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" ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2013-02-25 01:07:18 +0400
committer: Linus Torvalds <torvalds@linux-foundation.org> 2013-02-25 01:07:18 +0400
commit: 89f883372fa60f604d136924baf3e89ff1870e9e (patch)
tree: cb69b0a14957945ba00d3d392bf9ccbbef56f3b8 /arch
parent: 9e2d59ad580d590134285f361a0e80f0e98c0207 (diff)
parent: 6b73a96065e89dc9fa75ba4f78b1aa3a3bbd0470 (diff)
download: linux-89f883372fa60f604d136924baf3e89ff1870e9e.tar.xz
51 files changed, 3044 insertions, 1539 deletions
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 6d6a5ac48d85..cfa74983c675 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -23,9 +23,7 @@
 #ifndef __ASM_KVM_HOST_H
 #define __ASM_KVM_HOST_H
 
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 32
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index bd1c51555038..ad3126a58644 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -955,7 +955,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 					kvm_mem.guest_phys_addr;
 		kvm_userspace_mem.memory_size = kvm_mem.memory_size;
 		r = kvm_vm_ioctl_set_memory_region(kvm,
-					&kvm_userspace_mem, 0);
+					&kvm_userspace_mem, false);
 		if (r)
 			goto out;
 		break;
@@ -1580,7 +1580,7 @@ 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)
 {
 	unsigned long i;
 	unsigned long pfn;
@@ -1611,7 +1611,7 @@ 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)
 {
 	return;
 }
@@ -1834,7 +1834,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	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/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h
index c5f92a926a9a..c3e2935b6db4 100644
--- a/arch/ia64/kvm/lapic.h
+++ b/arch/ia64/kvm/lapic.h
@@ -27,4 +27,10 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
 #define kvm_apic_present(x) (true)
 #define kvm_lapic_enabled(x) (true)
 
+static inline bool kvm_apic_vid_enabled(void)
+{
+	/* IA64 has no apicv supporting, do nothing here */
+	return false;
+}
+
 #endif
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 03d7beae89a0..d1bb86074721 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -37,10 +37,8 @@
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS 32
+#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -523,6 +521,8 @@ struct kvm_vcpu_arch {
 	u8 sane;
 	u8 cpu_type;
 	u8 hcall_needed;
+	u8 epr_enabled;
+	u8 epr_needed;
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 572aa7530619..44a657adf416 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -44,12 +44,11 @@ enum emulation_result {
 	EMULATE_DO_DCR,       /* kvm_run filled with DCR request */
 	EMULATE_FAIL,         /* can't emulate this instruction */
 	EMULATE_AGAIN,        /* something went wrong. go again */
+	EMULATE_DO_PAPR,      /* kvm_run filled with PAPR request */
 };
 
 extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
-extern char kvmppc_handlers_start[];
-extern unsigned long kvmppc_handler_len;
 extern void kvmppc_handler_highmem(void);
 
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
@@ -263,6 +262,15 @@ static inline void kvm_linear_init(void)
 {}
 #endif
 
+static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GEPR, epr);
+#elif defined(CONFIG_BOOKE)
+	vcpu->arch.epr = epr;
+#endif
+}
+
 int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 			      struct kvm_config_tlb *cfg);
 int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7035e608f3fa..e66586122030 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -956,8 +956,6 @@
 #define SPRN_SPRG_RSCRATCH_DBG	SPRN_SPRG9
 #define SPRN_SPRG_WSCRATCH_DBG	SPRN_SPRG9
 #endif
-#define SPRN_SPRG_RVCPU		SPRN_SPRG1
-#define SPRN_SPRG_WVCPU		SPRN_SPRG1
 #endif
 
 #ifdef CONFIG_8xx
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index e07e6af5e1ff..b417de3cc2c4 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -56,6 +56,7 @@
 #define SPRN_SPRG7W	0x117	/* Special Purpose Register General 7 Write */
 #define SPRN_EPCR	0x133	/* Embedded Processor Control Register */
 #define SPRN_DBCR2	0x136	/* Debug Control Register 2 */
+#define SPRN_DBCR4	0x233	/* Debug Control Register 4 */
 #define SPRN_MSRP	0x137	/* MSR Protect Register */
 #define SPRN_IAC3	0x13A	/* Instruction Address Compare 3 */
 #define SPRN_IAC4	0x13B	/* Instruction Address Compare 4 */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 2fba8a66fb10..16064d00adb9 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -114,7 +114,10 @@ struct kvm_regs {
 /* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
 #define KVM_SREGS_E_SPE			(1 << 9)
 
-/* External Proxy (EXP) -- EPR */
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
 #define KVM_SREGS_EXP			(1 << 10)
 
 /* External PID (E.PD) -- EPSC/EPLC */
@@ -412,5 +415,6 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
 
 #define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
 
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 781190367292..b6c17ec9b169 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -118,7 +118,7 @@ int main(void)
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
 #endif
-#ifdef CONFIG_KVM_BOOKE_HV
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
 	DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
 #endif
 
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 1e473d46322c..b772eded8c26 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 d31a716f7f2b..836c56975e21 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 71d0c90b62bf..80dcc53a1aba 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 6702442ca818..5e93438afb06 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 69f114015780..020923e43134 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 e9b88e433f64..5fd1ba693579 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 4685b8cf2249..27a4b2877c10 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 bb46b32f9813..f4bb55c96517 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 b479ed77c515..6dd4de7802bf 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 c70d37ed770a..41cefd43655f 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 cf3f18012371..5c4475983f78 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 000000000000..a222edfb9a9b
--- /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 000000000000..7624835b76c7
--- /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 9d9cddc5b346..7a73b6f72a8b 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 70739a089560..934413cd3a1b 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;
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 7def77302d63..87c17bfb2968 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -41,6 +41,7 @@ enum interruption_class {
 	IRQIO_CSC,
 	IRQIO_PCI,
 	IRQIO_MSI,
+	IRQIO_VIR,
 	NMI_NMI,
 	CPU_RST,
 	NR_ARCH_IRQS
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index b7841546991f..16bd5d169cdb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -20,9 +20,7 @@
 #include <asm/cpu.h>
 
 #define KVM_MAX_VCPUS 64
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 32
 
 struct sca_entry {
 	atomic_t scn;
@@ -76,8 +74,11 @@ struct kvm_s390_sie_block {
 	__u64	epoch;			/* 0x0038 */
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
+#define LCTL_CR6	0x0200
+#define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
+#define ICTL_LPSW 0x00400000
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
 	__u8	icptcode;		/* 0x0050 */
@@ -127,6 +128,7 @@ struct kvm_vcpu_stat {
 	u32 deliver_prefix_signal;
 	u32 deliver_restart_signal;
 	u32 deliver_program_int;
+	u32 deliver_io_int;
 	u32 exit_wait_state;
 	u32 instruction_stidp;
 	u32 instruction_spx;
@@ -187,6 +189,11 @@ struct kvm_s390_emerg_info {
 	__u16 code;
 };
 
+struct kvm_s390_mchk_info {
+	__u64 cr14;
+	__u64 mcic;
+};
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -197,6 +204,7 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_extcall_info extcall;
 		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_mchk_info mchk;
 	};
 };
 
@@ -254,6 +262,7 @@ struct kvm_arch{
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct gmap *gmap;
+	int css_support;
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 9df824ea1667..1630f439cd2a 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -81,6 +81,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	[IRQIO_CSC]  = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"},
 	[IRQIO_PCI]  = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
 	[IRQIO_MSI]  = {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
+	[IRQIO_VIR]  = {.name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
 	[NMI_NMI]    = {.name = "NMI", .desc = "[NMI] Machine Check"},
 	[CPU_RST]    = {.name = "RST", .desc = "[CPU] CPU Restart"},
 };
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 22798ec33fd1..f26ff1e31bdb 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -26,27 +26,20 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
-			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
 	u64 useraddr;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctlg++;
-	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
-		return -EOPNOTSUPP;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	reg = reg1;
 
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
 
 	do {
@@ -68,23 +61,19 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	u32 val = 0;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctl++;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
 
 	reg = reg1;
@@ -104,14 +93,31 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static intercept_handler_t instruction_handlers[256] = {
+static const intercept_handler_t eb_handlers[256] = {
+	[0x2f] = handle_lctlg,
+	[0x8a] = kvm_s390_handle_priv_eb,
+};
+
+static int handle_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
+	[0x82] = kvm_s390_handle_lpsw,
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = handle_lctlg,
+	[0xeb] = handle_eb,
 };
 
 static int handle_noop(struct kvm_vcpu *vcpu)
@@ -258,6 +264,7 @@ static const intercept_handler_t intercept_funcs[] = {
 	[0x0C >> 2] = handle_instruction_and_prog,
 	[0x10 >> 2] = handle_noop,
 	[0x14 >> 2] = handle_noop,
+	[0x18 >> 2] = handle_noop,
 	[0x1C >> 2] = kvm_s390_handle_wait,
 	[0x20 >> 2] = handle_validity,
 	[0x28 >> 2] = handle_stop,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 87418b50f21c..37116a77cb4b 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -21,11 +21,31 @@
 #include "gaccess.h"
 #include "trace-s390.h"
 
+#define IOINT_SCHID_MASK 0x0000ffff
+#define IOINT_SSID_MASK 0x00030000
+#define IOINT_CSSID_MASK 0x03fc0000
+#define IOINT_AI_MASK 0x04000000
+
+static int is_ioint(u64 type)
+{
+	return ((type & 0xfffe0000u) != 0xfffe0000u);
+}
+
 static int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
 }
 
+static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
+}
+
+static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
+}
+
 static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 {
 	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
@@ -35,6 +55,13 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static u64 int_word_to_isc_bits(u32 int_word)
+{
+	u8 isc = (int_word & 0x38000000) >> 27;
+
+	return (0x80 >> isc) << 24;
+}
+
 static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 				      struct kvm_s390_interrupt_info *inti)
 {
@@ -67,7 +94,22 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_SET_PREFIX:
 	case KVM_S390_RESTART:
 		return 1;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
+			return 1;
+		return 0;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[6] &
+		    int_word_to_isc_bits(inti->io.io_int_word))
+			return 1;
+		return 0;
 	default:
+		printk(KERN_WARNING "illegal interrupt type %llx\n",
+		       inti->type);
 		BUG();
 	}
 	return 0;
@@ -93,6 +135,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
 		&vcpu->arch.sie_block->cpuflags);
 	vcpu->arch.sie_block->lctl = 0x0000;
+	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
@@ -116,6 +159,18 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_STOP:
 		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
 		break;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR14;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR6;
+		break;
 	default:
 		BUG();
 	}
@@ -297,6 +352,73 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			exception = 1;
 		break;
 
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+			   inti->mchk.mcic);
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->mchk.cr14,
+						 inti->mchk.mcic);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_PREFIXED);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u64(vcpu, __LC_MCCK_CODE, inti->mchk.mcic);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
+				   &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				     __LC_MCK_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+	{
+		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
+			inti->io.subchannel_nr;
+		__u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
+			inti->io.io_int_word;
+		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
+		vcpu->stat.deliver_io_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 param0, param1);
+		rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_ID,
+				   inti->io.subchannel_id);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_NR,
+				   inti->io.subchannel_nr);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_IO_INT_PARM,
+				   inti->io.io_int_parm);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_IO_INT_WORD,
+				   inti->io.io_int_word);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_IO_OLD_PSW,
+				   &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				     __LC_IO_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+	}
 	default:
 		BUG();
 	}
@@ -518,6 +640,61 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	}
 }
 
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -540,12 +717,50 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	return 0;
 }
 
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti, *iter;
+
+	if ((!schid && !cr6) || (schid && cr6))
+		return NULL;
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	inti = NULL;
+	list_for_each_entry(iter, &fi->list, list) {
+		if (!is_ioint(iter->type))
+			continue;
+		if (cr6 &&
+		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
+			continue;
+		if (schid) {
+			if (((schid & 0x00000000ffff0000) >> 16) !=
+			    iter->io.subchannel_id)
+				continue;
+			if ((schid & 0x000000000000ffff) !=
+			    iter->io.subchannel_nr)
+				continue;
+		}
+		inti = iter;
+		break;
+	}
+	if (inti)
+		list_del_init(&inti->list);
+	if (list_empty(&fi->list))
+		atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return inti;
+}
+
 int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt_info *inti, *iter;
 	int sigcpu;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
@@ -569,6 +784,29 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	case KVM_S390_SIGP_STOP:
 	case KVM_S390_INT_EXTERNAL_CALL:
 	case KVM_S390_INT_EMERGENCY:
+		kfree(inti);
+		return -EINVAL;
+	case KVM_S390_MCHK:
+		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+			 s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
+		inti->mchk.mcic = s390int->parm64;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (s390int->type & IOINT_AI_MASK)
+			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
+		else
+			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
+				 s390int->type & IOINT_CSSID_MASK,
+				 s390int->type & IOINT_SSID_MASK,
+				 s390int->type & IOINT_SCHID_MASK);
+		inti->type = s390int->type;
+		inti->io.subchannel_id = s390int->parm >> 16;
+		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
+		inti->io.io_int_parm = s390int->parm64 >> 32;
+		inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull;
+		break;
 	default:
 		kfree(inti);
 		return -EINVAL;
@@ -579,7 +817,22 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
-	list_add_tail(&inti->list, &fi->list);
+	if (!is_ioint(inti->type))
+		list_add_tail(&inti->list, &fi->list);
+	else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+		/* Keep I/O interrupts sorted in isc order. */
+		list_for_each_entry(iter, &fi->list, list) {
+			if (!is_ioint(iter->type))
+				continue;
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
+				continue;
+			break;
+		}
+		list_add_tail(&inti->list, &iter->list);
+	}
 	atomic_set(&fi->active, 1);
 	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
 	if (sigcpu == KVM_MAX_VCPUS) {
@@ -651,8 +904,15 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		inti->type = s390int->type;
 		inti->emerg.code = s390int->parm;
 		break;
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+			   s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.mcic = s390int->parm64;
+		break;
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 	default:
 		kfree(inti);
 		return -EINVAL;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2923781590a6..4cf35a0a79e7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -140,6 +140,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 	case KVM_CAP_SYNC_REGS:
 	case KVM_CAP_ONE_REG:
+	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_S390_CSS_SUPPORT:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -234,6 +236,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		if (!kvm->arch.gmap)
 			goto out_nogmap;
 	}
+
+	kvm->arch.css_support = 0;
+
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
@@ -659,6 +664,7 @@ rerun_vcpu:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
 	case KVM_EXIT_S390_UCONTROL:
+	case KVM_EXIT_S390_TSCH:
 		break;
 	default:
 		BUG();
@@ -766,6 +772,14 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	} else
 		prefix = 0;
 
+	/*
+	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+	 * copying in vcpu load/put. Lets update our copies before we save
+	 * it into the save area
+	 */
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->run->s.regs.acrs);
+
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
 			vcpu->arch.guest_fpregs.fprs, 128, prefix))
 		return -EFAULT;
@@ -810,6 +824,29 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_S390_CSS_SUPPORT:
+		if (!vcpu->kvm->arch.css_support) {
+			vcpu->kvm->arch.css_support = 1;
+			trace_kvm_s390_enable_css(vcpu->kvm);
+		}
+		r = 0;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -896,6 +933,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = 0;
 		break;
 	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			break;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -930,7 +976,7 @@ 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)
 {
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
@@ -960,7 +1006,7 @@ 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)
 {
 	int rc;
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index d75bc5e92c5b..4d89d64a8161 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -65,21 +65,67 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	vcpu->arch.sie_block->ihcpu  = 0xffff;
 }
 
