Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Fixes and features for 3.18.

  Apart from the usual cleanups, here is the summary of new features:

   - s390 moves closer towards host large page support

   - PowerPC has improved support for debugging (both inside the guest
     and via gdbstub) and support for e6500 processors

   - ARM/ARM64 support read-only memory (which is necessary to put
     firmware in emulated NOR flash)

   - x86 has the usual emulator fixes and nested virtualization
     improvements (including improved Windows support on Intel and
     Jailhouse hypervisor support on AMD), adaptive PLE which helps
     overcommitting of huge guests.  Also included are some patches that
     make KVM more friendly to memory hot-unplug, and fixes for rare
     caching bugs.

  Two patches have trivial mm/ parts that were acked by Rik and Andrew.

  Note: I will soon switch to a subkey for signing purposes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (157 commits)
  kvm: do not handle APIC access page if in-kernel irqchip is not in use
  KVM: s390: count vcpu wakeups in stat.halt_wakeup
  KVM: s390/facilities: allow TOD-CLOCK steering facility bit
  KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode
  arm/arm64: KVM: Report correct FSC for unsupported fault types
  arm/arm64: KVM: Fix VTTBR_BADDR_MASK and pgd alloc
  kvm: Fix kvm_get_page_retry_io __gup retval check
  arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset
  kvm: x86: Unpin and remove kvm_arch->apic_access_page
  kvm: vmx: Implement set_apic_access_page_addr
  kvm: x86: Add request bit to reload APIC access page address
  kvm: Add arch specific mmu notifier for page invalidation
  kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static
  kvm: Fix page ageing bugs
  kvm/x86/mmu: Pass gfn and level to rmapp callback.
  x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
  kvm: x86: use macros to compute bank MSRs
  KVM: x86: Remove debug assertion of non-PAE reserved bits
  kvm: don't take vcpu mutex for obviously invalid vcpu ioctls
  kvm: Faults which trigger IO release the mmap_sem
  ...

13 files changed, 682 insertions, 262 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 38a0afe83c6b..976e3a57f9ea 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -53,14 +53,14 @@ u64 kvm_supported_xcr0(void)
 	return xcr0;
 }
 
-void kvm_update_cpuid(struct kvm_vcpu *vcpu)
+int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	if (!best)
-		return;
+		return 0;
 
 	/* Update OSXSAVE bit */
 	if (cpu_has_xsave && best->function == 0x1) {
@@ -88,7 +88,17 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			xstate_required_size(vcpu->arch.xcr0);
 	}
 
+	/*
+	 * The existing code assumes virtual address is 48-bit in the canonical
+	 * address checks; exit if it is ever changed.
+	 */
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && ((best->eax & 0xff00) >> 8) != 48 &&
+		((best->eax & 0xff00) >> 8) != 0)
+		return -EINVAL;
+
 	kvm_pmu_cpuid_update(vcpu);
+	return 0;
 }
 
 static int is_efer_nx(void)
@@ -112,8 +122,8 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
 			break;
 		}
 	}
-	if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
-		entry->edx &= ~(1 << 20);
+	if (entry && (entry->edx & bit(X86_FEATURE_NX)) && !is_efer_nx()) {
+		entry->edx &= ~bit(X86_FEATURE_NX);
 		printk(KERN_INFO "kvm: guest NX capability removed\n");
 	}
 }
@@ -151,10 +161,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	}
 	vcpu->arch.cpuid_nent = cpuid->nent;
 	cpuid_fix_nx_cap(vcpu);
-	r = 0;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
-	kvm_update_cpuid(vcpu);
+	r = kvm_update_cpuid(vcpu);
 
 out_free:
 	vfree(cpuid_entries);
@@ -178,9 +187,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 	vcpu->arch.cpuid_nent = cpuid->nent;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
-	kvm_update_cpuid(vcpu);
-	return 0;
-
+	r = kvm_update_cpuid(vcpu);
 out:
 	return r;
 }
@@ -767,6 +774,12 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 	if (!best)
 		best = check_cpuid_limit(vcpu, function, index);
 
+	/*
+	 * Perfmon not yet supported for L2 guest.
+	 */
+	if (is_guest_mode(vcpu) && function == 0xa)
+		best = NULL;
+
 	if (best) {
 		*eax = best->eax;
 		*ebx = best->ebx;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a5380590ab0e..4452eedfaedd 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -3,7 +3,7 @@
 
 #include "x86.h"
 
-void kvm_update_cpuid(struct kvm_vcpu *vcpu);
+int kvm_update_cpuid(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
 int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
@@ -88,6 +88,14 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
 	return best && (best->ecx & bit(X86_FEATURE_X2APIC));
 }
 
+static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0, 0);
+	return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx;
+}
+
 static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 03954f7900f5..a46207a05835 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -527,6 +527,7 @@ static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
 static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec,
 			     u32 error, bool valid)
 {
+	WARN_ON(vec > 0x1f);
 	ctxt->exception.vector = vec;
 	ctxt->exception.error_code = error;
 	ctxt->exception.error_code_valid = valid;
@@ -1468,7 +1469,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		return ret;
 
 	err_code = selector & 0xfffc;
-	err_vec = GP_VECTOR;
+	err_vec = in_task_switch ? TS_VECTOR : GP_VECTOR;
 
 	/* can't load system descriptor into segment selector */
 	if (seg <= VCPU_SREG_GS && !seg_desc.s)
@@ -1503,6 +1504,15 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 			if (rpl > cpl || dpl != cpl)
 				goto exception;
 		}
+		/* in long-mode d/b must be clear if l is set */
+		if (seg_desc.d && seg_desc.l) {
+			u64 efer = 0;
+
+			ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+			if (efer & EFER_LMA)
+				goto exception;
+		}
+
 		/* CS(RPL) <- CPL */
 		selector = (selector & 0xfffc) | cpl;
 		break;
@@ -1549,8 +1559,7 @@ load:
 	ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
 	return X86EMUL_CONTINUE;
 exception:
-	emulate_exception(ctxt, err_vec, err_code, true);
-	return X86EMUL_PROPAGATE_FAULT;
+	return emulate_exception(ctxt, err_vec, err_code, true);
 }
 
 static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
@@ -2723,8 +2732,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	if (!next_tss_desc.p ||
 	    ((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
 	     desc_limit < 0x2b)) {
-		emulate_ts(ctxt, tss_selector & 0xfffc);
-		return X86EMUL_PROPAGATE_FAULT;
+		return emulate_ts(ctxt, tss_selector & 0xfffc);
 	}
 
 	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
@@ -3016,7 +3024,7 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
 		ctxt->dst.val = swab64(ctxt->src.val);
 		break;
 	default:
-		return X86EMUL_PROPAGATE_FAULT;
+		BUG();
 	}
 	return X86EMUL_CONTINUE;
 }
@@ -3140,12 +3148,8 @@ static int em_clts(struct x86_emulate_ctxt *ctxt)
 
 static int em_vmcall(struct x86_emulate_ctxt *ctxt)
 {
-	int rc;
-
-	if (ctxt->modrm_mod != 3 || ctxt->modrm_rm != 1)
-		return X86EMUL_UNHANDLEABLE;
+	int rc = ctxt->ops->fix_hypercall(ctxt);
 
