23 files changed, 330 insertions, 524 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3c3622176340..b1b78ffe01d0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -71,8 +71,8 @@ obj-$(CONFIG_LIVEPATCH)		+= livepatch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
-obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
+obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-y				+= kprobes/
@@ -94,7 +94,7 @@ obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
-obj-$(CONFIG_X86_PMEM_LEGACY)	+= pmem.o
+obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 75e8bad53798..ded848c20e05 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -445,6 +445,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
 	mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+	acpi_penalize_sci_irq(bus_irq, trigger, polarity);
 
 	/*
 	 * stash over-ride to indicate we've been here
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5aba9220a5ac..3ca3e46aa405 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -462,40 +462,40 @@ static int lapic_next_deadline(unsigned long delta,
 	return 0;
 }
 
-/*
- * Setup the lapic timer in periodic or oneshot mode
- */
-static void lapic_timer_setup(enum clock_event_mode mode,
-			      struct clock_event_device *evt)
+static int lapic_timer_shutdown(struct clock_event_device *evt)
 {
-	unsigned long flags;
 	unsigned int v;
 
 	/* Lapic used as dummy for broadcast ? */
 	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
-		return;
+		return 0;
 
-	local_irq_save(flags);
+	v = apic_read(APIC_LVTT);
+	v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+	apic_write(APIC_LVTT, v);
+	apic_write(APIC_TMICT, 0);
+	return 0;
+}
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-	case CLOCK_EVT_MODE_ONESHOT:
-		__setup_APIC_LVTT(lapic_timer_frequency,
-				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		v = apic_read(APIC_LVTT);
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write(APIC_LVTT, v);
-		apic_write(APIC_TMICT, 0);
-		break;
-	case CLOCK_EVT_MODE_RESUME:
-		/* Nothing to do here */
-		break;
-	}
+static inline int
+lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
+{
+	/* Lapic used as dummy for broadcast ? */
+	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
 
-	local_irq_restore(flags);
+	__setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+	return 0;
+}
+
+static int lapic_timer_set_periodic(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, false);
+}
+
+static int lapic_timer_set_oneshot(struct clock_event_device *evt)
+{
+	return lapic_timer_set_periodic_oneshot(evt, true);
 }
 
 /*
@@ -513,15 +513,18 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
  * The local apic timer can be used for any function which is CPU local.
  */
 static struct clock_event_device lapic_clockevent = {
-	.name		= "lapic",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
-			| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
-	.shift		= 32,
-	.set_mode	= lapic_timer_setup,
-	.set_next_event	= lapic_next_event,
-	.broadcast	= lapic_timer_broadcast,
-	.rating		= 100,
-	.irq		= -1,
+	.name			= "lapic",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
+				  | CLOCK_EVT_FEAT_DUMMY,
+	.shift			= 32,
+	.set_state_shutdown	= lapic_timer_shutdown,
+	.set_state_periodic	= lapic_timer_set_periodic,
+	.set_state_oneshot	= lapic_timer_set_oneshot,
+	.set_next_event		= lapic_next_event,
+	.broadcast		= lapic_timer_broadcast,
+	.rating			= 100,
+	.irq			= -1,
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
@@ -778,7 +781,7 @@ static int __init calibrate_APIC_clock(void)
 		 * Setup the apic timer manually
 		 */
 		levt->event_handler = lapic_cal_handler;
-		lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
+		lapic_timer_set_periodic(levt);
 		lapic_cal_loops = -1;
 
 		/* Let the interrupts run */
@@ -788,7 +791,8 @@ static int __init calibrate_APIC_clock(void)
 			cpu_relax();
 
 		/* Stop the lapic timer */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
+		local_irq_disable();
+		lapic_timer_shutdown(levt);
 
 		/* Jiffies delta */
 		deltaj = lapic_cal_j2 - lapic_cal_j1;
@@ -799,8 +803,8 @@ static int __init calibrate_APIC_clock(void)
 			apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
 		else
 			levt->features |= CLOCK_EVT_FEAT_DUMMY;
-	} else
-		local_irq_enable();
+	}
+	local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
@@ -878,7 +882,7 @@ static void local_apic_timer_interrupt(void)
 	if (!evt->event_handler) {
 		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
 		/* Switch it off */
-		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		lapic_timer_shutdown(evt);
 		return;
 	}
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 6873ab925d00..045e424fb368 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -28,146 +28,21 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh)
 #endif
 