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
+					      u64 *address1, u64 *address2)
+{
+	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	u32 base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	u32 disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+
+	*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+	*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+	/* The displacement is a 20bit _SIGNED_ value */
+	if (disp2 & 0x80000)
+		disp2+=0xfff00000;
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_vm(struct kvm *kvm,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid);
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d768906f15c8..0ef9894606e5 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -18,23 +18,21 @@
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
+#include <asm/ptrace.h>
+#include <asm/compat.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
 #include "trace.h"
 
 static int handle_set_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address = 0;
 	u8 tmp;
 
 	vcpu->stat.instruction_spx++;
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -67,15 +65,12 @@ out:
 
 static int handle_store_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address;
 
 	vcpu->stat.instruction_stpx++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -100,15 +95,12 @@ out:
 
 static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	int rc;
 
 	vcpu->stat.instruction_stap++;
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+
+	useraddr = kvm_s390_get_base_disp_s(vcpu);
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -135,24 +127,96 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_stsch(struct kvm_vcpu *vcpu)
+static int handle_tpi(struct kvm_vcpu *vcpu)
 {
-	vcpu->stat.instruction_stsch++;
-	VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
-	/* condition code 3 */
+	u64 addr;
+	struct kvm_s390_interrupt_info *inti;
+	int cc;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0);
+	if (inti) {
+		if (addr) {
+			/*
+			 * Store the two-word I/O interruption code into the
+			 * provided area.
+			 */
+			put_guest_u16(vcpu, addr, inti->io.subchannel_id);
+			put_guest_u16(vcpu, addr + 2, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, addr + 4, inti->io.io_int_parm);
+		} else {
+			/*
+			 * Store the three-word I/O interruption code into
+			 * the appropriate lowcore area.
+			 */
+			put_guest_u16(vcpu, 184, inti->io.subchannel_id);
+			put_guest_u16(vcpu, 186, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, 188, inti->io.io_int_parm);
+			put_guest_u32(vcpu, 192, inti->io.io_int_word);
+		}
+		cc = 1;
+	} else
+		cc = 0;
+	kfree(inti);
+	/* Set condition code and we're done. */
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+	vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
 	return 0;
 }
 
-static int handle_chsc(struct kvm_vcpu *vcpu)
+static int handle_tsch(struct kvm_vcpu *vcpu)
 {
-	vcpu->stat.instruction_chsc++;
-	VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
-	/* condition code 3 */
-	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
-	return 0;
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
+				   vcpu->run->s.regs.gprs[1]);
+
+	/*
+	 * Prepare exit to userspace.
+	 * We indicate whether we dequeued a pending I/O interrupt
+	 * so that userspace can re-inject it if the instruction gets
+	 * a program check. While this may re-order the pending I/O
+	 * interrupts, this is no problem since the priority is kept
+	 * intact.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_S390_TSCH;
+	vcpu->run->s390_tsch.dequeued = !!inti;
+	if (inti) {
+		vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id;
+		vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr;
+		vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm;
+		vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word;
+	}
+	vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb;
+	kfree(inti);
+	return -EREMOTE;
+}
+
+static int handle_io_inst(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
+
+	if (vcpu->kvm->arch.css_support) {
+		/*
+		 * Most I/O instructions will be handled by userspace.
+		 * Exceptions are tpi and the interrupt portion of tsch.
+		 */
+		if (vcpu->arch.sie_block->ipa == 0xb236)
+			return handle_tpi(vcpu);
+		if (vcpu->arch.sie_block->ipa == 0xb235)
+			return handle_tsch(vcpu);
+		/* Handle in userspace. */
+		return -EOPNOTSUPP;
+	} else {
+		/*
+		 * Set condition code 3 to stop the guest from issueing channel
+		 * I/O instructions.
+		 */
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+		return 0;
+	}
 }
 
 static int handle_stfl(struct kvm_vcpu *vcpu)
@@ -176,17 +240,107 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void handle_new_psw(struct kvm_vcpu *vcpu)
+{
+	/* Check whether the new psw is enabled for machine checks. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK)
+		kvm_s390_deliver_pending_machine_checks(vcpu);
+}
+
+#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA)
+#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL
+#define PSW_ADDR_24 0x00000000000fffffUL
+#define PSW_ADDR_31 0x000000007fffffffUL
+
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_compat_t new_psw;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	if (!(new_psw.mask & PSW32_MASK_BASE)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask =
+		(new_psw.mask & ~PSW32_MASK_BASE) << 32;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
+static int handle_lpswe(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_t new_psw;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask = new_psw.mask;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	      PSW_MASK_BA) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_31)) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	int rc;
 
 	vcpu->stat.instruction_stidp++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -240,17 +394,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
 	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
 	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	unsigned long mem;
 
 	vcpu->stat.instruction_stsi++;
 	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -297,7 +447,7 @@ out_fail:
 	return 0;
 }
 
-static intercept_handler_t priv_handlers[256] = {
+static const intercept_handler_t b2_handlers[256] = {
 	[0x02] = handle_stidp,
 	[0x10] = handle_set_prefix,
 	[0x11] = handle_store_prefix,
@@ -305,10 +455,25 @@ static intercept_handler_t priv_handlers[256] = {
 	[0x29] = handle_skey,
 	[0x2a] = handle_skey,
 	[0x2b] = handle_skey,
-	[0x34] = handle_stsch,
-	[0x5f] = handle_chsc,
+	[0x30] = handle_io_inst,
+	[0x31] = handle_io_inst,
+	[0x32] = handle_io_inst,
+	[0x33] = handle_io_inst,
+	[0x34] = handle_io_inst,
+	[0x35] = handle_io_inst,
+	[0x36] = handle_io_inst,
+	[0x37] = handle_io_inst,
+	[0x38] = handle_io_inst,
+	[0x39] = handle_io_inst,
+	[0x3a] = handle_io_inst,
+	[0x3b] = handle_io_inst,
+	[0x3c] = handle_io_inst,
+	[0x5f] = handle_io_inst,
+	[0x74] = handle_io_inst,
+	[0x76] = handle_io_inst,
 	[0x7d] = handle_stsi,
 	[0xb1] = handle_stfl,
+	[0xb2] = handle_lpswe,
 };
 
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
@@ -322,7 +487,7 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	 * state bit and (a) handle the instruction or (b) send a code 2
 	 * program check.
 	 * Anything else goes to userspace.*/
-	handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
 	if (handler) {
 		if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 			return kvm_s390_inject_program_int(vcpu,
@@ -333,19 +498,74 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static int handle_epsw(struct kvm_vcpu *vcpu)
+{
+	int reg1, reg2;
+
+	reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24;
+	reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
+
+	/* This basically extracts the mask half of the psw. */
+	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000;
+	vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32;
+	if (reg2) {
+		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000;
+		vcpu->run->s.regs.gprs[reg2] |=
+			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff;
+	}
+	return 0;
+}
+
+static const intercept_handler_t b9_handlers[256] = {
+	[0x8d] = handle_epsw,
+	[0x9c] = handle_io_inst,
+};
+
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* This is handled just as for the B2 instructions. */
+	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler) {
+		if ((handler != handle_epsw) &&
+		    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE))
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t eb_handlers[256] = {
+	[0x8a] = handle_io_inst,
+};
+
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* All eb instructions that end up here are privileged. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
-	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
-	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
-	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
-	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
-	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
+	u64 address1, address2;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
 	vcpu->stat.instruction_tprot++;
 
+	kvm_s390_get_base_disp_sse(vcpu, &address1, &address2);
+
 	/* we only handle the Linux memory detection case:
 	 * access key == 0
 	 * guest DAT == off
@@ -405,7 +625,7 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static intercept_handler_t x01_handlers[256] = {
+static const intercept_handler_t x01_handlers[256] = {
 	[0x07] = handle_sckpf,
 };
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 566ddf6e8dfb..1c48ab2845e0 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -137,8 +137,10 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
-	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED))
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+		kfree(inti);
 		goto out;
+	}
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
@@ -324,8 +326,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
 	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
@@ -336,9 +336,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu,
 						   PGM_PRIVILEGED_OPERATION);
 
-	order_code = disp2;
-	if (base2)
-		order_code += vcpu->run->s.regs.gprs[base2];
+	order_code = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (r1 % 2)
 		parameter = vcpu->run->s.regs.gprs[r1];
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 90fdf85b5ff7..13f30f58a2df 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -141,13 +141,13 @@ TRACE_EVENT(kvm_s390_inject_vcpu,
  * Trace point for the actual delivery of interrupts.
  */
 TRACE_EVENT(kvm_s390_deliver_interrupt,
-	    TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1),
+	    TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1),
 	    TP_ARGS(id, type, data0, data1),
 
 	    TP_STRUCT__entry(
 		    __field(int, id)
 		    __field(__u32, inttype)
-		    __field(__u32, data0)
+		    __field(__u64, data0)
 		    __field(__u64, data1)
 		    ),
 
@@ -159,7 +159,7 @@ TRACE_EVENT(kvm_s390_deliver_interrupt,
 		    ),
 
 	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
-		      "data:%08x %016llx",
+		      "data:%08llx %016llx",
 		      __entry->id, __entry->inttype,
 		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
 		      __entry->data0, __entry->data1)
@@ -204,6 +204,26 @@ TRACE_EVENT(kvm_s390_stop_request,
 	);
 
 
+/*
+ * Trace point for enabling channel I/O instruction support.
+ */
+TRACE_EVENT(kvm_s390_enable_css,
+	    TP_PROTO(void *kvm),
+	    TP_ARGS(kvm),
+
+	    TP_STRUCT__entry(
+		    __field(void *, kvm)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->kvm = kvm;
+		    ),
+
+	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+		      __entry->kvm)
+	);
+
+
 #endif /* _TRACE_KVMS390_H */
 
 /* This part must be outside protection */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dc87b65e9c3a..635a74d22409 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -33,10 +33,10 @@
 
 #define KVM_MAX_VCPUS 254
 #define KVM_SOFT_MAX_VCPUS 160
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS 125
+/* memory slots that are not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
 #define KVM_MMIO_SIZE 16
 
@@ -219,11 +219,6 @@ struct kvm_mmu_page {
 	u64 *spt;
 	/* hold the gfn of each spte inside spt */
 	gfn_t *gfns;
-	/*
-	 * One bit set per slot which has memory
-	 * in this shadow page.
-	 */
-	DECLARE_BITMAP(slot_bitmap, KVM_MEM_SLOTS_NUM);
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
@@ -502,6 +497,13 @@ struct kvm_vcpu_arch {
 		u64 msr_val;
 		struct gfn_to_hva_cache data;
 	} pv_eoi;
+
+	/*
+	 * Indicate whether the access faults on its page table in guest
+	 * which is set when fix page fault and used to detect unhandeable
+	 * instruction.
+	 */
+	bool write_fault_to_shadow_pgtable;
 };
 
 struct kvm_lpage_info {
@@ -697,6 +699,11 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
+	int (*vm_has_apicv)(struct kvm *kvm);
+	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
+	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
@@ -991,6 +998,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 65231e173baf..695399f2d5eb 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -27,7 +27,7 @@ static inline bool kvm_check_and_clear_guest_paused(void)
  *
  * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
  * The hypercall number should be placed in rax and the return value will be
- * placed in rax.  No other registers will be clobbered unless explicited
+ * placed in rax.  No other registers will be clobbered unless explicitly
  * noted by the particular hypercall.
  */
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 235b49fa554b..b6fbf860e398 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -57,9 +57,12 @@
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE   0x00000010
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT       0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY    0x00000200
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 
@@ -97,6 +100,7 @@ enum vmcs_field {
 	GUEST_GS_SELECTOR               = 0x0000080a,
 	GUEST_LDTR_SELECTOR             = 0x0000080c,
 	GUEST_TR_SELECTOR               = 0x0000080e,
+	GUEST_INTR_STATUS               = 0x00000810,
 	HOST_ES_SELECTOR                = 0x00000c00,
 	HOST_CS_SELECTOR                = 0x00000c02,
 	HOST_SS_SELECTOR                = 0x00000c04,
@@ -124,6 +128,14 @@ enum vmcs_field {
 	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
 	EPT_POINTER                     = 0x0000201a,
 	EPT_POINTER_HIGH                = 0x0000201b,
+	EOI_EXIT_BITMAP0                = 0x0000201c,
+	EOI_EXIT_BITMAP0_HIGH           = 0x0000201d,
+	EOI_EXIT_BITMAP1                = 0x0000201e,
+	EOI_EXIT_BITMAP1_HIGH           = 0x0000201f,
+	EOI_EXIT_BITMAP2                = 0x00002020,
+	EOI_EXIT_BITMAP2_HIGH           = 0x00002021,
+	EOI_EXIT_BITMAP3                = 0x00002022,
+	EOI_EXIT_BITMAP3_HIGH           = 0x00002023,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
 	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
 	VMCS_LINK_POINTER               = 0x00002800,
@@ -346,9 +358,9 @@ enum vmcs_field {
 
 #define AR_RESERVD_MASK 0xfffe0f00
 
-#define TSS_PRIVATE_MEMSLOT			(KVM_MEMORY_SLOTS + 0)
-#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_MEMORY_SLOTS + 1)
-#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_MEMORY_SLOTS + 2)
+#define TSS_PRIVATE_MEMSLOT			(KVM_USER_MEM_SLOTS + 0)
+#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 1)
+#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 2)
 
 #define VMX_NR_VPIDS				(1 << 16)
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 979d03bce135..2871fccfee68 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -62,10 +62,12 @@
 #define EXIT_REASON_MCE_DURING_VMENTRY  41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EOI_INDUCED         45
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
+#define EXIT_REASON_APIC_WRITE          56
 #define EXIT_REASON_INVPCID             58
 
 #define VMX_EXIT_REASONS \
@@ -103,7 +105,12 @@
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
-	{ EXIT_REASON_WBINVD,                "WBINVD" }
+	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
+	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
+	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
+	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_INVD,                  "INVD" }, \
+	{ EXIT_REASON_INVPCID,               "INVPCID" }
 
 
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 9f966dc0b9e4..0732f0089a3d 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -218,6 +218,9 @@ static void kvm_shutdown(void)
 void __init kvmclock_init(void)
 {
 	unsigned long mem;
+	int size;
+
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
 	if (!kvm_para_available())
 		return;
@@ -231,16 +234,14 @@ void __init kvmclock_init(void)
 	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
-	mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS,
-			     PAGE_SIZE);
+	mem = memblock_alloc(size, PAGE_SIZE);
 	if (!mem)
 		return;
 	hv_clock = __va(mem);
 
 	if (kvm_register_clock("boot clock")) {
 		hv_clock = NULL;
-		memblock_free(mem,
-			sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
+		memblock_free(mem, size);
 		return;
 	}
 	pv_time_ops.sched_clock = kvm_clock_read;
@@ -275,7 +276,7 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned int size;
 
-	size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS;
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
 	preempt_disable();
 	cpu = smp_processor_id();
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a27e76371108..a335cc6cde72 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -24,6 +24,7 @@
 #include "kvm_cache_regs.h"
 #include <linux/module.h>
 #include <asm/kvm_emulate.h>
+#include <linux/stringify.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -43,7 +44,7 @@
 #define OpCL               9ull  /* CL register (for shifts) */
 #define OpImmByte         10ull  /* 8-bit sign extended immediate */
 #define OpOne             11ull  /* Implied 1 */
-#define OpImm             12ull  /* Sign extended immediate */
+#define OpImm             12ull  /* Sign extended up to 32-bit immediate */
 #define OpMem16           13ull  /* Memory operand (16-bit). */
 #define OpMem32           14ull  /* Memory operand (32-bit). */
 #define OpImmU            15ull  /* Immediate operand, zero extended */
@@ -58,6 +59,7 @@
 #define OpFS              24ull  /* FS */
 #define OpGS              25ull  /* GS */
 #define OpMem8            26ull  /* 8-bit zero extended memory operand */
+#define OpImm64           27ull  /* Sign extended 16/32/64-bit immediate */
 