-	rc = ctxt->ops->fix_hypercall(ctxt);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -3563,6 +3567,12 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 		F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
 		F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
 
+static const struct opcode group7_rm0[] = {
+	N,
+	I(SrcNone | Priv | EmulateOnUD,	em_vmcall),
+	N, N, N, N, N, N,
+};
+
 static const struct opcode group7_rm1[] = {
 	DI(SrcNone | Priv, monitor),
 	DI(SrcNone | Priv, mwait),
@@ -3656,7 +3666,7 @@ static const struct group_dual group7 = { {
 	II(SrcMem16 | Mov | Priv,		em_lmsw, lmsw),
 	II(SrcMem | ByteOp | Priv | NoAccess,	em_invlpg, invlpg),
 }, {
-	I(SrcNone | Priv | EmulateOnUD,	em_vmcall),
+	EXT(0, group7_rm0),
 	EXT(0, group7_rm1),
 	N, EXT(0, group7_rm3),
 	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
@@ -3687,14 +3697,18 @@ static const struct gprefix pfx_0f_6f_0f_7f = {
 	I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
 };
 
-static const struct gprefix pfx_vmovntpx = {
-	I(0, em_mov), N, N, N,
+static const struct gprefix pfx_0f_2b = {
+	I(0, em_mov), I(0, em_mov), N, N,
 };
 
 static const struct gprefix pfx_0f_28_0f_29 = {
 	I(Aligned, em_mov), I(Aligned, em_mov), N, N,
 };
 
+static const struct gprefix pfx_0f_e7 = {
+	N, I(Sse, em_mov), N, N,
+};
+
 static const struct escape escape_d9 = { {
 	N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
 }, {
@@ -3901,7 +3915,7 @@ static const struct opcode twobyte_table[256] = {
 	N, N, N, N,
 	GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
 	GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),
-	N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+	N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b),
 	N, N, N, N,
 	/* 0x30 - 0x3F */
 	II(ImplicitOps | Priv, em_wrmsr, wrmsr),
@@ -3965,7 +3979,8 @@ static const struct opcode twobyte_table[256] = {
 	/* 0xD0 - 0xDF */
 	N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
 	/* 0xE0 - 0xEF */
-	N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
+	N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7),
+	N, N, N, N, N, N, N, N,
 	/* 0xF0 - 0xFF */
 	N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
 };
@@ -4829,8 +4844,10 @@ writeback:
 	ctxt->eip = ctxt->_eip;
 
 done:
-	if (rc == X86EMUL_PROPAGATE_FAULT)
+	if (rc == X86EMUL_PROPAGATE_FAULT) {
+		WARN_ON(ctxt->exception.vector > 0x1f);
 		ctxt->have_exception = true;
+	}
 	if (rc == X86EMUL_INTERCEPTED)
 		return EMULATION_INTERCEPTED;
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 08e8a899e005..b8345dd41b25 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -112,17 +112,6 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
 struct static_key_deferred apic_hw_disabled __read_mostly;
 struct static_key_deferred apic_sw_disabled __read_mostly;
 
-static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
-{
-	if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) {
-		if (val & APIC_SPIV_APIC_ENABLED)
-			static_key_slow_dec_deferred(&apic_sw_disabled);
-		else
-			static_key_slow_inc(&apic_sw_disabled.key);
-	}
-	apic_set_reg(apic, APIC_SPIV, val);
-}
-
 static inline int apic_enabled(struct kvm_lapic *apic)
 {
 	return kvm_apic_sw_enabled(apic) &&	kvm_apic_hw_enabled(apic);
@@ -210,6 +199,20 @@ out:
 	kvm_vcpu_request_scan_ioapic(kvm);
 }
 
+static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
+{
+	u32 prev = kvm_apic_get_reg(apic, APIC_SPIV);
+
+	apic_set_reg(apic, APIC_SPIV, val);
+	if ((prev ^ val) & APIC_SPIV_APIC_ENABLED) {
+		if (val & APIC_SPIV_APIC_ENABLED) {
+			static_key_slow_dec_deferred(&apic_sw_disabled);
+			recalculate_apic_map(apic->vcpu->kvm);
+		} else
+			static_key_slow_inc(&apic_sw_disabled.key);
+	}
+}
+
 static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
 {
 	apic_set_reg(apic, APIC_ID, id << 24);
@@ -706,6 +709,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	int result = 0;
 	struct kvm_vcpu *vcpu = apic->vcpu;
 
+	trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
+				  trig_mode, vector);
 	switch (delivery_mode) {
 	case APIC_DM_LOWEST:
 		vcpu->arch.apic_arb_prio++;
@@ -727,8 +732,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
-		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
-					  trig_mode, vector, false);
 		break;
 
 	case APIC_DM_REMRD:
@@ -1352,6 +1355,9 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 		return;
 
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	/* Inject here so clearing tscdeadline won't override new value */
+	if (apic_has_pending_timer(vcpu))
+		kvm_inject_apic_timer_irqs(vcpu);
 	apic->lapic_timer.tscdeadline = data;
 	start_apic_timer(apic);
 }
@@ -1639,6 +1645,8 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 
 	if (atomic_read(&apic->lapic_timer.pending) > 0) {
 		kvm_apic_local_deliver(apic, APIC_LVTT);
+		if (apic_lvtt_tscdeadline(apic))
+			apic->lapic_timer.tscdeadline = 0;
 		atomic_set(&apic->lapic_timer.pending, 0);
 	}
 }
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 931467881da7..3201e93ebd07 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -199,16 +199,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
 /*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates.  The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
  */
-#define MMIO_SPTE_GEN_LOW_SHIFT		3
+#define MMIO_SPTE_GEN_LOW_SHIFT		2
 #define MMIO_SPTE_GEN_HIGH_SHIFT	52
 
-#define MMIO_GEN_SHIFT			19
-#define MMIO_GEN_LOW_SHIFT		9
-#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT			20
+#define MMIO_GEN_LOW_SHIFT		10
+#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
 #define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)
 #define MMIO_MAX_GEN			((1 << MMIO_GEN_SHIFT) - 1)
 
@@ -236,12 +240,7 @@ static unsigned int get_mmio_spte_generation(u64 spte)
 
 static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
 {
-	/*
-	 * Init kvm generation close to MMIO_MAX_GEN to easily test the
-	 * code of handling generation number wrap-around.
-	 */
-	return (kvm_memslots(kvm)->generation +
-		      MMIO_MAX_GEN - 150) & MMIO_GEN_MASK;
+	return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
 }
 
 static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
@@ -296,11 +295,6 @@ static bool check_mmio_spte(struct kvm *kvm, u64 spte)
 	return likely(kvm_gen == spte_gen);
 }
 
-static inline u64 rsvd_bits(int s, int e)
-{
-	return ((1ULL << (e - s + 1)) - 1) << s;
-}
-
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask)
 {
@@ -1180,7 +1174,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
  * Write-protect on the specified @sptep, @pt_protect indicates whether
  * spte write-protection is caused by protecting shadow page table.
  *
- * Note: write protection is difference between drity logging and spte
+ * Note: write protection is difference between dirty logging and spte
  * protection:
  * - for dirty logging, the spte can be set to writable at anytime if
  *   its dirty bitmap is properly set.
@@ -1268,7 +1262,8 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 }
 
