Merge 5.6-rc3 into char-misc-next

We need the char/misc fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

20 files changed, 162 insertions, 76 deletions

diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
index 748456c365f4..9557c5a15b91 100644
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ b/arch/x86/boot/compressed/kaslr_64.c
@@ -29,9 +29,6 @@
 #define __PAGE_OFFSET __PAGE_OFFSET_BASE
 #include "../../mm/ident_map.c"
 
-/* Used by pgtable.h asm code to force instruction serialization. */
-unsigned long __force_order;
-
 /* Used to track our page table allocation area. */
 struct alloc_pgt_data {
 	unsigned char *pgt_buf;
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1f22b6bbda68..39eb276d0277 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,6 +250,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3be51aa06e67..dff6623804c2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4765,6 +4765,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e1daf4151e11..4814c964692c 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,17 +40,18 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT,GLM,CNL
+ *			 Available model: SLM,AMT,GLM,CNL,TNT
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- *						CNL,KBL,CML
+ *						CNL,KBL,CML,TNT
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -60,17 +61,18 @@
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL,TGL
+ *						KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML,ICL,TGL
+ *						GLM,CNL,KBL,CML,ICL,TGL,TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -87,7 +89,8 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+ *						TNT
  *			       Scope: Package (physical package)
  *
  */
@@ -640,8 +643,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT,   glm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
-
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4b94ae4ae369..dc43cc124e09 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	old = ((s64)(prev_raw_count << shift) >> shift);
 	local64_add(new - old + count * period, &event->count);
 
+	local64_set(&hwc->period_left, -new);
+
 	perf_event_update_userpage(event);
 
 	return 0;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6f86650b3f77..a949f6f55991 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data)
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:
-
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_TREMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4dffbc10d3f8..40a0c0fd95ca 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -781,9 +781,19 @@ struct kvm_vcpu_arch {
 	u64 msr_kvm_poll_control;
 
 	/*
-	 * Indicate whether the access faults on its page table in guest
-	 * which is set when fix page fault and used to detect unhandeable
-	 * instruction.
+	 * Indicates the guest is trying to write a gfn that contains one or
+	 * more of the PTEs used to translate the write itself, i.e. the access
+	 * is changing its own translation in the guest page tables.  KVM exits
+	 * to userspace if emulation of the faulting instruction fails and this
+	 * flag is set, as KVM cannot make forward progress.
+	 *
+	 * If emulation fails for a write to guest page tables, KVM unprotects
+	 * (zaps) the shadow page for the target gfn and resumes the guest to
+	 * retry the non-emulatable instruction (on hardware).  Unprotecting the
+	 * gfn doesn't allow forward progress for a self-changing access because
+	 * doing so also zaps the translation for the gfn, i.e. retrying the
+	 * instruction will hit a !PRESENT fault, which results in a new shadow
+	 * page and sends KVM back to square one.
 	 */
 	bool write_fault_to_shadow_pgtable;
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ebe1685e92dd..d5e517d1c3dd 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ac83a0fef628..1f875fbe1384 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -28,6 +28,7 @@
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
+static const int amd_erratum_1054[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 /*
@@ -972,6 +973,15 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+	/*
+	 * Turn on the Instructions Retired free counter on machines not
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (cpu_has(c, X86_FEATURE_IRPERF) &&
+	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 }
 
 #ifdef CONFIG_X86_32
@@ -1099,6 +1109,10 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
 	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index b3a50d962851..52de616a8065 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1163,9 +1163,12 @@ static const struct sysfs_ops threshold_ops = {
 	.store			= store,
 };
 
+static void threshold_block_release(struct kobject *kobj);
+
 static struct kobj_type threshold_ktype = {
 	.sysfs_ops		= &threshold_ops,
 	.default_attrs		= default_attrs,
+	.release		= threshold_block_release,
 };
 
 static const char *get_name(unsigned int bank, struct threshold_block *b)
@@ -1198,8 +1201,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 	return buf_mcatype;
 }
 
-static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
-				     unsigned int block, u32 address)
+static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb,
+				     unsigned int bank, unsigned int block,
+				     u32 address)
 {
 	struct threshold_block *b = NULL;
 	u32 low, high;
@@ -1243,16 +1247,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 
 	INIT_LIST_HEAD(&b->miscj);
 
-	if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
-		list_add(&b->miscj,
-			 &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
-	} else {
-		per_cpu(threshold_banks, cpu)[bank]->blocks = b;
-	}
+	if (tb->blocks)
+		list_add(&b->miscj, &tb->blocks->miscj);
+	else
+		tb->blocks = b;
 
