23 files changed, 186 insertions, 179 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 829e89cfcee2..9fb9a1f1e47b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	if (lockup_detector_suspend() != 0) {
-		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
-		return 0;
-	}
+	cpus_read_lock();
+
+	hardlockup_detector_perf_stop();
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	lockup_detector_resume();
-
-	cpus_read_lock();
+	hardlockup_detector_perf_restart();
 
 	for_each_online_cpu(c)
 		free_excl_cntrs(c);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4cf100ff2a37..72db0664a53d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
@@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 8e2457cb6b4a..005908ee9333 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index db1fe377e6dd..a7196818416a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IIO0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IIO0_MSR_PMON_CTR0,
@@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = {
 static struct intel_uncore_type skx_uncore_irp = {
 	.name			= "irp",
 	.num_counters		= 2,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IRP0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IRP0_MSR_PMON_CTR0,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 4bb3ec69e8ea..06723671ae4e 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -63,6 +63,14 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_ATOM_SILVERMONT1:
 	case INTEL_FAM6_ATOM_SILVERMONT2:
 	case INTEL_FAM6_ATOM_AIRMONT:
+
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
+
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index c1eadbaf1115..b0dc91f4bedc 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -11,10 +11,12 @@
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
-#ifdef CONFIG_X86_32
+#ifndef __x86_64__
+/* 32 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(a)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
+/* 64 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(b)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
@@ -139,8 +141,8 @@
  * gets set up by the containing function.  If you forget to do this, objtool
  * may print a "call without frame pointer save/setup" warning.
  */
-register unsigned int __asm_call_sp asm("esp");
-#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp)
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index bc62e7cbf1b1..59ad3d132353 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
@@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void)
 
 #else /* CONFIG_KVM_GUEST */
 #define kvm_guest_init() do {} while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
 static inline bool kvm_para_available(void)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 5161da1a0fa0..89e7eeb5cec1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -158,17 +158,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 /*
  * Walks up the stack frames to make sure that the specified object is
  * entirely contained by a single stack frame.
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 78e8fcc87d4c..4b892917edeb 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -337,7 +337,7 @@ do {									\
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
 		     : "=r" (retval), "=&A"(x)				\
-		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
+		     : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 128a1a0b1450..7cb282e9e587 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -551,13 +551,13 @@ static inline void
 MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
-	u32 *p = (u32 *) &desc;
-
 	mcl->op = __HYPERVISOR_update_descriptor;
 	if (sizeof(maddr) == sizeof(long)) {
 		mcl->args[0] = maddr;
 		mcl->args[1] = *(unsigned long *)&desc;
 	} else {
+		u32 *p = (u32 *)&desc;
+
 		mcl->args[0] = maddr;
 		mcl->args[1] = maddr >> 32;
 		mcl->args[2] = *p++;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1f38d9a4d9de..d4eb450144fd 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -64,7 +64,7 @@ static void call_on_stack(void *func, void *stack)
 
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
 static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
@@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -139,7 +139,7 @@ void do_softirq_own_stack(void)
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer();
+	*prev_esp = current_stack_pointer;
 
 	call_on_stack(__do_softirq, isp);
 }
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 4b0592ca9e47..8c1cc08f514f 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent)
 	return 0;
 
 out_clean_nodes:
-	for (j = i - 1; j > 0; j--)
+	for (j = i - 1; j >= 0; j--)
 		cleanup_setup_data_node(*(kobjp + j));
 	kfree(kobjp);
 out_setup_data_kobj:
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index aa60a08b65b1..8bb9594d0761 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
 	return NULL;
 }
 