 #define OpBits             5  /* Width of operand field */
 #define OpMask             ((1ull << OpBits) - 1)
@@ -101,6 +103,7 @@
 #define SrcMemFAddr (OpMemFAddr << SrcShift)
 #define SrcAcc      (OpAcc << SrcShift)
 #define SrcImmU16   (OpImmU16 << SrcShift)
+#define SrcImm64    (OpImm64 << SrcShift)
 #define SrcDX       (OpDX << SrcShift)
 #define SrcMem8     (OpMem8 << SrcShift)
 #define SrcMask     (OpMask << SrcShift)
@@ -113,6 +116,7 @@
 #define GroupDual   (2<<15)     /* Alternate decoding of mod == 3 */
 #define Prefix      (3<<15)     /* Instruction varies with 66/f2/f3 prefix */
 #define RMExt       (4<<15)     /* Opcode extension in ModRM r/m if mod == 3 */
+#define Escape      (5<<15)     /* Escape to coprocessor instruction */
 #define Sse         (1<<18)     /* SSE Vector instruction */
 /* Generic ModRM decode. */
 #define ModRM       (1<<19)
@@ -146,6 +150,8 @@
 #define Aligned     ((u64)1 << 41)  /* Explicitly aligned (e.g. MOVDQA) */
 #define Unaligned   ((u64)1 << 42)  /* Explicitly unaligned (e.g. MOVDQU) */
 #define Avx         ((u64)1 << 43)  /* Advanced Vector Extensions */
+#define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
+#define NoWrite     ((u64)1 << 45)  /* No writeback */
 
 #define X2(x...) x, x
 #define X3(x...) X2(x), x
@@ -156,6 +162,27 @@
 #define X8(x...) X4(x), X4(x)
 #define X16(x...) X8(x), X8(x)
 
+#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
+#define FASTOP_SIZE 8
+
+/*
+ * fastop functions have a special calling convention:
+ *
+ * dst:    [rdx]:rax  (in/out)
+ * src:    rbx        (in/out)
+ * src2:   rcx        (in)
+ * flags:  rflags     (in/out)
+ *
+ * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
+ * different operand sizes can be reached by calculation, rather than a jump
+ * table (which would be bigger than the code).
+ *
+ * fastop functions are declared as taking a never-defined fastop parameter,
+ * so they can't be called from C directly.
+ */
+
+struct fastop;
+
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -164,6 +191,8 @@ struct opcode {
 		const struct opcode *group;
 		const struct group_dual *gdual;
 		const struct gprefix *gprefix;
+		const struct escape *esc;
+		void (*fastop)(struct fastop *fake);
 	} u;
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 };
@@ -180,6 +209,11 @@ struct gprefix {
 	struct opcode pfx_f3;
 };
 
+struct escape {
+	struct opcode op[8];
+	struct opcode high[64];
+};
+
 /* EFLAGS bit definitions. */
 #define EFLG_ID (1<<21)
 #define EFLG_VIP (1<<20)
@@ -407,6 +441,97 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 		}							\
 	} while (0)
 
+static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
+
+#define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t"
+#define FOP_RET   "ret \n\t"
+
+#define FOP_START(op) \
+	extern void em_##op(struct fastop *fake); \
+	asm(".pushsection .text, \"ax\" \n\t" \
+	    ".global em_" #op " \n\t" \
+            FOP_ALIGN \
+	    "em_" #op ": \n\t"
+
+#define FOP_END \
+	    ".popsection")
+
+#define FOPNOP() FOP_ALIGN FOP_RET
+
+#define FOP1E(op,  dst) \
+	FOP_ALIGN #op " %" #dst " \n\t" FOP_RET
+
+#define FASTOP1(op) \
+	FOP_START(op) \
+	FOP1E(op##b, al) \
+	FOP1E(op##w, ax) \
+	FOP1E(op##l, eax) \
+	ON64(FOP1E(op##q, rax))	\
+	FOP_END
+
+#define FOP2E(op,  dst, src)	   \
+	FOP_ALIGN #op " %" #src ", %" #dst " \n\t" FOP_RET
+
+#define FASTOP2(op) \
+	FOP_START(op) \
+	FOP2E(op##b, al, bl) \
+	FOP2E(op##w, ax, bx) \
+	FOP2E(op##l, eax, ebx) \
+	ON64(FOP2E(op##q, rax, rbx)) \
+	FOP_END
+
+/* 2 operand, word only */
+#define FASTOP2W(op) \
+	FOP_START(op) \
+	FOPNOP() \
+	FOP2E(op##w, ax, bx) \
+	FOP2E(op##l, eax, ebx) \
+	ON64(FOP2E(op##q, rax, rbx)) \
+	FOP_END
+
+/* 2 operand, src is CL */
+#define FASTOP2CL(op) \
+	FOP_START(op) \
+	FOP2E(op##b, al, cl) \
+	FOP2E(op##w, ax, cl) \
+	FOP2E(op##l, eax, cl) \
+	ON64(FOP2E(op##q, rax, cl)) \
+	FOP_END
+
+#define FOP3E(op,  dst, src, src2) \
+	FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
+
+/* 3-operand, word-only, src2=cl */
+#define FASTOP3WCL(op) \
+	FOP_START(op) \
+	FOPNOP() \
+	FOP3E(op##w, ax, bx, cl) \
+	FOP3E(op##l, eax, ebx, cl) \
+	ON64(FOP3E(op##q, rax, rbx, cl)) \
+	FOP_END
+
+/* Special case for SETcc - 1 instruction per cc */
+#define FOP_SETCC(op) ".align 4; " #op " %al; ret \n\t"
+
+FOP_START(setcc)
+FOP_SETCC(seto)
+FOP_SETCC(setno)
+FOP_SETCC(setc)
+FOP_SETCC(setnc)
+FOP_SETCC(setz)
+FOP_SETCC(setnz)
+FOP_SETCC(setbe)
+FOP_SETCC(setnbe)
+FOP_SETCC(sets)
+FOP_SETCC(setns)
+FOP_SETCC(setp)
+FOP_SETCC(setnp)
+FOP_SETCC(setl)
+FOP_SETCC(setnl)
+FOP_SETCC(setle)
+FOP_SETCC(setnle)
+FOP_END;
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
@@ -663,7 +788,7 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 	ulong la;
 	u32 lim;
 	u16 sel;
-	unsigned cpl, rpl;
+	unsigned cpl;
 
 	la = seg_base(ctxt, addr.seg) + addr.ea;
 	switch (ctxt->mode) {
@@ -697,11 +822,6 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 				goto bad;
 		}
 		cpl = ctxt->ops->cpl(ctxt);
-		if (ctxt->mode == X86EMUL_MODE_REAL)
-			rpl = 0;
-		else
-			rpl = sel & 3;
-		cpl = max(cpl, rpl);
 		if (!(desc.type & 8)) {
 			/* data segment */
 			if (cpl > desc.dpl)
@@ -852,39 +972,50 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
-static int test_cc(unsigned int condition, unsigned int flags)
-{
-	int rc = 0;
-
-	switch ((condition & 15) >> 1) {
-	case 0: /* o */
-		rc |= (flags & EFLG_OF);
-		break;
-	case 1: /* b/c/nae */
-		rc |= (flags & EFLG_CF);
-		break;
-	case 2: /* z/e */
-		rc |= (flags & EFLG_ZF);
-		break;
-	case 3: /* be/na */
-		rc |= (flags & (EFLG_CF|EFLG_ZF));
-		break;
-	case 4: /* s */
-		rc |= (flags & EFLG_SF);
-		break;
-	case 5: /* p/pe */
-		rc |= (flags & EFLG_PF);
-		break;
-	case 7: /* le/ng */
-		rc |= (flags & EFLG_ZF);
-		/* fall through */
-	case 6: /* l/nge */
-		rc |= (!(flags & EFLG_SF) != !(flags & EFLG_OF));
-		break;
-	}
-
-	/* Odd condition identifiers (lsb == 1) have inverted sense. */
-	return (!!rc ^ (condition & 1));
+FASTOP2(add);
+FASTOP2(or);
+FASTOP2(adc);
+FASTOP2(sbb);
+FASTOP2(and);
+FASTOP2(sub);
+FASTOP2(xor);
+FASTOP2(cmp);
+FASTOP2(test);
+
+FASTOP3WCL(shld);
+FASTOP3WCL(shrd);
+
+FASTOP2W(imul);
+
+FASTOP1(not);
+FASTOP1(neg);
+FASTOP1(inc);
+FASTOP1(dec);
+
+FASTOP2CL(rol);
+FASTOP2CL(ror);
+FASTOP2CL(rcl);
+FASTOP2CL(rcr);
+FASTOP2CL(shl);
+FASTOP2CL(shr);
+FASTOP2CL(sar);
+
+FASTOP2W(bsf);
+FASTOP2W(bsr);
+FASTOP2W(bt);
+FASTOP2W(bts);
+FASTOP2W(btr);
+FASTOP2W(btc);
+
+static u8 test_cc(unsigned int condition, unsigned long flags)
+{
+	u8 rc;
+	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
+
+	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
+	asm("push %[flags]; popf; call *%[fastop]"
+	    : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+	return rc;
 }
 
 static void fetch_register_operand(struct operand *op)
@@ -994,6 +1125,53 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	ctxt->ops->put_fpu(ctxt);
 }
 
+static int em_fninit(struct x86_emulate_ctxt *ctxt)
+{
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fninit");
+	ctxt->ops->put_fpu(ctxt);
+	return X86EMUL_CONTINUE;
+}
+
+static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
+{
+	u16 fcw;
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fnstcw %0": "+m"(fcw));
+	ctxt->ops->put_fpu(ctxt);
+
+	/* force 2 byte destination */
+	ctxt->dst.bytes = 2;
+	ctxt->dst.val = fcw;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
+{
+	u16 fsw;
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fnstsw %0": "+m"(fsw));
+	ctxt->ops->put_fpu(ctxt);
+
+	/* force 2 byte destination */
+	ctxt->dst.bytes = 2;
+	ctxt->dst.val = fsw;
+
+	return X86EMUL_CONTINUE;
+}
+
 static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 				    struct operand *op)
 {
@@ -1534,6 +1712,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
+	if (ctxt->d & NoWrite)
+		return X86EMUL_CONTINUE;
+
 	switch (ctxt->dst.type) {
 	case OP_REG:
 		write_register_operand(&ctxt->dst);
@@ -1918,47 +2099,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_grp2(struct x86_emulate_ctxt *ctxt)
-{
-	switch (ctxt->modrm_reg) {
-	case 0:	/* rol */
-		emulate_2op_SrcB(ctxt, "rol");
-		break;
-	case 1:	/* ror */
-		emulate_2op_SrcB(ctxt, "ror");
-		break;
-	case 2:	/* rcl */
-		emulate_2op_SrcB(ctxt, "rcl");
-		break;
-	case 3:	/* rcr */
-		emulate_2op_SrcB(ctxt, "rcr");
-		break;
-	case 4:	/* sal/shl */
-	case 6:	/* sal/shl */
-		emulate_2op_SrcB(ctxt, "sal");
-		break;
-	case 5:	/* shr */
-		emulate_2op_SrcB(ctxt, "shr");
-		break;
-	case 7:	/* sar */
-		emulate_2op_SrcB(ctxt, "sar");
-		break;
-	}
-	return X86EMUL_CONTINUE;
-}
-
-static int em_not(struct x86_emulate_ctxt *ctxt)
-{
-	ctxt->dst.val = ~ctxt->dst.val;
-	return X86EMUL_CONTINUE;
-}
-
-static int em_neg(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_1op(ctxt, "neg");
-	return X86EMUL_CONTINUE;
-}
-
 static int em_mul_ex(struct x86_emulate_ctxt *ctxt)
 {
 	u8 ex = 0;
@@ -2000,12 +2140,6 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt)
 	int rc = X86EMUL_CONTINUE;
 
 	switch (ctxt->modrm_reg) {
-	case 0:	/* inc */
-		emulate_1op(ctxt, "inc");
-		break;
-	case 1:	/* dec */
-		emulate_1op(ctxt, "dec");
-		break;
 	case 2: /* call near abs */ {
 		long int old_eip;
 		old_eip = ctxt->_eip;
@@ -2075,7 +2209,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 	/* Save real source value, then compare EAX against destination. */
 	ctxt->src.orig_val = ctxt->src.val;
 	ctxt->src.val = reg_read(ctxt, VCPU_REGS_RAX);
-	emulate_2op_SrcV(ctxt, "cmp");
+	fastop(ctxt, em_cmp);
 
 	if (ctxt->eflags & EFLG_ZF) {
 		/* Success: write back to memory. */
@@ -2843,7 +2977,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt)
 	ctxt->src.type = OP_IMM;
 	ctxt->src.val = 0;
 	ctxt->src.bytes = 1;
-	emulate_2op_SrcV(ctxt, "or");
+	fastop(ctxt, em_or);
 	ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF);
 	if (cf)
 		ctxt->eflags |= X86_EFLAGS_CF;
@@ -2852,6 +2986,24 @@ static int em_das(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_aad(struct x86_emulate_ctxt *ctxt)
+{
+	u8 al = ctxt->dst.val & 0xff;
+	u8 ah = (ctxt->dst.val >> 8) & 0xff;
+
+	al = (al + (ah * ctxt->src.val)) & 0xff;
+
+	ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al;
+
+	/* Set PF, ZF, SF */
+	ctxt->src.type = OP_IMM;
+	ctxt->src.val = 0;
+	ctxt->src.bytes = 1;
+	fastop(ctxt, em_or);
+
+	return X86EMUL_CONTINUE;
+}
+
 static int em_call(struct x86_emulate_ctxt *ctxt)
 {
 	long rel = ctxt->src.val;
@@ -2900,64 +3052,6 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_add(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "add");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_or(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "or");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_adc(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "adc");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_sbb(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "sbb");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_and(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "and");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_sub(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "sub");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_xor(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "xor");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_cmp(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "cmp");
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
-	return X86EMUL_CONTINUE;
-}
-
-static int em_test(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "test");
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
-	return X86EMUL_CONTINUE;
-}
-
 static int em_xchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Write back the register source. */
@@ -2970,16 +3064,10 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_imul(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "imul");
-	return X86EMUL_CONTINUE;
-}
-
 static int em_imul_3op(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = ctxt->src2.val;
-	return em_imul(ctxt);
+	return fastop(ctxt, em_imul);
 }
 
 static int em_cwd(struct x86_emulate_ctxt *ctxt)
@@ -3300,47 +3388,6 @@ static int em_sti(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_bt(struct x86_emulate_ctxt *ctxt)
-{
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
-	/* only subword offset */
-	ctxt->src.val &= (ctxt->dst.bytes << 3) - 1;
-
-	emulate_2op_SrcV_nobyte(ctxt, "bt");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bts(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bts");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_btr(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "btr");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_btc(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "btc");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bsf(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bsf");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bsr(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bsr");
-	return X86EMUL_CONTINUE;
-}
-
 static int em_cpuid(struct x86_emulate_ctxt *ctxt)
 {
 	u32 eax, ebx, ecx, edx;
@@ -3572,7 +3619,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
 #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
 #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
+#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
+#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
 #define II(_f, _e, _i) \
 	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
 #define IIP(_f, _e, _i, _p) \
@@ -3583,12 +3632,13 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define D2bv(_f)      D((_f) | ByteOp), D(_f)
 #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p)
 #define I2bv(_f, _e)  I((_f) | ByteOp, _e), I(_f, _e)
+#define F2bv(_f, _e)  F((_f) | ByteOp, _e), F(_f, _e)
 #define I2bvIP(_f, _e, _i, _p) \
 	IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p)
 
