1 when sc 1 doesn't trap */
+#define OP_31_XOP_FAKE_SC1	308
 #define OP_31_XOP_SLBMTE	402
 #define OP_31_XOP_SLBIE		434
 #define OP_31_XOP_SLBIA		498
@@ -170,6 +172,32 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
+#ifdef CONFIG_KVM_BOOK3S_64_PR
+		case OP_31_XOP_FAKE_SC1:
+		{
+			/* SC 1 papr hypercalls */
+			ulong cmd = kvmppc_get_gpr(vcpu, 3);
+			int i;
+
+		        if ((vcpu->arch.shared->msr & MSR_PR) ||
+			    !vcpu->arch.papr_enabled) {
+				emulated = EMULATE_FAIL;
+				break;
+			}
+
+			if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE)
+				break;
+
+			run->papr_hcall.nr = cmd;
+			for (i = 0; i < 9; ++i) {
+				ulong gpr = kvmppc_get_gpr(vcpu, 4 + i);
+				run->papr_hcall.args[i] = gpr;
+			}
+
+			emulated = EMULATE_DO_PAPR;
+			break;
+		}
+#endif
 		case OP_31_XOP_EIOIO:
 			break;
 		case OP_31_XOP_SLBMTE:
@@ -427,6 +455,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
+	case SPRN_MSSSR0:
 		break;
 unprivileged:
 	default:
@@ -523,6 +552,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
+	case SPRN_MSSSR0:
 		*spr_val = 0;
 		break;
 	default:
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 71d0c90..80dcc53 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1549,7 +1549,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 6702442..5e93438 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -762,6 +762,11 @@ program_interrupt:
 			run->exit_reason = KVM_EXIT_MMIO;
 			r = RESUME_HOST_NV;
 			break;
+		case EMULATE_DO_PAPR:
+			run->exit_reason = KVM_EXIT_PAPR_HCALL;
+			vcpu->arch.hcall_needed = 1;
+			r = RESUME_HOST_NV;
+			break;
 		default:
 			BUG();
 		}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 69f1140..020923e 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -182,6 +182,14 @@ static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu,
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
 }
 
+static void kvmppc_core_queue_alignment(struct kvm_vcpu *vcpu, ulong dear_flags,
+					ulong esr_flags)
+{
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALIGNMENT);
+}
+
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
 {
 	vcpu->arch.queued_esr = esr_flags;
@@ -300,13 +308,22 @@ static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
 #endif
 }
 
+static unsigned long get_guest_epr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GEPR);
+#else
+	return vcpu->arch.epr;
+#endif
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
 {
 	int allowed = 0;
 	ulong msr_mask = 0;
-	bool update_esr = false, update_dear = false;
+	bool update_esr = false, update_dear = false, update_epr = false;
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
@@ -330,9 +347,13 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		keep_irq = true;
 	}
 
+	if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled)
+		update_epr = true;
+
 	switch (priority) {
 	case BOOKE_IRQPRIO_DTLB_MISS:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
+	case BOOKE_IRQPRIO_ALIGNMENT:
 		update_dear = true;
 		/* fall through */
 	case BOOKE_IRQPRIO_INST_STORAGE:
@@ -346,7 +367,6 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_SPE_FP_DATA:
 	case BOOKE_IRQPRIO_SPE_FP_ROUND:
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
-	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
 		msr_mask = MSR_CE | MSR_ME | MSR_DE;
 		int_class = INT_CLASS_NONCRIT;
@@ -408,6 +428,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
 			set_guest_dear(vcpu, vcpu->arch.queued_dear);
+		if (update_epr == true)
+			kvm_make_request(KVM_REQ_EPR_EXIT, vcpu);
 
 		new_msr &= msr_mask;
 #if defined(CONFIG_64BIT)
@@ -581,6 +603,11 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	kvmppc_core_check_exceptions(vcpu);
 
+	if (vcpu->requests) {
+		/* Exception delivery raised request; start over */
+		return 1;
+	}
+
 	if (vcpu->arch.shared->msr & MSR_WE) {
 		local_irq_enable();
 		kvm_vcpu_block(vcpu);
@@ -610,6 +637,13 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 		r = 0;
 	}
 
+	if (kvm_check_request(KVM_REQ_EPR_EXIT, vcpu)) {
+		vcpu->run->epr.epr = 0;
+		vcpu->arch.epr_needed = true;
+		vcpu->run->exit_reason = KVM_EXIT_EPR;
+		r = 0;
+	}
+
 	return r;
 }
 
@@ -945,6 +979,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_ALIGNMENT:
+		kvmppc_core_queue_alignment(vcpu, vcpu->arch.fault_dear,
+		                            vcpu->arch.fault_esr);
+		r = RESUME_GUEST;
+		break;
+
 #ifdef CONFIG_KVM_BOOKE_HV
 	case BOOKE_INTERRUPT_HV_SYSCALL:
 		if (!(vcpu->arch.shared->msr & MSR_PR)) {
@@ -1388,6 +1428,11 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				 &vcpu->arch.dbg_reg.dac[dac], sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 epr = get_guest_epr(vcpu);
+		r = put_user(epr, (u32 __user *)(long)reg->addr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR:
 		r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr);
@@ -1420,6 +1465,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			     (u64 __user *)(long)reg->addr, sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 new_epr;
+		r = get_user(new_epr, (u32 __user *)(long)reg->addr);
+		if (!r)
+			kvmppc_set_epr(vcpu, new_epr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR: {
 		u32 new_epcr;
@@ -1556,7 +1608,9 @@ int __init kvmppc_booke_init(void)
 {
 #ifndef CONFIG_KVM_BOOKE_HV
 	unsigned long ivor[16];
+	unsigned long *handler = kvmppc_booke_handler_addr;
 	unsigned long max_ivor = 0;
+	unsigned long handler_len;
 	int i;
 
 	/* We install our own exception handlers by hijacking IVPR. IVPR must
@@ -1589,14 +1643,16 @@ int __init kvmppc_booke_init(void)
 
 	for (i = 0; i < 16; i++) {
 		if (ivor[i] > max_ivor)
-			max_ivor = ivor[i];
+			max_ivor = i;
 