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			   struct kvm_memory_slot *slot, unsigned long data)
+			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			   unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1276,7 +1271,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	while ((sptep = rmap_get_first(*rmapp, &iter))) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep);
+		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
+			     sptep, *sptep, gfn, level);
 
 		drop_spte(kvm, sptep);
 		need_tlb_flush = 1;
@@ -1286,7 +1282,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			     struct kvm_memory_slot *slot, unsigned long data)
+			     struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			     unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1300,7 +1297,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!is_shadow_present_pte(*sptep));
-		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep);
+		rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
+			     sptep, *sptep, gfn, level);
 
 		need_flush = 1;
 
@@ -1334,6 +1332,8 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 				int (*handler)(struct kvm *kvm,
 					       unsigned long *rmapp,
 					       struct kvm_memory_slot *slot,
+					       gfn_t gfn,
+					       int level,
 					       unsigned long data))
 {
 	int j;
@@ -1363,6 +1363,7 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
 			unsigned long idx, idx_end;
 			unsigned long *rmapp;
+			gfn_t gfn = gfn_start;
 
 			/*
 			 * {idx(page_j) | page_j intersects with
@@ -1373,8 +1374,10 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 
 			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
 
-			for (; idx <= idx_end; ++idx)
-				ret |= handler(kvm, rmapp++, memslot, data);
+			for (; idx <= idx_end;
+			       ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
+				ret |= handler(kvm, rmapp++, memslot,
+					       gfn, j, data);
 		}
 	}
 
@@ -1385,6 +1388,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 			  unsigned long data,
 			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
 					 struct kvm_memory_slot *slot,
+					 gfn_t gfn, int level,
 					 unsigned long data))
 {
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
@@ -1406,24 +1410,14 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			 struct kvm_memory_slot *slot, unsigned long data)
+			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			 unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator uninitialized_var(iter);
 	int young = 0;
 
-	/*
-	 * In case of absence of EPT Access and Dirty Bits supports,
-	 * emulate the accessed bit for EPT, by checking if this page has
-	 * an EPT mapping, and clearing it if it does. On the next access,
-	 * a new EPT mapping will be established.
-	 * This has some overhead, but not as much as the cost of swapping
-	 * out actively used pages or breaking up actively used hugepages.
-	 */
-	if (!shadow_accessed_mask) {
-		young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
-		goto out;
-	}
+	BUG_ON(!shadow_accessed_mask);
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
 	     sptep = rmap_get_next(&iter)) {
@@ -1435,14 +1429,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 				 (unsigned long *)sptep);
 		}
 	}
-out:
-	/* @data has hva passed to kvm_age_hva(). */
-	trace_kvm_age_page(data, slot, young);
+	trace_kvm_age_page(gfn, level, slot, young);
 	return young;
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			      struct kvm_memory_slot *slot, unsigned long data)
+			      struct kvm_memory_slot *slot, gfn_t gfn,
+			      int level, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1480,13 +1473,33 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
+	/*
+	 * In case of absence of EPT Access and Dirty Bits supports,
+	 * emulate the accessed bit for EPT, by checking if this page has
+	 * an EPT mapping, and clearing it if it does. On the next access,
+	 * a new EPT mapping will be established.
+	 * This has some overhead, but not as much as the cost of swapping
+	 * out actively used pages or breaking up actively used hugepages.
+	 */
+	if (!shadow_accessed_mask) {
+		/*
+		 * We are holding the kvm->mmu_lock, and we are blowing up
+		 * shadow PTEs. MMU notifier consumers need to be kept at bay.
+		 * This is correct as long as we don't decouple the mmu_lock
+		 * protected regions (like invalidate_range_start|end does).
+		 */
+		kvm->mmu_notifier_seq++;
+		return kvm_handle_hva_range(kvm, start, end, 0,
+					    kvm_unmap_rmapp);
+	}
+
+	return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
@@ -1749,7 +1762,7 @@ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return 1;
 	}
 
-	kvm_mmu_flush_tlb(vcpu);
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
@@ -1802,7 +1815,7 @@ static void kvm_sync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 	if (flush)
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 struct mmu_page_path {
@@ -2536,7 +2549,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	      true, host_writable)) {
 		if (write_fault)
 			*emulate = 1;
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
 
 	if (unlikely(is_mmio_spte(*sptep) && emulate))
@@ -3163,7 +3176,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	vcpu_clear_mmio_info(vcpu, ~0ul);
+	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 	if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3206,7 +3219,7 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
 {
 	if (exception)
 		exception->error_code = 0;
-	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access);
+	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
 }
 
 static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
@@ -3450,13 +3463,6 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu,
 	context->nx = false;
 }
 
-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);
-
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
 {
 	mmu_free_roots(vcpu);
@@ -3518,6 +3524,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
+	u64 nonleaf_bit8_rsvd = 0;
 
 	context->bad_mt_xwr = 0;
 
@@ -3525,6 +3532,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 		exb_bit_rsvd = rsvd_bits(63, 63);
 	if (!guest_cpuid_has_gbpages(vcpu))
 		gbpages_bit_rsvd = rsvd_bits(7, 7);
+
+	/*
+	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
+	 * leaf entries) on AMD CPUs only.
+	 */
+	if (guest_cpuid_is_amd(vcpu))
+		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
+
 	switch (context->root_level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
@@ -3559,9 +3574,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 		break;
 	case PT64_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
+			nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
+			nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
@@ -3962,7 +3977,7 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
 	if (remote_flush)
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	else if (local_flush)
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
@@ -4223,7 +4238,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	vcpu->arch.mmu.invlpg(vcpu, gva);
-	kvm_mmu_flush_tlb(vcpu);
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -4433,7 +4448,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
+	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
 		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 b982112d2ca5..bde8ee725754 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -56,6 +56,11 @@
 #define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
 #define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
 
+static inline u64 rsvd_bits(int s, int e)
+{
+	return ((1ULL << (e - s + 1)) - 1) << s;
+}
+
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 410776528265..806d58e3c320 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -298,8 +298,7 @@ retry_walk:
 	}
 #endif
 	walker->max_level = walker->level;
-	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
-	       (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
+	ASSERT(!is_long_mode(vcpu) && is_pae(vcpu));
 
 	accessed_dirty = PT_GUEST_ACCESSED_MASK;
 	pt_access = pte_access = ACC_ALL;
@@ -321,9 +320,22 @@ retry_walk:
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
 		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
-					      PFERR_USER_MASK|PFERR_WRITE_MASK);
+					      PFERR_USER_MASK|PFERR_WRITE_MASK,
+					      &walker->fault);
+
+		/*
+		 * FIXME: This can happen if emulation (for of an INS/OUTS
+		 * instruction) triggers a nested page fault.  The exit
+		 * qualification / exit info field will incorrectly have
+		 * "guest page access" as the nested page fault's cause,
+		 * instead of "guest page structure access".  To fix this,
+		 * the x86_exception struct should be augmented with enough
+		 * information to fix the exit_qualification or exit_info_1
+		 * fields.
+		 */
 		if (unlikely(real_gfn == UNMAPPED_GVA))
-			goto error;
+			return 0;
+
 		real_gfn = gpa_to_gfn(real_gfn);
 
 		host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
@@ -364,7 +376,7 @@ retry_walk:
 	if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
 		gfn += pse36_gfn_delta(pte);
 
