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

Pull KVM updates from Paolo Bonzini:
 "At over 200 commits, covering almost all supported architectures, this
  was a pretty active cycle for KVM.  Changes include:

   - a lot of s390 changes: optimizations, support for migration, GDB
     support and more

   - ARM changes are pretty small: support for the PSCI 0.2 hypercall
     interface on both the guest and the host (the latter acked by
     Catalin)

   - initial POWER8 and little-endian host support

   - support for running u-boot on embedded POWER targets

   - pretty large changes to MIPS too, completing the userspace
     interface and improving the handling of virtualized timer hardware

   - for x86, a larger set of changes is scheduled for 3.17.  Still, we
     have a few emulator bugfixes and support for running nested
     fully-virtualized Xen guests (para-virtualized Xen guests have
     always worked).  And some optimizations too.

  The only missing architecture here is ia64.  It's not a coincidence
  that support for KVM on ia64 is scheduled for removal in 3.17"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (203 commits)
  KVM: add missing cleanup_srcu_struct
  KVM: PPC: Book3S PR: Rework SLB switching code
  KVM: PPC: Book3S PR: Use SLB entry 0
  KVM: PPC: Book3S HV: Fix machine check delivery to guest
  KVM: PPC: Book3S HV: Work around POWER8 performance monitor bugs
  KVM: PPC: Book3S HV: Make sure we don't miss dirty pages
  KVM: PPC: Book3S HV: Fix dirty map for hugepages
  KVM: PPC: Book3S HV: Put huge-page HPTEs in rmap chain for base address
  KVM: PPC: Book3S HV: Fix check for running inside guest in global_invalidates()
  KVM: PPC: Book3S: Move KVM_REG_PPC_WORT to an unused register number
  KVM: PPC: Book3S: Add ONE_REG register names that were missed
  KVM: PPC: Add CAP to indicate hcall fixes
  KVM: PPC: MPIC: Reset IRQ source private members
  KVM: PPC: Graciously fail broken LE hypercalls
  PPC: ePAPR: Fix hypercall on LE guest
  KVM: PPC: BOOK3S: Remove open coded make_dsisr in alignment handler
  KVM: PPC: BOOK3S: Always use the saved DAR value
  PPC: KVM: Make NX bit available with magic page
  KVM: PPC: Disable NX for old magic page using guests
  KVM: PPC: BOOK3S: HV: Add mixed page-size support for guest
  ...

13 files changed, 498 insertions, 284 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f47a104a749c..38a0afe83c6b 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -283,6 +283,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
 	/* cpuid 1.ecx */
 	const u32 kvm_supported_word4_x86_features =
+		/* NOTE: MONITOR (and MWAIT) are emulated as NOP,
+		 * but *not* advertised to guests via CPUID ! */
 		F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
 		0 /* DS-CPL, VMX, SMX, EST */ |
 		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
@@ -495,6 +497,13 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->ecx &= kvm_supported_word6_x86_features;
 		cpuid_mask(&entry->ecx, 6);
 		break;
+	case 0x80000007: /* Advanced power management */
+		/* invariant TSC is CPUID.80000007H:EDX[8] */
+		entry->edx &= (1 << 8);
+		/* mask against host */
+		entry->edx &= boot_cpu_data.x86_power;
+		entry->eax = entry->ebx = entry->ecx = 0;
+		break;
 	case 0x80000008: {
 		unsigned g_phys_as = (entry->eax >> 16) & 0xff;
 		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
@@ -525,7 +534,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	case 3: /* Processor serial number */
 	case 5: /* MONITOR/MWAIT */
 	case 6: /* Thermal management */
-	case 0x80000007: /* Advanced power management */
 	case 0xC0000002:
 	case 0xC0000003:
 	case 0xC0000004:
@@ -726,6 +734,7 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
 not_found:
 	return 36;
 }
+EXPORT_SYMBOL_GPL(cpuid_maxphyaddr);
 
 /*
  * If no match is found, check whether we exceed the vCPU's limit
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index eeecbed26ac7..f9087315e0cd 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -88,4 +88,11 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
 	return best && (best->ecx & bit(X86_FEATURE_X2APIC));
 }
 
+static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_GBPAGES));
+}
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 205b17eed93c..e4e833d3d7d7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -161,6 +161,7 @@
 #define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
+#define NoMod	    ((u64)1 << 47)  /* Mod field is ignored */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -1077,7 +1078,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	ctxt->modrm_rm |= (ctxt->modrm & 0x07);
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
-	if (ctxt->modrm_mod == 3) {
+	if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) {
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
 		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
@@ -1324,7 +1325,8 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 		rc->end = n * size;
 	}
 
-	if (ctxt->rep_prefix && !(ctxt->eflags & EFLG_DF)) {
+	if (ctxt->rep_prefix && (ctxt->d & String) &&
+	    !(ctxt->eflags & EFLG_DF)) {
 		ctxt->dst.data = rc->data + rc->pos;
 		ctxt->dst.type = OP_MEM_STR;
 		ctxt->dst.count = (rc->end - rc->pos) / size;
@@ -1409,11 +1411,11 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 }
 