+		handler_len = handler[i + 1] - handler[i];
 		memcpy((void *)kvmppc_booke_handlers + ivor[i],
-		       kvmppc_handlers_start + i * kvmppc_handler_len,
-		       kvmppc_handler_len);
+		       (void *)handler[i], handler_len);
 	}
-	flush_icache_range(kvmppc_booke_handlers,
-	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
+	handler_len = handler[max_ivor + 1] - handler[max_ivor];
+	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
+			   ivor[max_ivor] + handler_len);
 #endif /* !BOOKE_HV */
 	return 0;
 }
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index e9b88e4..5fd1ba6 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -65,6 +65,7 @@
 			  (1 << BOOKE_IRQPRIO_CRITICAL))
 
 extern unsigned long kvmppc_booke_handlers;
+extern unsigned long kvmppc_booke_handler_addr[];
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
 void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 4685b8c..27a4b28 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -269,6 +269,9 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_ESR:
 		*spr_val = vcpu->arch.shared->esr;
 		break;
+	case SPRN_EPR:
+		*spr_val = vcpu->arch.epr;
+		break;
 	case SPRN_CSRR0:
 		*spr_val = vcpu->arch.csrr0;
 		break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index bb46b32..f4bb55c 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -45,18 +45,21 @@
                         (1<<BOOKE_INTERRUPT_DEBUG))
 
 #define NEED_DEAR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
-                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                        (1<<BOOKE_INTERRUPT_ALIGNMENT))
 
 #define NEED_ESR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
                        (1<<BOOKE_INTERRUPT_INST_STORAGE) | \
                        (1<<BOOKE_INTERRUPT_PROGRAM) | \
-                       (1<<BOOKE_INTERRUPT_DTLB_MISS))
+                       (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                       (1<<BOOKE_INTERRUPT_ALIGNMENT))
 
 .macro KVM_HANDLER ivor_nr scratch srr0
 _GLOBAL(kvmppc_handler_\ivor_nr)
 	/* Get pointer to vcpu and record exit number. */
 	mtspr	\scratch , r4
-	mfspr	r4, SPRN_SPRG_RVCPU
+	mfspr   r4, SPRN_SPRG_THREAD
+	lwz     r4, THREAD_KVM_VCPU(r4)
 	stw	r3, VCPU_GPR(R3)(r4)
 	stw	r5, VCPU_GPR(R5)(r4)
 	stw	r6, VCPU_GPR(R6)(r4)
@@ -73,6 +76,14 @@ _GLOBAL(kvmppc_handler_\ivor_nr)
 	bctr
 .endm
 
+.macro KVM_HANDLER_ADDR ivor_nr
+	.long	kvmppc_handler_\ivor_nr
+.endm
+
+.macro KVM_HANDLER_END
+	.long	kvmppc_handlers_end
+.endm
+
 _GLOBAL(kvmppc_handlers_start)
 KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK  SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
@@ -93,9 +104,7 @@ KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
-
-_GLOBAL(kvmppc_handler_len)
-	.long kvmppc_handler_1 - kvmppc_handler_0
+_GLOBAL(kvmppc_handlers_end)
 
 /* Registers:
  *  SPRG_SCRATCH0: guest r4
@@ -402,9 +411,6 @@ lightweight_exit:
 	lwz	r8, kvmppc_booke_handlers@l(r8)
 	mtspr	SPRN_IVPR, r8
 
-	/* Save vcpu pointer for the exception handlers. */
-	mtspr	SPRN_SPRG_WVCPU, r4
-
 	lwz	r5, VCPU_SHARED(r4)
 
 	/* Can't switch the stack pointer until after IVPR is switched,
@@ -463,6 +469,31 @@ lightweight_exit:
 	lwz	r4, VCPU_GPR(R4)(r4)
 	rfi
 
+	.data
+	.align	4
+	.globl	kvmppc_booke_handler_addr
+kvmppc_booke_handler_addr:
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_CRITICAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_MACHINE_CHECK
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DATA_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_INST_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_EXTERNAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ALIGNMENT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_PROGRAM
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SYSCALL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_AP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DECREMENTER
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FIT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_WATCHDOG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DTLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ITLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DEBUG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_DATA
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER_END /*Always keep this in end*/
+
 #ifdef CONFIG_SPE
 _GLOBAL(kvmppc_save_guest_spe)
 	cmpi	0,r3,0
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index b479ed7..6dd4de7 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -491,6 +491,9 @@ static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];
+	/* Process remaining handlers above the generic first 16 */
+	unsigned long *handler = &kvmppc_booke_handler_addr[16];
+	unsigned long handler_len;
 	unsigned long max_ivor = 0;
 
 	r = kvmppc_core_check_processor_compat();
@@ -506,15 +509,16 @@ static int __init kvmppc_e500_init(void)
 	ivor[1] = mfspr(SPRN_IVOR33);
 	ivor[2] = mfspr(SPRN_IVOR34);
 	for (i = 0; i < 3; i++) {
-		if (ivor[i] > max_ivor)
-			max_ivor = ivor[i];
+		if (ivor[i] > ivor[max_ivor])
+			max_ivor = i;
 
+		handler_len = handler[i + 1] - handler[i];
 		memcpy((void *)kvmppc_booke_handlers + ivor[i],
-		       kvmppc_handlers_start + (i + 16) * kvmppc_handler_len,
-		       kvmppc_handler_len);
+		       (void *)handler[i], handler_len);
 	}
-	flush_icache_range(kvmppc_booke_handlers,
-			kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+	handler_len = handler[max_ivor + 1] - handler[max_ivor];
+	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
+			   ivor[max_ivor] + handler_len);
 
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 }
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index c70d37e..41cefd4 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -28,6 +28,7 @@
 