-void kvm_async_pf_task_wait(u32 token)
+/*
+ * @interrupt_kernel: Is this called from a routine which interrupts the kernel
+ * 		      (other than user space)?
+ */
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
@@ -140,7 +144,10 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.halted = is_idle_task(current) || preempt_count() > 1;
+	n.halted = is_idle_task(current) ||
+		   (IS_ENABLED(CONFIG_PREEMPT_COUNT)
+		    ? preempt_count() > 1 || rcu_preempt_depth()
+		    : interrupt_kernel);
 	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -268,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
 		prev_state = exception_enter();
-		kvm_async_pf_task_wait((u32)read_cr2());
+		kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs));
 		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 34ea3651362e..67db4f43309e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -142,7 +142,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	 * from double_fault.
 	 */
 	BUG_ON((unsigned long)(current_top_of_stack() -
-			       current_stack_pointer()) >= THREAD_SIZE);
+			       current_stack_pointer) >= THREAD_SIZE);
 
 	preempt_enable_no_resched();
 }
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3ea624452f93..3c48bc8bf08c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM
 	depends on HIGH_RES_TIMERS
 	# for TASKSTATS/TASK_DELAY_ACCT:
 	depends on NET && MULTIUSER
+	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a36254cbf776..d90cdc77e077 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	#op " %al \n\t" \
 	FOP_RET
 
-asm(".global kvm_fastop_exception \n"
-    "kvm_fastop_exception: xor %esi, %esi; ret");
+asm(".pushsection .fixup, \"ax\"\n"
+    ".global kvm_fastop_exception \n"
+    "kvm_fastop_exception: xor %esi, %esi; ret\n"
+    ".popsection");
 
 FOP_START(setcc)
 FOP_SETCC(seto)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca30c1eb1d9..106d4a029a8a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		vcpu->arch.apf.host_apf_reason = 0;
 		local_irq_disable();
-		kvm_async_pf_task_wait(fault_address);
+		kvm_async_pf_task_wait(fault_address, 0);
 		local_irq_enable();
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6970249c09fc..a2b804e10c95 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -200,6 +200,8 @@ struct loaded_vmcs {
 	int cpu;
 	bool launched;
 	bool nmi_known_unmasked;
+	unsigned long vmcs_host_cr3;	/* May not match real cr3 */
+	unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -600,8 +602,6 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
-		unsigned long vmcs_host_cr3;	/* May not match real cr3 */
-		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	struct pi_desc old, new;
 	unsigned int dest;
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	/*
+	 * In case of hot-plug or hot-unplug, we may have to undo
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
+	/*
+	 * First handle the simple case where no cmpxchg is necessary; just
+	 * allow posting non-urgent interrupts.
+	 *
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+	 * expects the VCPU to be on the blocked_vcpu_list that matches
+	 * PI.NDST.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+	    vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		return;
+	}
+
+	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
-		 * are two possible cases:
-		 * 1. After running 'pre_block', context switch
-		 *    happened. For this case, 'sn' was set in
-		 *    vmx_vcpu_put(), so we need to clear it here.
-		 * 2. After running 'pre_block', we were blocked,
-		 *    and woken up by some other guy. For this case,
-		 *    we don't need to do anything, 'pi_post_block'
-		 *    will do everything for us. However, we cannot
-		 *    check whether it is case #1 or case #2 here
-		 *    (maybe, not needed), so we also clear sn here,
-		 *    I think it is not a big deal.
-		 */
-		if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
-			if (vcpu->cpu != cpu) {
-				dest = cpu_physical_id(cpu);
-
-				if (x2apic_enabled())
-					new.ndst = dest;
-				else
-					new.ndst = (dest << 8) & 0xFF00;
-			}
+		dest = cpu_physical_id(cpu);
 
-			/* set 'NV' to 'notification vector' */
-			new.nv = POSTED_INTR_VECTOR;
-		}
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
 
-		/* Allow posting non-urgent interrupts */
 		new.sn = 0;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 }
 
 static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	 */
 	cr3 = __read_cr3();
 	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
-	vmx->host_state.vmcs_host_cr3 = cr3;
+	vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
 	cr4 = cr4_read_shadow();
 	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
-	vmx->host_state.vmcs_host_cr4 = cr4;
+	vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
@@ -9273,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+	if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
 		vmcs_writel(HOST_CR3, cr3);
-		vmx->host_state.vmcs_host_cr3 = cr3;
+		vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 	}
 