 /* Does not support long mode */
-static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
-				   u16 selector, int seg)
+static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				     u16 selector, int seg, u8 cpl, bool in_task_switch)
 {
 	struct desc_struct seg_desc, old_desc;
-	u8 dpl, rpl, cpl;
+	u8 dpl, rpl;
 	unsigned err_vec = GP_VECTOR;
 	u32 err_code = 0;
 	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
@@ -1441,7 +1443,6 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	}
 
 	rpl = selector & 3;
-	cpl = ctxt->ops->cpl(ctxt);
 
 	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
 	if ((seg == VCPU_SREG_CS
@@ -1486,6 +1487,9 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 			goto exception;
 		break;
 	case VCPU_SREG_CS:
+		if (in_task_switch && rpl != dpl)
+			goto exception;
+
 		if (!(seg_desc.type & 8))
 			goto exception;
 
@@ -1543,6 +1547,13 @@ exception:
 	return X86EMUL_PROPAGATE_FAULT;
 }
 
+static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   u16 selector, int seg)
+{
+	u8 cpl = ctxt->ops->cpl(ctxt);
+	return __load_segment_descriptor(ctxt, selector, seg, cpl, false);
+}
+
 static void write_register_operand(struct operand *op)
 {
 	/* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
@@ -2404,6 +2415,7 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
 				 struct tss_segment_16 *tss)
 {
 	int ret;
+	u8 cpl;
 
 	ctxt->_eip = tss->ip;
 	ctxt->eflags = tss->flag | 2;
@@ -2426,23 +2438,25 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
 	set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS);
 	set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
 
+	cpl = tss->cs & 3;
+
 	/*
 	 * Now load segment descriptors. If fault happens at this stage
 	 * it is handled in a context of new task
 	 */
-	ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR);
+	ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES);
+	ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS);
+	ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS);
+	ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS);
+	ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
@@ -2496,7 +2510,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
 				struct tss_segment_32 *tss)
 {
-	tss->cr3 = ctxt->ops->get_cr(ctxt, 3);
+	/* CR3 and ldt selector are not saved intentionally */
 	tss->eip = ctxt->_eip;
 	tss->eflags = ctxt->eflags;
 	tss->eax = reg_read(ctxt, VCPU_REGS_RAX);
@@ -2514,13 +2528,13 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
 	tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS);
 	tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS);
 	tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS);
-	tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR);
 }
 
 static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 				 struct tss_segment_32 *tss)
 {
 	int ret;
+	u8 cpl;
 
 	if (ctxt->ops->set_cr(ctxt, 3, tss->cr3))
 		return emulate_gp(ctxt, 0);
@@ -2539,7 +2553,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 
 	/*
 	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
+	 * descriptors.  This is important because CPL checks will
+	 * use CS.RPL.
 	 */
 	set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR);
 	set_segment_selector(ctxt, tss->es, VCPU_SREG_ES);
@@ -2553,43 +2568,38 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 	 * If we're switching between Protected Mode and VM86, we need to make
 	 * sure to update the mode before loading the segment descriptors so
 	 * that the selectors are interpreted correctly.
-	 *
-	 * Need to get rflags to the vcpu struct immediately because it
-	 * influences the CPL which is checked at least when loading the segment
-	 * descriptors and when pushing an error code to the new kernel stack.
-	 *
-	 * TODO Introduce a separate ctxt->ops->set_cpl callback
 	 */
-	if (ctxt->eflags & X86_EFLAGS_VM)
+	if (ctxt->eflags & X86_EFLAGS_VM) {
 		ctxt->mode = X86EMUL_MODE_VM86;
-	else
+		cpl = 3;
+	} else {
 		ctxt->mode = X86EMUL_MODE_PROT32;
-
-	ctxt->ops->set_rflags(ctxt, ctxt->eflags);
+		cpl = tss->cs & 3;
+	}
 
 	/*
 	 * Now load segment descriptors. If fault happenes at this stage
 	 * it is handled in a context of new task
 	 */
-	ret = load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR);
+	ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES);
+	ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS);
+	ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS);
+	ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS);
+	ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS);
+	ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
-	ret = load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS);
+	ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, true);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
@@ -2604,6 +2614,8 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 	struct tss_segment_32 tss_seg;
 	int ret;
 	u32 new_tss_base = get_desc_base(new_desc);
+	u32 eip_offset = offsetof(struct tss_segment_32, eip);
+	u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector);
 
 	ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
 			    &ctxt->exception);
@@ -2613,8 +2625,9 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 
 	save_state_to_tss32(ctxt, &tss_seg);
 
