Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Gleb Natapov:
 "The highlights of the release are nested EPT and pv-ticketlocks
  support (hypervisor part, guest part, which is most of the code, goes
  through tip tree).  Apart of that there are many fixes for all arches"

Fix up semantic conflicts as discussed in the pull request thread..

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (88 commits)
  ARM: KVM: Add newlines to panic strings
  ARM: KVM: Work around older compiler bug
  ARM: KVM: Simplify tracepoint text
  ARM: KVM: Fix kvm_set_pte assignment
  ARM: KVM: vgic: Bump VGIC_NR_IRQS to 256
  ARM: KVM: Bugfix: vgic_bytemap_get_reg per cpu regs
  ARM: KVM: vgic: fix GICD_ICFGRn access
  ARM: KVM: vgic: simplify vgic_get_target_reg
  KVM: MMU: remove unused parameter
  KVM: PPC: Book3S PR: Rework kvmppc_mmu_book3s_64_xlate()
  KVM: PPC: Book3S PR: Make instruction fetch fallback work for system calls
  KVM: PPC: Book3S PR: Don't corrupt guest state when kernel uses VMX
  KVM: x86: update masterclock when kvmclock_offset is calculated (v2)
  KVM: PPC: Book3S: Fix compile error in XICS emulation
  KVM: PPC: Book3S PR: return appropriate error when allocation fails
  arch: powerpc: kvm: add signed type cast for comparation
  KVM: x86: add comments where MMIO does not return to the emulator
  KVM: vmx: count exits to userspace during invalid guest emulation
  KVM: rename __kvm_io_bus_sort_cmp to kvm_io_bus_cmp
  kvm: optimize away THP checks in kvm_is_mmio_pfn()
  ...

14 files changed, 847 insertions, 328 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f87f7fcefa0a..c76ff74a98f2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -286,6 +286,7 @@ struct kvm_mmu {
 	u64 *pae_root;
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
+	u64 bad_mt_xwr;
 
 	/*
 	 * Bitmap: bit set = last pte in walk
@@ -323,6 +324,7 @@ struct kvm_pmu {
 	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
+	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
@@ -511,6 +513,14 @@ struct kvm_vcpu_arch {
 	 * instruction.
 	 */
 	bool write_fault_to_shadow_pgtable;
+
+	/* set at EPT violation at this point */
+	unsigned long exit_qualification;
+
+	/* pv related host specific info */
+	struct {
+		bool pv_unhalted;
+	} pv;
 };
 
 struct kvm_lpage_info {
@@ -802,8 +812,8 @@ extern u32  kvm_min_guest_tsc_khz;
 extern u32  kvm_max_guest_tsc_khz;
 
 enum emulation_result {
-	EMULATE_DONE,       /* no further processing */
-	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
+	EMULATE_DONE,         /* no further processing */
+	EMULATE_USER_EXIT,    /* kvm_run ready for userspace exit */
 	EMULATE_FAIL,         /* can't emulate this instruction */
 };
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 109a9dd5d454..be8269b00e2a 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -93,7 +93,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 
 struct pvclock_vsyscall_time_info {
 	struct pvclock_vcpu_time_info pvti;
-	u32 migrate_count;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f3e01a2cbaa1..966502d4682e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -387,6 +387,7 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
+#define VMX_EPT_EXTENT_SHIFT			24
 
 #define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
 #define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
@@ -394,6 +395,7 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
+#define VMX_EPT_INVEPT_BIT			(1ull << 20)
 #define VMX_EPT_AD_BIT				    (1ull << 21)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d651082c7cf7..0e79420376eb 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,7 @@
 #define EXIT_REASON_EOI_INDUCED         45
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT              50
 #define EXIT_REASON_PREEMPTION_TIMER    52
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
@@ -106,12 +107,13 @@
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
+	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
+	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }, \
 	{ 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" }, \
-	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }
+	{ EXIT_REASON_INVPCID,               "INVPCID" }
 
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2cb9470ea85b..a16bae3f83b3 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -128,46 +128,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
 
-static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
-
-static struct pvclock_vsyscall_time_info *
-pvclock_get_vsyscall_user_time_info(int cpu)
-{
-	if (!pvclock_vdso_info) {
-		BUG();
-		return NULL;
-	}
-
-	return &pvclock_vdso_info[cpu];
-}
-
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
-{
-	return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
-}
-
 #ifdef CONFIG_X86_64
-static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
-			        void *v)
-{
-	struct task_migration_notifier *mn = v;
-	struct pvclock_vsyscall_time_info *pvti;
-
-	pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
-
-	/* this is NULL when pvclock vsyscall is not initialized */
-	if (unlikely(pvti == NULL))
-		return NOTIFY_DONE;
-
-	pvti->migrate_count++;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block pvclock_migrate = {
-	.notifier_call = pvclock_task_migrate,
-};
-
 /*
  * Initialize the generic pvclock vsyscall state.  This will allocate
  * a/some page(s) for the per-vcpu pvclock information, set up a
@@ -181,17 +142,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
 
 	WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
 
-	pvclock_vdso_info = i;
-
 	for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
 		__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
 			     __pa(i) + (idx*PAGE_SIZE),
 			     PAGE_KERNEL_VVAR);
 	}
 
-
-	register_task_migration_notifier(&pvclock_migrate);
-
 	return 0;
 }
 #endif
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cbf..b110fe6c03d4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -413,7 +413,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
 			     (1 << KVM_FEATURE_PV_EOI) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afc11245827c..5439117d5c4c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -79,16 +79,6 @@ static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
 	*((u32 *) (apic->regs + reg_off)) = val;
 }
 
-static inline int apic_test_and_set_vector(int vec, void *bitmap)
-{
-	return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
-static inline int apic_test_and_clear_vector(int vec, void *bitmap)
-{
-	return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -331,10 +321,10 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
 }
 EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
-static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
+static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
 {
 	apic->irr_pending = true;
-	return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
+	apic_set_vector(vec, apic->regs + APIC_IRR);
 }
 
 static inline int apic_search_irr(struct kvm_lapic *apic)
@@ -681,32 +671,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		if (unlikely(!apic_enabled(apic)))
 			break;
 
+		result = 1;
+
 		if (dest_map)
 			__set_bit(vcpu->vcpu_id, dest_map);
 