 #define E500_TLB_VALID 1
 #define E500_TLB_BITMAP 2
+#define E500_TLB_TLB0		(1 << 2)
 
 struct tlbe_ref {
 	pfn_t pfn;
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_mmu.c
index cf3f180..5c44759 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -1,10 +1,11 @@
 /*
- * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, yu.liu@freescale.com
  *         Scott Wood, scottwood@freescale.com
  *         Ashish Kalra, ashish.kalra@freescale.com
  *         Varun Sethi, varun.sethi@freescale.com
+ *         Alexander Graf, agraf@suse.de
  *
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
@@ -33,10 +34,7 @@
 #include "e500.h"
 #include "trace.h"
 #include "timing.h"
-
-#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
-
-static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+#include "e500_mmu_host.h"
 
 static inline unsigned int gtlb0_get_next_victim(
 		struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -50,174 +48,6 @@ static inline unsigned int gtlb0_get_next_victim(
 	return victim;
 }
 
-static inline unsigned int tlb1_max_shadow_size(void)
-{
-	/* reserve one entry for magic page */
-	return host_tlb_params[1].entries - tlbcam_index - 1;
-}
-
-static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
-}
-
-static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
-{
-	/* Mask off reserved bits. */
-	mas3 &= MAS3_ATTRIB_MASK;
-
-#ifndef CONFIG_KVM_BOOKE_HV
-	if (!usermode) {
-		/* Guest is in supervisor mode,
-		 * so we need to translate guest
-		 * supervisor permissions into user permissions. */
-		mas3 &= ~E500_TLB_USER_PERM_MASK;
-		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
-	}
-	mas3 |= E500_TLB_SUPER_PERM_MASK;
-#endif
-	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
- */
-static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
-				     uint32_t mas0)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	mtspr(SPRN_MAS0, mas0);
-	mtspr(SPRN_MAS1, stlbe->mas1);
-	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
-	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
-	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
-#ifdef CONFIG_KVM_BOOKE_HV
-	mtspr(SPRN_MAS8, stlbe->mas8);
-#endif
-	asm volatile("isync; tlbwe" : : : "memory");
-
-#ifdef CONFIG_KVM_BOOKE_HV
-	/* Must clear mas8 for other host tlbwe's */
-	mtspr(SPRN_MAS8, 0);
-	isync();
-#endif
-	local_irq_restore(flags);
-
-	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
-	                              stlbe->mas2, stlbe->mas7_3);
-}
-
-/*
- * Acquire a mas0 with victim hint, as if we just took a TLB miss.
- *
- * We don't care about the address we're searching for, other than that it's
- * in the right set and is not present in the TLB.  Using a zero PID and a
- * userspace address means we don't have to set and then restore MAS5, or
- * calculate a proper MAS6 value.
- */
-static u32 get_host_mas0(unsigned long eaddr)
-{
-	unsigned long flags;
-	u32 mas0;
-
-	local_irq_save(flags);
-	mtspr(SPRN_MAS6, 0);
-	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
-	mas0 = mfspr(SPRN_MAS0);
-	local_irq_restore(flags);
-
-	return mas0;
-}
-
-/* sesel is for tlb1 only */
-static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	u32 mas0;
-
-	if (tlbsel == 0) {
-		mas0 = get_host_mas0(stlbe->mas2);
-		__write_host_tlbe(stlbe, mas0);
-	} else {
-		__write_host_tlbe(stlbe,
-				  MAS0_TLBSEL(1) |
-				  MAS0_ESEL(to_htlb1_esel(sesel)));
-	}
-}
-
-#ifdef CONFIG_KVM_E500V2
-void kvmppc_map_magic(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry magic;
-	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
-	unsigned int stid;
-	pfn_t pfn;
-
-	pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT;
-	get_page(pfn_to_page(pfn));
-
-	preempt_disable();
-	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);
-
-	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
-		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
-	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
-		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
-	magic.mas8 = 0;
-
-	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
-	preempt_enable();
-}
-#endif
-
-static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
-				int tlbsel, int esel)
-{
-	struct kvm_book3e_206_tlb_entry *gtlbe =
-		get_entry(vcpu_e500, tlbsel, esel);
-
-	if (tlbsel == 1 &&
-	    vcpu_e500->gtlb_priv[1][esel].ref.flags & E500_TLB_BITMAP) {
-		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
-		int hw_tlb_indx;
-		unsigned long flags;
-
-		local_irq_save(flags);
-		while (tmp) {
-			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
-			mtspr(SPRN_MAS0,
-			      MAS0_TLBSEL(1) |
-			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
-			mtspr(SPRN_MAS1, 0);
-			asm volatile("tlbwe");
-			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
-			tmp &= tmp - 1;
-		}
-		mb();
-		vcpu_e500->g2h_tlb1_map[esel] = 0;
-		vcpu_e500->gtlb_priv[1][esel].ref.flags &= ~E500_TLB_BITMAP;
-		local_irq_restore(flags);
-
-		return;
-	}
-
-	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
-	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
-}
-
 static int tlb0_set_base(gva_t addr, int sets, int ways)
 {
 	int set_base;
@@ -296,70 +126,6 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 	return -1;
 }
 
-static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
-					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 pfn_t pfn)
-{
-	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
-
-	if (tlbe_is_writable(gtlbe))
-		kvm_set_pfn_dirty(pfn);
-}
-
-static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
-{
-	if (ref->flags & E500_TLB_VALID) {
-		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
-		ref->flags = 0;
-	}
-}
-
-static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	if (vcpu_e500->g2h_tlb1_map)
-		memset(vcpu_e500->g2h_tlb1_map, 0,
-		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
-	if (vcpu_e500->h2g_tlb1_rmap)
-		memset(vcpu_e500->h2g_tlb1_rmap, 0,
-		       sizeof(unsigned int) * host_tlb_params[1].entries);
-}
-
-static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int tlbsel = 0;
-	int i;
-
-	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
-		kvmppc_e500_ref_release(ref);
-	}
-}
-
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int stlbsel = 1;
-	int i;
-
-	kvmppc_e500_tlbil_all(vcpu_e500);
-
-	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->tlb_refs[stlbsel][i];
-		kvmppc_e500_ref_release(ref);
-	}
-
-	clear_tlb_privs(vcpu_e500);
-}
-
-void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	clear_tlb_refs(vcpu_e500);
-	clear_tlb1_bitmap(vcpu_e500);
-}
-
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
@@ -385,216 +151,6 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		| (as ? MAS6_SAS : 0);
 }
 