-	ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
-			     &ctxt->exception);
+	/* Only GP registers and segment selectors are saved */
+	ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip,
+			     ldt_sel_offset - eip_offset, &ctxt->exception);
 	if (ret != X86EMUL_CONTINUE)
 		/* FIXME: need to provide precise fault address */
 		return ret;
@@ -3386,10 +3399,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
 		ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 		if (efer & EFER_LMA)
 			rsvd = CR3_L_MODE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE)
-			rsvd = CR3_PAE_RESERVED_BITS;
-		else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG)
-			rsvd = CR3_NONPAE_RESERVED_BITS;
 
 		if (new_val & rsvd)
 			return emulate_gp(ctxt, 0);
@@ -3869,10 +3878,12 @@ static const struct opcode twobyte_table[256] = {
 	N, N, N, N, N, N, N, N,
 	D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
 	/* 0x20 - 0x2F */
-	DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
-	DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
-	IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write),
-	IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write),
+	DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read),
+	DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read),
+	IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_cr_write, cr_write,
+						check_cr_write),
+	IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write,
+						check_dr_write),
 	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),
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc874688b..bd0da433e6d7 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -113,6 +113,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
 }
+EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9736529ade08..006911858174 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
 		++apic->isr_count;
 	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 	apic->highest_isr_cache = vec;
 }
 
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
+	/*
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
+	 */
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
+}
+
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
-}
-
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (vector == -1)
 		return -1;
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 813d31038b93..931467881da7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -22,6 +22,7 @@
 #include "mmu.h"
 #include "x86.h"
 #include "kvm_cache_regs.h"
+#include "cpuid.h"
 
 #include <linux/kvm_host.h>
 #include <linux/types.h>
@@ -595,7 +596,8 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
 	 * we always atomicly update it, see the comments in
 	 * spte_has_volatile_bits().
 	 */
-	if (is_writable_pte(old_spte) && !is_writable_pte(new_spte))
+	if (spte_is_locklessly_modifiable(old_spte) &&
+	      !is_writable_pte(new_spte))
 		ret = true;
 
 	if (!shadow_accessed_mask)
@@ -1176,8 +1178,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 
 /*
  * Write-protect on the specified @sptep, @pt_protect indicates whether
- * spte writ-protection is caused by protecting shadow page table.
- * @flush indicates whether tlb need be flushed.
+ * spte write-protection is caused by protecting shadow page table.
  *
  * Note: write protection is difference between drity logging and spte
  * protection:
@@ -1186,10 +1187,9 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
  * - for spte protection, the spte can be writable only after unsync-ing
  *   shadow page.
  *
- * Return true if the spte is dropped.
+ * Return true if tlb need be flushed.
  */
-static bool
-spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
+static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect)
 {
 	u64 spte = *sptep;
 
@@ -1199,17 +1199,11 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 
 	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
 
-	if (__drop_large_spte(kvm, sptep)) {
-		*flush |= true;
-		return true;
-	}
-
 	if (pt_protect)
 		spte &= ~SPTE_MMU_WRITEABLE;
 	spte = spte & ~PT_WRITABLE_MASK;
 
-	*flush |= mmu_spte_update(sptep, spte);
-	return false;
+	return mmu_spte_update(sptep, spte);
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
@@ -1221,11 +1215,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		if (spte_write_protect(kvm, sptep, &flush, pt_protect)) {
-			sptep = rmap_get_first(*rmapp, &iter);
-			continue;
-		}
 
+		flush |= spte_write_protect(kvm, sptep, pt_protect);
 		sptep = rmap_get_next(&iter);
 	}
 
@@ -2802,9 +2793,9 @@ static bool page_fault_can_be_fast(u32 error_code)
 }
 
 static bool
-fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte)
+fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+			u64 *sptep, u64 spte)
 {
-	struct kvm_mmu_page *sp = page_header(__pa(sptep));
 	gfn_t gfn;
 
 	WARN_ON(!sp->role.direct);
@@ -2830,6 +2821,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
+	struct kvm_mmu_page *sp;
 	bool ret = false;
 	u64 spte = 0ull;
 
@@ -2853,7 +2845,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		goto exit;
 	}
 
-	if (!is_last_spte(spte, level))
+	sp = page_header(__pa(iterator.sptep));
+	if (!is_last_spte(spte, sp->role.level))
 		goto exit;
 
 	/*
@@ -2875,11 +2868,24 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		goto exit;
 
 	/*
+	 * Do not fix write-permission on the large spte since we only dirty
+	 * the first page into the dirty-bitmap in fast_pf_fix_direct_spte()
+	 * that means other pages are missed if its slot is dirty-logged.
+	 *
+	 * Instead, we let the slow page fault path create a normal spte to
+	 * fix the access.
+	 *
+	 * See the comments in kvm_arch_commit_memory_region().
+	 */
+	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+		goto exit;
+
+	/*
 	 * Currently, fast page fault only works for direct mapping since
 	 * the gfn is not stable for indirect shadow page.
 	 * See Documentation/virtual/kvm/locking.txt to get more detail.
 	 */
-	ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte);
+	ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte);
 exit:
 	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
 			      spte, ret);
@@ -3511,11 +3517,14 @@ 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;
 
 	context->bad_mt_xwr = 0;
 