-		if (kvm_x86_ops->deliver_posted_interrupt) {
-			result = 1;
+		if (kvm_x86_ops->deliver_posted_interrupt)
 			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		} else {
-			result = !apic_test_and_set_irr(vector, apic);
-
-			if (!result) {
-				if (trig_mode)
-					apic_debug("level trig mode repeatedly "
-						"for vector %d", vector);
-				goto out;
-			}
+		else {
+			apic_set_irr(vector, apic);
 
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
-out:
 		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
-				trig_mode, vector, !result);
+					  trig_mode, vector, false);
 		break;
 
 	case APIC_DM_REMRD:
-		apic_debug("Ignoring delivery mode 3\n");
+		result = 1;
+		vcpu->arch.pv.pv_unhalted = 1;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_SMI:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9e9285ae9b94..6e2d2c8f230b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -132,8 +132,8 @@ module_param(dbg, bool, 0644);
 	(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
 					    * PT32_LEVEL_BITS))) - 1))
 
-#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
-			| PT64_NX_MASK)
+#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
+			| shadow_x_mask | shadow_nx_mask)
 
 #define ACC_EXEC_MASK    1
 #define ACC_WRITE_MASK   PT_WRITABLE_MASK
@@ -331,11 +331,6 @@ static int is_large_pte(u64 pte)
 	return pte & PT_PAGE_SIZE_MASK;
 }
 
-static int is_dirty_gpte(unsigned long pte)
-{
-	return pte & PT_DIRTY_MASK;
-}
-
 static int is_rmap_spte(u64 pte)
 {
 	return is_shadow_present_pte(pte);
@@ -2052,12 +2047,18 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
 	return __shadow_walk_next(iterator, *iterator->sptep);
 }
 
-static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
+static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed)
 {
 	u64 spte;
 
+	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
+			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+
 	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
-	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+	       shadow_user_mask | shadow_x_mask;
+
+	if (accessed)
+		spte |= shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
 }
@@ -2574,14 +2575,6 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 	mmu_free_roots(vcpu);
 }
 
-static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
-{
-	int bit7;
-
-	bit7 = (gpte >> 7) & 1;
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
-}
-
 static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {
@@ -2594,26 +2587,6 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return gfn_to_pfn_memslot_atomic(slot, gfn);
 }
 
-static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu_page *sp, u64 *spte,
-				  u64 gpte)
-{
-	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
-	if (!is_present_gpte(gpte))
-		goto no_present;
-
-	if (!(gpte & PT_ACCESSED_MASK))
-		goto no_present;
-
-	return false;
-
-no_present:
-	drop_spte(vcpu->kvm, spte);
-	return true;
-}
-
 static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 				    struct kvm_mmu_page *sp,
 				    u64 *start, u64 *end)
@@ -2710,7 +2683,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
 
-			link_shadow_page(iterator.sptep, sp);
+			link_shadow_page(iterator.sptep, sp, true);
 		}
 	}
 	return emulate;
@@ -2808,7 +2781,7 @@ exit:
 	return ret;
 }
 
-static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code)
+static bool page_fault_can_be_fast(u32 error_code)
 {
 	/*
 	 * Do not fix the mmio spte with invalid generation number which
@@ -2861,7 +2834,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	bool ret = false;
 	u64 spte = 0ull;
 
-	if (!page_fault_can_be_fast(vcpu, error_code))
+	if (!page_fault_can_be_fast(error_code))
 		return false;
 
 	walk_shadow_page_lockless_begin(vcpu);
@@ -3209,6 +3182,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 	mmu_sync_roots(vcpu);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
 				  u32 access, struct x86_exception *exception)
@@ -3478,6 +3452,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 	++vcpu->stat.tlb_flush;
 	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
 
 static void paging_new_cr3(struct kvm_vcpu *vcpu)
 {
@@ -3501,18 +3476,6 @@ static void paging_free(struct kvm_vcpu *vcpu)
 	nonpaging_free(vcpu);
 }
 
-static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
-{
-	unsigned mask;
-
-	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
-
-	mask = (unsigned)~ACC_WRITE_MASK;
-	/* Allow write access to dirty gptes */
-	mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK;
-	*access &= mask;
-}
-
 static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 			   unsigned access, int *nr_present)
 {
@@ -3530,16 +3493,6 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 	return false;
 }
 
-static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte)
-{
-	unsigned access;
-
-	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
-	access &= ~(gpte >> PT64_NX_SHIFT);
-
-	return access;
-}
-
 static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
 {
 	unsigned index;
@@ -3549,6 +3502,11 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
 	return mmu->last_pte_bitmap & (1 << index);
 }
 
+#define PTTYPE_EPT 18 /* arbitrary */
+#define PTTYPE PTTYPE_EPT
+#include "paging_tmpl.h"
+#undef PTTYPE
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -3563,6 +3521,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 
+	context->bad_mt_xwr = 0;
+
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
 	switch (context->root_level) {
@@ -3618,7 +3578,40 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *context, bool execonly)
+{
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+	int pte;
+
+	context->rsvd_bits_mask[0][3] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
+	context->rsvd_bits_mask[0][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+
+	/* large page */
+	context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+	context->rsvd_bits_mask[1][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
+	context->rsvd_bits_mask[1][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
+	context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+	for (pte = 0; pte < 64; pte++) {
+		int rwx_bits = pte & 7;
+		int mt = pte >> 3;
+		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
+				rwx_bits == 0x2 || rwx_bits == 0x6 ||
+				(rwx_bits == 0x4 && !execonly))
+			context->bad_mt_xwr |= (1ull << pte);
+	}
+}
+
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3636,12 +3629,16 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu
 			w = bit & ACC_WRITE_MASK;
 			u = bit & ACC_USER_MASK;
 