-#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
-		I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
-		I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
+#define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
+		F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
+		F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
 
 static const struct opcode group7_rm1[] = {
 	DI(SrcNone | Priv, monitor),
@@ -3614,25 +3664,36 @@ static const struct opcode group7_rm7[] = {
 };
 
 static const struct opcode group1[] = {
-	I(Lock, em_add),
-	I(Lock | PageTable, em_or),
-	I(Lock, em_adc),
-	I(Lock, em_sbb),
-	I(Lock | PageTable, em_and),
-	I(Lock, em_sub),
-	I(Lock, em_xor),
-	I(0, em_cmp),
+	F(Lock, em_add),
+	F(Lock | PageTable, em_or),
+	F(Lock, em_adc),
+	F(Lock, em_sbb),
+	F(Lock | PageTable, em_and),
+	F(Lock, em_sub),
+	F(Lock, em_xor),
+	F(NoWrite, em_cmp),
 };
 
 static const struct opcode group1A[] = {
 	I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
 };
 
+static const struct opcode group2[] = {
+	F(DstMem | ModRM, em_rol),
+	F(DstMem | ModRM, em_ror),
+	F(DstMem | ModRM, em_rcl),
+	F(DstMem | ModRM, em_rcr),
+	F(DstMem | ModRM, em_shl),
+	F(DstMem | ModRM, em_shr),
+	F(DstMem | ModRM, em_shl),
+	F(DstMem | ModRM, em_sar),
+};
+
 static const struct opcode group3[] = {
-	I(DstMem | SrcImm, em_test),
-	I(DstMem | SrcImm, em_test),
-	I(DstMem | SrcNone | Lock, em_not),
-	I(DstMem | SrcNone | Lock, em_neg),
+	F(DstMem | SrcImm | NoWrite, em_test),
+	F(DstMem | SrcImm | NoWrite, em_test),
+	F(DstMem | SrcNone | Lock, em_not),
+	F(DstMem | SrcNone | Lock, em_neg),
 	I(SrcMem, em_mul_ex),
 	I(SrcMem, em_imul_ex),
 	I(SrcMem, em_div_ex),
@@ -3640,14 +3701,14 @@ static const struct opcode group3[] = {
 };
 
 static const struct opcode group4[] = {
-	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
-	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
+	F(ByteOp | DstMem | SrcNone | Lock, em_inc),
+	F(ByteOp | DstMem | SrcNone | Lock, em_dec),
 	N, N, N, N, N, N,
 };
 
 static const struct opcode group5[] = {
-	I(DstMem | SrcNone | Lock,		em_grp45),
-	I(DstMem | SrcNone | Lock,		em_grp45),
+	F(DstMem | SrcNone | Lock,		em_inc),
+	F(DstMem | SrcNone | Lock,		em_dec),
 	I(SrcMem | Stack,			em_grp45),
 	I(SrcMemFAddr | ImplicitOps | Stack,	em_call_far),
 	I(SrcMem | Stack,			em_grp45),
@@ -3682,10 +3743,10 @@ static const struct group_dual group7 = { {
 
 static const struct opcode group8[] = {
 	N, N, N, N,
-	I(DstMem | SrcImmByte,				em_bt),
-	I(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
-	I(DstMem | SrcImmByte | Lock,			em_btr),
-	I(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
+	F(DstMem | SrcImmByte | NoWrite,		em_bt),
+	F(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
+	F(DstMem | SrcImmByte | Lock,			em_btr),
+	F(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
 };
 
 static const struct group_dual group9 = { {
@@ -3707,33 +3768,96 @@ static const struct gprefix pfx_vmovntpx = {
 	I(0, em_mov), N, N, N,
 };
 
+static const struct escape escape_d9 = { {
+	N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
+static const struct escape escape_db = { {
+	N, N, N, N, N, N, N, N,
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, I(ImplicitOps, em_fninit), N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
+static const struct escape escape_dd = { {
+	N, N, N, N, N, N, N, I(DstMem, em_fnstsw),
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
 static const struct opcode opcode_table[256] = {
 	/* 0x00 - 0x07 */
-	I6ALU(Lock, em_add),
+	F6ALU(Lock, em_add),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg),
 	/* 0x08 - 0x0F */
-	I6ALU(Lock | PageTable, em_or),
+	F6ALU(Lock | PageTable, em_or),
 	I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg),
 	N,
 	/* 0x10 - 0x17 */
-	I6ALU(Lock, em_adc),
+	F6ALU(Lock, em_adc),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg),
 	/* 0x18 - 0x1F */
-	I6ALU(Lock, em_sbb),
+	F6ALU(Lock, em_sbb),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg),
 	/* 0x20 - 0x27 */
-	I6ALU(Lock | PageTable, em_and), N, N,
+	F6ALU(Lock | PageTable, em_and), N, N,
 	/* 0x28 - 0x2F */
-	I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
+	F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
 	/* 0x30 - 0x37 */
-	I6ALU(Lock, em_xor), N, N,
+	F6ALU(Lock, em_xor), N, N,
 	/* 0x38 - 0x3F */
-	I6ALU(0, em_cmp), N, N,
+	F6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
-	X16(D(DstReg)),
+	X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)),
 	/* 0x50 - 0x57 */
 	X8(I(SrcReg | Stack, em_push)),
 	/* 0x58 - 0x5F */
@@ -3757,7 +3881,7 @@ static const struct opcode opcode_table[256] = {
 	G(DstMem | SrcImm, group1),
 	G(ByteOp | DstMem | SrcImm | No64, group1),
 	G(DstMem | SrcImmByte, group1),
-	I2bv(DstMem | SrcReg | ModRM, em_test),
+	F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
 	I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov),
@@ -3777,18 +3901,18 @@ static const struct opcode opcode_table[256] = {
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String, em_mov),
-	I2bv(SrcSI | DstDI | String, em_cmp),
+	F2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
 	/* 0xA8 - 0xAF */
-	I2bv(DstAcc | SrcImm, em_test),
+	F2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
-	I2bv(SrcAcc | DstDI | String, em_cmp),
+	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */
-	X8(I(DstReg | SrcImm | Mov, em_mov)),
+	X8(I(DstReg | SrcImm64 | Mov, em_mov)),
 	/* 0xC0 - 0xC7 */
-	D2bv(DstMem | SrcImmByte | ModRM),
+	G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
 	I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
 	I(ImplicitOps | Stack, em_ret),
 	I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
@@ -3800,10 +3924,11 @@ static const struct opcode opcode_table[256] = {
 	D(ImplicitOps), DI(SrcImmByte, intn),
 	D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
 	/* 0xD0 - 0xD7 */
-	D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM),
-	N, N, N, N,
+	G(Src2One | ByteOp, group2), G(Src2One, group2),
+	G(Src2CL | ByteOp, group2), G(Src2CL, group2),
+	N, I(DstAcc | SrcImmByte | No64, em_aad), N, N,
 	/* 0xD8 - 0xDF */
-	N, N, N, N, N, N, N, N,
+	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
 	/* 0xE0 - 0xE7 */
 	X3(I(SrcImmByte, em_loop)),
 	I(SrcImmByte, em_jcxz),
@@ -3870,28 +3995,29 @@ static const struct opcode twobyte_table[256] = {
 	X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
 	/* 0xA0 - 0xA7 */
 	I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg),
-	II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt),
-	D(DstMem | SrcReg | Src2ImmByte | ModRM),
-	D(DstMem | SrcReg | Src2CL | ModRM), N, N,
+	II(ImplicitOps, em_cpuid, cpuid),
+	F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt),
+	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
+	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
 	DI(ImplicitOps, rsm),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
-	D(DstMem | SrcReg | Src2ImmByte | ModRM),
-	D(DstMem | SrcReg | Src2CL | ModRM),
-	D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
+	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
+	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
+	D(ModRM), F(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
 	I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xB8 - 0xBF */
 	N, N,
 	G(BitOp, group8),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
-	I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
+	F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xC0 - 0xC7 */
 	D2bv(DstMem | SrcReg | ModRM | Lock),
@@ -3950,6 +4076,9 @@ static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case 4:
 		op->val = insn_fetch(s32, ctxt);
 		break;
+	case 8:
+		op->val = insn_fetch(s64, ctxt);
+		break;
 	}
 	if (!sign_extension) {
 		switch (op->bytes) {
@@ -4028,6 +4157,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpImm:
 		rc = decode_imm(ctxt, op, imm_size(ctxt), true);
 		break;
+	case OpImm64:
+		rc = decode_imm(ctxt, op, ctxt->op_bytes, true);
+		break;
 	case OpMem8:
 		ctxt->memop.bytes = 1;
 		goto mem_common;
@@ -4222,6 +4354,12 @@ done_prefixes:
 			case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break;
 			}
 			break;
+		case Escape:
+			if (ctxt->modrm > 0xbf)
+				opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
+			else
+				opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+			break;
 		default:
 			return EMULATION_FAILED;
 		}
@@ -4354,6 +4492,16 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
 		read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
 }
 
+static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
+{
+	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
+	fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
+	asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+	    : "+a"(ctxt->dst.val), "+b"(ctxt->src.val), [flags]"+D"(flags)
+	: "c"(ctxt->src2.val), [fastop]"S"(fop));
+	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
+	return X86EMUL_CONTINUE;
+}
 
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 {
@@ -4483,6 +4631,13 @@ special_insn:
 	}
 
 	if (ctxt->execute) {
+		if (ctxt->d & Fastop) {
+			void (*fop)(struct fastop *) = (void *)ctxt->execute;
+			rc = fastop(ctxt, fop);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+			goto writeback;
+		}
 		rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
@@ -4493,12 +4648,6 @@ special_insn:
 		goto twobyte_insn;
 
 	switch (ctxt->b) {
-	case 0x40 ... 0x47: /* inc r16/r32 */
-		emulate_1op(ctxt, "inc");
-		break;
-	case 0x48 ... 0x4f: /* dec r16/r32 */
-		emulate_1op(ctxt, "dec");
-		break;
 	case 0x63:		/* movsxd */
 		if (ctxt->mode != X86EMUL_MODE_PROT64)
 			goto cannot_emulate;
@@ -4523,9 +4672,6 @@ special_insn:
 		case 8: ctxt->dst.val = (s32)ctxt->dst.val; break;
 		}
 		break;
-	case 0xc0 ... 0xc1:
-		rc = em_grp2(ctxt);
-		break;
 	case 0xcc:		/* int3 */
 		rc = emulate_int(ctxt, 3);
 		break;
@@ -4536,13 +4682,6 @@ special_insn:
 		if (ctxt->eflags & EFLG_OF)
 			rc = emulate_int(ctxt, 4);
 		break;
-	case 0xd0 ... 0xd1:	/* Grp2 */
-		rc = em_grp2(ctxt);
-		break;
-	case 0xd2 ... 0xd3:	/* Grp2 */
-		ctxt->src.val = reg_read(ctxt, VCPU_REGS_RCX);
-		rc = em_grp2(ctxt);
-		break;
 	case 0xe9: /* jmp rel */
 	case 0xeb: /* jmp rel short */
 		jmp_rel(ctxt, ctxt->src.val);
@@ -4661,14 +4800,6 @@ twobyte_insn:
 	case 0x90 ... 0x9f:     /* setcc r/m8 */
 		ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
 		break;
-	case 0xa4: /* shld imm8, r, r/m */
-	case 0xa5: /* shld cl, r, r/m */
-		emulate_2op_cl(ctxt, "shld");
-		break;
-	case 0xac: /* shrd imm8, r, r/m */
-	case 0xad: /* shrd cl, r, r/m */
-		emulate_2op_cl(ctxt, "shrd");
-		break;
 	case 0xae:              /* clflush */
 		break;
 	case 0xb6 ... 0xb7:	/* movzx */
@@ -4682,7 +4813,7 @@ twobyte_insn:
 							(s16) ctxt->src.val;
 		break;
 	case 0xc0 ... 0xc1:	/* xadd */
-		emulate_2op_SrcV(ctxt, "add");
+		fastop(ctxt, em_add);
 		/* Write back the register source. */
 		ctxt->src.val = ctxt->dst.orig_val;
 		write_register_operand(&ctxt->src);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 11300d2fa714..c1d30b2fc9bb 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -122,7 +122,6 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	 */
 	remaining = hrtimer_get_remaining(&ps->timer);
 	elapsed = ps->period - ktime_to_ns(remaining);
-	elapsed = mod_64(elapsed, ps->period);
 
 	return elapsed;
 }
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 848206df0967..cc31f7c06d3d 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -241,6 +241,8 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	int irq, irq2, intno;
 	struct kvm_pic *s = pic_irqchip(kvm);
 
+	s->output = 0;
+
 	pic_lock(s);
 	irq = pic_get_irq(&s->pics[0]);
 	if (irq >= 0) {
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 7e06ba1618bd..484bc874688b 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -38,49 +38,81 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
 /*
+ * check if there is pending interrupt from
+ * non-APIC source without intack.
+ */
+static int kvm_cpu_has_extint(struct kvm_vcpu *v)
+{
+	if (kvm_apic_accept_pic_intr(v))
+		return pic_irqchip(v->kvm)->output;	/* PIC */
+	else
+		return 0;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
+	if (!irqchip_in_kernel(v->kvm))
+		return v->arch.interrupt.pending;
+
+	if (kvm_cpu_has_extint(v))
+		return 1;
+
+	if (kvm_apic_vid_enabled(v->kvm))
+		return 0;
+
+	return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
+}
+
+/*
  * check if there is pending interrupt without
  * intack.
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	struct kvm_pic *s;
-
 	if (!irqchip_in_kernel(v->kvm))
 		return v->arch.interrupt.pending;
 
-	if (kvm_apic_has_interrupt(v) == -1) {	/* LAPIC */
-		if (kvm_apic_accept_pic_intr(v)) {
-			s = pic_irqchip(v->kvm);	/* PIC */
-			return s->output;
-		} else
-			return 0;
-	}
-	return 1;
+	if (kvm_cpu_has_extint(v))
+		return 1;
+
+	return kvm_apic_has_interrupt(v) != -1;	/* LAPIC */
 }
 EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
 
 /*
+ * Read pending interrupt(from non-APIC source)
+ * vector and intack.
+ */
+static int kvm_cpu_get_extint(struct kvm_vcpu *v)
+{
+	if (kvm_cpu_has_extint(v))
+		return kvm_pic_read_irq(v->kvm); /* PIC */
+	return -1;
+}
+
+/*
  * Read pending interrupt vector and intack.
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	struct kvm_pic *s;
 	int vector;
 
 	if (!irqchip_in_kernel(v->kvm))
 		return v->arch.interrupt.nr;
 
-	vector = kvm_get_apic_interrupt(v);	/* APIC */
-	if (vector == -1) {
-		if (kvm_apic_accept_pic_intr(v)) {
-			s = pic_irqchip(v->kvm);
-			s->output = 0;		/* PIC */
-			vector = kvm_pic_read_irq(v->kvm);
-		}
-	}
-	return vector;
+	vector = kvm_cpu_get_extint(v);
+
+	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+		return vector;			/* PIC */
+
+	return kvm_get_apic_interrupt(v);	/* APIC */
 }
-EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9392f527f107..02b51dd4e4ad 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -140,31 +140,56 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline int apic_x2apic_mode(struct kvm_lapic *apic)
-{
-	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
-}
-
 static inline int kvm_apic_id(struct kvm_lapic *apic)
 {
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
-static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+				struct kvm_lapic_irq *irq,
+				u64 *eoi_exit_bitmap)
 {
-	u16 cid;
-	ldr >>= 32 - map->ldr_bits;
-	cid = (ldr >> map->cid_shift) & map->cid_mask;
+	struct kvm_lapic **dst;
+	struct kvm_apic_map *map;
+	unsigned long bitmap = 1;
+	int i;
 