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
+	if (!guest_cpuid_has_gbpages(vcpu))
+		gbpages_bit_rsvd = rsvd_bits(7, 7);
 	switch (context->root_level) {
 	case PT32_ROOT_LEVEL:
 		/* no rsvd bits for 2 level 4K page table entries */
@@ -3538,7 +3547,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	case PT32E_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][2] =
 			rsvd_bits(maxphyaddr, 63) |
-			rsvd_bits(7, 8) | rsvd_bits(1, 2);	/* PDPTE */
+			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
 		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62);	/* PDE */
 		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
@@ -3550,16 +3559,16 @@ 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, 8);
+			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
 		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+			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 |
 			rsvd_bits(maxphyaddr, 51);
 		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
 		context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
-			rsvd_bits(maxphyaddr, 51) |
+			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 29);
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
@@ -4304,15 +4313,32 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 			if (*rmapp)
 				__rmap_write_protect(kvm, rmapp, false);
 
-			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
-				kvm_flush_remote_tlbs(kvm);
+			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
 				cond_resched_lock(&kvm->mmu_lock);
-			}
 		}
 	}
 
-	kvm_flush_remote_tlbs(kvm);
 	spin_unlock(&kvm->mmu_lock);
+
+	/*
+	 * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log()
+	 * which do tlb flush out of mmu-lock should be serialized by
+	 * kvm->slots_lock otherwise tlb flush would be missed.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * We can flush all the TLBs out of the mmu lock without TLB
+	 * corruption since we just change the spte from writable to
+	 * readonly so that we only need to care the case of changing
+	 * spte from present to present (changing the spte from present
+	 * to nonpresent will flush all the TLBs immediately), in other
+	 * words, the only case we care is mmu_spte_update() where we
+	 * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
+	 * instead of PT_WRITABLE_MASK, that means it does not depend
+	 * on PT_WRITABLE_MASK anymore.
+	 */
+	kvm_flush_remote_tlbs(kvm);
 }
 
 #define BATCH_ZAP_PAGES	10
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 3842e70bdb7c..b982112d2ca5 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -104,6 +104,39 @@ static inline int is_present_gpte(unsigned long pte)
 	return pte & PT_PRESENT_MASK;
 }
 
+/*
+ * Currently, we have two sorts of write-protection, a) the first one
+ * write-protects guest page to sync the guest modification, b) another one is
+ * used to sync dirty bitmap when we do KVM_GET_DIRTY_LOG. The differences
+ * between these two sorts are:
+ * 1) the first case clears SPTE_MMU_WRITEABLE bit.
+ * 2) the first case requires flushing tlb immediately avoiding corrupting
+ *    shadow page table between all vcpus so it should be in the protection of
+ *    mmu-lock. And the another case does not need to flush tlb until returning
+ *    the dirty bitmap to userspace since it only write-protects the page
+ *    logged in the bitmap, that means the page in the dirty bitmap is not
+ *    missed, so it can flush tlb out of mmu-lock.
+ *
+ * So, there is the problem: the first case can meet the corrupted tlb caused
+ * by another case which write-protects pages but without flush tlb
+ * immediately. In order to making the first case be aware this problem we let
+ * it flush tlb if we try to write-protect a spte whose SPTE_MMU_WRITEABLE bit
+ * is set, it works since another case never touches SPTE_MMU_WRITEABLE bit.
+ *
+ * Anyway, whenever a spte is updated (only permission and status bits are
+ * changed) we need to check whether the spte with SPTE_MMU_WRITEABLE becomes
+ * readonly, if that happens, we need to flush tlb. Fortunately,
+ * mmu_spte_update() has already handled it perfectly.
+ *
+ * The rules to use SPTE_MMU_WRITEABLE and PT_WRITABLE_MASK:
+ * - if we want to see if it has writable tlb entry or if the spte can be
+ *   writable on the mmu mapping, check SPTE_MMU_WRITEABLE, this is the most
+ *   case, otherwise
+ * - if we fix page fault on the spte or do write-protection by dirty logging,
+ *   check PT_WRITABLE_MASK.
+ *
+ * TODO: introduce APIs to split these two cases.
+ */
 static inline int is_writable_pte(unsigned long pte)
 {
 	return pte & PT_WRITABLE_MASK;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 123efd3ec29f..410776528265 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -913,8 +913,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
  *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
  *   used by guest then tlbs are not flushed, so guest is allowed to access the
  *   freed pages.
- *   We set tlbs_dirty to let the notifier know this change and delay the flush
- *   until such a case actually happens.
+ *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -943,7 +942,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return -EINVAL;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			vcpu->kvm->tlbs_dirty = true;
+			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
@@ -958,7 +957,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			vcpu->kvm->tlbs_dirty = true;
+			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 5c4f63151b4d..cbecaa90399c 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -108,7 +108,10 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-	__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+	}
 }
 
 static void kvm_perf_overflow_intr(struct perf_event *perf_event,
@@ -117,7 +120,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
 	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
-		kvm_perf_overflow(perf_event, data, regs);
+		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 		/*
 		 * Inject PMI. If vcpu was in a guest mode during NMI PMI
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7f4f9c2badae..ec8366c5cfea 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1338,21 +1338,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 }
 