 #ifdef arch_trigger_all_cpu_backtrace
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-static cpumask_t printtrace_mask;
-
-#define NMI_BUF_SIZE		4096
-
-struct nmi_seq_buf {
-	unsigned char		buffer[NMI_BUF_SIZE];
-	struct seq_buf		seq;
-};
-
-/* Safe printing in NMI context */
-static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
-
-/* "in progress" flag of arch_trigger_all_cpu_backtrace */
-static unsigned long backtrace_flag;
-
-static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void nmi_raise_cpu_backtrace(cpumask_t *mask)
 {
-	const char *buf = s->buffer + start;
-
-	printk("%.*s", (end - start) + 1, buf);
+	apic->send_IPI_mask(mask, NMI_VECTOR);
 }
 
 void arch_trigger_all_cpu_backtrace(bool include_self)
 {
-	struct nmi_seq_buf *s;
-	int len;
-	int cpu;
-	int i;
-	int this_cpu = get_cpu();
-
-	if (test_and_set_bit(0, &backtrace_flag)) {
-		/*
-		 * If there is already a trigger_all_cpu_backtrace() in progress
-		 * (backtrace_flag == 1), don't output double cpu dump infos.
-		 */
-		put_cpu();
-		return;
-	}
-
-	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
-	if (!include_self)
-		cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
-
-	cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
-	/*
-	 * Set up per_cpu seq_buf buffers that the NMIs running on the other
-	 * CPUs will write to.
-	 */
-	for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
-		s = &per_cpu(nmi_print_seq, cpu);
-		seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
-	}
-
-	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
-		pr_info("sending NMI to %s CPUs:\n",
-			(include_self ? "all" : "other"));
-		apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
-	}
-
-	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
-	for (i = 0; i < 10 * 1000; i++) {
-		if (cpumask_empty(to_cpumask(backtrace_mask)))
-			break;
-		mdelay(1);
-		touch_softlockup_watchdog();
-	}
-
-	/*
-	 * Now that all the NMIs have triggered, we can dump out their
-	 * back traces safely to the console.
-	 */
-	for_each_cpu(cpu, &printtrace_mask) {
-		int last_i = 0;
-
-		s = &per_cpu(nmi_print_seq, cpu);
-		len = seq_buf_used(&s->seq);
-		if (!len)
-			continue;
-
-		/* Print line by line. */
-		for (i = 0; i < len; i++) {
-			if (s->buffer[i] == '\n') {
-				print_seq_line(s, last_i, i);
-				last_i = i + 1;
-			}
-		}
-		/* Check if there was a partial line. */
-		if (last_i < len) {
-			print_seq_line(s, last_i, len - 1);
-			pr_cont("\n");
-		}
-	}
-
-	clear_bit(0, &backtrace_flag);
-	smp_mb__after_atomic();
-	put_cpu();
-}
-
-/*
- * It is not safe to call printk() directly from NMI handlers.
- * It may be fine if the NMI detected a lock up and we have no choice
- * but to do so, but doing a NMI on all other CPUs to get a back trace
- * can be done with a sysrq-l. We don't want that to lock up, which
- * can happen if the NMI interrupts a printk in progress.
- *
- * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
- * the content into a per cpu seq_buf buffer. Then when the NMIs are
- * all done, we can safely dump the contents of the seq_buf to a printk()
- * from a non NMI context.
- */
-static int nmi_vprintk(const char *fmt, va_list args)
-{
-	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
-	unsigned int len = seq_buf_used(&s->seq);
-
-	seq_buf_vprintf(&s->seq, fmt, args);
-	return seq_buf_used(&s->seq) - len;
+	nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace);
 }
 