-	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
 	if (real_gpa == UNMAPPED_GVA)
 		return 0;
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 3dd6accb64ec..8e6b7d869d2f 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <asm/perf_event.h>
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
@@ -463,7 +464,8 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_cpuid_entry2 *entry;
-	unsigned bitmap_len;
+	union cpuid10_eax eax;
+	union cpuid10_edx edx;
 
 	pmu->nr_arch_gp_counters = 0;
 	pmu->nr_arch_fixed_counters = 0;
@@ -475,25 +477,27 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
 		return;
+	eax.full = entry->eax;
+	edx.full = entry->edx;
 
-	pmu->version = entry->eax & 0xff;
+	pmu->version = eax.split.version_id;
 	if (!pmu->version)
 		return;
 
-	pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff,
-			INTEL_PMC_MAX_GENERIC);
-	pmu->counter_bitmask[KVM_PMC_GP] =
-		((u64)1 << ((entry->eax >> 16) & 0xff)) - 1;
-	bitmap_len = (entry->eax >> 24) & 0xff;
-	pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
+	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
+					INTEL_PMC_MAX_GENERIC);
+	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+	pmu->available_event_types = ~entry->ebx &
+					((1ull << eax.split.mask_length) - 1);
 
 	if (pmu->version == 1) {
 		pmu->nr_arch_fixed_counters = 0;
 	} else {
-		pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
+		pmu->nr_arch_fixed_counters =
+			min_t(int, edx.split.num_counters_fixed,
 				INTEL_PMC_MAX_FIXED);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
-			((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
+			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
 	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ddf742768ecf..f7f6a4a157a6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -622,7 +622,7 @@ static int has_svm(void)
 	return 1;
 }
 
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -633,7 +633,7 @@ static void svm_hardware_disable(void *garbage)
 	amd_pmu_disable_virt();
 }
 
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
 {
 
 	struct svm_cpu_data *sd;
@@ -1257,7 +1257,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
-	svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+	svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+				   MSR_IA32_APICBASE_ENABLE;
 	if (kvm_vcpu_is_bsp(&svm->vcpu))
 		svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
 
@@ -1974,10 +1975,26 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->control.exit_code = SVM_EXIT_NPF;
-	svm->vmcb->control.exit_code_hi = 0;
-	svm->vmcb->control.exit_info_1 = fault->error_code;
-	svm->vmcb->control.exit_info_2 = fault->address;
+	if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) {
+		/*
+		 * TODO: track the cause of the nested page fault, and
+		 * correctly fill in the high bits of exit_info_1.
+		 */
+		svm->vmcb->control.exit_code = SVM_EXIT_NPF;
+		svm->vmcb->control.exit_code_hi = 0;
+		svm->vmcb->control.exit_info_1 = (1ULL << 32);
+		svm->vmcb->control.exit_info_2 = fault->address;
+	}
+
+	svm->vmcb->control.exit_info_1 &= ~0xffffffffULL;
+	svm->vmcb->control.exit_info_1 |= fault->error_code;
+
+	/*
+	 * The present bit is always zero for page structure faults on real
+	 * hardware.
+	 */
+	if (svm->vmcb->control.exit_info_1 & (2ULL << 32))
+		svm->vmcb->control.exit_info_1 &= ~1;
 
 	nested_svm_vmexit(svm);
 }
@@ -3031,7 +3048,7 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	return 0;
 }
 
-u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
 	struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
 	return vmcb->control.tsc_offset +
@@ -4305,6 +4322,10 @@ static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 }
 
+static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -4349,7 +4370,6 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
-	.fpu_activate = svm_fpu_activate,
 	.fpu_deactivate = svm_fpu_deactivate,
 
 	.tlb_flush = svm_flush_tlb,
@@ -4406,6 +4426,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 
 	.check_intercept = svm_check_intercept,
 	.handle_external_intr = svm_handle_external_intr,
+
+	.sched_in = svm_sched_in,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index e850a7d332be..6b06ab8748dd 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -415,15 +415,14 @@ TRACE_EVENT(kvm_apic_ipi,
 );
 
 TRACE_EVENT(kvm_apic_accept_irq,
-	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced),
-	    TP_ARGS(apicid, dm, tm, vec, coalesced),
+	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+	    TP_ARGS(apicid, dm, tm, vec),
 
 	TP_STRUCT__entry(
 		__field(	__u32,		apicid		)
 		__field(	__u16,		dm		)
 		__field(	__u8,		tm		)
 		__field(	__u8,		vec		)
-		__field(	bool,		coalesced	)
 	),
 
 	TP_fast_assign(
@@ -431,14 +430,12 @@ TRACE_EVENT(kvm_apic_accept_irq,
 		__entry->dm		= dm;
 		__entry->tm		= tm;
 		__entry->vec		= vec;
-		__entry->coalesced	= coalesced;
 	),
 
-	TP_printk("apicid %x vec %u (%s|%s)%s",
+	TP_printk("apicid %x vec %u (%s|%s)",
 		  __entry->apicid, __entry->vec,
 		  __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode),
-		  __entry->tm ? "level" : "edge",
-		  __entry->coalesced ? " (coalesced)" : "")
+		  __entry->tm ? "level" : "edge")
 );
 
 TRACE_EVENT(kvm_eoi,
@@ -850,6 +847,36 @@ TRACE_EVENT(kvm_track_tsc,
 
 #endif /* CONFIG_X86_64 */
 
+TRACE_EVENT(kvm_ple_window,
+	TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
+	TP_ARGS(grow, vcpu_id, new, old),
+
+	TP_STRUCT__entry(
+		__field(                bool,      grow         )
+		__field(        unsigned int,   vcpu_id         )
+		__field(                 int,       new         )
+		__field(                 int,       old         )
+	),
+
+	TP_fast_assign(
+		__entry->grow           = grow;
+		__entry->vcpu_id        = vcpu_id;
+		__entry->new            = new;
+		__entry->old            = old;
+	),
+
+	TP_printk("vcpu %u: ple_window %d (%s %d)",
+	          __entry->vcpu_id,
+	          __entry->new,
+	          __entry->grow ? "grow" : "shrink",
+	          __entry->old)
+);
+
+#define trace_kvm_ple_window_grow(vcpu_id, new, old) \
+	trace_kvm_ple_window(true, vcpu_id, new, old)
+#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \
+	trace_kvm_ple_window(false, vcpu_id, new, old)
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe11cf124a1..04fa1b8298c8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -125,14 +125,32 @@ module_param(nested, bool, S_IRUGO);
  * Time is measured based on a counter that runs at the same rate as the TSC,
  * refer SDM volume 3b section 21.6.13 & 22.1.3.
  */
-#define KVM_VMX_DEFAULT_PLE_GAP    128
-#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+#define KVM_VMX_DEFAULT_PLE_GAP           128
+#define KVM_VMX_DEFAULT_PLE_WINDOW        4096
+#define KVM_VMX_DEFAULT_PLE_WINDOW_GROW   2
+#define KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK 0
+#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX    \
+		INT_MAX / KVM_VMX_DEFAULT_PLE_WINDOW_GROW
+
 static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
 module_param(ple_gap, int, S_IRUGO);
 