-static void svm_update_cpl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int cpl;
-
-	if (!is_protmode(vcpu))
-		cpl = 0;
-	else if (svm->vmcb->save.rflags & X86_EFLAGS_VM)
-		cpl = 3;
-	else
-		cpl = svm->vmcb->save.cs.selector & 0x3;
-
-	svm->vmcb->save.cpl = cpl;
-}
-
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 {
 	return to_svm(vcpu)->vmcb->save.rflags;
@@ -1360,11 +1345,12 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags;
-
+       /*
+        * Any change of EFLAGS.VM is accompained by a reload of SS
+        * (caused by either a task switch or an inter-privilege IRET),
+        * so we do not need to update the CPL here.
+        */
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
-	if ((old_rflags ^ rflags) & X86_EFLAGS_VM)
-		svm_update_cpl(vcpu);
 }
 
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
@@ -1631,8 +1617,15 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 		s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
 		s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
 	}
-	if (seg == VCPU_SREG_CS)
-		svm_update_cpl(vcpu);
+
+	/*
+	 * This is always accurate, except if SYSRET returned to a segment
+	 * with SS.DPL != 3.  Intel does not have this quirk, and always
+	 * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it
+	 * would entail passing the CPL to userspace and back.
+	 */
+	if (seg == VCPU_SREG_SS)
+		svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
 
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }
@@ -2770,12 +2763,6 @@ static int xsetbv_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int invalid_op_interception(struct vcpu_svm *svm)
-{
-	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
-	return 1;
-}
-
 static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
@@ -3287,6 +3274,24 @@ static int pause_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
+static int nop_interception(struct vcpu_svm *svm)
+{
+	skip_emulated_instruction(&(svm->vcpu));
+	return 1;
+}
+
+static int monitor_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
+static int mwait_interception(struct vcpu_svm *svm)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return nop_interception(svm);
+}
+
 static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
@@ -3344,8 +3349,8 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= skinit_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
-	[SVM_EXIT_MONITOR]			= invalid_op_interception,
-	[SVM_EXIT_MWAIT]			= invalid_op_interception,
+	[SVM_EXIT_MONITOR]			= monitor_interception,
+	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 };
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 545245d7cc63..33574c95220d 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -91,16 +91,21 @@ TRACE_EVENT(kvm_hv_hypercall,
 /*
  * Tracepoint for PIO.
  */
+
+#define KVM_PIO_IN   0
+#define KVM_PIO_OUT  1
+
 TRACE_EVENT(kvm_pio,
 	TP_PROTO(unsigned int rw, unsigned int port, unsigned int size,
-		 unsigned int count),
-	TP_ARGS(rw, port, size, count),
+		 unsigned int count, void *data),
+	TP_ARGS(rw, port, size, count, data),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int, 	rw		)
 		__field(	unsigned int, 	port		)
 		__field(	unsigned int, 	size		)
 		__field(	unsigned int,	count		)
+		__field(	unsigned int,	val		)
 	),
 
 	TP_fast_assign(
@@ -108,11 +113,18 @@ TRACE_EVENT(kvm_pio,
 		__entry->port		= port;
 		__entry->size		= size;
 		__entry->count		= count;
+		if (size == 1)
+			__entry->val	= *(unsigned char *)data;
+		else if (size == 2)
+			__entry->val	= *(unsigned short *)data;
+		else
+			__entry->val	= *(unsigned int *)data;
 	),
 
-	TP_printk("pio_%s at 0x%x size %d count %d",
+	TP_printk("pio_%s at 0x%x size %d count %d val 0x%x %s",
 		  __entry->rw ? "write" : "read",
-		  __entry->port, __entry->size, __entry->count)
+		  __entry->port, __entry->size, __entry->count, __entry->val,
+		  __entry->count > 1 ? "(...)" : "")
 );
 
 /*
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 138ceffc6377..801332edefc3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -354,6 +354,7 @@ struct vmcs02_list {
 struct nested_vmx {
 	/* Has the level1 guest done vmxon? */
 	bool vmxon;
+	gpa_t vmxon_ptr;
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
@@ -413,7 +414,6 @@ struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
 	u8                    fail;
-	u8                    cpl;
 	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
@@ -2283,7 +2283,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	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
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
@@ -2291,7 +2291,8 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		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 | VM_EXIT_SAVE_IA32_EFER |
-		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
+
 	if (vmx_mpx_supported())
 		nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
@@ -2353,12 +2354,11 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 			 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
+		 * For nested guests, we don't do anything specific
+		 * for single context invalidation. Hence, only advertise
+		 * support for global context invalidation.
 		 */
-		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
-			VMX_EPT_EXTENT_CONTEXT_BIT;
+		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT;
 	} else
 		nested_vmx_ept_caps = 0;
 