 static int
 arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	int cpu;
-
-	cpu = smp_processor_id();
-
-	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		printk_func_t printk_func_save = this_cpu_read(printk_func);
-
-		/* Replace printk to write into the NMI seq */
-		this_cpu_write(printk_func, nmi_vprintk);
-		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
-		show_regs(regs);
-		this_cpu_write(printk_func, printk_func_save);
-
-		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+	if (nmi_cpu_backtrace(regs))
 		return NMI_HANDLED;
-	}
 
 	return NMI_DONE;
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 206052e55517..38a76f826530 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2541,7 +2541,7 @@ void __init setup_ioapic_dest(void)
 		 * Honour affinities which have been set in early boot
 		 */
 		if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
-			mask = idata->affinity;
+			mask = irq_data_get_affinity_mask(idata);
 		else
 			mask = apic->target_cpus();
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 1a9d735e09c6..5f1feb6854af 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -264,7 +264,7 @@ static inline int hpet_dev_id(struct irq_domain *domain)
 
 static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	hpet_msi_write(data->handler_data, msg);
+	hpet_msi_write(irq_data_get_irq_handler_data(data), msg);
 }
 
 static struct irq_chip hpet_msi_controller = {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 2683f36e4e0a..1bbd0fe2c806 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -169,8 +169,7 @@ next:
 			goto next;
 
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
-			if (per_cpu(vector_irq, new_cpu)[vector] >
-			    VECTOR_UNDEFINED)
+			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
@@ -182,7 +181,7 @@ next:
 			   cpumask_intersects(d->old_domain, cpu_online_mask);
 		}
 		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
-			per_cpu(vector_irq, new_cpu)[vector] = irq;
+			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
 		d->cfg.vector = vector;
 		cpumask_copy(d->domain, vector_cpumask);
 		err = 0;
@@ -224,15 +223,16 @@ static int assign_irq_vector_policy(int irq, int node,
 
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
-	int cpu, vector;
+	struct irq_desc *desc;
 	unsigned long flags;
+	int cpu, vector;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
-		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
@@ -242,12 +242,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		return;
 	}
 
+	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 		     vector++) {
-			if (per_cpu(vector_irq, cpu)[vector] != irq)
+			if (per_cpu(vector_irq, cpu)[vector] != desc)
 				continue;
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 			break;
 		}
 	}
@@ -296,7 +297,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	struct irq_alloc_info *info = arg;
 	struct apic_chip_data *data;
 	struct irq_data *irq_data;
-	int i, err;
+	int i, err, node;
 
 	if (disable_apic)
 		return -ENXIO;
@@ -308,12 +309,13 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		BUG_ON(!irq_data);
+		node = irq_data_get_node(irq_data);
 #ifdef	CONFIG_X86_IO_APIC
 		if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
 			data = legacy_irq_data[virq + i];
 		else
 #endif
-			data = alloc_apic_chip_data(irq_data->node);
+			data = alloc_apic_chip_data(node);
 		if (!data) {
 			err = -ENOMEM;
 			goto error;
@@ -322,8 +324,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector_policy(virq + i, irq_data->node, data,
-					       info);
+		err = assign_irq_vector_policy(virq + i, node, data, info);
 		if (err)
 			goto error;
 	}
@@ -403,32 +404,32 @@ int __init arch_early_irq_init(void)
 	return arch_early_ioapic_init();
 }
 
+/* Initialize vector_irq on a new cpu */
 static void __setup_vector_irq(int cpu)
 {
-	/* Initialize vector_irq on a new cpu */
-	int irq, vector;
 	struct apic_chip_data *data;
+	struct irq_desc *desc;
+	int irq, vector;
 
 	/* Mark the inuse vectors */
-	for_each_active_irq(irq) {
-		data = apic_chip_data(irq_get_irq_data(irq));
-		if (!data)
-			continue;
+	for_each_irq_desc(irq, desc) {
+		struct irq_data *idata = irq_desc_get_irq_data(desc);
 
-		if (!cpumask_test_cpu(cpu, data->domain))
+		data = apic_chip_data(idata);
+		if (!data || !cpumask_test_cpu(cpu, data->domain))
 			continue;
 		vector = data->cfg.vector;
-		per_cpu(vector_irq, cpu)[vector] = irq;
+		per_cpu(vector_irq, cpu)[vector] = desc;
 	}
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
-		irq = per_cpu(vector_irq, cpu)[vector];
-		if (irq <= VECTOR_UNDEFINED)
+		desc = per_cpu(vector_irq, cpu)[vector];
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		data = apic_chip_data(irq_get_irq_data(irq));
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!cpumask_test_cpu(cpu, data->domain))
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
 	}
 }
 