-	err = kobject_init_and_add(&b->kobj, &threshold_ktype,
-				   per_cpu(threshold_banks, cpu)[bank]->kobj,
-				   get_name(bank, b));
+	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
 	if (err)
 		goto out_free;
 recurse:
@@ -1260,7 +1260,7 @@ recurse:
 	if (!address)
 		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, block, address);
+	err = allocate_threshold_blocks(cpu, tb, bank, block, address);
 	if (err)
 		goto out_free;
 
@@ -1345,8 +1345,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		goto out_free;
 	}
 
-	per_cpu(threshold_banks, cpu)[bank] = b;
-
 	if (is_shared_bank(bank)) {
 		refcount_set(&b->cpus, 1);
 
@@ -1357,9 +1355,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		}
 	}
 
-	err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
-	if (!err)
-		goto out;
+	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+	if (err)
+		goto out_free;
+
+	per_cpu(threshold_banks, cpu)[bank] = b;
+
+	return 0;
 
  out_free:
 	kfree(b);
@@ -1368,8 +1370,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	return err;
 }
 
-static void deallocate_threshold_block(unsigned int cpu,
-						 unsigned int bank)
+static void threshold_block_release(struct kobject *kobj)
+{
+	kfree(to_block(kobj));
+}
+
+static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
 {
 	struct threshold_block *pos = NULL;
 	struct threshold_block *tmp = NULL;
@@ -1379,13 +1385,11 @@ static void deallocate_threshold_block(unsigned int cpu,
 		return;
 
 	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
-		kobject_put(&pos->kobj);
 		list_del(&pos->miscj);
-		kfree(pos);
+		kobject_put(&pos->kobj);
 	}
 
-	kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
-	per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
+	kobject_put(&head->blocks->kobj);
 }
 
 static void __threshold_remove_blocks(struct threshold_bank *b)
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index 4d4f5d9faac3..23054909c8dd 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -10,8 +10,6 @@ extern struct boot_params boot_params;
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;
@@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	/* Get variable contents into buffer */
-	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
 				  NULL, &size, &secboot);
 	if (status == EFI_NOT_FOUND) {
 		pr_info("ima: secureboot mode disabled\n");
@@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	size = sizeof(setupmode);
-	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
 				  NULL, &size, &setupmode);
 
 	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index eafc631d305c..afcd30d44cbb 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1080,9 +1080,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			result = 1;
 			/* assumes that there are only KVM_APIC_INIT/SIPI */
 			apic->pending_events = (1UL << KVM_APIC_INIT);
-			/* make sure pending_events is visible before sending
-			 * the request */
-			smp_wmb();
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d55674f44a18..a647601c9e1c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -102,6 +102,19 @@ static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu)
 					      kvm_get_active_pcid(vcpu));
 }
 
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+		       bool prefault);
+
+static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+					u32 err, bool prefault)
+{
+#ifdef CONFIG_RETPOLINE
+	if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault))
+		return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault);
+#endif
+	return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault);
+}
+
 /*
  * 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
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7011a4e54866..87e9ba27ada1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4219,8 +4219,8 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 }
 EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
-			  bool prefault)
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+		       bool prefault)
 {
 	int max_level;
 
@@ -4925,7 +4925,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		return;
 
 	context->mmu_role.as_u64 = new_role.as_u64;
-	context->page_fault = tdp_page_fault;
+	context->page_fault = kvm_tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
 	context->update_pte = nonpaging_update_pte;
@@ -5436,9 +5436,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
-					       lower_32_bits(error_code),
-					       false);
+		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
+					  lower_32_bits(error_code), false);
 		WARN_ON(r == RET_PF_INVALID);
 	}
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4e1ef0473663..e4c8a4cbf407 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -33,7 +33,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
 	#ifdef CONFIG_X86_64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 	#define CMPXCHG cmpxchg
 	#else
 	#define CMPXCHG cmpxchg64
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a3e32d61d60c..bef0ba35f121 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2175,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
-	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
 	svm->virt_spec_ctrl = 0;
 
@@ -2266,6 +2265,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	init_vmcb(svm);
 
 	svm_init_osvw(vcpu);
+	vcpu->arch.microcode_version = 0x01000065;
 
 	return 0;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 657c2eda357c..3589cd3c0fcc 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -544,7 +544,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
 	}
 }
 
-static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
+{
 	int msr;
 
 	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
@@ -1981,7 +1982,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
 	}
 
 	/*
-	 * Clean fields data can't de used on VMLAUNCH and when we switch
+	 * Clean fields data can't be used on VMLAUNCH and when we switch
 	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
 	 */
 	if (from_launch || evmcs_gpa_changed)
@@ -3575,6 +3576,33 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
 }
 