 	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+	if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
-		vmx->host_state.vmcs_host_cr4 = cr4;
+		vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 	}
 
 	/* When single-stepping over STI and MOV SS, we must clear the
@@ -9591,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -9839,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 
 	WARN_ON(!is_guest_mode(vcpu));
 
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+		!to_vmx(vcpu)->nested.nested_run_pending) {
 		vmcs12->vm_exit_intr_error_code = fault->error_code;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
@@ -11704,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
 /*
  * This routine does the following things for vCPU which is going
  * to be blocked if VT-d PI is enabled.
@@ -11719,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
  */
 static int pi_pre_block(struct kvm_vcpu *vcpu)
 {
-	unsigned long flags;
 	unsigned int dest;
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11729,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
-	vcpu->pre_pcpu = vcpu->cpu;
-	spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-			  vcpu->pre_pcpu), flags);
-	list_add_tail(&vcpu->blocked_vcpu_list,
-		      &per_cpu(blocked_vcpu_on_cpu,
-		      vcpu->pre_pcpu));
-	spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
-			       vcpu->pre_pcpu), flags);
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+		vcpu->pre_pcpu = vcpu->cpu;
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
+			      &per_cpu(blocked_vcpu_on_cpu,
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
 
 	do {
 		old.control = new.control = pi_desc->control;
 
-		/*
-		 * We should not block the vCPU if
-		 * an interrupt is posted for it.
-		 */
-		if (pi_test_on(pi_desc) == 1) {
-			spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
-					  vcpu->pre_pcpu), flags);
-			list_del(&vcpu->blocked_vcpu_list);
-			spin_unlock_irqrestore(
-					&per_cpu(blocked_vcpu_on_cpu_lock,
-					vcpu->pre_pcpu), flags);
-			vcpu->pre_pcpu = -1;
-
-			return 1;
-		}
-
 		WARN((pi_desc->sn == 1),
 		     "Warning: SN field of posted-interrupts "
 		     "is set before blocking\n");
@@ -11778,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 
-	return 0;
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
 }
 
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11797,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 
 static void pi_post_block(struct kvm_vcpu *vcpu)
 {
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-	unsigned long flags;
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (vcpu->pre_pcpu == -1)
 		return;
 
-	do {
-		old.control = new.control = pi_desc->control;
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* Allow posting non-urgent interrupts */
-		new.sn = 0;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
-
-	if(vcpu->pre_pcpu != -1) {
-		spin_lock_irqsave(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock_irqrestore(
-			&per_cpu(blocked_vcpu_on_cpu_lock,
-			vcpu->pre_pcpu), flags);
-		vcpu->pre_pcpu = -1;
-	}
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	__pi_post_block(vcpu);
+	local_irq_enable();
 }
 
 static void vmx_post_block(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 39567b5c33da..e2baeaa053a5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -192,8 +192,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
-		struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))
@@ -209,7 +208,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
 	 * valid VMA, so we should never reach this without a
 	 * valid VMA.
 	 */
-	if (!vma) {
+	if (!pkey) {
 		WARN_ONCE(1, "PKU fault with no VMA passed in");
 		info->si_pkey = 0;
 		return;
@@ -219,13 +218,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
 	 * absolutely guranteed to be 100% accurate because of
 	 * the race explained above.
 	 */
-	info->si_pkey = vma_pkey(vma);
+	info->si_pkey = *pkey;
 }
 
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk, struct vm_area_struct *vma,
-		     int fault)
+		     struct task_struct *tsk, u32 *pkey, int fault)
 {
 	unsigned lsb = 0;
 	siginfo_t info;
@@ -240,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, vma);
+	fill_sig_info_pkey(si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -762,8 +760,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	struct task_struct *tsk = current;
 	unsigned long flags;
 	int sig;
-	/* No context means no VMA to pass down */
-	struct vm_area_struct *vma = NULL;
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs, X86_TRAP_PF)) {
@@ -788,7 +784,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address,
-					     tsk, vma, 0);
+					     tsk, NULL, 0);
 		}
 