@@ -448,7 +449,7 @@ void setup_vector_irq(int cpu)
 	 * legacy vector to irq mapping:
 	 */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
+		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq);
 
 	__setup_vector_irq(cpu);
 }
@@ -490,7 +491,8 @@ static int apic_set_affinity(struct irq_data *irq_data,
 	if (err) {
 		struct irq_data *top = irq_get_irq_data(irq);
 
-		if (assign_irq_vector(irq, data, top->affinity))
+		if (assign_irq_vector(irq, data,
+				      irq_data_get_affinity_mask(top)))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
@@ -538,27 +540,30 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 
 	entering_ack_irq();
 
+	/* Prevent vectors vanishing under us */
+	raw_spin_lock(&vector_lock);
+
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		int irq;
-		unsigned int irr;
-		struct irq_desc *desc;
 		struct apic_chip_data *data;
+		struct irq_desc *desc;
+		unsigned int irr;
 
-		irq = __this_cpu_read(vector_irq[vector]);
-
-		if (irq <= VECTOR_UNDEFINED)
+	retry:
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
 			continue;
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
+		if (!raw_spin_trylock(&desc->lock)) {
+			raw_spin_unlock(&vector_lock);
+			cpu_relax();
+			raw_spin_lock(&vector_lock);
+			goto retry;
+		}
 
-		data = apic_chip_data(&desc->irq_data);
+		data = apic_chip_data(irq_desc_get_irq_data(desc));
 		if (!data)
-			continue;
-
-		raw_spin_lock(&desc->lock);
+			goto unlock;
 
 		/*
 		 * Check if the irq migration is in progress. If so, we
@@ -583,11 +588,13 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
 			goto unlock;
 		}
-		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
 
+	raw_spin_unlock(&vector_lock);
+
 	exiting_irq();
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3f124d553c5a..cd9b6d0b10bf 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <linux/watchdog.h>
+#include <linux/nmi.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
@@ -3627,7 +3627,10 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	watchdog_nmi_disable_all();
+	if (lockup_detector_suspend() != 0) {
+		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
+		return 0;
+	}
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -3635,7 +3638,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	watchdog_nmi_enable_all();
+	lockup_detector_resume();
 
 	get_online_cpus();
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f75c5908c7a6..88b4da373081 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -226,22 +226,7 @@ static void hpet_reserve_platform_timers(unsigned int id) { }
  */
 static unsigned long hpet_freq;
 
-static void hpet_legacy_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt);
-static int hpet_legacy_next_event(unsigned long delta,
-			   struct clock_event_device *evt);
-
-/*
- * The hpet clock event device
- */
-static struct clock_event_device hpet_clockevent = {
-	.name		= "hpet",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= hpet_legacy_set_mode,
-	.set_next_event = hpet_legacy_next_event,
-	.irq		= 0,
-	.rating		= 50,
-};
+static struct clock_event_device hpet_clockevent;
 
 static void hpet_stop_counter(void)
 {
@@ -306,64 +291,74 @@ static void hpet_legacy_clockevent_register(void)
 	printk(KERN_DEBUG "hpet clockevent registered\n");
 }
 
-static void hpet_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt, int timer)
+static int hpet_set_periodic(struct clock_event_device *evt, int timer)
 {
 	unsigned int cfg, cmp, now;
 	uint64_t delta;
 
