Merge branch 'linus' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 347 insertions, 146 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 2c860ad4fe06..8a958274b54c 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -34,6 +34,7 @@ KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 630e3664906b..16f49123d747 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -16,6 +16,15 @@
 #include "ctype.h"
 #include "string.h"
 
+/*
+ * Undef these macros so that the functions that we provide
+ * here will have the correct names regardless of how string.h
+ * may have chosen to #define them.
+ */
+#undef memcpy
+#undef memset
+#undef memcmp
+
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a9a8027a6c0e..d271fb79248f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -705,6 +705,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
 #ifdef CONFIG_HAVE_KVM
 apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
 apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
+apicinterrupt3 POSTED_INTR_NESTED_VECTOR	kvm_posted_intr_nested_ipi	smp_kvm_posted_intr_nested_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index dae2fedc1601..4f9127644b80 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -316,7 +316,7 @@
 #define SKX_UPI_PCI_PMON_CTL0		0x350
 #define SKX_UPI_PCI_PMON_CTR0		0x318
 #define SKX_UPI_PCI_PMON_BOX_CTL	0x378
-#define SKX_PMON_CTL_UMASK_EXT		0xff
+#define SKX_UPI_CTL_UMASK_EXT		0xffefff
 
 /* SKX M2M */
 #define SKX_M2M_PCI_PMON_CTL0		0x228
@@ -328,7 +328,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
 DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
 DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
 DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -351,7 +351,6 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12");
-DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
@@ -3302,7 +3301,6 @@ static struct attribute *skx_uncore_cha_formats_attr[] = {
 	&format_attr_inv.attr,
 	&format_attr_thresh8.attr,
 	&format_attr_filter_tid4.attr,
-	&format_attr_filter_link4.attr,
 	&format_attr_filter_state5.attr,
 	&format_attr_filter_rem.attr,
 	&format_attr_filter_loc.attr,
@@ -3312,7 +3310,6 @@ static struct attribute *skx_uncore_cha_formats_attr[] = {
 	&format_attr_filter_opc_0.attr,
 	&format_attr_filter_opc_1.attr,
 	&format_attr_filter_nc.attr,
-	&format_attr_filter_c6.attr,
 	&format_attr_filter_isoc.attr,
 	NULL,
 };
@@ -3333,8 +3330,11 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x3134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+	EVENT_EXTRA_END
 };
 
 static u64 skx_cha_filter_mask(int fields)
@@ -3347,6 +3347,17 @@ static u64 skx_cha_filter_mask(int fields)
 		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK;
 	if (fields & 0x4)
 		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8) {
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_REM;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LOC;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NM;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC0;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC1;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NC;
+		mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ISOC;
+	}
 	return mask;
 }
 
@@ -3492,6 +3503,26 @@ static struct intel_uncore_type skx_uncore_irp = {
 	.format_group		= &skx_uncore_format_group,
 };
 
+static struct attribute *skx_uncore_pcu_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge_det.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute_group skx_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_pcu_formats_attr,
+};
+
 static struct intel_uncore_ops skx_uncore_pcu_ops = {
 	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 	.hw_config		= hswep_pcu_hw_config,
@@ -3510,7 +3541,7 @@ static struct intel_uncore_type skx_uncore_pcu = {
 	.box_ctl		= HSWEP_PCU_MSR_PMON_BOX_CTL,
 	.num_shared_regs	= 1,
 	.ops			= &skx_uncore_pcu_ops,
-	.format_group		= &snbep_uncore_pcu_format_group,
+	.format_group		= &skx_uncore_pcu_format_group,
 };
 