-	BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+	rcu_read_lock();
+	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
-	return cid;
-}
+	if (unlikely(!map)) {
+		__set_bit(irq->vector, (unsigned long *)eoi_exit_bitmap);
+		goto out;
+	}
 
-static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
-{
-	ldr >>= (32 - map->ldr_bits);
-	return ldr & map->lid_mask;
+	if (irq->dest_mode == 0) { /* physical mode */
+		if (irq->delivery_mode == APIC_DM_LOWEST ||
+				irq->dest_id == 0xff) {
+			__set_bit(irq->vector,
+				  (unsigned long *)eoi_exit_bitmap);
+			goto out;
+		}
+		dst = &map->phys_map[irq->dest_id & 0xff];
+	} else {
+		u32 mda = irq->dest_id << (32 - map->ldr_bits);
+
+		dst = map->logical_map[apic_cluster_id(map, mda)];
+
+		bitmap = apic_logical_id(map, mda);
+	}
+
+	for_each_set_bit(i, &bitmap, 16) {
+		if (!dst[i])
+			continue;
+		if (dst[i]->vcpu == vcpu) {
+			__set_bit(irq->vector,
+				  (unsigned long *)eoi_exit_bitmap);
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
 }
 
 static void recalculate_apic_map(struct kvm *kvm)
@@ -230,6 +255,8 @@ out:
 
 	if (old)
 		kfree_rcu(old, rcu);
+
+	kvm_ioapic_make_eoibitmap_request(kvm);
 }
 
 static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
@@ -345,6 +372,10 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 {
 	int result;
 
+	/*
+	 * Note that irr_pending is just a hint. It will be always
+	 * true with virtual interrupt delivery enabled.
+	 */
 	if (!apic->irr_pending)
 		return -1;
 
@@ -461,6 +492,8 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static inline int apic_find_highest_isr(struct kvm_lapic *apic)
 {
 	int result;
+
+	/* Note that isr_count is always 1 with vid enabled */
 	if (!apic->isr_count)
 		return -1;
 	if (likely(apic->highest_isr_cache != -1))
@@ -740,6 +773,19 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
 }
 
+static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
+{
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+		int trigger_mode;
+		if (apic_test_vector(vector, apic->regs + APIC_TMR))
+			trigger_mode = IOAPIC_LEVEL_TRIG;
+		else
+			trigger_mode = IOAPIC_EDGE_TRIG;
+		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+	}
+}
+
 static int apic_set_eoi(struct kvm_lapic *apic)
 {
 	int vector = apic_find_highest_isr(apic);
@@ -756,19 +802,26 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
-		int trigger_mode;
-		if (apic_test_vector(vector, apic->regs + APIC_TMR))
-			trigger_mode = IOAPIC_LEVEL_TRIG;
-		else
-			trigger_mode = IOAPIC_EDGE_TRIG;
-		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
-	}
+	kvm_ioapic_send_eoi(apic, vector);
 	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 	return vector;
 }
 
+/*
+ * this interface assumes a trap-like exit, which has already finished
+ * desired side effect including vISR and vPPR update.
+ */
+void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	trace_kvm_eoi(apic, vector);
+
+	kvm_ioapic_send_eoi(apic, vector);
+	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);
+
 static void apic_send_ipi(struct kvm_lapic *apic)
 {
 	u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
@@ -1212,6 +1265,21 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
+/* emulate APIC access in a trap manner */
+void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
+{
+	u32 val = 0;
+
+	/* hw has done the conditional check and inst decode */
+	offset &= 0xff0;
+
+	apic_reg_read(vcpu->arch.apic, offset, 4, &val);
+
+	/* TODO: optimize to just emulate side effect w/o one more write */
+	apic_reg_write(vcpu->arch.apic, offset, val);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
+
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1288,6 +1356,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
+	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	if (!apic) {
@@ -1309,11 +1378,16 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		value &= ~MSR_IA32_APICBASE_BSP;
 
 	vcpu->arch.apic_base = value;
-	if (apic_x2apic_mode(apic)) {
-		u32 id = kvm_apic_id(apic);
-		u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
-		kvm_apic_set_ldr(apic, ldr);
+	if ((old_value ^ value) & X2APIC_ENABLE) {
+		if (value & X2APIC_ENABLE) {
+			u32 id = kvm_apic_id(apic);
+			u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+			kvm_apic_set_ldr(apic, ldr);
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
+		} else
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
 	}
+
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
 
@@ -1359,8 +1433,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
-	apic->irr_pending = false;
-	apic->isr_count = 0;
+	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
@@ -1575,8 +1649,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
-	apic->isr_count = count_vectors(apic->regs + APIC_ISR);
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
+	kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic));
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index e5ebf9f3571f..1676d34ddb4e 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -64,6 +64,9 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 
+void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
+void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
+
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
@@ -124,4 +127,35 @@ static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
 	return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
 }
 
+static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+{
+	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
+}
+
+static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
+{
+	return kvm_x86_ops->vm_has_apicv(kvm);
+}
+
+static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+{
+	u16 cid;
+	ldr >>= 32 - map->ldr_bits;
+	cid = (ldr >> map->cid_shift) & map->cid_mask;
+
+	BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+
+	return cid;
+}
+
+static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
+{
+	ldr >>= (32 - map->ldr_bits);
+	return ldr & map->lid_mask;
+}
+
+void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+				struct kvm_lapic_irq *irq,
+				u64 *eoi_bitmap);
+
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01d7c2ad05f5..4ed3edbe06bd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -448,7 +448,8 @@ static bool __check_direct_spte_mmio_pf(u64 spte)
 
 static bool spte_is_locklessly_modifiable(u64 spte)
 {
-	return !(~spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE));
+	return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) ==
+		(SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE);
 }
 
 static bool spte_has_volatile_bits(u64 spte)
@@ -831,8 +832,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
 
-	max_level = kvm_x86_ops->get_lpage_level() < host_level ?
-		kvm_x86_ops->get_lpage_level() : host_level;
+	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
 		if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
@@ -1142,7 +1142,7 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
-				 int level, bool pt_protect)
+				 bool pt_protect)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1180,7 +1180,7 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	while (mask) {
 		rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 				      PT_PAGE_TABLE_LEVEL, slot);
-		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false);
+		__rmap_write_protect(kvm, rmapp, false);
 
 		/* clear the first set bit */
 		mask &= mask - 1;
@@ -1199,7 +1199,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 	for (i = PT_PAGE_TABLE_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
 		rmapp = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(kvm, rmapp, i, true);
+		write_protected |= __rmap_write_protect(kvm, rmapp, true);
 	}
 
 	return write_protected;
@@ -1460,28 +1460,14 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
 }
 
-/*
- * Remove the sp from shadow page cache, after call it,
- * we can not find this sp from the cache, and the shadow
- * page table is still valid.
- * It should be under the protection of mmu lock.
- */
-static void kvm_mmu_isolate_page(struct kvm_mmu_page *sp)
+static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
 {
 	ASSERT(is_empty_shadow_page(sp->spt));
 	hlist_del(&sp->hash_link);
-	if (!sp->role.direct)
-		free_page((unsigned long)sp->gfns);
-}
-
-/*
- * Free the shadow page table and the sp, we can do it
- * out of the protection of mmu lock.
- */
-static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
-{
 	list_del(&sp->link);
 	free_page((unsigned long)sp->spt);
+	if (!sp->role.direct)
+		free_page((unsigned long)sp->gfns);
 	kmem_cache_free(mmu_page_header_cache, sp);
 }
 
@@ -1522,7 +1508,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM);
 	sp->parent_ptes = 0;
 	mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
@@ -1973,9 +1958,9 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
 {
 	u64 spte;
 
-	spte = __pa(sp->spt)
-		| PT_PRESENT_MASK | PT_ACCESSED_MASK
-		| PT_WRITABLE_MASK | PT_USER_MASK;
+	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+
 	mmu_spte_set(sptep, spte);
 }
 
@@ -2126,7 +2111,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	do {
 		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
 		WARN_ON(!sp->role.invalid || sp->root_count);
-		kvm_mmu_isolate_page(sp);
 		kvm_mmu_free_page(sp);
 	} while (!list_empty(invalid_list));
 }
@@ -2144,6 +2128,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	 * change the value
 	 */
 
+	spin_lock(&kvm->mmu_lock);
+
 	if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
 		while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages &&
 			!list_empty(&kvm->arch.active_mmu_pages)) {
@@ -2158,6 +2144,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	}
 
 	kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
+
+	spin_unlock(&kvm->mmu_lock);
 }
 
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
@@ -2183,14 +2171,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
-{
-	int slot = memslot_id(kvm, gfn);
-	struct kvm_mmu_page *sp = page_header(__pa(pte));
-
-	__set_bit(slot, sp->slot_bitmap);
-}
-
 /*
  * The function is based on mtrr_type_lookup() in
  * arch/x86/kernel/cpu/mtrr/generic.c
@@ -2332,9 +2312,8 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 		if (s->role.level != PT_PAGE_TABLE_LEVEL)
 			return 1;
 
-		if (!need_unsync && !s->unsync) {
+		if (!s->unsync)
 			need_unsync = true;
-		}
 	}
 	if (need_unsync)
 		kvm_unsync_pages(vcpu, gfn);
@@ -2342,8 +2321,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 }
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-		    unsigned pte_access, int user_fault,
-		    int write_fault, int level,
+		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
@@ -2378,20 +2356,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 	spte |= (u64)pfn << PAGE_SHIFT;
 
-	if ((pte_access & ACC_WRITE_MASK)
-	    || (!vcpu->arch.mmu.direct_map && write_fault
-		&& !is_write_protection(vcpu) && !user_fault)) {
+	if (pte_access & ACC_WRITE_MASK) {
 
 		/*
-		 * There are two cases:
-		 * - the one is other vcpu creates new sp in the window
-		 *   between mapping_level() and acquiring mmu-lock.
-		 * - the another case is the new sp is created by itself
-		 *   (page-fault path) when guest uses the target gfn as
-		 *   its page table.
-		 * Both of these cases can be fixed by allowing guest to
-		 * retry the access, it will refault, then we can establish
-		 * the mapping by using small page.
+		 * Other vcpu creates new sp in the window between
+		 * mapping_level() and acquiring mmu-lock. We can
+		 * allow guest to retry the access, the mapping can
+		 * be fixed if guest refault.
 		 */
 		if (level > PT_PAGE_TABLE_LEVEL &&
 		    has_wrprotected_page(vcpu->kvm, gfn, level))
@@ -2399,19 +2370,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
 
-		if (!vcpu->arch.mmu.direct_map
-		    && !(pte_access & ACC_WRITE_MASK)) {
-			spte &= ~PT_USER_MASK;
-			/*
-			 * If we converted a user page to a kernel page,
-			 * so that the kernel can write to it when cr0.wp=0,
-			 * then we should prevent the kernel from executing it
-			 * if SMEP is enabled.
-			 */
-			if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-				spte |= PT64_NX_MASK;
-		}
-
 		/*
 		 * Optimization: for pte sync, if spte was writable the hash
 		 * lookup is unnecessary (and expensive). Write protection
@@ -2441,19 +2399,15 @@ done:
 }
 
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-			 unsigned pt_access, unsigned pte_access,
-			 int user_fault, int write_fault,
-			 int *emulate, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative,
+			 unsigned pte_access, int write_fault, int *emulate,
+			 int level, gfn_t gfn, pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
 	int was_rmapped = 0;
 	int rmap_count;
 
-	pgprintk("%s: spte %llx access %x write_fault %d"
-		 " user_fault %d gfn %llx\n",
-		 __func__, *sptep, pt_access,
-		 write_fault, user_fault, gfn);
+	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
+		 *sptep, write_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
 		/*
@@ -2477,9 +2431,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			was_rmapped = 1;
 	}
 
-	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
-		      level, gfn, pfn, speculative, true,
-		      host_writable)) {
+	if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
+	      true, host_writable)) {
 		if (write_fault)
 			*emulate = 1;
 		kvm_mmu_flush_tlb(vcpu);
@@ -2497,7 +2450,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		++vcpu->kvm->stat.lpages;
 
 	if (is_shadow_present_pte(*sptep)) {
-		page_header_update_slot(vcpu->kvm, sptep, gfn);
 		if (!was_rmapped) {
 			rmap_count = rmap_add(vcpu, sptep, gfn);
 			if (rmap_count > RMAP_RECYCLE_THRESHOLD)
@@ -2571,10 +2523,9 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 		return -1;
 
 	for (i = 0; i < ret; i++, gfn++, start++)
-		mmu_set_spte(vcpu, start, ACC_ALL,
-			     access, 0, 0, NULL,
-			     sp->role.level, gfn,
-			     page_to_pfn(pages[i]), true, true);
+		mmu_set_spte(vcpu, start, access, 0, NULL,
+			     sp->role.level, gfn, page_to_pfn(pages[i]),
+			     true, true);
 
 	return 0;
 }
@@ -2633,11 +2584,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 
 	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
 		if (iterator.level == level) {
-			unsigned pte_access = ACC_ALL;
-
-			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
-				     0, write, &emulate,
-				     level, gfn, pfn, prefault, map_writable);
+			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
+				     write, &emulate, level, gfn, pfn,
+				     prefault, map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
 			++vcpu->stat.pf_fixed;
 			break;
@@ -2652,11 +2601,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
 
-			mmu_spte_set(iterator.sptep,
-				     __pa(sp->spt)
-				     | PT_PRESENT_MASK | PT_WRITABLE_MASK
-				     | shadow_user_mask | shadow_x_mask
-				     | shadow_accessed_mask);
+			link_shadow_page(iterator.sptep, sp);
 		}
 	}
 	return emulate;
@@ -3719,6 +3664,7 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	else
 		r = paging32_init_context(vcpu, context);
 
+	vcpu->arch.mmu.base_role.nxe = is_nx(vcpu);
 	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
 	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
 	vcpu->arch.mmu.base_role.smep_andnot_wp
@@ -3885,7 +3831,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
 		*gpa &= ~(gpa_t)7;
 		*bytes = 8;
-		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8));
+		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8);
 		if (r)
 			gentry = 0;
 		new = (const u8 *)&gentry;
@@ -4039,7 +3985,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			      !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
 			      & mask.word) && rmap_can_add(vcpu))
 				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
-			if (!remote_flush && need_remote_flush(entry, *spte))
+			if (need_remote_flush(entry, *spte))
 				remote_flush = true;
 			++spte;
 		}
@@ -4198,26 +4144,36 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu)
 
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 {
-	struct kvm_mmu_page *sp;
-	bool flush = false;
+	struct kvm_memory_slot *memslot;
+	gfn_t last_gfn;
+	int i;
 
-	list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) {
-		int i;
-		u64 *pt;
+	memslot = id_to_memslot(kvm->memslots, slot);
+	last_gfn = memslot->base_gfn + memslot->npages - 1;
 
-		if (!test_bit(slot, sp->slot_bitmap))
-			continue;
+	spin_lock(&kvm->mmu_lock);
 
-		pt = sp->spt;
-		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
-			if (!is_shadow_present_pte(pt[i]) ||
-			      !is_last_spte(pt[i], sp->role.level))
-				continue;
+	for (i = PT_PAGE_TABLE_LEVEL;
+	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+		unsigned long *rmapp;
+		unsigned long last_index, index;
 