-			/* Not really needed: !nx will cause pte.nx to fault */
-			x |= !mmu->nx;
-			/* Allow supervisor writes if !cr0.wp */
-			w |= !is_write_protection(vcpu) && !uf;
-			/* Disallow supervisor fetches of user code if cr4.smep */
-			x &= !(smep && u && !uf);
+			if (!ept) {
+				/* Not really needed: !nx will cause pte.nx to fault */
+				x |= !mmu->nx;
+				/* Allow supervisor writes if !cr0.wp */
+				w |= !is_write_protection(vcpu) && !uf;
+				/* Disallow supervisor fetches of user code if cr4.smep */
+				x &= !(smep && u && !uf);
+			} else
+				/* Not really needed: no U/S accesses on ept  */
+				u = 1;
 
 			fault = (ff && !x) || (uf && !u) || (wf && !w);
 			map |= fault << bit;
@@ -3676,7 +3673,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->root_level = level;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
@@ -3706,7 +3703,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->root_level = PT32_ROOT_LEVEL;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
@@ -3768,7 +3765,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	return 0;
@@ -3800,6 +3797,33 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+		bool execonly)
+{
+	ASSERT(vcpu);
+	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+
+	context->nx = true;
+	context->new_cr3 = paging_new_cr3;
+	context->page_fault = ept_page_fault;
+	context->gva_to_gpa = ept_gva_to_gpa;
+	context->sync_page = ept_sync_page;
+	context->invlpg = ept_invlpg;
+	context->update_pte = ept_update_pte;
+	context->free = paging_free;
+	context->root_level = context->shadow_root_level;
+	context->root_hpa = INVALID_PAGE;
+	context->direct_map = false;
+
+	update_permission_bitmask(vcpu, context, true);
+	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
+
 static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
 	int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
@@ -3847,7 +3871,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
-	update_permission_bitmask(vcpu, g_context);
+	update_permission_bitmask(vcpu, g_context, false);
 	update_last_pte_bitmap(vcpu, g_context);
 
 	return 0;
@@ -3923,8 +3947,8 @@ static bool need_remote_flush(u64 old, u64 new)
 		return true;
 	if ((old ^ new) & PT64_BASE_ADDR_MASK)
 		return true;
-	old ^= PT64_NX_MASK;
-	new ^= PT64_NX_MASK;
+	old ^= shadow_nx_mask;
+	new ^= shadow_nx_mask;
 	return (old & ~new & PT64_PERM_MASK) != 0;
 }
 
@@ -4182,7 +4206,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 	switch (er) {
 	case EMULATE_DONE:
 		return 1;
-	case EMULATE_DO_MMIO:
+	case EMULATE_USER_EXIT:
 		++vcpu->stat.mmio_exits;
 		/* fall through */
 	case EMULATE_FAIL:
@@ -4390,11 +4414,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	/*
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
-	 *
-	 * The max value is MMIO_MAX_GEN - 1 since it is not called
-	 * when mark memslot invalid.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= (MMIO_MAX_GEN - 1))) {
+	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
 		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 5b59c573aba7..77e044a0f5f7 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -71,6 +71,8 @@ enum {
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+		bool execonly);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7769699d48a8..043330159179 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -23,6 +23,13 @@
  * so the code in this file is compiled twice, once per pte size.
  */
 
+/*
+ * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro
+ * uses for EPT without A/D paging type.
+ */
+extern u64 __pure __using_nonexistent_pte_bit(void)
+	       __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT");
+
 #if PTTYPE == 64
 	#define pt_element_t u64
 	#define guest_walker guest_walker64
@@ -32,6 +39,10 @@
 	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#ifdef CONFIG_X86_64
 	#define PT_MAX_FULL_LEVELS 4
 	#define CMPXCHG cmpxchg
@@ -49,7 +60,26 @@
 	#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT32_LEVEL_BITS
 	#define PT_MAX_FULL_LEVELS 2
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define CMPXCHG cmpxchg
+#elif PTTYPE == PTTYPE_EPT
+	#define pt_element_t u64
+	#define guest_walker guest_walkerEPT
+	#define FNAME(name) ept_##name
+	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
+	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
+	#define PT_LEVEL_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK 0
+	#define PT_GUEST_DIRTY_MASK 0
+	#define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit()
+	#define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit()
+	#define CMPXCHG cmpxchg64
+	#define PT_MAX_FULL_LEVELS 4
 #else
 	#error Invalid PTTYPE value
 #endif
@@ -80,6 +110,40 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
 	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
+static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
+{
+	unsigned mask;
+
+	/* dirty bit is not supported, so no need to track it */
+	if (!PT_GUEST_DIRTY_MASK)
+		return;
+
+	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+	mask = (unsigned)~ACC_WRITE_MASK;
+	/* Allow write access to dirty gptes */
+	mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
+		PT_WRITABLE_MASK;
+	*access &= mask;
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
+
+	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
+		((mmu->bad_mt_xwr & (1ull << low6)) != 0);
+}
+
+static inline int FNAME(is_present_gpte)(unsigned long pte)
+{
+#if PTTYPE != PTTYPE_EPT
+	return is_present_gpte(pte);
+#else
+	return pte & 7;
+#endif
+}
+
 static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
@@ -103,6 +167,42 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
+static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu_page *sp, u64 *spte,
+				  u64 gpte)
+{
+	if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
+	if (!FNAME(is_present_gpte)(gpte))
+		goto no_present;
+
+	/* if accessed bit is not supported prefetch non accessed gpte */
+	if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK))
+		goto no_present;
+
+	return false;
+
+no_present:
+	drop_spte(vcpu->kvm, spte);
+	return true;
+}
+
+static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
+{
+	unsigned access;
+#if PTTYPE == PTTYPE_EPT
+	access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
+		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
+		ACC_USER_MASK;
+#else
+	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	access &= ~(gpte >> PT64_NX_SHIFT);
+#endif
+
+	return access;
+}
+
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
@@ -114,18 +214,23 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 	gfn_t table_gfn;
 	int ret;
 
+	/* dirty/accessed bits are not supported, so no need to update them */
+	if (!PT_GUEST_DIRTY_MASK)
+		return 0;
+
 	for (level = walker->max_level; level >= walker->level; --level) {
 		pte = orig_pte = walker->ptes[level - 1];
 		table_gfn = walker->table_gfn[level - 1];
 		ptep_user = walker->ptep_user[level - 1];
 		index = offset_in_page(ptep_user) / sizeof(pt_element_t);
-		if (!(pte & PT_ACCESSED_MASK)) {
+		if (!(pte & PT_GUEST_ACCESSED_MASK)) {
 			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_ACCESSED_MASK;
+			pte |= PT_GUEST_ACCESSED_MASK;
 		}
-		if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+		if (level == walker->level && write_fault &&
+				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_DIRTY_MASK;
+			pte |= PT_GUEST_DIRTY_MASK;
 		}
 		if (pte == orig_pte)
 			continue;
@@ -170,7 +275,7 @@ retry_walk:
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
-		if (!is_present_gpte(pte))
+		if (!FNAME(is_present_gpte)(pte))
 			goto error;
 		--walker->level;
 	}
@@ -179,7 +284,7 @@ retry_walk:
 	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
 	       (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
 