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
+/* Default doubles per-vcpu window every exit. */
+static int ple_window_grow = KVM_VMX_DEFAULT_PLE_WINDOW_GROW;
+module_param(ple_window_grow, int, S_IRUGO);
+
+/* Default resets per-vcpu window every exit to ple_window. */
+static int ple_window_shrink = KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK;
+module_param(ple_window_shrink, int, S_IRUGO);
+
+/* Default is to compute the maximum so we can never overflow. */
+static int ple_window_actual_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
+static int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
+module_param(ple_window_max, int, S_IRUGO);
+
 extern const ulong vmx_return;
 
 #define NR_AUTOLOAD_MSRS 8
@@ -379,6 +397,7 @@ struct nested_vmx {
 	 * we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
+	struct page *virtual_apic_page;
 	u64 msr_ia32_feature_control;
 
 	struct hrtimer preemption_timer;
@@ -484,6 +503,10 @@ struct vcpu_vmx {
 
 	/* Support for a guest hypervisor (nested VMX) */
 	struct nested_vmx nested;
+
+	/* Dynamic PLE window. */
+	int ple_window;
+	bool ple_window_dirty;
 };
 
 enum segment_cache_field {
@@ -533,6 +556,7 @@ static int max_shadow_read_only_fields =
 	ARRAY_SIZE(shadow_read_only_fields);
 
 static unsigned long shadow_read_write_fields[] = {
+	TPR_THRESHOLD,
 	GUEST_RIP,
 	GUEST_RSP,
 	GUEST_CR0,
@@ -743,6 +767,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
+static int alloc_identity_pagetable(struct kvm *kvm);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2135,7 +2160,7 @@ static u64 guest_read_tsc(void)
  * Like guest_read_tsc, but always returns L1's notion of the timestamp
  * counter, even if a nested guest (L2) is currently running.
  */
-u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
 	u64 tsc_offset;
 
@@ -2330,7 +2355,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
 		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
 		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
-		CPU_BASED_PAUSE_EXITING |
+		CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
 		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
@@ -2601,6 +2626,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+				return 1;
 			vmcs_write64(GUEST_IA32_PAT, data);
 			vcpu->arch.pat = data;
 			break;
@@ -2704,7 +2731,7 @@ static void kvm_cpu_vmxon(u64 addr)
 			: "memory", "cc");
 }
 
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2768,7 +2795,7 @@ static void kvm_cpu_vmxoff(void)
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
 }
 
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
 {
 	if (vmm_exclusive) {
 		vmclear_local_loaded_vmcss();
@@ -3107,9 +3134,17 @@ static __init int hardware_setup(void)
 	if (!cpu_has_vmx_unrestricted_guest())
 		enable_unrestricted_guest = 0;
 
-	if (!cpu_has_vmx_flexpriority())
+	if (!cpu_has_vmx_flexpriority()) {
 		flexpriority_enabled = 0;
 
+		/*
+		 * set_apic_access_page_addr() is used to reload apic access
+		 * page upon invalidation.  No need to do anything if the
+		 * processor does not have the APIC_ACCESS_ADDR VMCS field.
+		 */
+		kvm_x86_ops->set_apic_access_page_addr = NULL;
+	}
+
 	if (!cpu_has_vmx_tpr_shadow())
 		kvm_x86_ops->update_cr8_intercept = NULL;
 
@@ -3905,7 +3940,7 @@ static int init_rmode_tss(struct kvm *kvm)
 {
 	gfn_t fn;
 	u16 data = 0;
-	int r, idx, ret = 0;
+	int idx, r;
 
 	idx = srcu_read_lock(&kvm->srcu);
 	fn = kvm->arch.tss_addr >> PAGE_SHIFT;
@@ -3927,32 +3962,32 @@ static int init_rmode_tss(struct kvm *kvm)
 	r = kvm_write_guest_page(kvm, fn, &data,
 				 RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
 				 sizeof(u8));
-	if (r < 0)
-		goto out;
-
-	ret = 1;
 out:
 	srcu_read_unlock(&kvm->srcu, idx);
-	return ret;
+	return r;
 }
 
 static int init_rmode_identity_map(struct kvm *kvm)
 {
-	int i, idx, r, ret;
+	int i, idx, r = 0;
 	pfn_t identity_map_pfn;
 	u32 tmp;
 
 	if (!enable_ept)
-		return 1;
-	if (unlikely(!kvm->arch.ept_identity_pagetable)) {
-		printk(KERN_ERR "EPT: identity-mapping pagetable "
-			"haven't been allocated!\n");
 		return 0;
-	}
+
+	/* Protect kvm->arch.ept_identity_pagetable_done. */
+	mutex_lock(&kvm->slots_lock);
+
 	if (likely(kvm->arch.ept_identity_pagetable_done))
-		return 1;
-	ret = 0;
+		goto out2;
+
 	identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;
+
+	r = alloc_identity_pagetable(kvm);
+	if (r < 0)
+		goto out2;
+
 	idx = srcu_read_lock(&kvm->srcu);
 	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
 	if (r < 0)
@@ -3967,10 +4002,13 @@ static int init_rmode_identity_map(struct kvm *kvm)
 			goto out;
 	}
 	kvm->arch.ept_identity_pagetable_done = true;
-	ret = 1;
+
 out:
 	srcu_read_unlock(&kvm->srcu, idx);
-	return ret;
+
+out2:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
 }
 
 static void seg_setup(int seg)
@@ -3995,23 +4033,28 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	int r = 0;
 
 	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.apic_access_page)
+	if (kvm->arch.apic_access_page_done)
 		goto out;
 	kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
 	kvm_userspace_mem.flags = 0;
-	kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
+	kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
 	kvm_userspace_mem.memory_size = PAGE_SIZE;
 	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
 	if (r)
 		goto out;
 
-	page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
 	if (is_error_page(page)) {
 		r = -EFAULT;
 		goto out;
 	}
 
-	kvm->arch.apic_access_page = page;
+	/*
+	 * Do not pin the page in memory, so that memory hot-unplug
+	 * is able to migrate it.
+	 */
+	put_page(page);
+	kvm->arch.apic_access_page_done = true;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -4019,31 +4062,20 @@ out:
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
-	struct page *page;
+	/* Called with kvm->slots_lock held. */
+
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
-	mutex_lock(&kvm->slots_lock);
-	if (kvm->arch.ept_identity_pagetable)
-		goto out;
+	BUG_ON(kvm->arch.ept_identity_pagetable_done);
+
 	kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
 	kvm_userspace_mem.flags = 0;
 	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);
-	if (r)
-		goto out;
-
-	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		r = -EFAULT;
-		goto out;
-	}
 
-	kvm->arch.ept_identity_pagetable = page;
-out:
-	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
@@ -4402,7 +4434,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	if (ple_gap) {
 		vmcs_write32(PLE_GAP, ple_gap);
-		vmcs_write32(PLE_WINDOW, ple_window);
+		vmx->ple_window = ple_window;
+		vmx->ple_window_dirty = true;
 	}
 
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
@@ -4477,7 +4510,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	kvm_set_cr8(&vmx->vcpu, 0);
-	apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+	apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 	if (kvm_vcpu_is_bsp(&vmx->vcpu))
 		apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
 	apic_base_msr.host_initiated = true;
@@ -4537,9 +4570,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		vmcs_write32(TPR_THRESHOLD, 0);
 	}
 