-/* TID must be supplied by the caller */
-static inline void kvmppc_e500_setup_stlbe(
-	struct kvm_vcpu *vcpu,
-	struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tsize, struct tlbe_ref *ref, u64 gvaddr,
-	struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	pfn_t pfn = ref->pfn;
-	u32 pr = vcpu->arch.shared->msr & MSR_PR;
-
-	BUG_ON(!(ref->flags & E500_TLB_VALID));
-
-	/* 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->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
-			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
-
-#ifdef CONFIG_KVM_BOOKE_HV
-	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
-#endif
-}
-
-static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
-	struct tlbe_ref *ref)
-{
-	struct kvm_memory_slot *slot;
-	unsigned long pfn = 0; /* silence GCC warning */
-	unsigned long hva;
-	int pfnmap = 0;
-	int tsize = BOOK3E_PAGESZ_4K;
-
-	/*
-	 * Translate guest physical to true physical, acquiring
-	 * a page reference if it is normal, non-reserved memory.
-	 *
-	 * gfn_to_memslot() must succeed because otherwise we wouldn't
-	 * have gotten this far.  Eventually we should just pass the slot
-	 * pointer through from the first lookup.
-	 */
-	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
-	hva = gfn_to_hva_memslot(slot, gfn);
-
-	if (tlbsel == 1) {
-		struct vm_area_struct *vma;
-		down_read(&current->mm->mmap_sem);
-
-		vma = find_vma(current->mm, hva);
-		if (vma && hva >= vma->vm_start &&
-		    (vma->vm_flags & VM_PFNMAP)) {
-			/*
-			 * This VMA is a physically contiguous region (e.g.
-			 * /dev/mem) that bypasses normal Linux page
-			 * management.  Find the overlap between the
-			 * vma and the memslot.
-			 */
-
-			unsigned long start, end;
-			unsigned long slot_start, slot_end;
-
-			pfnmap = 1;
-
-			start = vma->vm_pgoff;
-			end = start +
-			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);
-
-			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
-
-			slot_start = pfn - (gfn - slot->base_gfn);
-			slot_end = slot_start + slot->npages;
-
-			if (start < slot_start)
-				start = slot_start;
-			if (end > slot_end)
-				end = slot_end;
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-
-			/*
-			 * Now find the largest tsize (up to what the guest
-			 * requested) that will cover gfn, stay within the
-			 * range, and for which gfn and pfn are mutually
-			 * aligned.
-			 */
-
-			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
-				unsigned long gfn_start, gfn_end, tsize_pages;
-				tsize_pages = 1 << (tsize - 2);
-
-				gfn_start = gfn & ~(tsize_pages - 1);
-				gfn_end = gfn_start + tsize_pages;
-
-				if (gfn_start + pfn - gfn < start)
-					continue;
-				if (gfn_end + pfn - gfn > end)
-					continue;
-				if ((gfn & (tsize_pages - 1)) !=
-				    (pfn & (tsize_pages - 1)))
-					continue;
-
-				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
-				pfn &= ~(tsize_pages - 1);
-				break;
-			}
-		} else if (vma && hva >= vma->vm_start &&
-			   (vma->vm_flags & VM_HUGETLB)) {
-			unsigned long psize = vma_kernel_pagesize(vma);
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * Take the largest page size that satisfies both host
-			 * and guest mapping
-			 */
-			tsize = min(__ilog2(psize) - 10, tsize);
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-		}
-
-		up_read(&current->mm->mmap_sem);
-	}
-
-	if (likely(!pfnmap)) {
-		unsigned long 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);
-			return;
-		}
-
-		/* Align guest and physical address to page map boundaries */
-		pfn &= ~(tsize_pages - 1);
-		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
-	}
-
-	/* Drop old ref and setup new one. */
-	kvmppc_e500_ref_release(ref);
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
-
-	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
-				ref, gvaddr, stlbe);
-
-	/* Clear i-cache for new pages */
-	kvmppc_mmu_flush_icache(pfn);
-
-	/* Drop refcount on page, so that mmu notifiers can clear it */
-	kvm_release_pfn_clean(pfn);
-}
-
-/* XXX only map the one-one case, for now use TLB0 */
-static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-				 int esel,
-				 struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	struct kvm_book3e_206_tlb_entry *gtlbe;
-	struct tlbe_ref *ref;
-
-	gtlbe = get_entry(vcpu_e500, 0, esel);
-	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
-
-	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
-			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-			gtlbe, 0, stlbe, ref);
-}
-
-/* Caller must ensure that the specified guest TLB entry is safe to insert into
- * the shadow TLB. */
-/* XXX for both one-one and one-to-many , for now use TLB1 */
-static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
-		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
-{
-	struct tlbe_ref *ref;
-	unsigned int victim;
-
-	victim = vcpu_e500->host_tlb1_nv++;
-
-	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
-		vcpu_e500->host_tlb1_nv = 0;
-
-	ref = &vcpu_e500->tlb_refs[1][victim];
-	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);
-
-	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << victim;
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
-	if (vcpu_e500->h2g_tlb1_rmap[victim]) {
-		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[victim];
-		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << victim);
-	}
-	vcpu_e500->h2g_tlb1_rmap[victim] = esel;
-
-	return victim;
-}
-
 static void kvmppc_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int size = vcpu_e500->gtlb_params[1].entries;
@@ -683,8 +239,8 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 		for (esel = 0; esel < vcpu_e500->gtlb_params[1].entries; esel++)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
-	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_tlbil_all(vcpu_e500);
+	/* Invalidate all host shadow mappings */
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 
 	return EMULATE_DONE;
 }
@@ -713,8 +269,8 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, gva_t ea)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
 	}
 