-	accessed_dirty = PT_ACCESSED_MASK;
+	accessed_dirty = PT_GUEST_ACCESSED_MASK;
 	pt_access = pte_access = ACC_ALL;
 	++walker->level;
 
@@ -215,17 +320,17 @@ retry_walk:
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
-		if (unlikely(!is_present_gpte(pte)))
+		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte,
-					      walker->level))) {
+		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
+					             walker->level))) {
 			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 
 		accessed_dirty &= pte;
-		pte_access = pt_access & gpte_access(vcpu, pte);
+		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
 
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
@@ -248,13 +353,15 @@ retry_walk:
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		protect_clean_gpte(&pte_access, pte);
+		FNAME(protect_clean_gpte)(&pte_access, pte);
 	else
 		/*
-		 * On a write fault, fold the dirty bit into accessed_dirty by
-		 * shifting it one place right.
+		 * On a write fault, fold the dirty bit into accessed_dirty.
+		 * For modes without A/D bits support accessed_dirty will be
+		 * always clear.
 		 */
-		accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
+		accessed_dirty &= pte >>
+			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
 		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -279,6 +386,25 @@ error:
 	walker->fault.vector = PF_VECTOR;
 	walker->fault.error_code_valid = true;
 	walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+	/*
+	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+	 * misconfiguration requires to be injected. The detection is
+	 * done by is_rsvd_bits_set() above.
+	 *
+	 * We set up the value of exit_qualification to inject:
+	 * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation
+	 * [5:3] - Calculated by the page walk of the guest EPT page tables
+	 * [7:8] - Derived from [7:8] of real exit_qualification
+	 *
+	 * The other bits are set to 0.
+	 */
+	if (!(errcode & PFERR_RSVD_MASK)) {
+		vcpu->arch.exit_qualification &= 0x187;
+		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+	}
+#endif
 	walker->fault.address = addr;
 	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
 
@@ -293,6 +419,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 					access);
 }
 
+#if PTTYPE != PTTYPE_EPT
 static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 				   struct kvm_vcpu *vcpu, gva_t addr,
 				   u32 access)
@@ -300,6 +427,7 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
 					addr, access);
 }
+#endif
 
 static bool
 FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -309,14 +437,14 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	gfn_t gfn;
 	pfn_t pfn;
 
-	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
+	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return false;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
 
 	gfn = gpte_to_gfn(gpte);
-	pte_access = sp->role.access & gpte_access(vcpu, gpte);
-	protect_clean_gpte(&pte_access, gpte);
+	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+	FNAME(protect_clean_gpte)(&pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
 	if (is_error_pfn(pfn))
@@ -446,7 +574,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			goto out_gpte_changed;
 
 		if (sp)
-			link_shadow_page(it.sptep, sp);
+			link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	for (;
@@ -466,7 +594,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
 				      true, direct_access, it.sptep);
-		link_shadow_page(it.sptep, sp);
+		link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
@@ -727,6 +855,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 	return gpa;
 }
 
+#if PTTYPE != PTTYPE_EPT
 static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
@@ -745,6 +874,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 
 	return gpa;
 }
+#endif
 
 /*
  * Using the cached information from sp->gfns is safe because:
@@ -785,15 +915,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
+		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
-		pte_access &= gpte_access(vcpu, gpte);
-		protect_clean_gpte(&pte_access, gpte);
+		pte_access &= FNAME(gpte_access)(vcpu, gpte);
+		FNAME(protect_clean_gpte)(&pte_access, gpte);
 
 		if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
 		      &nr_present))
@@ -830,3 +960,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 #undef gpte_to_gfn
 #undef gpte_to_gfn_lvl
 #undef CMPXCHG
+#undef PT_GUEST_ACCESSED_MASK
+#undef PT_GUEST_DIRTY_MASK
+#undef PT_GUEST_DIRTY_SHIFT
+#undef PT_GUEST_ACCESSED_SHIFT
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c53e797e7369..5c4f63151b4d 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
 
 static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		unsigned config, bool exclude_user, bool exclude_kernel,
-		bool intr)
+		bool intr, bool in_tx, bool in_tx_cp)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+	if (in_tx)
+		attr.config |= HSW_IN_TX;
+	if (in_tx_cp)
+		attr.config |= HSW_IN_TX_CHECKPOINTED;
 
 	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
 
@@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 				ARCH_PERFMON_EVENTSEL_INV |
-				ARCH_PERFMON_EVENTSEL_CMASK))) {
+				ARCH_PERFMON_EVENTSEL_CMASK |
+				HSW_IN_TX |
+				HSW_IN_TX_CHECKPOINTED))) {
 		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
 				unit_mask);
 		if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	reprogram_counter(pmc, type, config,
 			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			eventsel & ARCH_PERFMON_EVENTSEL_INT);
+			eventsel & ARCH_PERFMON_EVENTSEL_INT,
+			(eventsel & HSW_IN_TX),
+			(eventsel & HSW_IN_TX_CHECKPOINTED));
 }
 
 static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
 			arch_events[fixed_pmc_events[idx]].event_type,
 			!(en & 0x2), /* exclude user */
 			!(en & 0x1), /* exclude kernel */
-			pmi);
+			pmi, false, false);
 }
 
 static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -408,7 +416,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
 				return 0;
-			if (!(data & 0xffffffff00200000ull)) {
+			if (!(data & pmu->reserved_bits)) {
 				reprogram_gp_counter(pmc, data);
 				return 0;
 			}
@@ -450,6 +458,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_GP] = 0;
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -478,6 +487,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (entry &&
+	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 064d0be67ecc..1f1da43ff2a2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -373,6 +373,7 @@ struct nested_vmx {
 	 * we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
+	u64 msr_ia32_feature_control;
 };
 
 #define POSTED_INTR_ON  0
@@ -711,10 +712,10 @@ static void nested_release_page_clean(struct page *page)
 	kvm_release_page_clean(page);
 }
 
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
-static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -1039,12 +1040,16 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
 		(vmcs12->secondary_vm_exec_control & bit);
 }
 