-	if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
-		vmcs_write64(APIC_ACCESS_ADDR,
-			     page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
+	kvm_vcpu_reload_apic_access_page(vcpu);
 
 	if (vmx_vm_has_apicv(vcpu->kvm))
 		memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
@@ -4729,10 +4760,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	if (ret)
 		return ret;
 	kvm->arch.tss_addr = addr;
-	if (!init_rmode_tss(kvm))
-		return  -ENOMEM;
-
-	return 0;
+	return init_rmode_tss(kvm);
 }
 
 static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
@@ -5521,17 +5549,18 @@ static u64 ept_rsvd_mask(u64 spte, int level)
 	for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
 		mask |= (1ULL << i);
 
-	if (level > 2)
+	if (level == 4)
 		/* bits 7:3 reserved */
 		mask |= 0xf8;
-	else if (level == 2) {
-		if (spte & (1ULL << 7))
-			/* 2MB ref, bits 20:12 reserved */
-			mask |= 0x1ff000;
-		else
-			/* bits 6:3 reserved */
-			mask |= 0x78;
-	}
+	else if (spte & (1ULL << 7))
+		/*
+		 * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively,
+		 * level == 1 if the hypervisor is using the ignored bit 7.
+		 */
+		mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE;
+	else if (level > 1)
+		/* bits 6:3 reserved */
+		mask |= 0x78;
 
 	return mask;
 }
@@ -5561,7 +5590,8 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
 			WARN_ON(1);
 		}
 
-		if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
+		/* bits 5:3 are _not_ reserved for large page or leaf page */
+		if ((rsvd_bits & 0x38) == 0) {
 			u64 ept_mem_type = (spte & 0x38) >> 3;
 
 			if (ept_mem_type == 2 || ept_mem_type == 3 ||
@@ -5676,12 +5706,85 @@ out:
 	return ret;
 }
 
+static int __grow_ple_window(int val)
+{
+	if (ple_window_grow < 1)
+		return ple_window;
+
+	val = min(val, ple_window_actual_max);
+
+	if (ple_window_grow < ple_window)
+		val *= ple_window_grow;
+	else
+		val += ple_window_grow;
+
+	return val;
+}
+
+static int __shrink_ple_window(int val, int modifier, int minimum)
+{
+	if (modifier < 1)
+		return ple_window;
+
+	if (modifier < ple_window)
+		val /= modifier;
+	else
+		val -= modifier;
+
+	return max(val, minimum);
+}
+
+static void grow_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int old = vmx->ple_window;
+
+	vmx->ple_window = __grow_ple_window(old);
+
+	if (vmx->ple_window != old)
+		vmx->ple_window_dirty = true;
+
+	trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old);
+}
+
+static void shrink_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int old = vmx->ple_window;
+
+	vmx->ple_window = __shrink_ple_window(old,
+	                                      ple_window_shrink, ple_window);
+
+	if (vmx->ple_window != old)
+		vmx->ple_window_dirty = true;
+
+	trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old);
+}
+
+/*
+ * ple_window_actual_max is computed to be one grow_ple_window() below
+ * ple_window_max. (See __grow_ple_window for the reason.)
+ * This prevents overflows, because ple_window_max is int.
+ * ple_window_max effectively rounded down to a multiple of ple_window_grow in
+ * this process.
+ * ple_window_max is also prevented from setting vmx->ple_window < ple_window.
+ */
+static void update_ple_window_actual_max(void)
+{
+	ple_window_actual_max =
+			__shrink_ple_window(max(ple_window_max, ple_window),
+			                    ple_window_grow, INT_MIN);
+}
+
 /*
  * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
  * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
  */
 static int handle_pause(struct kvm_vcpu *vcpu)
 {
+	if (ple_gap)
+		grow_ple_window(vcpu);
+
 	skip_emulated_instruction(vcpu);
 	kvm_vcpu_on_spin(vcpu);
 
@@ -6146,7 +6249,11 @@ static void free_nested(struct vcpu_vmx *vmx)
 	/* Unpin physical memory we referred to in current vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
-		vmx->nested.apic_access_page = 0;
+		vmx->nested.apic_access_page = NULL;
+	}
+	if (vmx->nested.virtual_apic_page) {
+		nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page = NULL;
 	}
 
 	nested_free_all_saved_vmcss(vmx);
@@ -6617,7 +6724,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	switch (type) {
 	case VMX_EPT_EXTENT_GLOBAL:
 		kvm_mmu_sync_roots(vcpu);
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
@@ -6892,6 +6999,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_TASK_SWITCH:
 		return 1;
 	case EXIT_REASON_CPUID:
+		if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
+			return 0;
 		return 1;
 	case EXIT_REASON_HLT:
 		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
@@ -6936,7 +7045,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_MCE_DURING_VMENTRY:
 		return 0;
 	case EXIT_REASON_TPR_BELOW_THRESHOLD:
-		return 1;
+		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
 	case EXIT_REASON_APIC_ACCESS:
 		return nested_cpu_has2(vmcs12,
 			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
@@ -7057,6 +7166,12 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (is_guest_mode(vcpu) &&
+		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return;
+
 	if (irr == -1 || tpr < irr) {
 		vmcs_write32(TPR_THRESHOLD, 0);
 		return;
@@ -7094,6 +7209,29 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	vmx_set_msr_bitmap(vcpu);
 }
 
+static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * Currently we do not handle the nested case where L2 has an
+	 * APIC access page of its own; that page is still pinned.
+	 * Hence, we skip the case where the VCPU is in guest mode _and_
+	 * L1 prepared an APIC access page for L2.
+	 *
+	 * For the case where L1 and L2 share the same APIC access page
+	 * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear
+	 * in the vmcs12), this function will only update either the vmcs01
+	 * or the vmcs02.  If the former, the vmcs02 will be updated by
+	 * prepare_vmcs02.  If the latter, the vmcs01 will be updated in
+	 * the next L2->L1 exit.
+	 */
+	if (!is_guest_mode(vcpu) ||
+	    !nested_cpu_has2(vmx->nested.current_vmcs12,
+			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+		vmcs_write64(APIC_ACCESS_ADDR, hpa);
+}
+
 static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
 {
 	u16 status;
@@ -7387,6 +7525,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return;
 
+	if (vmx->ple_window_dirty) {
+		vmx->ple_window_dirty = false;
+		vmcs_write32(PLE_WINDOW, vmx->ple_window);
+	}
+
 	if (vmx->nested.sync_shadow_vmcs) {
 		copy_vmcs12_to_shadow(vmx);
 		vmx->nested.sync_shadow_vmcs = false;
@@ -7642,10 +7785,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 		if (!kvm->arch.ept_identity_map_addr)
 			kvm->arch.ept_identity_map_addr =
 				VMX_EPT_IDENTITY_PAGETABLE_ADDR;
-		err = -ENOMEM;
-		if (alloc_identity_pagetable(kvm) != 0)
-			goto free_vmcs;
-		if (!init_rmode_identity_map(kvm))
+		err = init_rmode_identity_map(kvm);
+		if (err)
 			goto free_vmcs;
 	}
 