-	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_tlbil_all(vcpu_e500);
+	/* Invalidate all host shadow mappings */
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 
 	return EMULATE_DONE;
 }
@@ -834,27 +390,11 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, gva_t ea)
 	return EMULATE_DONE;
 }
 
-/* sesel is for tlb1 only */
-static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-			struct kvm_book3e_206_tlb_entry *gtlbe,
-			struct kvm_book3e_206_tlb_entry *stlbe,
-			int stlbsel, int sesel)
-{
-	int stid;
-
-	preempt_disable();
-	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
-
-	stlbe->mas1 |= MAS1_TID(stid);
-	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
-	preempt_enable();
-}
-
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
-	int tlbsel, esel, stlbsel, sesel;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	int tlbsel, esel;
 	int recal = 0;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
@@ -892,40 +432,16 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
-		u64 eaddr;
-		u64 raddr;
+		u64 eaddr = get_tlb_eaddr(gtlbe);
+		u64 raddr = get_tlb_raddr(gtlbe);
 
-		switch (tlbsel) {
-		case 0:
-			/* TLB0 */
+		if (tlbsel == 0) {
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
 			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-
-			stlbsel = 0;
-			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
-			sesel = 0; /* unused */
-
-			break;
-
-		case 1:
-			/* TLB1 */
-			eaddr = get_tlb_eaddr(gtlbe);
-			raddr = get_tlb_raddr(gtlbe);
-
-			/* Create a 4KB mapping on the host.
-			 * If the guest wanted a large page,
-			 * only the first 4KB is mapped here and the rest
-			 * are mapped on the fly. */
-			stlbsel = 1;
-			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
-				    raddr >> PAGE_SHIFT, gtlbe, &stlbe, esel);
-			break;
-
-		default:
-			BUG();
 		}
 
-		write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
+		/* Premap the faulting page */
+		kvmppc_mmu_map(vcpu, eaddr, raddr, index_of(tlbsel, esel));
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
@@ -1019,100 +535,14 @@ void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
-			unsigned int index)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe_priv *priv;
-	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
-	int tlbsel = tlbsel_of(index);
-	int esel = esel_of(index);
-	int stlbsel, sesel;
-
-	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
-
-	switch (tlbsel) {
-	case 0:
-		stlbsel = 0;
-		sesel = 0; /* unused */
-		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
-
-		/* Only triggers after clear_tlb_refs */
-		if (unlikely(!(priv->ref.flags & E500_TLB_VALID)))
-			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
-		else
-			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
-						&priv->ref, eaddr, &stlbe);
-		break;
-
-	case 1: {
-		gfn_t gfn = gpaddr >> PAGE_SHIFT;
-
-		stlbsel = 1;
-		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn,
-					     gtlbe, &stlbe, esel);
-		break;
-	}
-
-	default:
-		BUG();
-		break;
-	}
-
-	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
-}
-
-/************* MMU Notifiers *************/
-
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
-	trace_kvm_unmap_hva(hva);
-
-	/*
-	 * Flush all shadow tlb entries everywhere. This is slow, but
-	 * we are 100% sure that we catch the to be unmapped page
-	 */
-	kvm_flush_remote_tlbs(kvm);
-
-	return 0;
-}
-
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
-{
-	/* kvm_unmap_hva flushes everything anyways */
-	kvm_unmap_hva(kvm, start);
-
-	return 0;
-}
-
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	/* XXX could be more clever ;) */
-	return 0;
-}
-
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	/* XXX could be more clever ;) */
-	return 0;
-}
-
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
-{
-	/* The page will get remapped properly on its next fault */
-	kvm_unmap_hva(kvm, hva);
-}
-
 /*****************************************/
 
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;
 
-	clear_tlb1_bitmap(vcpu_e500);
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 	kfree(vcpu_e500->g2h_tlb1_map);
-
-	clear_tlb_refs(vcpu_e500);
 	kfree(vcpu_e500->gtlb_priv[0]);
 	kfree(vcpu_e500->gtlb_priv[1]);
 
@@ -1303,7 +733,7 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	kvmppc_recalc_tlb1map_range(vcpu_e500);
-	clear_tlb_refs(vcpu_e500);
+	kvmppc_core_flush_tlb(vcpu);
 	return 0;
 }
 
@@ -1313,37 +743,8 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
 	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
 
-	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
-	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
-
-	/*
-	 * This should never happen on real e500 hardware, but is
-	 * architecturally possible -- e.g. in some weird nested
-	 * virtualization case.
-	 */
-	if (host_tlb_params[0].entries == 0 ||
-	    host_tlb_params[1].entries == 0) {
-		pr_err("%s: need to know host tlb size\n", __func__);
-		return -ENODEV;
-	}
-
-	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
-				  TLBnCFG_ASSOC_SHIFT;
-	host_tlb_params[1].ways = host_tlb_params[1].entries;
-
-	if (!is_power_of_2(host_tlb_params[0].entries) ||
-	    !is_power_of_2(host_tlb_params[0].ways) ||
-	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
-	    host_tlb_params[0].ways == 0) {
-		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
-		       __func__, host_tlb_params[0].entries,
-		       host_tlb_params[0].ways);
-		return -ENODEV;
-	}
-
-	host_tlb_params[0].sets =
-		host_tlb_params[0].entries / host_tlb_params[0].ways;
-	host_tlb_params[1].sets = 1;
+	if (e500_mmu_host_init(vcpu_e500))
+		goto err;
 
 	vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE;
 	vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE;
@@ -1362,18 +763,6 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
 
-	vcpu_e500->tlb_refs[0] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[0])
-		goto err;
-
-	vcpu_e500->tlb_refs[1] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[1])
-		goto err;
-
 	vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) *
 					  vcpu_e500->gtlb_params[0].entries,
 					  GFP_KERNEL);
@@ -1392,12 +781,6 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (!vcpu_e500->g2h_tlb1_map)
 		goto err;
 