+/*
+ * Returns true if a debug trap is pending delivery.
+ *
+ * In KVM, debug traps bear an exception payload. As such, the class of a #DB
+ * exception may be inferred from the presence of an exception payload.
+ */
+static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.exception.pending &&
+			vcpu->arch.exception.nr == DB_VECTOR &&
+			vcpu->arch.exception.payload;
+}
+
+/*
+ * Certain VM-exits set the 'pending debug exceptions' field to indicate a
+ * recognized #DB (data or single-step) that has yet to be delivered. Since KVM
+ * represents these debug traps with a payload that is said to be compatible
+ * with the 'pending debug exceptions' field, write the payload to the VMCS
+ * field if a VM-exit is delivered before the debug trap.
+ */
+static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
+{
+	if (vmx_pending_dbg_trap(vcpu))
+		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+			    vcpu->arch.exception.payload);
+}
+
 static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3587,6 +3615,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		nested_vmx_update_pending_dbg(vcpu);
 		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a6664886f2e..3be25ecae145 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2947,6 +2947,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
+	/* Nested EPT currently only supports 4-level walks. */
+	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+		return 4;
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
@@ -4238,7 +4241,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vmx->msr_ia32_umwait_control = 0;
 
-	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	vmx->hv_deadline_tsc = -1;
 	kvm_set_cr8(vcpu, 0);
@@ -6763,6 +6765,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
 
+	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fbabb2f06273..fb5d64ebc35d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -438,6 +438,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
 		 * for #DB exceptions under VMX.
 		 */
 		vcpu->arch.dr6 ^= payload & DR6_RTM;
+
+		/*
+		 * The #DB payload is defined as compatible with the 'pending
+		 * debug exceptions' field under VMX, not DR6. While bit 12 is
+		 * defined in the 'pending debug exceptions' field (enabled
+		 * breakpoint), it is reserved and must be zero in DR6.
+		 */
+		vcpu->arch.dr6 &= ~BIT(12);
 		break;
 	case PF_VECTOR:
 		vcpu->arch.cr2 = payload;
@@ -490,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		vcpu->arch.exception.error_code = error_code;
 		vcpu->arch.exception.has_payload = has_payload;
 		vcpu->arch.exception.payload = payload;
-		/*
-		 * In guest mode, payload delivery should be deferred,
-		 * so that the L1 hypervisor can intercept #PF before
-		 * CR2 is modified (or intercept #DB before DR6 is
-		 * modified under nVMX).  However, for ABI
-		 * compatibility with KVM_GET_VCPU_EVENTS and
-		 * KVM_SET_VCPU_EVENTS, we can't delay payload
-		 * delivery unless userspace has enabled this
-		 * functionality via the per-VM capability,
-		 * KVM_CAP_EXCEPTION_PAYLOAD.
-		 */
-		if (!vcpu->kvm->arch.exception_payload_enabled ||
-		    !is_guest_mode(vcpu))
+		if (!is_guest_mode(vcpu))
 			kvm_deliver_exception_payload(vcpu);
 		return;
 	}
@@ -2448,7 +2444,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
-	WARN_ON(vcpu->hv_clock.system_time < 0);
+	WARN_ON((s64)vcpu->hv_clock.system_time < 0);
 
 	/* If the host uses TSC clocksource, then it is stable */
 	pvclock_flags = 0;
@@ -3796,6 +3792,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	process_nmi(vcpu);
 
 	/*
+	 * In guest mode, payload delivery should be deferred,
+	 * so that the L1 hypervisor can intercept #PF before
+	 * CR2 is modified (or intercept #DB before DR6 is
+	 * modified under nVMX). Unless the per-VM capability,
+	 * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of
+	 * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we
+	 * opportunistically defer the exception payload, deliver it if the
+	 * capability hasn't been requested before processing a
+	 * KVM_GET_VCPU_EVENTS.
+	 */
+	if (!vcpu->kvm->arch.exception_payload_enabled &&
+	    vcpu->arch.exception.pending && vcpu->arch.exception.has_payload)
+		kvm_deliver_exception_payload(vcpu);
+
+	/*
 	 * The API doesn't provide the instruction length for software
 	 * exceptions, so don't report them. As long as the guest RIP
 	 * isn't advanced, we should expect to encounter the exception
@@ -8942,7 +8953,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 
 	kvm_rip_write(vcpu, ctxt->eip);
 	kvm_set_rflags(vcpu, ctxt->eflags);
-	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
@@ -10182,7 +10192,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
+	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 1f756ffffe8b..79409120a603 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -896,14 +896,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
+#ifdef CONFIG_X86_64
+	unsigned int which;
+	u64 base;
+#endif
 
 	ret = 0;
 
 	switch (msr) {
 #ifdef CONFIG_X86_64
-		unsigned which;
-		u64 base;
-
 	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
 	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
 	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;