-			spte_write_protect(kvm, &pt[i], &flush, false);
+		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
+		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
+
+		for (index = 0; index <= last_index; ++index, ++rmapp) {
+			if (*rmapp)
+				__rmap_write_protect(kvm, rmapp, false);
+
+			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+				kvm_flush_remote_tlbs(kvm);
+				cond_resched_lock(&kvm->mmu_lock);
+			}
 		}
 	}
+
 	kvm_flush_remote_tlbs(kvm);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_mmu_zap_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index cd6e98333ba3..b8f6172f4174 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -195,12 +195,6 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page,
 	TP_ARGS(sp)
 );
 
-DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_delay_free_pages,
-	TP_PROTO(struct kvm_mmu_page *sp),
-
-	TP_ARGS(sp)
-);
-
 TRACE_EVENT(
 	mark_mmio_spte,
 	TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access),
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 891eb6d93b8b..105dd5bd550e 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -151,7 +151,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, pte_access, accessed_dirty, shift;
+	unsigned index, pt_access, pte_access, accessed_dirty;
 	gpa_t pte_gpa;
 	int offset;
 	const int write_fault = access & PFERR_WRITE_MASK;
@@ -249,16 +249,12 @@ retry_walk:
 
 	if (!write_fault)
 		protect_clean_gpte(&pte_access, pte);
-
-	/*
-	 * On a write fault, fold the dirty bit into accessed_dirty by shifting it one
-	 * place right.
-	 *
-	 * On a read fault, do nothing.
-	 */
-	shift = write_fault >> ilog2(PFERR_WRITE_MASK);
-	shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT;
-	accessed_dirty &= pte >> shift;
+	else
+		/*
+		 * On a write fault, fold the dirty bit into accessed_dirty by
+		 * shifting it one place right.
+		 */
+		accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
 		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -330,8 +326,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
+	mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL,
+		     gfn, pfn, true, true);
 
 	return true;
 }
@@ -405,7 +401,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  */
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
-			 int user_fault, int write_fault, int hlevel,
+			 int write_fault, int hlevel,
 			 pfn_t pfn, bool map_writable, bool prefault)
 {
 	struct kvm_mmu_page *sp = NULL;
@@ -413,9 +409,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	unsigned direct_access, access = gw->pt_access;
 	int top_level, emulate = 0;
 
-	if (!is_present_gpte(gw->ptes[gw->level - 1]))
-		return 0;
-
 	direct_access = gw->pte_access;
 
 	top_level = vcpu->arch.mmu.root_level;
@@ -477,9 +470,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
-	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
-		     user_fault, write_fault, &emulate, it.level,
-		     gw->gfn, pfn, prefault, map_writable);
+	mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate,
+		     it.level, gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
 	return emulate;
@@ -491,6 +483,46 @@ out_gpte_changed:
 	return 0;
 }
 
+ /*
+ * To see whether the mapped gfn can write its page table in the current
+ * mapping.
+ *
+ * It is the helper function of FNAME(page_fault). When guest uses large page
+ * size to map the writable gfn which is used as current page table, we should
+ * force kvm to use small page size to map it because new shadow page will be
+ * created when kvm establishes shadow page table that stop kvm using large
+ * page size. Do it early can avoid unnecessary #PF and emulation.
+ *
+ * @write_fault_to_shadow_pgtable will return true if the fault gfn is
+ * currently used as its page table.
+ *
+ * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok
+ * since the PDPT is always shadowed, that means, we can not use large page
+ * size to map the gfn which is used as PDPT.
+ */
+static bool
+FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
+			      struct guest_walker *walker, int user_fault,
+			      bool *write_fault_to_shadow_pgtable)
+{
+	int level;
+	gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1);
+	bool self_changed = false;
+
+	if (!(walker->pte_access & ACC_WRITE_MASK ||
+	      (!is_write_protection(vcpu) && !user_fault)))
+		return false;
+
+	for (level = walker->level; level <= walker->max_level; level++) {
+		gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1];
+
+		self_changed |= !(gfn & mask);
+		*write_fault_to_shadow_pgtable |= !gfn;
+	}
+
+	return self_changed;
+}
+
 /*
  * Page fault handler.  There are several causes for a page fault:
  *   - there is no shadow pte for the guest pte
@@ -516,7 +548,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int level = PT_PAGE_TABLE_LEVEL;
 	int force_pt_level;
 	unsigned long mmu_seq;
-	bool map_writable;
+	bool map_writable, is_self_change_mapping;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -544,8 +576,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 	}
 
+	vcpu->arch.write_fault_to_shadow_pgtable = false;
+
+	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
+	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
+
 	if (walker.level >= PT_DIRECTORY_LEVEL)
-		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn);
+		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn)
+		   || is_self_change_mapping;
 	else
 		force_pt_level = 1;
 	if (!force_pt_level) {
@@ -564,6 +602,26 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 				walker.gfn, pfn, walker.pte_access, &r))
 		return r;
 
+	/*
+	 * Do not change pte_access if the pfn is a mmio page, otherwise
+	 * we will cache the incorrect access into mmio spte.
+	 */
+	if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) &&
+	     !is_write_protection(vcpu) && !user_fault &&
+	      !is_noslot_pfn(pfn)) {
+		walker.pte_access |= ACC_WRITE_MASK;
+		walker.pte_access &= ~ACC_USER_MASK;
+
+		/*
+		 * If we converted a user page to a kernel page,
+		 * so that the kernel can write to it when cr0.wp=0,
+		 * then we should prevent the kernel from executing it
+		 * if SMEP is enabled.
+		 */
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
+			walker.pte_access &= ~ACC_EXEC_MASK;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
@@ -572,7 +630,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_free_some_pages(vcpu);
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
-	r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
 			 level, pfn, map_writable, prefault);
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
@@ -747,7 +805,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
 
-		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
+		set_spte(vcpu, &sp->spt[i], pte_access,
 			 PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false,
 			 host_writable);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d29d3cd1c156..e1b1ce21bc00 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3571,6 +3571,26 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
 }
 
+static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+{
+	return;
+}
+
+static int svm_vm_has_apicv(struct kvm *kvm)
+{
+	return 0;
+}
+
+static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	return;
+}
+
+static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
+{
+	return;
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4290,6 +4310,10 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
+	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
+	.vm_has_apicv = svm_vm_has_apicv,
+	.load_eoi_exitmap = svm_load_eoi_exitmap,
+	.hwapic_isr_update = svm_hwapic_isr_update,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9120ae1901e4..6667042714cc 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -84,6 +84,8 @@ module_param(vmm_exclusive, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
+static bool __read_mostly enable_apicv_reg_vid;
+
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
  * VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -92,12 +94,8 @@ module_param(fasteoi, bool, S_IRUGO);
 static bool __read_mostly nested = 0;
 module_param(nested, bool, S_IRUGO);
 
-#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
-#define KVM_GUEST_CR0_MASK						\
-	(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE)
+#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
 #define KVM_VM_CR0_ALWAYS_ON						\
 	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
 #define KVM_CR4_GUEST_OWNED_BITS				      \
@@ -624,6 +622,8 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 static void vmx_get_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
+static bool guest_state_valid(struct kvm_vcpu *vcpu);
+static u32 vmx_segment_access_rights(struct kvm_segment *var);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -638,6 +638,8 @@ static unsigned long *vmx_io_bitmap_a;
 static unsigned long *vmx_io_bitmap_b;
 static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
+static unsigned long *vmx_msr_bitmap_legacy_x2apic;
+static unsigned long *vmx_msr_bitmap_longmode_x2apic;
 
 static bool cpu_has_load_ia32_efer;
 static bool cpu_has_load_perf_global_ctrl;
@@ -762,6 +764,24 @@ static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
 }
 
+static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+}
+
+static inline bool cpu_has_vmx_apic_register_virt(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_APIC_REGISTER_VIRT;
+}
+
+static inline bool cpu_has_vmx_virtual_intr_delivery(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
+}
+
 static inline bool cpu_has_vmx_flexpriority(void)
 {
 	return cpu_has_vmx_tpr_shadow() &&
@@ -1694,7 +1714,6 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
 	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 	to_vmx(vcpu)->rflags = rflags;
 	if (to_vmx(vcpu)->rmode.vm86_active) {
 		to_vmx(vcpu)->rmode.save_rflags = rflags;
@@ -1820,6 +1839,25 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 	vmx->guest_msrs[from] = tmp;
 }
 
+static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
+{
+	unsigned long *msr_bitmap;
+
+	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+		if (is_long_mode(vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
+	} else {
+		if (is_long_mode(vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy;
+	}
+
+	vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
+}
+
 /*
  * Set up the vmcs to automatically save and restore system
  * msrs.  Don't touch the 64-bit msrs if the guest is in legacy
@@ -1828,7 +1866,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
 	int save_nmsrs, index;
-	unsigned long *msr_bitmap;
 
 	save_nmsrs = 0;
 #ifdef CONFIG_X86_64
@@ -1860,14 +1897,8 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 
 	vmx->save_nmsrs = save_nmsrs;
 
-	if (cpu_has_vmx_msr_bitmap()) {
-		if (is_long_mode(&vmx->vcpu))
-			msr_bitmap = vmx_msr_bitmap_longmode;
-		else
-			msr_bitmap = vmx_msr_bitmap_legacy;
-
-		vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-	}
+	if (cpu_has_vmx_msr_bitmap())
+		vmx_set_msr_bitmap(&vmx->vcpu);
 }
 
 /*
@@ -2533,13 +2564,16 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
 		min2 = 0;
 		opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+			SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 			SECONDARY_EXEC_WBINVD_EXITING |
 			SECONDARY_EXEC_ENABLE_VPID |
 			SECONDARY_EXEC_ENABLE_EPT |
 			SECONDARY_EXEC_UNRESTRICTED_GUEST |
 			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
 			SECONDARY_EXEC_RDTSCP |
-			SECONDARY_EXEC_ENABLE_INVPCID;
+			SECONDARY_EXEC_ENABLE_INVPCID |
+			SECONDARY_EXEC_APIC_REGISTER_VIRT |
+			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
 		if (adjust_vmx_controls(min2, opt2,
 					MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
@@ -2550,6 +2584,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
 		_cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
 #endif
+
+	if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
+		_cpu_based_2nd_exec_control &= ~(
+				SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
+				SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+
 	if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
 		/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
 		   enabled */
@@ -2747,6 +2788,15 @@ static __init int hardware_setup(void)
 	if (!cpu_has_vmx_ple())
 		ple_gap = 0;
 
+	if (!cpu_has_vmx_apic_register_virt() ||
+				!cpu_has_vmx_virtual_intr_delivery())
+		enable_apicv_reg_vid = 0;
+
+	if (enable_apicv_reg_vid)
+		kvm_x86_ops->update_cr8_intercept = NULL;
+	else
+		kvm_x86_ops->hwapic_irr_update = NULL;
+
 	if (nested)
 		nested_vmx_setup_ctls_msrs();
 
@@ -2758,18 +2808,28 @@ static __exit void hardware_unsetup(void)
 	free_kvm_area();
 }
 
-static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save)
+static bool emulation_required(struct kvm_vcpu *vcpu)
 {
-	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-	struct kvm_segment tmp = *save;
+	return emulate_invalid_guest_state && !guest_state_valid(vcpu);
+}
 
-	if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) {
-		tmp.base = vmcs_readl(sf->base);
-		tmp.selector = vmcs_read16(sf->selector);
-		tmp.dpl = tmp.selector & SELECTOR_RPL_MASK;
-		tmp.s = 1;
+static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
+		struct kvm_segment *save)
+{
+	if (!emulate_invalid_guest_state) {
+		/*
+		 * CS and SS RPL should be equal during guest entry according
+		 * to VMX spec, but in reality it is not always so. Since vcpu
+		 * is in the middle of the transition from real mode to
+		 * protected mode it is safe to assume that RPL 0 is a good
+		 * default value.
+		 */
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
+			save->selector &= ~SELECTOR_RPL_MASK;
+		save->dpl = save->selector & SELECTOR_RPL_MASK;
+		save->s = 1;
 	}
-	vmx_set_segment(vcpu, &tmp, seg);
+	vmx_set_segment(vcpu, save, seg);
 }
 
 static void enter_pmode(struct kvm_vcpu *vcpu)
@@ -2777,7 +2837,17 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	unsigned long flags;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	vmx->emulation_required = 1;
+	/*
+	 * Update real mode segment cache. It may be not up-to-date if sement
+	 * register was written while vcpu was in a guest mode.
+	 */
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
+
 	vmx->rmode.vm86_active = 0;
 
 	vmx_segment_cache_clear(vmx);
@@ -2794,22 +2864,16 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 
 	update_exception_bitmap(vcpu);
 
-	if (emulate_invalid_guest_state)
-		return;
-
-	fix_pmode_dataseg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
-	fix_pmode_dataseg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
-	fix_pmode_dataseg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
-	fix_pmode_dataseg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-
-	vmx_segment_cache_clear(vmx);
+	fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
+	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
 
-	vmcs_write16(GUEST_SS_SELECTOR, 0);
-	vmcs_write32(GUEST_SS_AR_BYTES, 0x93);
-
-	vmcs_write16(GUEST_CS_SELECTOR,
-		     vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK);
-	vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);
+	/* CPL is always 0 when CPU enters protected mode */
+	__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+	vmx->cpl = 0;
 }
 
 static gva_t rmode_tss_base(struct kvm *kvm)
@@ -2831,36 +2895,51 @@ static gva_t rmode_tss_base(struct kvm *kvm)
 static void fix_rmode_seg(int seg, struct kvm_segment *save)
 {
 	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-
-	vmcs_write16(sf->selector, save->base >> 4);
-	vmcs_write32(sf->base, save->base & 0xffff0);
-	vmcs_write32(sf->limit, 0xffff);
-	vmcs_write32(sf->ar_bytes, 0xf3);
-	if (save->base & 0xf)
-		printk_once(KERN_WARNING "kvm: segment base is not paragraph"
-			    " aligned when entering protected mode (seg=%d)",
-			    seg);
+	struct kvm_segment var = *save;
+
+	var.dpl = 0x3;
+	if (seg == VCPU_SREG_CS)
+		var.type = 0x3;
+
+	if (!emulate_invalid_guest_state) {
+		var.selector = var.base >> 4;
+		var.base = var.base & 0xffff0;
+		var.limit = 0xffff;
+		var.g = 0;
+		var.db = 0;
+		var.present = 1;
+		var.s = 1;
+		var.l = 0;
+		var.unusable = 0;
+		var.type = 0x3;
+		var.avl = 0;
+		if (save->base & 0xf)
+			printk_once(KERN_WARNING "kvm: segment base is not "
+					"paragraph aligned when entering "
+					"protected mode (seg=%d)", seg);
+	}
+
+	vmcs_write16(sf->selector, var.selector);
+	vmcs_write32(sf->base, var.base);
+	vmcs_write32(sf->limit, var.limit);
+	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
 }
 
 static void enter_rmode(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_segment var;
-
-	if (enable_unrestricted_guest)
-		return;
 
 	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
 	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
 	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
 	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
 	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS);
 
-	vmx->emulation_required = 1;
 	vmx->rmode.vm86_active = 1;
 
-
 	/*
 	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
 	 * vcpu. Call it here with phys address pointing 16M below 4G.
@@ -2888,28 +2967,13 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
 	update_exception_bitmap(vcpu);
 