@@ -7824,6 +7965,55 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 		kvm_inject_page_fault(vcpu, fault);
 }
 
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
+					struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		/* TODO: Also verify bits beyond physical address width are 0 */
+		if (!PAGE_ALIGNED(vmcs12->apic_access_addr))
+			return false;
+
+		/*
+		 * Translate L1 physical address to host physical
+		 * address for vmcs02. Keep the page pinned, so this
+		 * physical address remains valid. We keep a reference
+		 * to it so we can release it later.
+		 */
+		if (vmx->nested.apic_access_page) /* shouldn't happen */
+			nested_release_page(vmx->nested.apic_access_page);
+		vmx->nested.apic_access_page =
+			nested_get_page(vcpu, vmcs12->apic_access_addr);
+	}
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		/* TODO: Also verify bits beyond physical address width are 0 */
+		if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr))
+			return false;
+
+		if (vmx->nested.virtual_apic_page) /* shouldn't happen */
+			nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page =
+			nested_get_page(vcpu, vmcs12->virtual_apic_page_addr);
+
+		/*
+		 * Failing the vm entry is _not_ what the processor does
+		 * but it's basically the only possibility we have.
+		 * We could still enter the guest if CR8 load exits are
+		 * enabled, CR8 store exits are enabled, and virtualize APIC
+		 * access is disabled; in this case the processor would never
+		 * use the TPR shadow and we could simply clear the bit from
+		 * the execution control.  But such a configuration is useless,
+		 * so let's keep the code simple.
+		 */
+		if (!vmx->nested.virtual_apic_page)
+			return false;
+	}
+
+	return true;
+}
+
 static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
 {
 	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
@@ -7849,7 +8039,7 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
 /*
  * 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
- * with L0's requirements for its guest (a.k.a. vmsc01), so we can run the L2
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
  * guest in a way that will both be appropriate to L1's requests, and our
  * needs. In addition to modifying the active vmcs (which is vmcs02), this
  * function also has additional necessary side-effects, like setting various
@@ -7970,16 +8160,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 		if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) {
 			/*
-			 * Translate L1 physical address to host physical
-			 * address for vmcs02. Keep the page pinned, so this
-			 * physical address remains valid. We keep a reference
-			 * to it so we can release it later.
-			 */
-			if (vmx->nested.apic_access_page) /* shouldn't happen */
-				nested_release_page(vmx->nested.apic_access_page);
-			vmx->nested.apic_access_page =
-				nested_get_page(vcpu, vmcs12->apic_access_addr);
-			/*
 			 * If translation failed, no matter: This feature asks
 			 * to exit when accessing the given address, and if it
 			 * can never be accessed, this feature won't do
@@ -7994,8 +8174,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		} else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) {
 			exec_control |=
 				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-			vmcs_write64(APIC_ACCESS_ADDR,
-				page_to_phys(vcpu->kvm->arch.apic_access_page));
+			kvm_vcpu_reload_apic_access_page(vcpu);
 		}
 
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
@@ -8024,6 +8203,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+	if (exec_control & CPU_BASED_TPR_SHADOW) {
+		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+				page_to_phys(vmx->nested.virtual_apic_page));
+		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+	}
+
 	/*
 	 * Merging of IO and MSR bitmaps not currently supported.
 	 * Rather, exit every time.
@@ -8185,8 +8371,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return 1;
 	}
 
-	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
-			!PAGE_ALIGNED(vmcs12->apic_access_addr)) {
+	if (!nested_get_vmcs12_pages(vcpu, vmcs12)) {
 		/*TODO: Also verify bits beyond physical address width are 0*/
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 		return 1;
@@ -8790,10 +8975,20 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	/* Unpin physical memory we referred to in vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
-		vmx->nested.apic_access_page = 0;
+		vmx->nested.apic_access_page = NULL;
+	}
+	if (vmx->nested.virtual_apic_page) {
+		nested_release_page(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page = NULL;
 	}
 
 	/*
+	 * We are now running in L2, mmu_notifier will force to reload the
+	 * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
+	 */
+	kvm_vcpu_reload_apic_access_page(vcpu);
+
+	/*
 	 * Exiting from L2 to L1, we're now back to L1 which thinks it just
 	 * finished a VMLAUNCH or VMRESUME instruction, so we need to set the
 	 * success or failure flag accordingly.
@@ -8846,6 +9041,12 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	return X86EMUL_CONTINUE;
 }
 
+static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (ple_gap)
+		shrink_ple_window(vcpu);
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -8890,7 +9091,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
-	.fpu_activate = vmx_fpu_activate,
 	.fpu_deactivate = vmx_fpu_deactivate,
 
 	.tlb_flush = vmx_flush_tlb,
@@ -8913,6 +9113,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
 	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
 	.vm_has_apicv = vmx_vm_has_apicv,
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
@@ -8951,6 +9152,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.mpx_supported = vmx_mpx_supported,
 
 	.check_nested_events = vmx_check_nested_events,
+
+	.sched_in = vmx_sched_in,
 };
 
 static int __init vmx_init(void)
@@ -9065,6 +9268,8 @@ static int __init vmx_init(void)
 	} else
 		kvm_disable_tdp();
 
+	update_ple_window_actual_max();
+
 	return 0;
 
 out7:
@@ -9098,7 +9303,7 @@ static void __exit vmx_exit(void)
 	free_page((unsigned long)vmx_vmread_bitmap);
 
 #ifdef CONFIG_KEXEC
-	rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL);
+	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
 	synchronize_rcu();
 #endif
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f1e22d3b286..5430e4b0af29 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,7 +246,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -408,12 +408,14 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
 
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
 	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
 		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
 	else
 		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+
+	return fault->nested_page_fault;
 }
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -457,11 +459,12 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			    gfn_t ngfn, void *data, int offset, int len,
 			    u32 access)
 {
+	struct x86_exception exception;
 	gfn_t real_gfn;
 	gpa_t ngpa;
 
 	ngpa     = gfn_to_gpa(ngfn);
-	real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
+	real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception);
 	if (real_gfn == UNMAPPED_GVA)
 		return -EFAULT;
 
@@ -726,7 +729,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
 		kvm_mmu_sync_roots(vcpu);
-		kvm_mmu_flush_tlb(vcpu);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		return 0;
 	}
 
@@ -1518,7 +1521,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	pvclock_update_vm_gtod_copy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
 	/* guest entries allowed */
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -1661,7 +1664,7 @@ static void kvmclock_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
 }
@@ -1670,7 +1673,7 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
 {
 	struct kvm *kvm = v->kvm;
 
-	set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+	kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
 	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
 					KVMCLOCK_UPDATE_DELAY);
 }
@@ -1723,9 +1726,10 @@ static bool valid_mtrr_type(unsigned t)
 	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
 }
 
-static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	int i;
+	u64 mask;
 
 	if (!msr_mtrr_valid(msr))
 		return false;
@@ -1747,14 +1751,31 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	}
 