 static struct intel_uncore_type *skx_msr_uncores[] = {
@@ -3603,8 +3634,8 @@ static struct intel_uncore_type skx_uncore_upi = {
 	.perf_ctr_bits	= 48,
 	.perf_ctr	= SKX_UPI_PCI_PMON_CTR0,
 	.event_ctl	= SKX_UPI_PCI_PMON_CTL0,
-	.event_mask	= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.event_mask_ext = SKX_PMON_CTL_UMASK_EXT,
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,
+	.event_mask_ext = SKX_UPI_CTL_UMASK_EXT,
 	.box_ctl	= SKX_UPI_PCI_PMON_BOX_CTL,
 	.ops		= &skx_upi_uncore_pci_ops,
 	.format_group	= &skx_upi_uncore_format_group,
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index df002992d8fd..07b06955a05d 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -25,6 +25,8 @@ BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 		 smp_kvm_posted_intr_ipi)
 BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
 		 smp_kvm_posted_intr_wakeup_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR,
+		 smp_kvm_posted_intr_nested_ipi)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 9b76cd331990..ad1ed531febc 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -15,6 +15,7 @@ typedef struct {
 #ifdef CONFIG_HAVE_KVM
 	unsigned int kvm_posted_intr_ipis;
 	unsigned int kvm_posted_intr_wakeup_ipis;
+	unsigned int kvm_posted_intr_nested_ipis;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b90e1053049b..d6dbafbd4207 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -30,6 +30,7 @@ extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
 extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
+extern asmlinkage void kvm_posted_intr_nested_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -62,6 +63,7 @@ extern void trace_call_function_single_interrupt(void);
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
 #define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
+#define trace_kvm_posted_intr_nested_ipi kvm_posted_intr_nested_ipi
 #endif /* CONFIG_TRACING */
 
 #ifdef	CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6ca9fd6234e1..aaf8d28b5d00 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -83,7 +83,6 @@
  */
 #define X86_PLATFORM_IPI_VECTOR		0xf7
 
-#define POSTED_INTR_WAKEUP_VECTOR	0xf1
 /*
  * IRQ work vector:
  */
@@ -98,6 +97,8 @@
 /* Vector for KVM to deliver posted interrupt IPI */
 #ifdef CONFIG_HAVE_KVM
 #define POSTED_INTR_VECTOR		0xf2
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
+#define POSTED_INTR_NESTED_VECTOR	0xf0
 #endif
 
 /*
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index d869c8671e36..7cf7c70b6ef2 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -8,20 +8,25 @@
  * This file is licensed under GPLv2.
  */
 
-#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
 #include <linux/math64.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
 
 struct aperfmperf_sample {
 	unsigned int	khz;
-	unsigned long	jiffies;
+	ktime_t	time;
 	u64	aperf;
 	u64	mperf;
 };
 
 static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
 
+#define APERFMPERF_CACHE_THRESHOLD_MS	10
+#define APERFMPERF_REFRESH_DELAY_MS	20
+#define APERFMPERF_STALE_THRESHOLD_MS	1000
+
 /*
  * aperfmperf_snapshot_khz()
  * On the current CPU, snapshot APERF, MPERF, and jiffies
@@ -33,9 +38,11 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	u64 aperf, aperf_delta;
 	u64 mperf, mperf_delta;
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
+	ktime_t now = ktime_get();
+	s64 time_delta = ktime_ms_delta(now, s->time);
 
-	/* Don't bother re-computing within 10 ms */
-	if (time_before(jiffies, s->jiffies + HZ/100))
+	/* Don't bother re-computing within the cache threshold time. */
+	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
 	rdmsrl(MSR_IA32_APERF, aperf);
@@ -51,22 +58,21 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	if (mperf_delta == 0)
 		return;
 
-	/*
-	 * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
-	 *	khz = (cpu_khz * aperf_delta) / mperf_delta
-	 */
-	if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta)
-		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
-	else	/* khz = aperf_delta / (mperf_delta / cpu_khz) */
-		s->khz = div64_u64(aperf_delta,
-			div64_u64(mperf_delta, cpu_khz));
-	s->jiffies = jiffies;
+	s->time = now;
 	s->aperf = aperf;
 	s->mperf = mperf;
+
+	/* If the previous iteration was too long ago, discard it. */
+	if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
+		s->khz = 0;
+	else
+		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
 }
 
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
+	unsigned int khz;
+
 	if (!cpu_khz)
 		return 0;
 
@@ -74,6 +80,12 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 		return 0;
 
 	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
+	khz = per_cpu(samples.khz, cpu);
+	if (khz)
+		return khz;
+
+	msleep(APERFMPERF_REFRESH_DELAY_MS);
+	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
 
 	return per_cpu(samples.khz, cpu);
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 16f82a3aaec7..8ce4212e2b8d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer)
 	return 0;
 }
 
-static int hpet_resume(struct clock_event_device *evt, int timer)
-{
-	if (!timer) {
-		hpet_enable_legacy_int();
-	} else {
-		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
-		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
-		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_hardirq(hdev->irq);
-		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
-		enable_irq(hdev->irq);
-	}
+static int hpet_resume(struct clock_event_device *evt)
+{
+	hpet_enable_legacy_int();
 	hpet_print_config();
-
 	return 0;
 }
 