-	if (emulate_invalid_guest_state)
-		goto continue_rmode;
-
-	vmx_get_segment(vcpu, &var, VCPU_SREG_SS);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_SS);
-
-	vmx_get_segment(vcpu, &var, VCPU_SREG_CS);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_CS);
-
-	vmx_get_segment(vcpu, &var, VCPU_SREG_ES);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_ES);
-
-	vmx_get_segment(vcpu, &var, VCPU_SREG_DS);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_DS);
+	fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]);
+	fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]);
+	fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+	fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+	fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
+	fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
 
-	vmx_get_segment(vcpu, &var, VCPU_SREG_GS);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_GS);
-
-	vmx_get_segment(vcpu, &var, VCPU_SREG_FS);
-	vmx_set_segment(vcpu, &var, VCPU_SREG_FS);
-
-continue_rmode:
 	kvm_mmu_reset_context(vcpu);
 }
 
@@ -3068,17 +3132,18 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long hw_cr0;
 
+	hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
 	if (enable_unrestricted_guest)
-		hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST)
-			| KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
-	else
-		hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
+	else {
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;
 
-	if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
-		enter_pmode(vcpu);
+		if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
+			enter_pmode(vcpu);
 
-	if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
-		enter_rmode(vcpu);
+		if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
+			enter_rmode(vcpu);
+	}
 
 #ifdef CONFIG_X86_64
 	if (vcpu->arch.efer & EFER_LME) {
@@ -3098,7 +3163,9 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	vmcs_writel(CR0_READ_SHADOW, cr0);
 	vmcs_writel(GUEST_CR0, hw_cr0);
 	vcpu->arch.cr0 = cr0;
-	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+
+	/* depends on vcpu->arch.cr0 to be set to a new value */
+	vmx->emulation_required = emulation_required(vcpu);
 }
 
 static u64 construct_eptp(unsigned long root_hpa)
@@ -3155,6 +3222,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		if (!is_paging(vcpu)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 			hw_cr4 |= X86_CR4_PSE;
+			/*
+			 * SMEP is disabled if CPU is in non-paging mode in
+			 * hardware. However KVM always uses paging mode to
+			 * emulate guest non-paging mode with TDP.
+			 * To emulate this behavior, SMEP needs to be manually
+			 * disabled when guest switches to non-paging mode.
+			 */
+			hw_cr4 &= ~X86_CR4_SMEP;
 		} else if (!(cr4 & X86_CR4_PAE)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 		}
@@ -3171,10 +3246,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 ar;
 
-	if (vmx->rmode.vm86_active
-	    && (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES
-		|| seg == VCPU_SREG_DS || seg == VCPU_SREG_FS
-		|| seg == VCPU_SREG_GS)) {
+	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
 		*var = vmx->rmode.segs[seg];
 		if (seg == VCPU_SREG_TR
 		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
@@ -3187,8 +3259,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	var->limit = vmx_read_guest_seg_limit(vmx, seg);
 	var->selector = vmx_read_guest_seg_selector(vmx, seg);
 	ar = vmx_read_guest_seg_ar(vmx, seg);
-	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
-		ar = 0;
 	var->type = ar & 15;
 	var->s = (ar >> 4) & 1;
 	var->dpl = (ar >> 5) & 3;
@@ -3211,8 +3281,10 @@ static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
 }
 
-static int __vmx_get_cpl(struct kvm_vcpu *vcpu)
+static int vmx_get_cpl(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
 	if (!is_protmode(vcpu))
 		return 0;
 
@@ -3220,24 +3292,9 @@ static int __vmx_get_cpl(struct kvm_vcpu *vcpu)
 	    && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
 		return 3;
 
-	return vmx_read_guest_seg_selector(to_vmx(vcpu), VCPU_SREG_CS) & 3;
-}
-
-static int vmx_get_cpl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	/*
-	 * If we enter real mode with cs.sel & 3 != 0, the normal CPL calculations
-	 * fail; use the cache instead.
-	 */
-	if (unlikely(vmx->emulation_required && emulate_invalid_guest_state)) {
-		return vmx->cpl;
-	}
-
 	if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
 		__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-		vmx->cpl = __vmx_get_cpl(vcpu);
+		vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3;
 	}
 
 	return vmx->cpl;
@@ -3269,28 +3326,23 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
-	u32 ar;
 
 	vmx_segment_cache_clear(vmx);
+	if (seg == VCPU_SREG_CS)
+		__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 
-	if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
-		vmcs_write16(sf->selector, var->selector);
-		vmx->rmode.segs[VCPU_SREG_TR] = *var;
-		return;
+	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
+		vmx->rmode.segs[seg] = *var;
+		if (seg == VCPU_SREG_TR)
+			vmcs_write16(sf->selector, var->selector);
+		else if (var->s)
+			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
+		goto out;
 	}
+
 	vmcs_writel(sf->base, var->base);
 	vmcs_write32(sf->limit, var->limit);
 	vmcs_write16(sf->selector, var->selector);
-	if (vmx->rmode.vm86_active && var->s) {
-		vmx->rmode.segs[seg] = *var;
-		/*
-		 * Hack real-mode segments into vm86 compatibility.
-		 */
-		if (var->base == 0xffff0000 && var->selector == 0xf000)
-			vmcs_writel(sf->base, 0xf0000);
-		ar = 0xf3;
-	} else
-		ar = vmx_segment_access_rights(var);
 
 	/*
 	 *   Fix the "Accessed" bit in AR field of segment registers for older
@@ -3304,42 +3356,12 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	 * kvm hack.
 	 */
 	if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
-		ar |= 0x1; /* Accessed */
+		var->type |= 0x1; /* Accessed */
 
-	vmcs_write32(sf->ar_bytes, ar);
-	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
 
-	/*
-	 * Fix segments for real mode guest in hosts that don't have
-	 * "unrestricted_mode" or it was disabled.
-	 * This is done to allow migration of the guests from hosts with
-	 * unrestricted guest like Westmere to older host that don't have
-	 * unrestricted guest like Nehelem.
-	 */
-	if (vmx->rmode.vm86_active) {
-		switch (seg) {
-		case VCPU_SREG_CS:
-			vmcs_write32(GUEST_CS_AR_BYTES, 0xf3);
-			vmcs_write32(GUEST_CS_LIMIT, 0xffff);
-			if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000)
-				vmcs_writel(GUEST_CS_BASE, 0xf0000);
-			vmcs_write16(GUEST_CS_SELECTOR,
-				     vmcs_readl(GUEST_CS_BASE) >> 4);
-			break;
-		case VCPU_SREG_ES:
-		case VCPU_SREG_DS:
-		case VCPU_SREG_GS:
-		case VCPU_SREG_FS:
-			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
-			break;
-		case VCPU_SREG_SS:
-			vmcs_write16(GUEST_SS_SELECTOR,
-				     vmcs_readl(GUEST_SS_BASE) >> 4);
-			vmcs_write32(GUEST_SS_LIMIT, 0xffff);
-			vmcs_write32(GUEST_SS_AR_BYTES, 0xf3);
-			break;
-		}
-	}
+out:
+	vmx->emulation_required |= emulation_required(vcpu);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -3380,13 +3402,16 @@ static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
 	u32 ar;
 
 	vmx_get_segment(vcpu, &var, seg);
+	var.dpl = 0x3;
+	if (seg == VCPU_SREG_CS)
+		var.type = 0x3;
 	ar = vmx_segment_access_rights(&var);
 
 	if (var.base != (var.selector << 4))
 		return false;
-	if (var.limit < 0xffff)
+	if (var.limit != 0xffff)
 		return false;
-	if (((ar | (3 << AR_DPL_SHIFT)) & ~(AR_G_MASK | AR_DB_MASK)) != 0xf3)
+	if (ar != 0xf3)
 		return false;
 
 	return true;
@@ -3521,6 +3546,9 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
  */
 static bool guest_state_valid(struct kvm_vcpu *vcpu)
 {
+	if (enable_unrestricted_guest)
+		return true;
+
 	/* real mode guest state checks */
 	if (!is_protmode(vcpu)) {
 		if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
@@ -3644,12 +3672,9 @@ static void seg_setup(int seg)
 	vmcs_write16(sf->selector, 0);
 	vmcs_writel(sf->base, 0);
 	vmcs_write32(sf->limit, 0xffff);
-	if (enable_unrestricted_guest) {
-		ar = 0x93;
-		if (seg == VCPU_SREG_CS)
-			ar |= 0x08; /* code segment */
-	} else
-		ar = 0xf3;
+	ar = 0x93;
+	if (seg == VCPU_SREG_CS)
+		ar |= 0x08; /* code segment */
 
 	vmcs_write32(sf->ar_bytes, ar);
 }
@@ -3667,7 +3692,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	kvm_userspace_mem.flags = 0;
 	kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
 	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
+	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false);
 	if (r)
 		goto out;
 
@@ -3697,7 +3722,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	kvm_userspace_mem.guest_phys_addr =
 		kvm->arch.ept_identity_map_addr;
 	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
+	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false);
 	if (r)
 		goto out;
 
@@ -3739,7 +3764,10 @@ static void free_vpid(struct vcpu_vmx *vmx)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
+#define MSR_TYPE_R	1
+#define MSR_TYPE_W	2
+static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+						u32 msr, int type)
 {
 	int f = sizeof(unsigned long);
 
@@ -3752,20 +3780,93 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
 	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
 	 */
 	if (msr <= 0x1fff) {
-		__clear_bit(msr, msr_bitmap + 0x000 / f); /* read-low */
-		__clear_bit(msr, msr_bitmap + 0x800 / f); /* write-low */
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__clear_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__clear_bit(msr, msr_bitmap + 0x800 / f);
+
 	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
 		msr &= 0x1fff;
-		__clear_bit(msr, msr_bitmap + 0x400 / f); /* read-high */
-		__clear_bit(msr, msr_bitmap + 0xc00 / f); /* write-high */
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__clear_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__clear_bit(msr, msr_bitmap + 0xc00 / f);
+
+	}
+}
+
+static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+						u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R)
+			/* read-low */
+			__set_bit(msr, msr_bitmap + 0x000 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-low */
+			__set_bit(msr, msr_bitmap + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R)
+			/* read-high */
+			__set_bit(msr, msr_bitmap + 0x400 / f);
+
+		if (type & MSR_TYPE_W)
+			/* write-high */
+			__set_bit(msr, msr_bitmap + 0xc00 / f);
+
 	}
 }
 
 static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
 {
 	if (!longmode_only)
-		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr);
-	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr);
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
+						msr, MSR_TYPE_R | MSR_TYPE_W);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
+						msr, MSR_TYPE_R | MSR_TYPE_W);
+}
+
+static void vmx_enable_intercept_msr_read_x2apic(u32 msr)
+{
+	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_R);
+	__vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_R);
+}
+
+static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+{
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_R);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_R);
+}
+
+static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+{
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
+			msr, MSR_TYPE_W);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
+			msr, MSR_TYPE_W);
 }
 
 /*
@@ -3844,6 +3945,11 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	return exec_control;
 }
 
+static int vmx_vm_has_apicv(struct kvm *kvm)
+{
+	return enable_apicv_reg_vid && irqchip_in_kernel(kvm);
+}
+
 static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 {
 	u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
@@ -3861,6 +3967,10 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 		exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
 	if (!ple_gap)
 		exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+	if (!vmx_vm_has_apicv(vmx->vcpu.kvm))
+		exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+	exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 	return exec_control;
 }
 
@@ -3905,6 +4015,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 				vmx_secondary_exec_control(vmx));
 	}
 
+	if (enable_apicv_reg_vid) {
+		vmcs_write64(EOI_EXIT_BITMAP0, 0);
+		vmcs_write64(EOI_EXIT_BITMAP1, 0);
+		vmcs_write64(EOI_EXIT_BITMAP2, 0);
+		vmcs_write64(EOI_EXIT_BITMAP3, 0);
+
+		vmcs_write16(GUEST_INTR_STATUS, 0);
+	}
+
 	if (ple_gap) {
 		vmcs_write32(PLE_GAP, ple_gap);
 		vmcs_write32(PLE_WINDOW, ple_window);
@@ -3990,14 +4109,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmx_segment_cache_clear(vmx);
 
 	seg_setup(VCPU_SREG_CS);
-	/*
-	 * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
-	 * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4.  Sigh.
-	 */
-	if (kvm_vcpu_is_bsp(&vmx->vcpu)) {
+	if (kvm_vcpu_is_bsp(&vmx->vcpu))
 		vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
-		vmcs_writel(GUEST_CS_BASE, 0x000f0000);
-	} else {
+	else {
 		vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8);
 		vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12);
 	}
@@ -4073,9 +4187,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	ret = 0;
 
-	/* HACK: Don't enable emulation on guest boot/reset */
-	vmx->emulation_required = 0;
-
 	return ret;
 }
 
@@ -4251,7 +4362,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 		.flags = 0,
 	};
 
-	ret = kvm_set_memory_region(kvm, &tss_mem, 0);
+	ret = kvm_set_memory_region(kvm, &tss_mem, false);
 	if (ret)
 		return ret;
 	kvm->arch.tss_addr = addr;
@@ -4261,28 +4372,9 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	return 0;
 }
 
-static int handle_rmode_exception(struct kvm_vcpu *vcpu,
-				  int vec, u32 err_code)
+static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
 {
-	/*
-	 * Instruction with address size override prefix opcode 0x67
-	 * Cause the #SS fault with 0 error code in VM86 mode.
-	 */
-	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0)
-		if (emulate_instruction(vcpu, 0) == EMULATE_DONE)
-			return 1;
-	/*
-	 * Forward all other exceptions that are valid in real mode.
-	 * FIXME: Breaks guest debugging in real mode, needs to be fixed with
-	 *        the required debugging infrastructure rework.
-	 */
 	switch (vec) {
-	case DB_VECTOR:
-		if (vcpu->guest_debug &
-		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
-			return 0;
-		kvm_queue_exception(vcpu, vec);
-		return 1;
 	case BP_VECTOR:
 		/*
 		 * Update instruction length as we may reinject the exception
@@ -4291,7 +4383,12 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 		to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
 			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
-			return 0;
+			return false;
+		/* fall through */
+	case DB_VECTOR:
+		if (vcpu->guest_debug &
+			(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return false;
 		/* fall through */
 	case DE_VECTOR:
 	case OF_VECTOR:
@@ -4301,10 +4398,37 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	case SS_VECTOR:
 	case GP_VECTOR:
 	case MF_VECTOR:
-		kvm_queue_exception(vcpu, vec);
-		return 1;
+		return true;
+	break;
 	}
-	return 0;
+	return false;
+}
+
+static int handle_rmode_exception(struct kvm_vcpu *vcpu,
+				  int vec, u32 err_code)
+{
+	/*
+	 * Instruction with address size override prefix opcode 0x67
+	 * Cause the #SS fault with 0 error code in VM86 mode.
+	 */
+	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
+		if (emulate_instruction(vcpu, 0) == EMULATE_DONE) {
+			if (vcpu->arch.halt_request) {
+				vcpu->arch.halt_request = 0;
+				return kvm_emulate_halt(vcpu);
+			}
+			return 1;
+		}
+		return 0;
+	}
+
+	/*
+	 * Forward all other exceptions that are valid in real mode.
+	 * FIXME: Breaks guest debugging in real mode, needs to be fixed with
+	 *        the required debugging infrastructure rework.
+	 */
+	kvm_queue_exception(vcpu, vec);
+	return 1;
 }
 
 /*
@@ -4392,17 +4516,11 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
 	}
 