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
-	struct kvm_vcpu *vcpu)
+static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
 {
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
+}
+
 static inline bool is_exception(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -2155,6 +2160,7 @@ static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high;
 static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high;
 static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high;
 static u32 nested_vmx_misc_low, nested_vmx_misc_high;
+static u32 nested_vmx_ept_caps;
 static __init void nested_vmx_setup_ctls_msrs(void)
 {
 	/*
@@ -2190,14 +2196,17 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	 * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and
 	 * 17 must be 1.
 	 */
+	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
+		nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
 	nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
 	/* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
+	nested_vmx_exit_ctls_high &=
 #ifdef CONFIG_X86_64
-	nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE;
-#else
-	nested_vmx_exit_ctls_high = 0;
+		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-	nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+	nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
+				      VM_EXIT_LOAD_IA32_EFER);
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2205,8 +2214,12 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	/* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */
 	nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_entry_ctls_high &=
-		VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE;
-	nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+#ifdef CONFIG_X86_64
+		VM_ENTRY_IA32E_MODE |
+#endif
+		VM_ENTRY_LOAD_IA32_PAT;
+	nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |
+				       VM_ENTRY_LOAD_IA32_EFER);
 
 	/* cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
@@ -2241,6 +2254,22 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
+	if (enable_ept) {
+		/* nested EPT: emulate EPT also to L1 */
+		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
+		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
+			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+		nested_vmx_ept_caps &= vmx_capability.ept;
+		/*
+		 * Since invept is completely emulated we support both global
+		 * and context invalidation independent of what host cpu
+		 * supports
+		 */
+		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
+			VMX_EPT_EXTENT_CONTEXT_BIT;
+	} else
+		nested_vmx_ept_caps = 0;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high);
 	nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK |
@@ -2282,8 +2311,11 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 
 	switch (msr_index) {
 	case MSR_IA32_FEATURE_CONTROL:
-		*pdata = 0;
-		break;
+		if (nested_vmx_allowed(vcpu)) {
+			*pdata = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+			break;
+		}
+		return 0;
 	case MSR_IA32_VMX_BASIC:
 		/*
 		 * This MSR reports some information about VMX support. We
@@ -2346,8 +2378,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 					nested_vmx_secondary_ctls_high);
 		break;
 	case MSR_IA32_VMX_EPT_VPID_CAP:
-		/* Currently, no nested ept or nested vpid */
-		*pdata = 0;
+		/* Currently, no nested vpid support */
+		*pdata = nested_vmx_ept_caps;
 		break;
 	default:
 		return 0;
@@ -2356,14 +2388,24 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	return 1;
 }
 
-static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
+static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
+	u32 msr_index = msr_info->index;
+	u64 data = msr_info->data;
+	bool host_initialized = msr_info->host_initiated;
+
 	if (!nested_vmx_allowed(vcpu))
 		return 0;
 
-	if (msr_index == MSR_IA32_FEATURE_CONTROL)
-		/* TODO: the right thing. */
+	if (msr_index == MSR_IA32_FEATURE_CONTROL) {
+		if (!host_initialized &&
+				to_vmx(vcpu)->nested.msr_ia32_feature_control
+				& FEATURE_CONTROL_LOCKED)
+			return 0;
+		to_vmx(vcpu)->nested.msr_ia32_feature_control = data;
 		return 1;
+	}
+
 	/*
 	 * No need to treat VMX capability MSRs specially: If we don't handle
 	 * them, handle_wrmsr will #GP(0), which is correct (they are readonly)
@@ -2494,7 +2536,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		/* Otherwise falls through */
 	default:
-		if (vmx_set_vmx_msr(vcpu, msr_index, data))
+		if (vmx_set_vmx_msr(vcpu, msr_info))
 			break;
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
@@ -5302,9 +5344,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 
 	/* It is a write fault? */
 	error_code = exit_qualification & (1U << 1);
+	/* It is a fetch fault? */
+	error_code |= (exit_qualification & (1U << 2)) << 2;
 	/* ept page table is present? */
 	error_code |= (exit_qualification >> 3) & 0x1;
 
+	vcpu->arch.exit_qualification = exit_qualification;
+
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
@@ -5438,7 +5484,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
 
-		if (err == EMULATE_DO_MMIO) {
+		if (err == EMULATE_USER_EXIT) {
+			++vcpu->stat.mmio_exits;
 			ret = 0;
 			goto out;
 		}
@@ -5567,8 +5614,47 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
 		free_loaded_vmcs(&vmx->vmcs01);
 }
 
+/*
+ * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
+ * set the success or error code of an emulated VMX instruction, as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions".
+ */
+static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+}
+
+static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_CF);
+}
+
 static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
-				 u32 vm_instruction_error);
+					u32 vm_instruction_error)
+{
+	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
+		/*
+		 * failValid writes the error number to the current VMCS, which
+		 * can't be done there isn't a current VMCS.
+		 */
+		nested_vmx_failInvalid(vcpu);
+		return;
+	}
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_ZF);
+	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
+	/*
+	 * We don't need to force a shadow sync because
+	 * VM_INSTRUCTION_ERROR is not shadowed
+	 */
+}
 
 /*
  * Emulate the VMXON instruction.
@@ -5583,6 +5669,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	struct kvm_segment cs;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs *shadow_vmcs;
+	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
+		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 
 	/* The Intel VMX Instruction Reference lists a bunch of bits that
 	 * are prerequisite to running VMXON, most notably cr4.VMXE must be
@@ -5611,6 +5699,13 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		skip_emulated_instruction(vcpu);
 		return 1;
 	}
+
+	if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+			!= VMXON_NEEDED_FEATURES) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
 		if (!shadow_vmcs)
@@ -5628,6 +5723,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	vmx->nested.vmxon = true;
 
 	skip_emulated_instruction(vcpu);
+	nested_vmx_succeed(vcpu);
 	return 1;
 }
 
@@ -5712,6 +5808,7 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 		return 1;
 	free_nested(to_vmx(vcpu));
 	skip_emulated_instruction(vcpu);
+	nested_vmx_succeed(vcpu);
 	return 1;
 }
 