@@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt)
 
 static int hpet_legacy_resume(struct clock_event_device *evt)
 {
-	return hpet_resume(evt, 0);
+	return hpet_resume(evt);
 }
 
 static int hpet_legacy_next_event(unsigned long delta,
@@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt)
 static int hpet_msi_resume(struct clock_event_device *evt)
 {
 	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+	struct irq_data *data = irq_get_irq_data(hdev->irq);
+	struct msi_msg msg;
 
-	return hpet_resume(evt, hdev->num);
+	/* Restore the MSI msg and unmask the interrupt */
+	irq_chip_compose_msi_msg(data, &msg);
+	hpet_msi_write(hdev, &msg);
+	hpet_msi_unmask(data);
+	return 0;
 }
 
 static int hpet_msi_next_event(unsigned long delta,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4aa03c5a14c9..4ed0aba8dbc8 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
 	seq_puts(p, "  Posted-interrupt notification event\n");
 
+	seq_printf(p, "%*s: ", prec, "NPI");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ",
+			   irq_stats(j)->kvm_posted_intr_nested_ipis);
+	seq_puts(p, "  Nested posted-interrupt event\n");
+
 	seq_printf(p, "%*s: ", prec, "PIW");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ",
@@ -313,6 +319,19 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
 	exiting_irq();
 	set_irq_regs(old_regs);
 }
+
+/*
+ * Handler for POSTED_INTERRUPT_NESTED_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	entering_ack_irq();
+	inc_irq_stat(kvm_posted_intr_nested_ipis);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 #endif
 
 __visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 7468c6987547..c7fd18526c3e 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -150,6 +150,8 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
 	/* IPI for KVM to deliver interrupt to wake up tasks */
 	alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
+	/* IPI for KVM to deliver nested posted interrupt */
+	alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi);
 #endif
 
 	/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6b877807598b..f0153714ddac 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -457,6 +457,8 @@ static int arch_copy_kprobe(struct kprobe *p)
 
 int arch_prepare_kprobe(struct kprobe *p)
 {
+	int ret;
+
 	if (alternatives_text_reserved(p->addr, p->addr))
 		return -EINVAL;
 
@@ -467,7 +469,13 @@ int arch_prepare_kprobe(struct kprobe *p)
 	if (!p->ainsn.insn)
 		return -ENOMEM;
 
-	return arch_copy_kprobe(p);
+	ret = arch_copy_kprobe(p);
+	if (ret) {
+		free_insn_slot(p->ainsn.insn, 0);
+		p->ainsn.insn = NULL;
+	}
+
+	return ret;
 }
 
 void arch_arm_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 71c17a5be983..d04e30e3c0ff 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
 			local_irq_disable();
-			rcu_irq_enter();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_swait(&n.wq, &wait);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 67393fc88353..a56bf6051f4e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -471,12 +471,12 @@ static int __init reboot_init(void)
 
 	/*
 	 * The DMI quirks table takes precedence. If no quirks entry
-	 * matches and the ACPI Hardware Reduced bit is set, force EFI
-	 * reboot.
+	 * matches and the ACPI Hardware Reduced bit is set and EFI
+	 * runtime services are enabled, force EFI reboot.
 	 */
 	rv = dmi_check_system(reboot_dmi_table);
 
-	if (!rv && efi_reboot_required())
+	if (!rv && efi_reboot_required() && !efi_runtime_disabled())
 		reboot_type = BOOT_EFI;
 
 	return 0;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 2819d4c123eb..589dcc117086 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1495,11 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	WARN_ON(preemptible());
 	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
-	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
-	preempt_enable();
 }
 
 static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1507,6 +1506,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 	int r;
 
+	WARN_ON(preemptible());
 	if (!kvm_x86_ops->set_hv_timer)
 		return false;
 
@@ -1538,6 +1538,8 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 static void start_sw_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	WARN_ON(preemptible());
 	if (apic->lapic_timer.hv_timer_in_use)
 		cancel_hv_timer(apic);
 	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
@@ -1552,15 +1554,20 @@ static void start_sw_timer(struct kvm_lapic *apic)
 
 static void restart_apic_timer(struct kvm_lapic *apic)
 {
+	preempt_disable();
 	if (!start_hv_timer(apic))
 		start_sw_timer(apic);
+	preempt_enable();
 }
 