 	/* variable MTRRs */
-	return valid_mtrr_type(data & 0xff);
+	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
+
+	mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	if ((msr & 1) == 0) {
+		/* MTRR base */
+		if (!valid_mtrr_type(data & 0xff))
+			return false;
+		mask |= 0xf00;
+	} else
+		/* MTRR mask */
+		mask |= 0x7ff;
+	if (data & mask) {
+		kvm_inject_gp(vcpu, 0);
+		return false;
+	}
+
+	return true;
 }
+EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
 
 static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
 
-	if (!mtrr_valid(vcpu, msr, data))
+	if (!kvm_mtrr_valid(vcpu, msr, data))
 		return 1;
 
 	if (msr == MSR_MTRRdefType) {
@@ -1805,7 +1826,7 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
-		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+		    msr < MSR_IA32_MCx_CTL(bank_num)) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
@@ -2164,7 +2185,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
-	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return set_msr_mce(vcpu, msr, data);
 
 	/* Performance counters are not protected by a CPUID bit,
@@ -2330,7 +2351,7 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		break;
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
-		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+		    msr < MSR_IA32_MCx_CTL(bank_num)) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
 			data = vcpu->arch.mce_banks[offset];
 			break;
@@ -2419,7 +2440,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K7_EVNTSEL0:
+	case MSR_K7_EVNTSEL1:
+	case MSR_K7_EVNTSEL2:
+	case MSR_K7_EVNTSEL3:
 	case MSR_K7_PERFCTR0:
+	case MSR_K7_PERFCTR1:
+	case MSR_K7_PERFCTR2:
+	case MSR_K7_PERFCTR3:
 	case MSR_K8_INT_PENDING_MSG:
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
@@ -2505,7 +2532,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_CAP:
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
-	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr, pdata);
 	case MSR_K7_CLK_CTL:
 		/*
@@ -2823,7 +2850,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
 		vcpu->arch.tsc_offset_adjustment = 0;
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	}
 
 	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
@@ -4040,16 +4067,16 @@ void kvm_get_segment(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->get_segment(vcpu, var, seg);
 }
 
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+			   struct x86_exception *exception)
 {
 	gpa_t t_gpa;
-	struct x86_exception exception;
 
 	BUG_ON(!mmu_is_nested(vcpu));
 
 	/* NPT walks are always user-walks */
 	access |= PFERR_USER_MASK;
-	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
+	t_gpa  = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
 
 	return t_gpa;
 }
@@ -4906,16 +4933,18 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 	}
 }
 
-static void inject_emulated_exception(struct kvm_vcpu *vcpu)
+static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	if (ctxt->exception.vector == PF_VECTOR)
-		kvm_propagate_fault(vcpu, &ctxt->exception);
-	else if (ctxt->exception.error_code_valid)
+		return kvm_propagate_fault(vcpu, &ctxt->exception);
+
+	if (ctxt->exception.error_code_valid)
 		kvm_queue_exception_e(vcpu, ctxt->exception.vector,
 				      ctxt->exception.error_code);
 	else
 		kvm_queue_exception(vcpu, ctxt->exception.vector);
+	return false;
 }
 
 static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -4972,7 +5001,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
-	if (!is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
@@ -5224,6 +5253,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 		ctxt->interruptibility = 0;
 		ctxt->have_exception = false;
+		ctxt->exception.vector = -1;
 		ctxt->perm_ok = false;
 
 		ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
@@ -5276,8 +5306,9 @@ restart:
 	}
 
 	if (ctxt->have_exception) {
-		inject_emulated_exception(vcpu);
 		r = EMULATE_DONE;
+		if (inject_emulated_exception(vcpu))
+			return r;
 	} else if (vcpu->arch.pio.count) {
 		if (!vcpu->arch.pio.in) {
 			/* FIXME: return into emulator if single-stepping.  */
@@ -5545,7 +5576,7 @@ static void kvm_set_mmio_spte_mask(void)
 	 * entry to generate page fault with PFER.RSV = 1.
 	 */
 	 /* Mask the reserved physical address bits. */
-	mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr;
+	mask = rsvd_bits(maxphyaddr, 51);
 
 	/* Bit 62 is always reserved for 32bit host. */
 	mask |= 0x3ull << 62;
@@ -5576,7 +5607,7 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
-			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
+			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 	atomic_set(&kvm_guest_has_master_clock, 0);
 	spin_unlock(&kvm_lock);
 }
@@ -5989,6 +6020,44 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	kvm_apic_update_tmr(vcpu, tmr);
 }
 
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	kvm_x86_ops->tlb_flush(vcpu);
+}
+
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+{
+	struct page *page = NULL;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return;
+
+	if (!kvm_x86_ops->set_apic_access_page_addr)
+		return;
+
+	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
+
+	/*
+	 * Do not pin apic access page in memory, the MMU notifier
+	 * will call us again if it is migrated or swapped out.
+	 */
+	put_page(page);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+					   unsigned long address)
+{
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 /*
  * Returns 1 to let __vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -6018,7 +6087,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
 			kvm_mmu_sync_roots(vcpu);
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			kvm_x86_ops->tlb_flush(vcpu);
+			kvm_vcpu_flush_tlb(vcpu);
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
@@ -6049,6 +6118,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
 			vcpu_scan_ioapic(vcpu);
+		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
+			kvm_vcpu_reload_apic_access_page(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -6934,7 +7005,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
 	kvm_rip_write(vcpu, 0);
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -6945,7 +7016,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	ret = kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable();
 	if (ret != 0)
 		return ret;
 
@@ -6954,7 +7025,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (!stable && vcpu->cpu == smp_processor_id())
-				set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			if (stable && vcpu->arch.last_host_tsc > local_tsc) {
 				backwards_tsc = true;
 				if (vcpu->arch.last_host_tsc > max_tsc)
@@ -7008,8 +7079,7 @@ int kvm_arch_hardware_enable(void *garbage)
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;
 				vcpu->arch.last_host_tsc = local_tsc;
-				set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
-					&vcpu->requests);
+				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 			}
 
 			/*
@@ -7026,10 +7096,10 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
-	kvm_x86_ops->hardware_disable(garbage);
-	drop_user_return_notifiers(garbage);
+	kvm_x86_ops->hardware_disable();
+	drop_user_return_notifiers();
 }
 
 int kvm_arch_hardware_setup(void)
@@ -7146,6 +7216,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvm_x86_ops->sched_in(vcpu, cpu);
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	if (type)
@@ -7237,10 +7312,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
-	if (kvm->arch.apic_access_page)
-		put_page(kvm->arch.apic_access_page);
-	if (kvm->arch.ept_identity_pagetable)
-		put_page(kvm->arch.ept_identity_pagetable);
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
@@ -7643,3 +7714,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 306a1b77581f..7cb9c45a5fe0 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -88,15 +88,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmio_gva = gva & PAGE_MASK;
 	vcpu->arch.access = access;
 	vcpu->arch.mmio_gfn = gfn;
+	vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
 }
 
 /*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
  */
+#define MMIO_GVA_ANY (~(gva_t)0)
+
 static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+	if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
 		return;
 
 	vcpu->arch.mmio_gva = 0;
@@ -104,7 +112,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 
 static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 {
-	if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+	      vcpu->arch.mmio_gva == (gva & PAGE_MASK))
 		return true;
 
 	return false;
@@ -112,7 +121,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 
 static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
-	if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+	      vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
 		return true;
 
 	return false;
@@ -149,6 +159,8 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);
 
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+
 #define KVM_SUPPORTED_XCR0     (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
 				| XSTATE_BNDREGS | XSTATE_BNDCSR)
 extern u64 host_xcr0;