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		hpet_stop_counter();
-		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
-		delta >>= evt->shift;
-		now = hpet_readl(HPET_COUNTER);
-		cmp = now + (unsigned int) delta;
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
-		       HPET_TN_SETVAL | HPET_TN_32BIT;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		hpet_writel(cmp, HPET_Tn_CMP(timer));
-		udelay(1);
-		/*
-		 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
-		 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
-		 * bit is automatically cleared after the first write.
-		 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
-		 * Publication # 24674)
-		 */
-		hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer));
-		hpet_start_counter();
-		hpet_print_config();
-		break;
+	hpet_stop_counter();
+	delta = ((uint64_t)(NSEC_PER_SEC / HZ)) * evt->mult;
+	delta >>= evt->shift;
+	now = hpet_readl(HPET_COUNTER);
+	cmp = now + (unsigned int)delta;
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
+	       HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_Tn_CFG(timer));
+	hpet_writel(cmp, HPET_Tn_CMP(timer));
+	udelay(1);
+	/*
+	 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+	 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+	 * bit is automatically cleared after the first write.
+	 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+	 * Publication # 24674)
+	 */
+	hpet_writel((unsigned int)delta, HPET_Tn_CMP(timer));
+	hpet_start_counter();
+	hpet_print_config();
 
-	case CLOCK_EVT_MODE_ONESHOT:
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg &= ~HPET_TN_PERIODIC;
-		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		break;
+	return 0;
+}
 
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		cfg = hpet_readl(HPET_Tn_CFG(timer));
-		cfg &= ~HPET_TN_ENABLE;
-		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		break;
+static int hpet_set_oneshot(struct clock_event_device *evt, int timer)
+{
+	unsigned int cfg;
 
-	case CLOCK_EVT_MODE_RESUME:
-		if (timer == 0) {
-			hpet_enable_legacy_int();
-		} else {
-			struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-			irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-			disable_irq(hdev->irq);
-			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
-			enable_irq(hdev->irq);
-		}
-		hpet_print_config();
-		break;
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg &= ~HPET_TN_PERIODIC;
+	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_Tn_CFG(timer));
+
+	return 0;
+}
+
+static int hpet_shutdown(struct clock_event_device *evt, int timer)
+{
+	unsigned int cfg;
+
+	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg &= ~HPET_TN_ENABLE;
+	hpet_writel(cfg, HPET_Tn_CFG(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_activate_irq(irq_get_irq_data(hdev->irq));
+		disable_irq(hdev->irq);
+		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
+		enable_irq(hdev->irq);
 	}
+	hpet_print_config();
+
+	return 0;
 }
 
 static int hpet_next_event(unsigned long delta,
@@ -403,10 +398,24 @@ static int hpet_next_event(unsigned long delta,
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
-static void hpet_legacy_set_mode(enum clock_event_mode mode,
-			struct clock_event_device *evt)
+static int hpet_legacy_shutdown(struct clock_event_device *evt)
+{
+	return hpet_shutdown(evt, 0);
+}
+
+static int hpet_legacy_set_oneshot(struct clock_event_device *evt)
+{
+	return hpet_set_oneshot(evt, 0);
+}
+
+static int hpet_legacy_set_periodic(struct clock_event_device *evt)
 {
-	hpet_set_mode(mode, evt, 0);
+	return hpet_set_periodic(evt, 0);
+}
+
+static int hpet_legacy_resume(struct clock_event_device *evt)
+{
+	return hpet_resume(evt, 0);
 }
 
 static int hpet_legacy_next_event(unsigned long delta,
@@ -416,6 +425,22 @@ static int hpet_legacy_next_event(unsigned long delta,
 }
 
 /*
+ * The hpet clock event device
+ */
+static struct clock_event_device hpet_clockevent = {
+	.name			= "hpet",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_periodic	= hpet_legacy_set_periodic,
+	.set_state_oneshot	= hpet_legacy_set_oneshot,
+	.set_state_shutdown	= hpet_legacy_shutdown,
+	.tick_resume		= hpet_legacy_resume,
+	.set_next_event		= hpet_legacy_next_event,
+	.irq			= 0,
+	.rating			= 50,
+};
+
+/*
  * HPET MSI Support
  */
 #ifdef CONFIG_PCI_MSI
@@ -426,7 +451,7 @@ static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* unmask it */
@@ -437,7 +462,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 void hpet_msi_mask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = data->handler_data;
+	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
 	/* mask it */
@@ -459,11 +484,32 @@ void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 	msg->address_hi = 0;
 }
 