-	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
-					   host_tlb_params[1].entries,
-					   GFP_KERNEL);
-	if (!vcpu_e500->h2g_tlb1_rmap)
-		goto err;
-
 	/* Init TLB configuration register */
 	vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
@@ -1416,15 +799,11 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 err:
 	free_gtlb(vcpu_e500);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
 	return -1;
 }
 
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	free_gtlb(vcpu_e500);
-	kfree(vcpu_e500->h2g_tlb1_rmap);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
+	e500_mmu_host_uninit(vcpu_e500);
 }
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
new file mode 100644
index 0000000..a222edf
--- /dev/null
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -0,0 +1,699 @@
+/*
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *         Scott Wood, scottwood@freescale.com
+ *         Ashish Kalra, ashish.kalra@freescale.com
+ *         Varun Sethi, varun.sethi@freescale.com
+ *         Alexander Graf, agraf@suse.de
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <linux/vmalloc.h>
+#include <linux/hugetlb.h>
+#include <asm/kvm_ppc.h>
+
+#include "e500.h"
+#include "trace.h"
+#include "timing.h"
+#include "e500_mmu_host.h"
+
+#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
+
+static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+
+static inline unsigned int tlb1_max_shadow_size(void)
+{
+	/* reserve one entry for magic page */
+	return host_tlb_params[1].entries - tlbcam_index - 1;
+}
+
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+{
+	/* Mask off reserved bits. */
+	mas3 &= MAS3_ATTRIB_MASK;
+
+#ifndef CONFIG_KVM_BOOKE_HV
+	if (!usermode) {
+		/* Guest is in supervisor mode,
+		 * so we need to translate guest
+		 * supervisor permissions into user permissions. */
+		mas3 &= ~E500_TLB_USER_PERM_MASK;
+		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
+	}
+	mas3 |= E500_TLB_SUPER_PERM_MASK;
+#endif
+	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
+ */
+static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
+				     uint32_t mas0)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS0, mas0);
+	mtspr(SPRN_MAS1, stlbe->mas1);
+	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
+	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
+	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_MAS8, stlbe->mas8);
+#endif
+	asm volatile("isync; tlbwe" : : : "memory");
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/* Must clear mas8 for other host tlbwe's */
+	mtspr(SPRN_MAS8, 0);
+	isync();
+#endif
+	local_irq_restore(flags);
+
+	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
+	                              stlbe->mas2, stlbe->mas7_3);
+}
+
+/*
+ * Acquire a mas0 with victim hint, as if we just took a TLB miss.
+ *
+ * We don't care about the address we're searching for, other than that it's
+ * in the right set and is not present in the TLB.  Using a zero PID and a
+ * userspace address means we don't have to set and then restore MAS5, or
+ * calculate a proper MAS6 value.
+ */
+static u32 get_host_mas0(unsigned long eaddr)
+{
+	unsigned long flags;
+	u32 mas0;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS6, 0);
+	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
+	mas0 = mfspr(SPRN_MAS0);
+	local_irq_restore(flags);
+
+	return mas0;
+}
+
+/* sesel is for tlb1 only */
+static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	u32 mas0;
+
+	if (tlbsel == 0) {
+		mas0 = get_host_mas0(stlbe->mas2);
+		__write_host_tlbe(stlbe, mas0);
+	} else {
+		__write_host_tlbe(stlbe,
+				  MAS0_TLBSEL(1) |
+				  MAS0_ESEL(to_htlb1_esel(sesel)));
+	}
+}
+
+/* sesel is for tlb1 only */
+static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+			struct kvm_book3e_206_tlb_entry *gtlbe,
+			struct kvm_book3e_206_tlb_entry *stlbe,
+			int stlbsel, int sesel)
+{
+	int stid;
+
+	preempt_disable();
+	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
+
+	stlbe->mas1 |= MAS1_TID(stid);
+	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
+	preempt_enable();
+}
+
+#ifdef CONFIG_KVM_E500V2
+/* XXX should be a hook in the gva2hpa translation */
+void kvmppc_map_magic(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct kvm_book3e_206_tlb_entry magic;
+	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
+	unsigned int stid;
+	pfn_t pfn;
+
+	pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT;
+	get_page(pfn_to_page(pfn));
+
+	preempt_disable();
+	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);
+
+	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
+		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
+	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
+	magic.mas8 = 0;
+
+	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
+	preempt_enable();
+}
+#endif
+
+void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+			 int esel)
+{
+	struct kvm_book3e_206_tlb_entry *gtlbe =
+		get_entry(vcpu_e500, tlbsel, esel);
+	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
+
+	/* Don't bother with unmapped entries */
+	if (!(ref->flags & E500_TLB_VALID))
+		return;
+
+	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
+		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
+		int hw_tlb_indx;
+		unsigned long flags;
+
+		local_irq_save(flags);
+		while (tmp) {
+			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
+			mtspr(SPRN_MAS0,
+			      MAS0_TLBSEL(1) |
+			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
+			mtspr(SPRN_MAS1, 0);
+			asm volatile("tlbwe");
+			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
+			tmp &= tmp - 1;
+		}
+		mb();
+		vcpu_e500->g2h_tlb1_map[esel] = 0;
+		ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
+		local_irq_restore(flags);
+	}
+
+	if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) {
+		/*
+		 * TLB1 entry is backed by 4k pages. This should happen
+		 * rarely and is not worth optimizing. Invalidate everything.
+		 */
+		kvmppc_e500_tlbil_all(vcpu_e500);
+		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);
+
+	/* Mark the TLB as not backed by the host anymore */
+	ref->flags &= ~E500_TLB_VALID;
+}
+
+static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
+}
+
+static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
+					 struct kvm_book3e_206_tlb_entry *gtlbe,
+					 pfn_t pfn)
+{
+	ref->pfn = pfn;
+	ref->flags = E500_TLB_VALID;
+
+	if (tlbe_is_writable(gtlbe))
+		kvm_set_pfn_dirty(pfn);
+}
+
+static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
+{
+	if (ref->flags & E500_TLB_VALID) {
+		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
+		ref->flags = 0;
+	}
+}
+
+static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	if (vcpu_e500->g2h_tlb1_map)
+		memset(vcpu_e500->g2h_tlb1_map, 0,
+		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
+	if (vcpu_e500->h2g_tlb1_rmap)
+		memset(vcpu_e500->h2g_tlb1_rmap, 0,
+		       sizeof(unsigned int) * host_tlb_params[1].entries);
+}
+
+static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int tlbsel = 0;
+	int i;
+
+	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
+		kvmppc_e500_ref_release(ref);
+	}
+}
+
+static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int stlbsel = 1;
+	int i;
+
+	kvmppc_e500_tlbil_all(vcpu_e500);
+
+	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->tlb_refs[stlbsel][i];
+		kvmppc_e500_ref_release(ref);
+	}
+
+	clear_tlb_privs(vcpu_e500);
+}
+
+void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	clear_tlb_refs(vcpu_e500);
+	clear_tlb1_bitmap(vcpu_e500);
+}
+
+/* TID must be supplied by the caller */
+static void kvmppc_e500_setup_stlbe(
+	struct kvm_vcpu *vcpu,
+	struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tsize, struct tlbe_ref *ref, u64 gvaddr,
+	struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	pfn_t pfn = ref->pfn;
+	u32 pr = vcpu->arch.shared->msr & MSR_PR;
+
+	BUG_ON(!(ref->flags & E500_TLB_VALID));
+
+	/* 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->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
+#endif
+}
+
+static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
+	struct tlbe_ref *ref)
+{
+	struct kvm_memory_slot *slot;
+	unsigned long pfn = 0; /* silence GCC warning */
+	unsigned long hva;
+	int pfnmap = 0;
+	int tsize = BOOK3E_PAGESZ_4K;
+
+	/*
+	 * Translate guest physical to true physical, acquiring
+	 * a page reference if it is normal, non-reserved memory.
+	 *
+	 * gfn_to_memslot() must succeed because otherwise we wouldn't
+	 * have gotten this far.  Eventually we should just pass the slot
+	 * pointer through from the first lookup.
+	 */
+	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