@@ -3186,10 +3186,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
 	fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-
-	/* CPL is always 0 when CPU enters protected mode */
-	__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-	vmx->cpl = 0;
 }
 
 static void fix_rmode_seg(int seg, struct kvm_segment *save)
@@ -3591,22 +3587,14 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!is_protmode(vcpu))
+	if (unlikely(vmx->rmode.vm86_active))
 		return 0;
-
-	if (!is_long_mode(vcpu)
-	    && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
-		return 3;
-
-	if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
-		vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3;
+	else {
+		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+		return AR_DPL(ar);
 	}
-
-	return vmx->cpl;
 }
 
-
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
@@ -3634,8 +3622,6 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 
 	vmx_segment_cache_clear(vmx);
-	if (seg == VCPU_SREG_CS)
-		__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 
 	if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
 		vmx->rmode.segs[seg] = *var;
@@ -4564,6 +4550,16 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu)
 		PIN_BASED_EXT_INTR_MASK;
 }
 
+/*
+ * In nested virtualization, check if L1 has set
+ * VM_EXIT_ACK_INTR_ON_EXIT
+ */
+static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->vm_exit_controls &
+		VM_EXIT_ACK_INTR_ON_EXIT;
+}
+
 static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
 {
 	return get_vmcs12(vcpu)->pin_based_vm_exec_control &
@@ -4878,6 +4874,9 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
 			vcpu->arch.dr6 |= dr6;
+			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+				skip_emulated_instruction(vcpu);
+
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			return 1;
 		}
@@ -5166,7 +5165,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 			return 1;
 		kvm_register_write(vcpu, reg, val);
 	} else
-		if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]))
+		if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)))
 			return 1;
 
 	skip_emulated_instruction(vcpu);
@@ -5439,7 +5438,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 	}
 
 	/* clear all local breakpoint enable flags */
-	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55);
 
 	/*
 	 * TODO: What about debug traps on tss switch?
@@ -5565,6 +5564,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 	gpa_t gpa;
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+	if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		skip_emulated_instruction(vcpu);
+		return 1;
+	}
 
 	ret = handle_mmio_page_fault_common(vcpu, gpa, true);
 	if (likely(ret == RET_MMIO_PF_EMULATE))
@@ -5669,12 +5672,24 @@ static int handle_pause(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_invalid_op(struct kvm_vcpu *vcpu)
+static int handle_nop(struct kvm_vcpu *vcpu)
 {
-	kvm_queue_exception(vcpu, UD_VECTOR);
+	skip_emulated_instruction(vcpu);
 	return 1;
 }
 
+static int handle_mwait(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
+static int handle_monitor(struct kvm_vcpu *vcpu)
+{
+	printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
+	return handle_nop(vcpu);
+}
+
 /*
  * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
  * We could reuse a single VMCS for all the L2 guests, but we also want the
@@ -5812,6 +5827,154 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
 }
 