-static void hpet_msi_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
+static int hpet_msi_shutdown(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_shutdown(evt, hdev->num);
+}
+
+static int hpet_msi_set_oneshot(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_set_oneshot(evt, hdev->num);
+}
+
+static int hpet_msi_set_periodic(struct clock_event_device *evt)
 {
 	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-	hpet_set_mode(mode, evt, hdev->num);
+
+	return hpet_set_periodic(evt, hdev->num);
+}
+
+static int hpet_msi_resume(struct clock_event_device *evt)
+{
+	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+
+	return hpet_resume(evt, hdev->num);
 }
 
 static int hpet_msi_next_event(unsigned long delta,
@@ -523,10 +569,14 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 
 	evt->rating = 110;
 	evt->features = CLOCK_EVT_FEAT_ONESHOT;
-	if (hdev->flags & HPET_DEV_PERI_CAP)
+	if (hdev->flags & HPET_DEV_PERI_CAP) {
 		evt->features |= CLOCK_EVT_FEAT_PERIODIC;
+		evt->set_state_periodic = hpet_msi_set_periodic;
+	}
 
-	evt->set_mode = hpet_msi_set_mode;
+	evt->set_state_shutdown = hpet_msi_shutdown;
+	evt->set_state_oneshot = hpet_msi_set_oneshot;
+	evt->tick_resume = hpet_msi_resume;
 	evt->set_next_event = hpet_msi_next_event;
 	evt->cpumask = cpumask_of(hdev->cpu);
 
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index f2b96de3c7c1..efb82f07b29c 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -34,7 +34,7 @@ static int __init init_pit_clocksource(void)
 	  * - when local APIC timer is active (PIT is switched off)
 	  */
 	if (num_possible_cpus() > 1 || is_hpet_enabled() ||
-	    i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC)
+	    !clockevent_state_periodic(&i8253_clockevent))
 		return 0;
 
 	return clocksource_i8253_init();
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index ae00b355114d..f8062aaf5df9 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -214,10 +214,9 @@ u64 arch_irq_stat(void)
 __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-
+	struct irq_desc * desc;
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
-	unsigned irq;
 
 	/*
 	 * NB: Unlike exception entries, IRQ entries do not reliably
@@ -236,17 +235,17 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	/* entering_irq() tells RCU that we're not quiescent.  Check it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
 
-	irq = __this_cpu_read(vector_irq[vector]);
+	desc = __this_cpu_read(vector_irq[vector]);
 
-	if (!handle_irq(irq, regs)) {
+	if (!handle_irq(desc, regs)) {
 		ack_APIC_irq();
 
-		if (irq != VECTOR_RETRIGGERED) {
-			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n",
+		if (desc != VECTOR_RETRIGGERED) {
+			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
 					     __func__, smp_processor_id(),
-					     vector, irq);
+					     vector);
 		} else {
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 		}
 	}
 
@@ -348,10 +347,10 @@ static struct cpumask affinity_new, online_new;
  */
 int check_irq_vectors_for_cpu_disable(void)
 {
-	int irq, cpu;
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
+	int cpu;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
@@ -359,47 +358,43 @@ int check_irq_vectors_for_cpu_disable(void)
 
 	this_count = 0;
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		irq = __this_cpu_read(vector_irq[vector]);
-		if (irq >= 0) {
-			desc = irq_to_desc(irq);
-			if (!desc)
-				continue;
-
-			/*
-			 * Protect against concurrent action removal,
-			 * affinity changes etc.
-			 */
-			raw_spin_lock(&desc->lock);
-			data = irq_desc_get_irq_data(desc);
-			cpumask_copy(&affinity_new, data->affinity);
-			cpumask_clear_cpu(this_cpu, &affinity_new);
-
-			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
-				raw_spin_unlock(&desc->lock);
-				continue;
-			}
+		desc = __this_cpu_read(vector_irq[vector]);
+		if (IS_ERR_OR_NULL(desc))
+			continue;
+		/*
+		 * Protect against concurrent action removal, affinity
+		 * changes etc.
+		 */
+		raw_spin_lock(&desc->lock);
+		data = irq_desc_get_irq_data(desc);
+		cpumask_copy(&affinity_new,
+			     irq_data_get_affinity_mask(data));
+		cpumask_clear_cpu(this_cpu, &affinity_new);
 