-	if (vmx->rmode.vm86_active &&
-	    handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK,
-								error_code)) {
-		if (vcpu->arch.halt_request) {
-			vcpu->arch.halt_request = 0;
-			return kvm_emulate_halt(vcpu);
-		}
-		return 1;
-	}
-
 	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+
+	if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no))
+		return handle_rmode_exception(vcpu, ex_no, error_code);
+
 	switch (ex_no) {
 	case DB_VECTOR:
 		dr6 = vmcs_readl(EXIT_QUALIFICATION);
@@ -4820,6 +4938,26 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
 	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }
 
+static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	int vector = exit_qualification & 0xff;
+
+	/* EOI-induced VM exit is trap-like and thus no need to adjust IP */
+	kvm_apic_set_eoi_accelerated(vcpu, vector);
+	return 1;
+}
+
+static int handle_apic_write(struct kvm_vcpu *vcpu)
+{
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	u32 offset = exit_qualification & 0xfff;
+
+	/* APIC-write VM exit is trap-like and thus no need to adjust IP */
+	kvm_apic_write_nodecode(vcpu, offset);
+	return 1;
+}
+
 static int handle_task_switch(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5065,7 +5203,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 			schedule();
 	}
 
-	vmx->emulation_required = !guest_state_valid(vcpu);
+	vmx->emulation_required = emulation_required(vcpu);
 out:
 	return ret;
 }
@@ -5754,6 +5892,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_VMON]                    = handle_vmon,
 	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
+	[EXIT_REASON_APIC_WRITE]              = handle_apic_write,
+	[EXIT_REASON_EOI_INDUCED]             = handle_apic_eoi_induced,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
 	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
 	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
@@ -5780,7 +5920,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
 	u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
 	gpa_t bitmap;
 
-	if (!nested_cpu_has(get_vmcs12(vcpu), CPU_BASED_USE_MSR_BITMAPS))
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
 		return 1;
 
 	/*
@@ -6008,7 +6148,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
 	/* If guest state is invalid, start emulating */
-	if (vmx->emulation_required && emulate_invalid_guest_state)
+	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
 	/*
@@ -6103,6 +6243,85 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	vmcs_write32(TPR_THRESHOLD, irr);
 }
 
+static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+{
+	u32 sec_exec_control;
+
+	/*
+	 * There is not point to enable virtualize x2apic without enable
+	 * apicv
+	 */
+	if (!cpu_has_vmx_virtualize_x2apic_mode() ||
+				!vmx_vm_has_apicv(vcpu->kvm))
+		return;
+
+	if (!vm_need_tpr_shadow(vcpu->kvm))
+		return;
+
+	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+	if (set) {
+		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+	} else {
+		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	}
+	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
+
+	vmx_set_msr_bitmap(vcpu);
+}
+
+static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
+{
+	u16 status;
+	u8 old;
+
+	if (!vmx_vm_has_apicv(kvm))
+		return;
+
+	if (isr == -1)
+		isr = 0;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = status >> 8;
+	if (isr != old) {
+		status &= 0xff;
+		status |= isr << 8;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_set_rvi(int vector)
+{
+	u16 status;
+	u8 old;
+
+	status = vmcs_read16(GUEST_INTR_STATUS);
+	old = (u8)status & 0xff;
+	if ((u8)vector != old) {
+		status &= ~0xff;
+		status |= (u8)vector;
+		vmcs_write16(GUEST_INTR_STATUS, status);
+	}
+}
+
+static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+{
+	if (max_irr == -1)
+		return;
+
+	vmx_set_rvi(max_irr);
+}
+
+static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]);
+	vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]);
+	vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]);
+	vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
+}
+
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -6291,7 +6510,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	/* Don't enter VMX if guest state is invalid, let the exit handler
 	   start emulation until we arrive back to a valid state */
-	if (vmx->emulation_required && emulate_invalid_guest_state)
+	if (vmx->emulation_required)
 		return;
 
 	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
@@ -7366,6 +7585,11 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
+	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+	.vm_has_apicv = vmx_vm_has_apicv,
+	.load_eoi_exitmap = vmx_load_eoi_exitmap,
+	.hwapic_irr_update = vmx_hwapic_irr_update,
+	.hwapic_isr_update = vmx_hwapic_isr_update,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
@@ -7398,7 +7622,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 static int __init vmx_init(void)
 {
-	int r, i;
+	int r, i, msr;
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
 
@@ -7419,11 +7643,19 @@ static int __init vmx_init(void)
 	if (!vmx_msr_bitmap_legacy)
 		goto out1;
 
+	vmx_msr_bitmap_legacy_x2apic =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_legacy_x2apic)
+		goto out2;
 
 	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_msr_bitmap_longmode)
-		goto out2;
+		goto out3;
 
+	vmx_msr_bitmap_longmode_x2apic =
+				(unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_longmode_x2apic)
+		goto out4;
 
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
@@ -7455,6 +7687,28 @@ static int __init vmx_init(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
+	memcpy(vmx_msr_bitmap_legacy_x2apic,
+			vmx_msr_bitmap_legacy, PAGE_SIZE);
+	memcpy(vmx_msr_bitmap_longmode_x2apic,
+			vmx_msr_bitmap_longmode, PAGE_SIZE);
+
+	if (enable_apicv_reg_vid) {
+		for (msr = 0x800; msr <= 0x8ff; msr++)
+			vmx_disable_intercept_msr_read_x2apic(msr);
+
+		/* According SDM, in x2apic mode, the whole id reg is used.
+		 * But in KVM, it only use the highest eight bits. Need to
+		 * intercept it */
+		vmx_enable_intercept_msr_read_x2apic(0x802);
+		/* TMCCT */
+		vmx_enable_intercept_msr_read_x2apic(0x839);
+		/* TPR */
+		vmx_disable_intercept_msr_write_x2apic(0x808);
+		/* EOI */
+		vmx_disable_intercept_msr_write_x2apic(0x80b);
+		/* SELF-IPI */
+		vmx_disable_intercept_msr_write_x2apic(0x83f);
+	}
 
 	if (enable_ept) {
 		kvm_mmu_set_mask_ptes(0ull,
@@ -7468,8 +7722,10 @@ static int __init vmx_init(void)
 
 	return 0;
 
-out3:
+out4:
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
+out3:
+	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
 out2:
 	free_page((unsigned long)vmx_msr_bitmap_legacy);
 out1:
@@ -7481,6 +7737,8 @@ out:
 
 static void __exit vmx_exit(void)
 {
+	free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+	free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
 	free_page((unsigned long)vmx_msr_bitmap_legacy);
 	free_page((unsigned long)vmx_msr_bitmap_longmode);
 	free_page((unsigned long)vmx_io_bitmap_b);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 37040079cd6b..f71500af1f81 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -872,8 +872,6 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 	kvm_x86_ops->set_efer(vcpu, efer);
 
-	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
-
 	/* Update reserved bits */
 	if ((efer ^ old_efer) & EFER_NX)
 		kvm_mmu_reset_context(vcpu);
@@ -2522,7 +2520,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_MEMORY_SLOTS;
+		r = KVM_USER_MEM_SLOTS;
 		break;
 	case KVM_CAP_PV_MMU:	/* obsolete */
 		r = 0;
@@ -3274,12 +3272,10 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 		return -EINVAL;
 
 	mutex_lock(&kvm->slots_lock);
-	spin_lock(&kvm->mmu_lock);
 
 	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
 	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
 
-	spin_unlock(&kvm->mmu_lock);
 	mutex_unlock(&kvm->slots_lock);
 	return 0;
 }
@@ -3439,7 +3435,7 @@ 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);
@@ -4495,8 +4491,10 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 	kvm_get_segment(emul_to_vcpu(ctxt), &var, seg);
 	*selector = var.selector;
 
-	if (var.unusable)
+	if (var.unusable) {
+		memset(desc, 0, sizeof(*desc));
 		return false;
+	}
 
 	if (var.g)
 		var.limit >>= 12;
@@ -4757,26 +4755,26 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 	return r;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+				  bool write_fault_to_shadow_pgtable)
 {
-	gpa_t gpa;
+	gpa_t gpa = cr2;
 	pfn_t pfn;
 
-	if (tdp_enabled)
-		return false;
-
-	/*
-	 * if emulation was due to access to shadowed page table
-	 * and it failed try to unshadow page and re-enter the
-	 * guest to let CPU execute the instruction.
-	 */
-	if (kvm_mmu_unprotect_page_virt(vcpu, gva))
-		return true;
-
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva, NULL);
+	if (!vcpu->arch.mmu.direct_map) {
+		/*
+		 * Write permission should be allowed since only
+		 * write access need to be emulated.
+		 */
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
 
-	if (gpa == UNMAPPED_GVA)
-		return true; /* let cpu generate fault */
+		/*
+		 * If the mapping is invalid in guest, let cpu retry
+		 * it to generate fault.
+		 */
+		if (gpa == UNMAPPED_GVA)
+			return true;
+	}
 
 	/*
 	 * Do not retry the unhandleable instruction if it faults on the
@@ -4785,12 +4783,43 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	 * instruction -> ...
 	 */
 	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
-	if (!is_error_noslot_pfn(pfn)) {
-		kvm_release_pfn_clean(pfn);
+
+	/*
+	 * If the instruction failed on the error pfn, it can not be fixed,
+	 * report the error to userspace.
+	 */
+	if (is_error_noslot_pfn(pfn))
+		return false;
+
+	kvm_release_pfn_clean(pfn);
+
+	/* The instructions are well-emulated on direct mmu. */
+	if (vcpu->arch.mmu.direct_map) {
+		unsigned int indirect_shadow_pages;
+
+		spin_lock(&vcpu->kvm->mmu_lock);
+		indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages;
+		spin_unlock(&vcpu->kvm->mmu_lock);
+
+		if (indirect_shadow_pages)
+			kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
+
 		return true;
 	}
 
-	return false;
+	/*
+	 * if emulation was due to access to shadowed page table
+	 * and it failed try to unshadow page and re-enter the
+	 * guest to let CPU execute the instruction.
+	 */
+	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
+
+	/*
+	 * If the access faults on its page table, it can not
+	 * be fixed by unprotecting shadow page and it should
+	 * be reported to userspace.
+	 */
+	return !write_fault_to_shadow_pgtable;
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
@@ -4832,7 +4861,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (!vcpu->arch.mmu.direct_map)
 		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
 
-	kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
 	return true;
 }
@@ -4849,7 +4878,13 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	bool writeback = true;
+	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	/*
+	 * Clear write_fault_to_shadow_pgtable here to ensure it is
+	 * never reused.
+	 */
+	vcpu->arch.write_fault_to_shadow_pgtable = false;
 	kvm_clear_exception_queue(vcpu);
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
@@ -4868,7 +4903,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		if (r != EMULATION_OK)  {
 			if (emulation_type & EMULTYPE_TRAP_UD)
 				return EMULATE_FAIL;
-			if (reexecute_instruction(vcpu, cr2))
+			if (reexecute_instruction(vcpu, cr2,
+						  write_fault_to_spt))
 				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
@@ -4898,7 +4934,7 @@ restart:
 		return EMULATE_DONE;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2))
+		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt))
 			return EMULATE_DONE;
 
 		return handle_emulation_failure(vcpu);
@@ -5541,7 +5577,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 			vcpu->arch.nmi_injected = true;
 			kvm_x86_ops->set_nmi(vcpu);
 		}
-	} else if (kvm_cpu_has_interrupt(vcpu)) {
+	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);
@@ -5609,6 +5645,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 #endif
 }
 
+static void update_eoi_exitmap(struct kvm_vcpu *vcpu)
+{
+	u64 eoi_exit_bitmap[4];
+
+	memset(eoi_exit_bitmap, 0, 32);
+
+	kvm_ioapic_calculate_eoi_exitmap(vcpu, eoi_exit_bitmap);
+	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -5662,6 +5708,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_handle_pmu_event(vcpu);
 		if (kvm_check_request(KVM_REQ_PMI, vcpu))
 			kvm_deliver_pmi(vcpu);
+		if (kvm_check_request(KVM_REQ_EOIBITMAP, vcpu))
+			update_eoi_exitmap(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -5670,10 +5718,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		/* enable NMI/IRQ window open exits if needed */
 		if (vcpu->arch.nmi_pending)
 			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
+		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
 			kvm_x86_ops->enable_irq_window(vcpu);
 
 		if (kvm_lapic_enabled(vcpu)) {
+			/*
+			 * Update architecture specific hints for APIC
+			 * virtual interrupt delivery.
+			 */
+			if (kvm_x86_ops->hwapic_irr_update)
+				kvm_x86_ops->hwapic_irr_update(vcpu,
+					kvm_lapic_find_highest_irr(vcpu));
 			update_cr8_intercept(vcpu);
 			kvm_lapic_sync_to_vapic(vcpu);
 		}
@@ -6853,48 +6908,43 @@ 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)
 {
 	int npages = memslot->npages;
-	int map_flags = MAP_PRIVATE | MAP_ANONYMOUS;
 
-	/* Prevent internal slot pages from being moved by fork()/COW. */
-	if (memslot->id >= KVM_MEMORY_SLOTS)
-		map_flags = MAP_SHARED | MAP_ANONYMOUS;
-
-	/*To keep backward compatibility with older userspace,
-	 *x86 needs to handle !user_alloc case.
+	/*
+	 * Only private memory slots need to be mapped here since
+	 * KVM_SET_MEMORY_REGION ioctl is no longer supported.
 	 */
-	if (!user_alloc) {
-		if (npages && !old.npages) {
-			unsigned long userspace_addr;
+	if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) {
+		unsigned long userspace_addr;
 
-			userspace_addr = vm_mmap(NULL, 0,
-						 npages * PAGE_SIZE,
-						 PROT_READ | PROT_WRITE,
-						 map_flags,
-						 0);
+		/*
+		 * MAP_SHARED to prevent internal slot pages from being moved
+		 * by fork()/COW.
+		 */
+		userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE,
+					 PROT_READ | PROT_WRITE,
+					 MAP_SHARED | MAP_ANONYMOUS, 0);
 
-			if (IS_ERR((void *)userspace_addr))
-				return PTR_ERR((void *)userspace_addr);
+		if (IS_ERR((void *)userspace_addr))
+			return PTR_ERR((void *)userspace_addr);
 
-			memslot->userspace_addr = userspace_addr;
-		}
+		memslot->userspace_addr = userspace_addr;
 	}
 
-
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
-				int user_alloc)
+				bool user_alloc)
 {
 
 	int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
 
-	if (!user_alloc && !old.user_alloc && old.npages && !npages) {
+	if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) {
 		int ret;
 
 		ret = vm_munmap(old.userspace_addr,
@@ -6908,11 +6958,15 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!kvm->arch.n_requested_mmu_pages)
 		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
 
-	spin_lock(&kvm->mmu_lock);
 	if (nr_mmu_pages)
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
-	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
-	spin_unlock(&kvm->mmu_lock);
+	/*
+	 * Write protect all pages for dirty logging.
+	 * Existing largepage mappings are destroyed here and new ones will
+	 * not be created until the end of the logging.
+	 */
+	if (npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
+		kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	/*
 	 * If memory slot is created, or moved, we need to clear all
 	 * mmio sptes.
author	Linus Torvalds <torvalds@linux-foundation.org>	2013-02-25 01:07:18 +0400
committer	Linus Torvalds <torvalds@linux-foundation.org>	2013-02-25 01:07:18 +0400
commit	89f883372fa60f604d136924baf3e89ff1870e9e (patch)
tree	cb69b0a14957945ba00d3d392bf9ccbbef56f3b8 /arch
parent	9e2d59ad580d590134285f361a0e80f0e98c0207 (diff)
parent	6b73a96065e89dc9fa75ba4f78b1aa3a3bbd0470 (diff)
download	linux-89f883372fa60f604d136924baf3e89ff1870e9e.tar.xz