 /*
+ * Decode the memory-address operand of a vmx instruction, as recorded on an
+ * exit caused by such an instruction (run by a guest hypervisor).
+ * On success, returns 0. When the operand is invalid, returns 1 and throws
+ * #UD or #GP.
+ */
+static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
+				 unsigned long exit_qualification,
+				 u32 vmx_instruction_info, gva_t *ret)
+{
+	/*
+	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
+	 * Execution", on an exit, vmx_instruction_info holds most of the
+	 * addressing components of the operand. Only the displacement part
+	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
+	 * For how an actual address is calculated from all these components,
+	 * refer to Vol. 1, "Operand Addressing".
+	 */
+	int  scaling = vmx_instruction_info & 3;
+	int  addr_size = (vmx_instruction_info >> 7) & 7;
+	bool is_reg = vmx_instruction_info & (1u << 10);
+	int  seg_reg = (vmx_instruction_info >> 15) & 7;
+	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
+	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
+	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
+	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
+
+	if (is_reg) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/* Addr = segment_base + offset */
+	/* offset = base + [index * scale] + displacement */
+	*ret = vmx_get_segment_base(vcpu, seg_reg);
+	if (base_is_valid)
+		*ret += kvm_register_read(vcpu, base_reg);
+	if (index_is_valid)
+		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
+	*ret += exit_qualification; /* holds the displacement */
+
+	if (addr_size == 1) /* 32 bit */
+		*ret &= 0xffffffff;
+
+	/*
+	 * TODO: throw #GP (and return 1) in various cases that the VM*
+	 * instructions require it - e.g., offset beyond segment limit,
+	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
+	 * address, and so on. Currently these are not checked.
+	 */
+	return 0;
+}
+
+/*
+ * This function performs the various checks including
+ * - if it's 4KB aligned
+ * - No bits beyond the physical address width are set
+ * - Returns 0 on success or else 1
+ * (Intel SDM Section 30.3)
+ */
+static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
+				  gpa_t *vmpointer)
+{
+	gva_t gva;
+	gpa_t vmptr;
+	struct x86_exception e;
+	struct page *page;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
+		return 1;
+
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
+				sizeof(vmptr), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (exit_reason) {
+	case EXIT_REASON_VMON:
+		/*
+		 * SDM 3: 24.11.5
+		 * The first 4 bytes of VMXON region contain the supported
+		 * VMCS revision identifier
+		 *
+		 * Note - IA32_VMX_BASIC[48] will never be 1
+		 * for the nested case;
+		 * which replaces physical address width with 32
+		 *
+		 */
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failInvalid(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		page = nested_get_page(vcpu, vmptr);
+		if (page == NULL ||
+		    *(u32 *)kmap(page) != VMCS12_REVISION) {
+			nested_vmx_failInvalid(vcpu);
+			kunmap(page);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		kunmap(page);
+		vmx->nested.vmxon_ptr = vmptr;
+		break;
+	case EXIT_REASON_VMCLEAR:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	case EXIT_REASON_VMPTRLD:
+		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMPTRLD_INVALID_ADDRESS);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+
+		if (vmptr == vmx->nested.vmxon_ptr) {
+			nested_vmx_failValid(vcpu,
+					     VMXERR_VMCLEAR_VMXON_POINTER);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
+	default:
+		return 1; /* shouldn't happen */
+	}
+
+	if (vmpointer)
+		*vmpointer = vmptr;
+	return 0;
+}
+
+/*
  * Emulate the VMXON instruction.
  * Currently, we just remember that VMX is active, and do not save or even
  * inspect the argument to VMXON (the so-called "VMXON pointer") because we
@@ -5849,6 +6012,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
+
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+		return 1;
+
 	if (vmx->nested.vmxon) {
 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
 		skip_emulated_instruction(vcpu);
@@ -5971,87 +6138,19 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-/*
- * Decode the memory-address operand of a vmx instruction, as recorded on an
- * exit caused by such an instruction (run by a guest hypervisor).
- * On success, returns 0. When the operand is invalid, returns 1 and throws
- * #UD or #GP.
- */
-static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
-				 unsigned long exit_qualification,
-				 u32 vmx_instruction_info, gva_t *ret)
-{
-	/*
-	 * According to Vol. 3B, "Information for VM Exits Due to Instruction
-	 * Execution", on an exit, vmx_instruction_info holds most of the
-	 * addressing components of the operand. Only the displacement part
-	 * is put in exit_qualification (see 3B, "Basic VM-Exit Information").
-	 * For how an actual address is calculated from all these components,
-	 * refer to Vol. 1, "Operand Addressing".
-	 */
-	int  scaling = vmx_instruction_info & 3;
-	int  addr_size = (vmx_instruction_info >> 7) & 7;
-	bool is_reg = vmx_instruction_info & (1u << 10);
-	int  seg_reg = (vmx_instruction_info >> 15) & 7;
-	int  index_reg = (vmx_instruction_info >> 18) & 0xf;
-	bool index_is_valid = !(vmx_instruction_info & (1u << 22));
-	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;
-	bool base_is_valid  = !(vmx_instruction_info & (1u << 27));
-
-	if (is_reg) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
-	}
-
-	/* Addr = segment_base + offset */
-	/* offset = base + [index * scale] + displacement */
-	*ret = vmx_get_segment_base(vcpu, seg_reg);
-	if (base_is_valid)
-		*ret += kvm_register_read(vcpu, base_reg);
-	if (index_is_valid)
-		*ret += kvm_register_read(vcpu, index_reg)<<scaling;
-	*ret += exit_qualification; /* holds the displacement */
-
-	if (addr_size == 1) /* 32 bit */
-		*ret &= 0xffffffff;
-
-	/*
-	 * TODO: throw #GP (and return 1) in various cases that the VM*
-	 * instructions require it - e.g., offset beyond segment limit,
-	 * unusable or unreadable/unwritable segment, non-canonical 64-bit
-	 * address, and so on. Currently these are not checked.
-	 */
-	return 0;
-}
-
 /* Emulate the VMCLEAR instruction */
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
 	struct vmcs12 *vmcs12;
 	struct page *page;
-	struct x86_exception e;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
 		return 1;
-	}
 
 	if (vmptr == vmx->nested.current_vmptr) {
 		nested_release_vmcs12(vmx);
@@ -6372,29 +6471,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 static int handle_vmptrld(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gva_t gva;
 	gpa_t vmptr;
-	struct x86_exception e;
 	u32 exec_control;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
-			vmcs_read32(VMX_INSTRUCTION_INFO), &gva))
-		return 1;
-
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
-		kvm_inject_page_fault(vcpu, &e);
-		return 1;
-	}
-
-	if (!IS_ALIGNED(vmptr, PAGE_SIZE)) {
-		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
-		skip_emulated_instruction(vcpu);
+	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
 		return 1;
-	}
 
 	if (vmx->nested.current_vmptr != vmptr) {
 		struct vmcs12 *new_vmcs12;
@@ -6471,7 +6555,6 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	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)) {
@@ -6511,16 +6594,13 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	}
 