+		/* Do not count inactive or per-cpu irqs. */
+		if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) {
 			raw_spin_unlock(&desc->lock);
-			/*
-			 * A single irq may be mapped to multiple
-			 * cpu's vector_irq[] (for example IOAPIC cluster
-			 * mode).  In this case we have two
-			 * possibilities:
-			 *
-			 * 1) the resulting affinity mask is empty; that is
-			 * this the down'd cpu is the last cpu in the irq's
-			 * affinity mask, or
-			 *
-			 * 2) the resulting affinity mask is no longer
-			 * a subset of the online cpus but the affinity
-			 * mask is not zero; that is the down'd cpu is the
-			 * last online cpu in a user set affinity mask.
-			 */
-			if (cpumask_empty(&affinity_new) ||
-			    !cpumask_subset(&affinity_new, &online_new))
-				this_count++;
+			continue;
 		}
+
+		raw_spin_unlock(&desc->lock);
+		/*
+		 * A single irq may be mapped to multiple cpu's
+		 * vector_irq[] (for example IOAPIC cluster mode).  In
+		 * this case we have two possibilities:
+		 *
+		 * 1) the resulting affinity mask is empty; that is
+		 * this the down'd cpu is the last cpu in the irq's
+		 * affinity mask, or
+		 *
+		 * 2) the resulting affinity mask is no longer a
+		 * subset of the online cpus but the affinity mask is
+		 * not zero; that is the down'd cpu is the last online
+		 * cpu in a user set affinity mask.
+		 */
+		if (cpumask_empty(&affinity_new) ||
+		    !cpumask_subset(&affinity_new, &online_new))
+			this_count++;
 	}
 
 	count = 0;
@@ -418,8 +413,8 @@ int check_irq_vectors_for_cpu_disable(void)
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
 			if (!test_bit(vector, used_vectors) &&
-			    per_cpu(vector_irq, cpu)[vector] < 0)
-					count++;
+			    IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
+			    count++;
 		}
 	}
 
@@ -455,7 +450,7 @@ void fixup_irqs(void)
 		raw_spin_lock(&desc->lock);
 
 		data = irq_desc_get_irq_data(desc);
-		affinity = data->affinity;
+		affinity = irq_data_get_affinity_mask(data);
 		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
 		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -523,14 +518,13 @@ void fixup_irqs(void)
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
-		if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED)
+		if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
 			continue;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
 		if (irr  & (1 << (vector % 32))) {
-			irq = __this_cpu_read(vector_irq[vector]);
+			desc = __this_cpu_read(vector_irq[vector]);
 
-			desc = irq_to_desc(irq);
 			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
@@ -541,7 +535,7 @@ void fixup_irqs(void)
 			raw_spin_unlock(&desc->lock);
 		}
 		if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
-			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+			__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
 	}
 }
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index cd74f5978ab9..c80cf6699678 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -148,21 +148,21 @@ void do_softirq_own_stack(void)
 	call_on_stack(__do_softirq, isp);
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
+	unsigned int irq;
 	int overflow;
 
 	overflow = check_stack_overflow();
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (IS_ERR_OR_NULL(desc))
 		return false;
 
+	irq = irq_desc_get_irq(desc);
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
-		desc->handle_irq(irq, desc);
+		generic_handle_irq_desc(irq, desc);
 	}
 
 	return true;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index bc4604e500a3..ff16ccb918f2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -68,16 +68,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 #endif
 }
 
-bool handle_irq(unsigned irq, struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	struct irq_desc *desc;
-
 	stack_overflow_check(regs);
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc))
+	if (unlikely(IS_ERR_OR_NULL(desc)))
 		return false;
 
-	generic_handle_irq_desc(irq, desc);
+	generic_handle_irq_desc(irq_desc_get_irq(desc), desc);
 	return true;
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a3a5e158ed69..1423ab1b0312 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -52,7 +52,7 @@ static struct irqaction irq2 = {
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED,
+	[0 ... NR_VECTORS - 1] = VECTOR_UNUSED,
 };
 
 int vector_used_by_percpu_irq(unsigned int vector)
@@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED)
+		if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector]))
 			return 1;
 	}
 