@@ -5768,48 +5865,6 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
- */
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
-}
-
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_CF);
-}
-
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
-					u32 vm_instruction_error)
-{
-	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
-		/*
-		 * failValid writes the error number to the current VMCS, which
-		 * can't be done there isn't a current VMCS.
-		 */
-		nested_vmx_failInvalid(vcpu);
-		return;
-	}
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_ZF);
-	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
-	/*
-	 * We don't need to force a shadow sync because
-	 * VM_INSTRUCTION_ERROR is not shadowed
-	 */
-}
-
 /* Emulate the VMCLEAR instruction */
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
@@ -5972,8 +6027,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 	unsigned long field;
 	u64 field_value;
 	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
-	unsigned long *fields = (unsigned long *)shadow_read_write_fields;
-	int num_fields = max_shadow_read_write_fields;
+	const unsigned long *fields = shadow_read_write_fields;
+	const int num_fields = max_shadow_read_write_fields;
 
 	vmcs_load(shadow_vmcs);
 
@@ -6002,12 +6057,11 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 {
-	unsigned long *fields[] = {
-		(unsigned long *)shadow_read_write_fields,
-		(unsigned long *)shadow_read_only_fields
+	const unsigned long *fields[] = {
+		shadow_read_write_fields,
+		shadow_read_only_fields
 	};
-	int num_lists =  ARRAY_SIZE(fields);
-	int max_fields[] = {
+	const int max_fields[] = {
 		max_shadow_read_write_fields,
 		max_shadow_read_only_fields
 	};
@@ -6018,7 +6072,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 
 	vmcs_load(shadow_vmcs);
 
-	for (q = 0; q < num_lists; q++) {
+	for (q = 0; q < ARRAY_SIZE(fields); q++) {
 		for (i = 0; i < max_fields[q]; i++) {
 			field = fields[q][i];
 			vmcs12_read_any(&vmx->vcpu, field, &field_value);
@@ -6248,6 +6302,74 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/* Emulate the INVEPT instruction */
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+	u32 vmx_instruction_info, types;
+	unsigned long type;
+	gva_t gva;
+	struct x86_exception e;
+	struct {
+		u64 eptp, gpa;
+	} operand;
+	u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK;
+
+	if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
+	    !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
+
+	if (!(types & (1UL << type))) {
+		nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		return 1;
+	}
+
+	/* According to the Intel VMX instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, &gva))
+		return 1;
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
+				sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (type) {
+	case VMX_EPT_EXTENT_CONTEXT:
+		if ((operand.eptp & eptp_mask) !=
+				(nested_ept_get_cr3(vcpu) & eptp_mask))
+			break;
+	case VMX_EPT_EXTENT_GLOBAL:
+		kvm_mmu_sync_roots(vcpu);
+		kvm_mmu_flush_tlb(vcpu);
+		nested_vmx_succeed(vcpu);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	skip_emulated_instruction(vcpu);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -6292,6 +6414,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6518,6 +6641,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
 	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
 	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+	case EXIT_REASON_INVEPT:
 		/*
 		 * VMX instructions trap unconditionally. This allows L1 to
 		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6550,7 +6674,20 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12,
 			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
 	case EXIT_REASON_EPT_VIOLATION:
+		/*
+		 * L0 always deals with the EPT violation. If nested EPT is
+		 * used, and the nested mmu code discovers that the address is
+		 * missing in the guest EPT table (EPT12), the EPT violation
+		 * will be injected with nested_ept_inject_page_fault()
+		 */
+		return 0;
 	case EXIT_REASON_EPT_MISCONFIG:
+		/*
+		 * L2 never uses directly L1's EPT, but rather L0's own EPT
+		 * table (shadow on EPT) or a merged EPT table that L0 built
+		 * (EPT on EPT). So any problems with the structure of the
+		 * table is L0's fault.
+		 */
 		return 0;
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return vmcs12->pin_based_vm_exec_control &
@@ -6638,7 +6775,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked &&
 	    !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis(
-	                                get_vmcs12(vcpu), vcpu)))) {
+					get_vmcs12(vcpu))))) {
 		if (vmx_interrupt_allowed(vcpu)) {
 			vmx->soft_vnmi_blocked = 0;
 		} else if (vmx->vnmi_blocked_time > 1000000000LL &&
@@ -7326,6 +7463,48 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 		entry->ecx |= bit(X86_FEATURE_VMX);
 }
 
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12;
+	nested_vmx_vmexit(vcpu);
+	vmcs12 = get_vmcs12(vcpu);
+
+	if (fault->error_code & PFERR_RSVD_MASK)
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+	else
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+	vmcs12->exit_qualification = vcpu->arch.exit_qualification;
+	vmcs12->guest_physical_address = fault->address;
+}
+
+/* Callbacks for nested_ept_init_mmu_context: */
+
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+{
+	/* return the page table to be shadowed - in our case, EPT12 */
+	return get_vmcs12(vcpu)->ept_pointer;
+}
+
+static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+	int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
+			nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT);
+
+	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
+	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
+	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+
+	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
+
+	return r;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7388,7 +7567,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs12->guest_interruptibility_info);
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
 	kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-	vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags);
+	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
 	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
 		vmcs12->guest_pending_dbg_exceptions);
 	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
@@ -7508,15 +7687,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
 
-	/* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */
-	vmcs_write32(VM_EXIT_CONTROLS,
-		vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl);
-	vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls |
+	/* L2->L1 exit controls are emulated - the hardware exit is to L0 so
+	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+	 * bits are further modified by vmx_set_efer() below.
+	 */
+	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
+
+	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
+	 * emulated by vmx_set_efer(), below.
+	 */
+	vmcs_write32(VM_ENTRY_CONTROLS,
+		(vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
+			~VM_ENTRY_IA32E_MODE) |
 		(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
 
-	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
-	else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+		vcpu->arch.pat = vmcs12->guest_ia32_pat;
+	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
 
@@ -7538,6 +7726,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmx_flush_tlb(vcpu);
 	}
 