 	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:
+		/* Trap single context invalidation invept calls */
 		BUG_ON(1);
 		break;
 	}
@@ -6571,8 +6651,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
-	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
-	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_mwait,
+	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_monitor,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
@@ -7413,7 +7493,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
 				  | (1 << VCPU_EXREG_RFLAGS)
-				  | (1 << VCPU_EXREG_CPL)
 				  | (1 << VCPU_EXREG_PDPTR)
 				  | (1 << VCPU_EXREG_SEGMENTS)
 				  | (1 << VCPU_EXREG_CR3));
@@ -8601,6 +8680,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
 		       exit_qualification);
 
+	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+	    && nested_exit_intr_ack_set(vcpu)) {
+		int irq = kvm_cpu_get_interrupt(vcpu);
+		WARN_ON(irq < 0);
+		vmcs12->vm_exit_intr_info = irq |
+			INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
+	}
+
 	trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
 				       vmcs12->exit_qualification,
 				       vmcs12->idt_vectoring_info_field,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 20316c67b824..f32a02578c0d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -704,25 +704,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	}
 
 	if (is_long_mode(vcpu)) {
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) {
-			if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS)
-				return 1;
-		} else
-			if (cr3 & CR3_L_MODE_RESERVED_BITS)
-				return 1;
-	} else {
-		if (is_pae(vcpu)) {
-			if (cr3 & CR3_PAE_RESERVED_BITS)
-				return 1;
-			if (is_paging(vcpu) &&
-			    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
-				return 1;
-		}
-		/*
-		 * We don't check reserved bits in nonpae mode, because
-		 * this isn't enforced, and VMware depends on this.
-		 */
-	}
+		if (cr3 & CR3_L_MODE_RESERVED_BITS)
+			return 1;
+	} else if (is_pae(vcpu) && is_paging(vcpu) &&
+		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+		return 1;
 
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
@@ -1935,6 +1921,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 
 		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
 			vcpu->arch.hv_vapic = data;
+			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+				return 1;
 			break;
 		}
 		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
@@ -1945,6 +1933,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			return 1;
 		vcpu->arch.hv_vapic = data;
 		mark_page_dirty(vcpu->kvm, gfn);
+		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+			return 1;
 		break;
 	}
 	case HV_X64_MSR_EOI:
@@ -2647,6 +2637,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
@@ -3649,11 +3640,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 		offset = i * BITS_PER_LONG;
 		kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
 	}
-	if (is_dirty)
-		kvm_flush_remote_tlbs(kvm);
 
 	spin_unlock(&kvm->mmu_lock);
 
+	/* See the comments in kvm_mmu_slot_remove_write_access(). */
+	lockdep_assert_held(&kvm->slots_lock);
+
+	/*
+	 * All the TLBs can be flushed out of mmu lock, see the comments in
+	 * kvm_mmu_slot_remove_write_access().
+	 */
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
+
 	r = -EFAULT;
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		goto out;
@@ -4489,8 +4488,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 			       unsigned short port, void *val,
 			       unsigned int count, bool in)
 {
-	trace_kvm_pio(!in, port, size, count);
-
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = in;
 	vcpu->arch.pio.count  = count;
@@ -4525,6 +4522,7 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (ret) {
 data_avail:
 		memcpy(val, vcpu->arch.pio_data, size * count);
+		trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
 		vcpu->arch.pio.count = 0;
 		return 1;
 	}
@@ -4539,6 +4537,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 
 	memcpy(vcpu->arch.pio_data, val, size * count);
+	trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
 	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
 }
 
@@ -4650,11 +4649,6 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
 	return res;
 }
 
-static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
-{
-	kvm_set_rflags(emul_to_vcpu(ctxt), val);
-}
-
 static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
 {
 	return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt));
@@ -4839,7 +4833,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.set_idt	     = emulator_set_idt,
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
-	.set_rflags          = emulator_set_rflags,
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,
@@ -4905,7 +4898,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	ctxt->eip = kvm_rip_read(vcpu);
 	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
 		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
-		     cs_l				? X86EMUL_MODE_PROT64 :
+		     (cs_l && is_long_mode(vcpu))	? X86EMUL_MODE_PROT64 :
 		     cs_db				? X86EMUL_MODE_PROT32 :
 							  X86EMUL_MODE_PROT16;
 	ctxt->guest_mode = is_guest_mode(vcpu);
@@ -7333,8 +7326,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
 	/*
 	 * Write protect all pages for dirty logging.
-	 * Existing largepage mappings are destroyed here and new ones will
-	 * not be created until the end of the logging.
+	 *
+	 * All the sptes including the large sptes which point to this
+	 * slot are set to readonly. We can not create any new large
+	 * spte on this slot until the end of the logging.
+	 *
+	 * See the comments in fast_page_fault().
 	 */
 	if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
 		kvm_mmu_slot_remove_write_access(kvm, mem->slot);