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	preempt_disable();
+	/* If the preempt notifier has already run, it also called apic_timer_expired */
+	if (!apic->lapic_timer.hv_timer_in_use)
+		goto out;
 	WARN_ON(swait_active(&vcpu->wq));
 	cancel_hv_timer(apic);
 	apic_timer_expired(apic);
@@ -1569,6 +1576,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 		advance_periodic_target_expiration(apic);
 		restart_apic_timer(apic);
 	}
+out:
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
 
@@ -1582,9 +1591,11 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	preempt_disable();
 	/* Possibly the TSC deadline timer is not enabled yet */
 	if (apic->lapic_timer.hv_timer_in_use)
 		start_sw_timer(apic);
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 4d8141e533c3..1107626938cc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2430,6 +2430,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
 	svm->vmcb->control.exit_code_hi = 0;
 	svm->vmcb->control.exit_info_1 = error_code;
+
+	/*
+	 * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
+	 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+	 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
+	 * written only when inject_pending_event runs (DR6 would written here
+	 * too).  This should be conditional on a new capability---if the
+	 * capability is disabled, kvm_multiple_exception would write the
+	 * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+	 */
 	if (svm->vcpu.arch.exception.nested_apf)
 		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
 	else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 29fd8af5c347..9b21b1223035 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -416,13 +416,10 @@ struct nested_vmx {
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
-	/* The host-usable pointer to the above */
-	struct page *current_vmcs12_page;
-	struct vmcs12 *current_vmcs12;
 	/*
 	 * Cache of the guest's VMCS, existing outside of guest memory.
 	 * Loaded from guest memory during VMPTRLD. Flushed to guest
-	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
+	 * memory during VMCLEAR and VMPTRLD.
 	 */
 	struct vmcs12 *cached_vmcs12;
 	/*
@@ -563,7 +560,6 @@ struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
 	u8                    fail;
-	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
@@ -928,6 +924,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+					    u16 error_code);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2429,6 +2429,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	vmx_set_interrupt_shadow(vcpu, 0);
 }
 
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+					       unsigned long exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+	if (vcpu->arch.exception.has_error_code) {
+		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
+
+	if (kvm_exception_is_soft(nr))
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+	    vmx_get_nmi_mask(vcpu))
+		intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
 /*
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
@@ -2438,23 +2462,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	unsigned int nr = vcpu->arch.exception.nr;
 
-	if (!((vmcs12->exception_bitmap & (1u << nr)) ||
-		(nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
-		return 0;
+	if (nr == PF_VECTOR) {
+		if (vcpu->arch.exception.nested_apf) {
+			nested_vmx_inject_exception_vmexit(vcpu,
+							   vcpu->arch.apf.nested_apf_token);
+			return 1;
+		}
+		/*
+		 * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
+		 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+		 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
+		 * can be written only when inject_pending_event runs.  This should be
+		 * conditional on a new capability---if the capability is disabled,
+		 * kvm_multiple_exception would write the ancillary information to
+		 * CR2 or DR6, for backwards ABI-compatibility.
+		 */
+		if (nested_vmx_is_page_fault_vmexit(vmcs12,
+						    vcpu->arch.exception.error_code)) {
+			nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+			return 1;
+		}
+	} else {
+		unsigned long exit_qual = 0;
+		if (nr == DB_VECTOR)
+			exit_qual = vcpu->arch.dr6;
 
-	if (vcpu->arch.exception.nested_apf) {
-		vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
-			INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
-			vcpu->arch.apf.nested_apf_token);
-		return 1;
+		if (vmcs12->exception_bitmap & (1u << nr)) {
+			nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+			return 1;
+		}
 	}
 
-	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			  vmcs_read32(VM_EXIT_INTR_INFO),
-			  vmcs_readl(EXIT_QUALIFICATION));
-	return 1;
+	return 0;
 }
 
 static void vmx_queue_exception(struct kvm_vcpu *vcpu)
@@ -2668,7 +2707,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * reason is that if one of these bits is necessary, it will appear
 	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
 	 * fields of vmcs01 and vmcs02, will turn these bits off - and
-	 * nested_vmx_exit_handled() will not pass related exits to L1.
+	 * nested_vmx_exit_reflected() will not pass related exits to L1.
 	 * These rules have exceptions below.
 	 */
 
@@ -4956,6 +4995,28 @@ static bool vmx_get_enable_apicv(void)
 	return enable_apicv;
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4963,18 +5024,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	void *vapic_page;
 	u16 status;
 