+	if (nested_cpu_has_ept(vmcs12)) {
+		kvm_mmu_unload(vcpu);
+		nested_ept_init_mmu_context(vcpu);
+	}
+
 	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->guest_ia32_efer;
 	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
@@ -7565,6 +7758,16 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	kvm_set_cr3(vcpu, vmcs12->guest_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	/*
+	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
+	 */
+	if (enable_ept) {
+		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+	}
+
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
 	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
 }
@@ -7887,6 +8090,22 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_pending_dbg_exceptions =
 		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 
+	/*
+	 * In some cases (usually, nested EPT), L2 is allowed to change its
+	 * own CR3 without exiting. If it has changed it, we must keep it.
+	 * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
+	 * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
+	 *
+	 * Additionally, restore L2's PDPTR to vmcs12.
+	 */
+	if (enable_ept) {
+		vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3);
+		vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
+		vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
+		vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
+		vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
+	}
+
 	vmcs12->vm_entry_controls =
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE);
@@ -7948,6 +8167,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 				   struct vmcs12 *vmcs12)
 {
+	struct kvm_segment seg;
+
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->host_ia32_efer;
 	else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
@@ -7982,7 +8203,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	/* shadow page tables on either EPT or shadow page tables */
+	if (nested_cpu_has_ept(vmcs12))
+		nested_ept_uninit_mmu_context(vcpu);
+
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
 
@@ -8001,23 +8224,61 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
 	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
 	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
-	vmcs_writel(GUEST_TR_BASE, vmcs12->host_tr_base);
-	vmcs_writel(GUEST_GS_BASE, vmcs12->host_gs_base);
-	vmcs_writel(GUEST_FS_BASE, vmcs12->host_fs_base);
-	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->host_es_selector);
-	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->host_cs_selector);
-	vmcs_write16(GUEST_SS_SELECTOR, vmcs12->host_ss_selector);
-	vmcs_write16(GUEST_DS_SELECTOR, vmcs12->host_ds_selector);
-	vmcs_write16(GUEST_FS_SELECTOR, vmcs12->host_fs_selector);
-	vmcs_write16(GUEST_GS_SELECTOR, vmcs12->host_gs_selector);
-	vmcs_write16(GUEST_TR_SELECTOR, vmcs12->host_tr_selector);
-
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT)
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+		vcpu->arch.pat = vmcs12->host_ia32_pat;
+	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
 		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
 			vmcs12->host_ia32_perf_global_ctrl);
 
+	/* Set L1 segment info according to Intel SDM
+	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.selector = vmcs12->host_cs_selector,
+		.type = 11,
+		.present = 1,
+		.s = 1,
+		.g = 1
+	};
+	if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+		seg.l = 1;
+	else
+		seg.db = 1;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.type = 3,
+		.present = 1,
+		.s = 1,
+		.db = 1,
+		.g = 1
+	};
+	seg.selector = vmcs12->host_ds_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
+	seg.selector = vmcs12->host_es_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
+	seg.selector = vmcs12->host_ss_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
+	seg.selector = vmcs12->host_fs_selector;
+	seg.base = vmcs12->host_fs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
+	seg.selector = vmcs12->host_gs_selector;
+	seg.base = vmcs12->host_gs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
+	seg = (struct kvm_segment) {
+		.base = vmcs12->host_tr_base,
+		.limit = 0x67,
+		.selector = vmcs12->host_tr_selector,
+		.type = 11,
+		.present = 1
+	};
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);
+
 	kvm_set_dr(vcpu, 7, 0x400);
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d21bce505315..e5ca72a5cdb6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -682,17 +682,6 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		 */
 	}
 
-	/*
-	 * Does the new cr3 value map to physical memory? (Note, we
-	 * catch an invalid cr3 even in real-mode, because it would
-	 * cause trouble later on when we turn on paging anyway.)
-	 *
-	 * A real CPU would silently accept an invalid cr3 and would
-	 * attempt to use it - with largely undefined (and often hard
-	 * to debug) behavior on the guest side.
-	 */
-	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
-		return 1;
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
 	vcpu->arch.mmu.new_cr3(vcpu);
@@ -850,7 +839,8 @@ static u32 msrs_to_save[] = {
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
+	MSR_IA32_FEATURE_CONTROL
 };
 
 static unsigned num_msrs_to_save;
@@ -1457,6 +1447,29 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 #endif
 }
 
+static void kvm_gen_update_masterclock(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+	int i;
+	struct kvm_vcpu *vcpu;
+	struct kvm_arch *ka = &kvm->arch;
+
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	kvm_make_mclock_inprogress_request(kvm);
+	/* no guest entries from this point */
+	pvclock_update_vm_gtod_copy(kvm);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+
+	/* guest entries allowed */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+#endif
+}
+
 static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags, this_tsc_khz;
@@ -3806,6 +3819,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		delta = user_ns.clock - now_ns;
 		local_irq_enable();
 		kvm->arch.kvmclock_offset = delta;
+		kvm_gen_update_masterclock(kvm);
 		break;
 	}
 	case KVM_GET_CLOCK: {
@@ -4955,6 +4969,97 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
 static int complete_emulated_pio(struct kvm_vcpu *vcpu);
 
+static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
+				unsigned long *db)
+{
+	u32 dr6 = 0;
+	int i;
+	u32 enable, rwlen;
+
+	enable = dr7;
+	rwlen = dr7 >> 16;
+	for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4)
+		if ((enable & 3) && (rwlen & 15) == type && db[i] == addr)
+			dr6 |= (1 << i);
+	return dr6;
+}
+
+static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
+{
+	struct kvm_run *kvm_run = vcpu->run;
+
+	/*
+	 * Use the "raw" value to see if TF was passed to the processor.
+	 * Note that the new value of the flags has not been saved yet.
+	 *
+	 * This is correct even for TF set by the guest, because "the
+	 * processor will not generate this exception after the instruction
+	 * that sets the TF flag".
+	 */
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+	if (unlikely(rflags & X86_EFLAGS_TF)) {
+		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1;
+			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			*r = EMULATE_USER_EXIT;
+		} else {
+			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+			/*
+			 * "Certain debug exceptions may clear bit 0-3.  The
+			 * remaining contents of the DR6 register are never
+			 * cleared by the processor".
+			 */
+			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 |= DR6_BS;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+		}
+	}
+}
+
+static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
+{
+	struct kvm_run *kvm_run = vcpu->run;
+	unsigned long eip = vcpu->arch.emulate_ctxt.eip;
+	u32 dr6 = 0;
+
+	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
+	    (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
+		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+					   vcpu->arch.guest_debug_dr7,
+					   vcpu->arch.eff_db);
+
+		if (dr6 != 0) {
+			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+			kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
+				get_segment_base(vcpu, VCPU_SREG_CS);
+
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			*r = EMULATE_USER_EXIT;
+			return true;
+		}
+	}
+
+	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) {
+		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+					   vcpu->arch.dr7,
+					   vcpu->arch.db);
+
+		if (dr6 != 0) {
+			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 |= dr6;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			*r = EMULATE_DONE;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			    unsigned long cr2,
 			    int emulation_type,
@@ -4975,6 +5080,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		init_emulate_ctxt(vcpu);
+
+		/*
+		 * We will reenter on the same instruction since
+		 * we do not set complete_userspace_io.  This does not
+		 * handle watchpoints yet, those would be handled in
+		 * the emulate_ops.
+		 */
+		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+			return r;
+
 		ctxt->interruptibility = 0;
 		ctxt->have_exception = false;
 		ctxt->perm_ok = false;
@@ -5031,17 +5146,18 @@ restart:
 		inject_emulated_exception(vcpu);
 		r = EMULATE_DONE;
 	} else if (vcpu->arch.pio.count) {
-		if (!vcpu->arch.pio.in)
+		if (!vcpu->arch.pio.in) {
+			/* FIXME: return into emulator if single-stepping.  */
 			vcpu->arch.pio.count = 0;
-		else {
+		} else {
 			writeback = false;
 			vcpu->arch.complete_userspace_io = complete_emulated_pio;
 		}
-		r = EMULATE_DO_MMIO;
+		r = EMULATE_USER_EXIT;
 	} else if (vcpu->mmio_needed) {
 		if (!vcpu->mmio_is_write)
 			writeback = false;
-		r = EMULATE_DO_MMIO;
+		r = EMULATE_USER_EXIT;
 		vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	} else if (r == EMULATION_RESTART)
 		goto restart;
@@ -5050,10 +5166,12 @@ restart:
 