 		/*
@@ -896,8 +892,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		       unsigned long address, struct vm_area_struct *vma,
-		       int si_code)
+		       unsigned long address, u32 *pkey, int si_code)
 {
 	struct task_struct *tsk = current;
 
@@ -945,7 +940,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
 
 		return;
 	}
@@ -958,9 +953,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 
 static noinline void
 bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		     unsigned long address, struct vm_area_struct *vma)
+		     unsigned long address, u32 *pkey)
 {
-	__bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+	__bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
 }
 
 static void
@@ -968,6 +963,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
 	   unsigned long address,  struct vm_area_struct *vma, int si_code)
 {
 	struct mm_struct *mm = current->mm;
+	u32 pkey;
+
+	if (vma)
+		pkey = vma_pkey(vma);
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..
@@ -975,7 +974,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
 	 */
 	up_read(&mm->mmap_sem);
 
-	__bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+	__bad_area_nosemaphore(regs, error_code, address,
+			       (vma) ? &pkey : NULL, si_code);
 }
 
 static noinline void
@@ -1018,7 +1018,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
 
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
-	  struct vm_area_struct *vma, unsigned int fault)
+	  u32 *pkey, unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	int code = BUS_ADRERR;
@@ -1045,13 +1045,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 		code = BUS_MCEERR_AR;
 	}
 #endif
-	force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+	force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
 }
 
 static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, struct vm_area_struct *vma,
-	       unsigned int fault)
+	       unsigned long address, u32 *pkey, unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
 		no_context(regs, error_code, address, 0, 0);
@@ -1075,9 +1074,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
-			do_sigbus(regs, error_code, address, vma, fault);
+			do_sigbus(regs, error_code, address, pkey, fault);
 		else if (fault & VM_FAULT_SIGSEGV)
-			bad_area_nosemaphore(regs, error_code, address, vma);
+			bad_area_nosemaphore(regs, error_code, address, pkey);
 		else
 			BUG();
 	}
@@ -1267,6 +1266,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	struct mm_struct *mm;
 	int fault, major = 0;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	u32 pkey;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1467,9 +1467,10 @@ good_area:
 		return;
 	}
 
+	pkey = vma_pkey(vma);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, vma, fault);
+		mm_fault_error(regs, error_code, address, &pkey, fault);
 		return;
 	}
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 3fcc8e01683b..16c5f37933a2 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 93fe97cce581..49d9778376d7 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -191,7 +191,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			 * mapped in the new pgd, we'll double-fault.  Forcibly
 			 * map it.
 			 */
-			unsigned int index = pgd_index(current_stack_pointer());
+			unsigned int index = pgd_index(current_stack_pointer);
 			pgd_t *pgd = next->pgd + index;
 
 			if (unlikely(pgd_none(*pgd)))
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c9573660d51..0554e8aef4d5 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	/* if (index >= array->map.max_entries)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
+	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
 #define OFFSET1 43 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 7330cb3b2283..71495f1a86d7 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void)
 	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
 	 * the ramdisk). We continue on, erasing PMD entries that point to page
 	 * tables - do note that they are accessible at this stage via __va.
-	 * For good measure we also round up to the PMD - which means that if
+	 * As Xen is aligning the memory end to a 4MB boundary, for good
+	 * measure we also round up to PMD_SIZE * 2 - which means that if
 	 * anybody is using __ka address to the initial boot-stack - and try
 	 * to use it - they are going to crash. The xen_start_info has been
 	 * taken care of already in xen_setup_kernel_pagetable. */
 	addr = xen_start_info->pt_base;
-	size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+	size = xen_start_info->nr_pt_frames * PAGE_SIZE;
 
-	xen_cleanhighmap(addr, addr + size);
+	xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
 	xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
-#ifdef DEBUG
-	/* This is superfluous and is not necessary, but you know what
-	 * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
-	 * anything at this stage. */
-	xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
-#endif
 }
 #endif