-	if (vmx->nested.pi_desc &&
-	    vmx->nested.pi_pending) {
-		vmx->nested.pi_pending = false;
-		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return;
-
-		max_irr = find_last_bit(
-			(unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
 
-		if (max_irr == 256)
-			return;
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
 
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
@@ -4986,11 +5044,16 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+						     bool nested)
 {
 #ifdef CONFIG_SMP
+	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
+
 	if (vcpu->mode == IN_GUEST_MODE) {
 		struct vcpu_vmx *vmx = to_vmx(vcpu);
 
@@ -5008,8 +5071,7 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
 		 */
 		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
 
-		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
 		return true;
 	}
 #endif
@@ -5024,7 +5086,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
 		/* the PIR and ON have been set by L1. */
-		kvm_vcpu_trigger_posted_interrupt(vcpu);
+		kvm_vcpu_trigger_posted_interrupt(vcpu, true);
 		/*
 		 * If a posted intr is not recognized by hardware,
 		 * we will accomplish it in the next vmentry.
@@ -5058,7 +5120,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return;
 
-	if (!kvm_vcpu_trigger_posted_interrupt(vcpu))
+	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 }
 
@@ -7133,34 +7195,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
 static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 {
 	if (vmx->nested.current_vmptr == -1ull)
 		return;
 
-	/* current_vmptr and current_vmcs12 are always set/reset together */
-	if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
-		return;
-
 	if (enable_shadow_vmcs) {
 		/* copy to memory all shadowed fields in case
 		   they were modified */
 		copy_shadow_to_vmcs12(vmx);
 		vmx->nested.sync_shadow_vmcs = false;
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-				SECONDARY_EXEC_SHADOW_VMCS);
-		vmcs_write64(VMCS_LINK_POINTER, -1ull);
+		vmx_disable_shadow_vmcs(vmx);
 	}
 	vmx->nested.posted_intr_nv = -1;
 
 	/* Flush VMCS12 to guest memory */
-	memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
-	       VMCS12_SIZE);
+	kvm_vcpu_write_guest_page(&vmx->vcpu,
+				  vmx->nested.current_vmptr >> PAGE_SHIFT,
+				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
 
-	kunmap(vmx->nested.current_vmcs12_page);
-	nested_release_page(vmx->nested.current_vmcs12_page);
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 }
 
 /*
@@ -7174,12 +7234,14 @@ static void free_nested(struct vcpu_vmx *vmx)
 
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
-	nested_release_vmcs12(vmx);
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
 	if (vmx->nested.msr_bitmap) {
 		free_page((unsigned long)vmx->nested.msr_bitmap);
 		vmx->nested.msr_bitmap = NULL;
 	}
 	if (enable_shadow_vmcs) {
+		vmx_disable_shadow_vmcs(vmx);
 		vmcs_clear(vmx->vmcs01.shadow_vmcs);
 		free_vmcs(vmx->vmcs01.shadow_vmcs);
 		vmx->vmcs01.shadow_vmcs = NULL;
@@ -7578,14 +7640,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		}
 
 		nested_release_vmcs12(vmx);
-		vmx->nested.current_vmcs12 = new_vmcs12;
-		vmx->nested.current_vmcs12_page = page;
 		/*
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12,
-		       vmx->nested.current_vmcs12, VMCS12_SIZE);
+		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+		kunmap(page);
+		nested_release_page_clean(page);
+
 		set_current_vmptr(vmx, vmptr);
 	}
 
@@ -8018,12 +8080,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
  * should handle it ourselves in L0 (and then continue L2). Only call this
  * when in is_guest_mode (L2).
  */
-static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 {
 	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 exit_reason = vmx->exit_reason;
 
 	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
 				vmcs_readl(EXIT_QUALIFICATION),
@@ -8032,6 +8093,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
+	 * may write to these pages via their host physical address while
+	 * L2 is running, bypassing any address-translation-based dirty
+	 * tracking (e.g. EPT write protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
 	if (vmx->nested.nested_run_pending)
 		return false;
 