 	if (writeback) {
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
-		kvm_set_rflags(vcpu, ctxt->eflags);
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
+		if (r == EMULATE_DONE)
+			kvm_vcpu_check_singlestep(vcpu, &r);
+		kvm_set_rflags(vcpu, ctxt->eflags);
 	} else
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = true;
 
@@ -5347,7 +5465,7 @@ static struct notifier_block pvclock_gtod_notifier = {
 int kvm_arch_init(void *opaque)
 {
 	int r;
-	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
+	struct kvm_x86_ops *ops = opaque;
 
 	if (kvm_x86_ops) {
 		printk(KERN_ERR "kvm: already loaded the other module\n");
@@ -5495,6 +5613,23 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
+{
+	struct kvm_lapic_irq lapic_irq;
+
+	lapic_irq.shorthand = 0;
+	lapic_irq.dest_mode = 0;
+	lapic_irq.dest_id = apicid;
+
+	lapic_irq.delivery_mode = APIC_DM_REMRD;
+	kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -5528,6 +5663,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -5689,29 +5828,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
-static void kvm_gen_update_masterclock(struct kvm *kvm)
-{
-#ifdef CONFIG_X86_64
-	int i;
-	struct kvm_vcpu *vcpu;
-	struct kvm_arch *ka = &kvm->arch;
-
-	spin_lock(&ka->pvclock_gtod_sync_lock);
-	kvm_make_mclock_inprogress_request(kvm);
-	/* no guest entries from this point */
-	pvclock_update_vm_gtod_copy(kvm);
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
-
-	/* guest entries allowed */
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
-
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
-#endif
-}
-
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
 	u64 eoi_exit_bitmap[4];
@@ -5950,6 +6066,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 				kvm_apic_accept_events(vcpu);
 				switch(vcpu->arch.mp_state) {
 				case KVM_MP_STATE_HALTED:
+					vcpu->arch.pv.pv_unhalted = false;
 					vcpu->arch.mp_state =
 						KVM_MP_STATE_RUNNABLE;
 				case KVM_MP_STATE_RUNNABLE:
@@ -6061,6 +6178,8 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
+
+		/* FIXME: return into emulator if single-stepping.  */
 		if (vcpu->mmio_is_write)
 			return 1;
 		vcpu->mmio_read_completed = 1;
@@ -6249,7 +6368,12 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
 	kvm_apic_accept_events(vcpu);
-	mp_state->mp_state = vcpu->arch.mp_state;
+	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+					vcpu->arch.pv.pv_unhalted)
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+	else
+		mp_state->mp_state = vcpu->arch.mp_state;
+
 	return 0;
 }
 
@@ -6770,6 +6894,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	BUG_ON(vcpu->kvm == NULL);
 	kvm = vcpu->kvm;
 
+	vcpu->arch.pv.pv_unhalted = false;
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -7019,6 +7144,15 @@ out_free:
 	return -ENOMEM;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+	/*
+	 * memslots->generation has been incremented.
+	 * mmio generation may have reached its maximum value.
+	 */
+	kvm_mmu_invalidate_mmio_sptes(kvm);
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem,
@@ -7079,11 +7213,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	 */
 	if ((change != KVM_MR_DELETE) && (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.
-	 */
-	kvm_mmu_invalidate_mmio_sptes(kvm);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -7103,6 +7232,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| kvm_apic_has_events(vcpu)
+		|| vcpu->arch.pv.pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index c74436e687bf..72074d528400 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -85,15 +85,18 @@ static notrace cycle_t vread_pvclock(int *mode)
 	cycle_t ret;
 	u64 last;
 	u32 version;
-	u32 migrate_count;
 	u8 flags;
 	unsigned cpu, cpu1;
 
 
 	/*
-	 * When looping to get a consistent (time-info, tsc) pair, we
-	 * also need to deal with the possibility we can switch vcpus,
-	 * so make sure we always re-fetch time-info for the current vcpu.
+	 * Note: hypervisor must guarantee that:
+	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
+	 * 2. that per-CPU pvclock time info is updated if the
+	 *    underlying CPU changes.
+	 * 3. that version is increased whenever underlying CPU
+	 *    changes.
+	 *
 	 */
 	do {
 		cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -104,8 +107,6 @@ static notrace cycle_t vread_pvclock(int *mode)
 
 		pvti = get_pvti(cpu);
 
-		migrate_count = pvti->migrate_count;
-
 		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
 		/*
@@ -117,8 +118,7 @@ static notrace cycle_t vread_pvclock(int *mode)
 		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
 	} while (unlikely(cpu != cpu1 ||
 			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version ||
-			  pvti->migrate_count != migrate_count));
+			  pvti->pvti.version != version));
 
 	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
 		*mode = VCLOCK_NONE;