+	hva = gfn_to_hva_memslot(slot, gfn);
+
+	if (tlbsel == 1) {
+		struct vm_area_struct *vma;
+		down_read(&current->mm->mmap_sem);
+
+		vma = find_vma(current->mm, hva);
+		if (vma && hva >= vma->vm_start &&
+		    (vma->vm_flags & VM_PFNMAP)) {
+			/*
+			 * This VMA is a physically contiguous region (e.g.
+			 * /dev/mem) that bypasses normal Linux page
+			 * management.  Find the overlap between the
+			 * vma and the memslot.
+			 */
+
+			unsigned long start, end;
+			unsigned long slot_start, slot_end;
+
+			pfnmap = 1;
+
+			start = vma->vm_pgoff;
+			end = start +
+			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);
+
+			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
+
+			slot_start = pfn - (gfn - slot->base_gfn);
+			slot_end = slot_start + slot->npages;
+
+			if (start < slot_start)
+				start = slot_start;
+			if (end > slot_end)
+				end = slot_end;
+
+			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+				MAS1_TSIZE_SHIFT;
+
+			/*
+			 * e500 doesn't implement the lowest tsize bit,
+			 * or 1K pages.
+			 */
+			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+
+			/*
+			 * Now find the largest tsize (up to what the guest
+			 * requested) that will cover gfn, stay within the
+			 * range, and for which gfn and pfn are mutually
+			 * aligned.
+			 */
+
+			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
+				unsigned long gfn_start, gfn_end, tsize_pages;
+				tsize_pages = 1 << (tsize - 2);
+
+				gfn_start = gfn & ~(tsize_pages - 1);
+				gfn_end = gfn_start + tsize_pages;
+
+				if (gfn_start + pfn - gfn < start)
+					continue;
+				if (gfn_end + pfn - gfn > end)
+					continue;
+				if ((gfn & (tsize_pages - 1)) !=
+				    (pfn & (tsize_pages - 1)))
+					continue;
+
+				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+				pfn &= ~(tsize_pages - 1);
+				break;
+			}
+		} else if (vma && hva >= vma->vm_start &&
+			   (vma->vm_flags & VM_HUGETLB)) {
+			unsigned long psize = vma_kernel_pagesize(vma);
+
+			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+				MAS1_TSIZE_SHIFT;
+
+			/*
+			 * Take the largest page size that satisfies both host
+			 * and guest mapping
+			 */
+			tsize = min(__ilog2(psize) - 10, tsize);
+
+			/*
+			 * e500 doesn't implement the lowest tsize bit,
+			 * or 1K pages.
+			 */
+			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+		}
+
+		up_read(&current->mm->mmap_sem);
+	}
+
+	if (likely(!pfnmap)) {
+		unsigned long 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);
+			return -EINVAL;
+		}
+
+		/* Align guest and physical address to page map boundaries */
+		pfn &= ~(tsize_pages - 1);
+		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+	}
+
+	/* Drop old ref and setup new one. */
+	kvmppc_e500_ref_release(ref);
+	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
+
+	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
+				ref, gvaddr, stlbe);
+
+	/* Clear i-cache for new pages */
+	kvmppc_mmu_flush_icache(pfn);
+
+	/* Drop refcount on page, so that mmu notifiers can clear it */
+	kvm_release_pfn_clean(pfn);
+
+	return 0;
+}
+
+/* XXX only map the one-one case, for now use TLB0 */
+static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
+				struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	struct tlbe_ref *ref;
+	int stlbsel = 0;
+	int sesel = 0;
+	int r;
+
+	gtlbe = get_entry(vcpu_e500, 0, esel);
+	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
+
+	r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
+			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
+			gtlbe, 0, stlbe, ref);
+	if (r)
+		return r;
+
+	write_stlbe(vcpu_e500, gtlbe, stlbe, stlbsel, sesel);
+
+	return 0;
+}
+
+static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
+				     struct tlbe_ref *ref,
+				     int esel)
+{
+	unsigned int sesel = vcpu_e500->host_tlb1_nv++;
+
+	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
+		vcpu_e500->host_tlb1_nv = 0;
+
+	vcpu_e500->tlb_refs[1][sesel] = *ref;
+	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
+		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
+	}
+	vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+	return sesel;
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+/* For both one-one and one-to-many */
+static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
+{
+	struct tlbe_ref ref;
+	int sesel;
+	int r;
+
+	ref.flags = 0;
+	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
+				   &ref);
+	if (r)
+		return r;
+
+	/* Use TLB0 when we can only map a page with 4k */
+	if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) {
+		vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0;
+		write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0);
+		return 0;
+	}
+
+	/* Otherwise map into TLB1 */
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
+
+	return 0;
+}
+
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
+		    unsigned int index)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe_priv *priv;
+	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
+	int tlbsel = tlbsel_of(index);
+	int esel = esel_of(index);
+
+	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
+
+	switch (tlbsel) {
+	case 0:
+		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
+
+		/* Triggers after clear_tlb_refs or on initial mapping */
+		if (!(priv->ref.flags & E500_TLB_VALID)) {
+			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+		} else {
+			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
+						&priv->ref, eaddr, &stlbe);
+			write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0);
+		}
+		break;
+
+	case 1: {
+		gfn_t gfn = gpaddr >> PAGE_SHIFT;
+		kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe, &stlbe,
+				     esel);
+		break;
+	}
+
+	default:
+		BUG();
+		break;
+	}
+}
+
+/************* MMU Notifiers *************/
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_unmap_hva(hva);
+
+	/*
+	 * Flush all shadow tlb entries everywhere. This is slow, but
+	 * we are 100% sure that we catch the to be unmapped page
+	 */
+	kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	/* kvm_unmap_hva flushes everything anyways */
+	kvm_unmap_hva(kvm, start);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	/* The page will get remapped properly on its next fault */
+	kvm_unmap_hva(kvm, hva);
+}
+
+/*****************************************/
+
+int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
+	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	/*
+	 * This should never happen on real e500 hardware, but is
+	 * architecturally possible -- e.g. in some weird nested
+	 * virtualization case.
+	 */
+	if (host_tlb_params[0].entries == 0 ||
+	    host_tlb_params[1].entries == 0) {
+		pr_err("%s: need to know host tlb size\n", __func__);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
+				  TLBnCFG_ASSOC_SHIFT;
+	host_tlb_params[1].ways = host_tlb_params[1].entries;
+
+	if (!is_power_of_2(host_tlb_params[0].entries) ||
+	    !is_power_of_2(host_tlb_params[0].ways) ||
+	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
+	    host_tlb_params[0].ways == 0) {
+		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
+		       __func__, host_tlb_params[0].entries,
+		       host_tlb_params[0].ways);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].sets =
+		host_tlb_params[0].entries / host_tlb_params[0].ways;
+	host_tlb_params[1].sets = 1;
+
+	vcpu_e500->tlb_refs[0] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[0])
+		goto err;
+
+	vcpu_e500->tlb_refs[1] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[1])
+		goto err;
+
+	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
+					   host_tlb_params[1].entries,
+					   GFP_KERNEL);
+	if (!vcpu_e500->h2g_tlb1_rmap)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
+	return -EINVAL;
+}
+
+void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->h2g_tlb1_rmap);
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
+}
diff --git a/arch/powerpc/kvm/e500_mmu_host.h b/arch/powerpc/kvm/e500_mmu_host.h
new file mode 100644
index 0000000..7624835
--- /dev/null
+++ b/arch/powerpc/kvm/e500_mmu_host.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KVM_E500_MMU_HOST_H
+#define KVM_E500_MMU_HOST_H
+
+void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+			 int esel);
+
+int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500);
+void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+#endif /* KVM_E500_MMU_HOST_H */
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 9d9cddc..7a73b6f 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -150,8 +150,6 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_TBWL: break;
 	case SPRN_TBWU: break;
 