@@ -8168,6 +8241,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	}
 }
 
+static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/*
+	 * At this point, the exit interruption info in exit_intr_info
+	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
+	 * we need to query the in-kernel LAPIC.
+	 */
+	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+	if ((exit_intr_info &
+	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		vmcs12->vm_exit_intr_error_code =
+			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+	}
+
+	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+			  vmcs_readl(EXIT_QUALIFICATION));
+	return 1;
+}
+
 static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 {
 	*info1 = vmcs_readl(EXIT_QUALIFICATION);
@@ -8414,12 +8510,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
-	if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
-		nested_vmx_vmexit(vcpu, exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-		return 1;
-	}
+	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+		return nested_vmx_reflect_vmexit(vcpu, exit_reason);
 
 	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
 		dump_vmcs();
@@ -9222,7 +9314,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
@@ -9508,12 +9599,15 @@ 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))
-		nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-	else
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+		vmcs12->vm_exit_intr_error_code = fault->error_code;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+				  fault->address);
+	} else {
 		kvm_inject_page_fault(vcpu, fault);
+	}
 }
 
 static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
@@ -10041,6 +10135,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			     vmcs12->vm_entry_instruction_len);
 		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
 			     vmcs12->guest_interruptibility_info);
+		vmx->loaded_vmcs->nmi_known_unmasked =
+			!(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
 	} else {
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
 	}
@@ -10065,13 +10161,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
 	if (nested_cpu_has_posted_intr(vmcs12)) {
-		/*
-		 * Note that we use L0's vector here and in
-		 * vmx_deliver_nested_posted_interrupt.
-		 */
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
 		vmx->nested.pi_pending = false;
-		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
 	} else {
 		exec_control &= ~PIN_BASED_POSTED_INTR;
 	}
@@ -10095,12 +10187,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
 	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
 	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
-	 *
-	 * A problem with this approach (when !enable_ept) is that L1 may be
-	 * injected with more page faults than it asked for. This could have
-	 * caused problems, but in practice existing hypervisors don't care.
-	 * To fix this, we will need to emulate the PFEC checking (on the L1
-	 * page tables), using walk_addr(), when injecting PFs to L1.
 	 */
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
 		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
@@ -10848,13 +10934,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	vmcs12->vm_exit_reason = exit_reason;
 	vmcs12->exit_qualification = exit_qualification;
-
 	vmcs12->vm_exit_intr_info = exit_intr_info;
-	if ((vmcs12->vm_exit_intr_info &
-	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
-	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK))
-		vmcs12->vm_exit_intr_error_code =
-			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
 	vmcs12->idt_vectoring_info_field = 0;
 	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
@@ -10942,7 +11023,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		 */
 		vmx_flush_tlb(vcpu);
 	}
-
+	/* Restore posted intr vector. */
+	if (nested_cpu_has_posted_intr(vmcs12))
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
 
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
 	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
@@ -11048,8 +11131,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
-	    && nested_exit_intr_ack_set(vcpu)) {
+	/*
+	 * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of
+	 * the VM-exit interrupt information (valid interrupt) is always set to
+	 * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need
+	 * kvm_cpu_has_interrupt().  See the commit message for details.
+	 */
+	if (nested_exit_intr_ack_set(vcpu) &&
+	    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+	    kvm_cpu_has_interrupt(vcpu)) {
 		int irq = kvm_cpu_get_interrupt(vcpu);
 		WARN_ON(irq < 0);
 		vmcs12->vm_exit_intr_info = irq |
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 82a63c59f77b..d734aa8c5b4f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -597,8 +597,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 		      (unsigned long *)&vcpu->arch.regs_avail))
 		return true;
 
-	gfn = (kvm_read_cr3(vcpu) & ~31ul) >> PAGE_SHIFT;
-	offset = (kvm_read_cr3(vcpu) & ~31ul) & (PAGE_SIZE - 1);
+	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
+	offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1);
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
@@ -3159,15 +3159,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		kvm_set_hflags(vcpu, hflags);
 
 		vcpu->arch.smi_pending = events->smi.pending;
-		if (events->smi.smm_inside_nmi)
-			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
-		else
-			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-		if (lapic_in_kernel(vcpu)) {
-			if (events->smi.latched_init)
-				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+
+		if (events->smi.smm) {
+			if (events->smi.smm_inside_nmi)
+				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
-				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+			if (lapic_in_kernel(vcpu)) {
+				if (events->smi.latched_init)
+					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				else
+					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			}
 		}
 	}
 
@@ -6215,6 +6218,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 
 	lapic_irq.shorthand = 0;
 	lapic_irq.dest_mode = 0;
+	lapic_irq.level = 0;
 	lapic_irq.dest_id = apicid;
 	lapic_irq.msi_redir_hint = false;