-	case SPRN_MSSSR0: break;
-
 	case SPRN_DEC:
 		vcpu->arch.dec = spr_val;
 		kvmppc_emulate_dec(vcpu);
@@ -202,9 +200,6 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_PIR:
 		spr_val = vcpu->vcpu_id;
 		break;
-	case SPRN_MSSSR0:
-		spr_val = 0;
-		break;
 
 	/* Note: mftb and TBRL/TBWL are user-accessible, so
 	 * the guest can always access the real TB anyways.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 70739a0..934413c 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -237,7 +237,8 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		r = RESUME_HOST;
 		break;
 	default:
-		BUG();
+		WARN_ON(1);
+		r = RESUME_GUEST;
 	}
 
 	return r;
@@ -305,6 +306,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_SREGS:
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
+	case KVM_CAP_PPC_EPR:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_HIOR:
@@ -412,7 +414,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_memory_slot *memslot,
                                    struct kvm_memory_slot old,
                                    struct kvm_userspace_memory_region *mem,
-                                   int user_alloc)
+                                   bool user_alloc)
 {
 	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
 }
@@ -420,7 +422,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 void kvm_arch_commit_memory_region(struct kvm *kvm,
                struct kvm_userspace_memory_region *mem,
                struct kvm_memory_slot old,
-               int user_alloc)
+               bool user_alloc)
 {
 	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
@@ -720,6 +722,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		for (i = 0; i < 9; ++i)
 			kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
 		vcpu->arch.hcall_needed = 0;
+#ifdef CONFIG_BOOKE
+	} else if (vcpu->arch.epr_needed) {
+		kvmppc_set_epr(vcpu, run->epr.epr);
+		vcpu->arch.epr_needed = 0;
+#endif
 	}
 
 	r = kvmppc_vcpu_run(run, vcpu);
@@ -761,6 +768,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+	case KVM_CAP_PPC_EPR:
+		r = 0;
+		vcpu->arch.epr_enabled = cap->args[0];
+		break;
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
 		r = 0;