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
 	 * irq's migrate etc.
 	 */
 	for (i = 0; i < nr_legacy_irqs(); i++)
-		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
+		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
 	x86_init.irqs.intr_init();
 }
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 26d5a55a2736..e565e0e4d216 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -45,7 +45,7 @@ static void __jump_label_transform(struct jump_entry *entry,
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
 			 * Jump label is enabled for the first time.
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 961e51e9c6f6..0f8a6bbaaa44 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -533,7 +533,9 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 	int ret;
 
 	ret = verify_pefile_signature(kernel, kernel_len,
-				      system_trusted_keyring, &trusted);
+				      system_trusted_keyring,
+				      VERIFYING_KEXEC_PE_SIGNATURE,
+				      &trusted);
 	if (ret < 0)
 		return ret;
 	if (!trusted)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 49487b488061..2c7aafa70702 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -200,7 +200,7 @@ static void kvm_setup_secondary_clock(void)
  * kind of shutdown from our side, we unregister the clock by writting anything
  * that does not have the 'enable' bit set in the msr
  */
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
@@ -259,7 +259,7 @@ void __init kvmclock_init(void)
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
 	machine_ops.shutdown  = kvm_shutdown;
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
 	kvm_get_preset_lpj();
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 353972c1946c..84b8ef82a159 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -58,17 +58,6 @@ EXPORT_SYMBOL(x86_dma_fallback_dev);
 /* Number of entries preallocated for DMA-API debugging */
 #define PREALLOC_DMA_DEBUG_ENTRIES       65536
 
-int dma_set_mask(struct device *dev, u64 mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
 void __init pci_iommu_alloc(void)
 {
 	struct iommu_table_entry *p;
@@ -140,50 +129,19 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
 		free_pages((unsigned long)vaddr, get_order(size));
 }
 
-void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		      gfp_t gfp, struct dma_attrs *attrs)
+bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
 {
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *memory;
-
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
-		return memory;
-
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(dev))
-		return NULL;
-
-	if (!ops->alloc)
-		return NULL;
-
-	memory = ops->alloc(dev, size, dma_handle,
-			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
-
-	return memory;
-}
-EXPORT_SYMBOL(dma_alloc_attrs);
-
-void dma_free_attrs(struct device *dev, size_t size,
-		    void *vaddr, dma_addr_t bus,
-		    struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	WARN_ON(irqs_disabled());       /* for portability */
+	*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
+	*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
 
-	if (dma_release_from_coherent(dev, get_order(size), vaddr))
-		return;
+	if (!*dev)
+		*dev = &x86_dma_fallback_dev;
+	if (!is_device_dma_capable(*dev))
+		return false;
+	return true;
 
-	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free)
-		ops->free(dev, size, vaddr, bus, attrs);
 }
-EXPORT_SYMBOL(dma_free_attrs);
+EXPORT_SYMBOL(arch_dma_alloc_attrs);
 
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 64f90f53bb85..4f00b63d7ff3 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -3,80 +3,17 @@
  * Copyright (c) 2015, Intel Corporation.
  */
 #include <linux/platform_device.h>
-#include <linux/libnvdimm.h>
 #include <linux/module.h>
-#include <asm/e820.h>
-
-static void e820_pmem_release(struct device *dev)
-{
-	struct nvdimm_bus *nvdimm_bus = dev->platform_data;
-
-	if (nvdimm_bus)
-		nvdimm_bus_unregister(nvdimm_bus);
-}
-
-static struct platform_device e820_pmem = {
-	.name = "e820_pmem",
-	.id = -1,
-	.dev = {
-		.release = e820_pmem_release,
-	},
-};
-
-static const struct attribute_group *e820_pmem_attribute_groups[] = {
-	&nvdimm_bus_attribute_group,
-	NULL,
-};
-
-static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
-	&nd_region_attribute_group,
-	&nd_device_attribute_group,
-	NULL,
-};
 
 static __init int register_e820_pmem(void)
 {
-	static struct nvdimm_bus_descriptor nd_desc;
-	struct device *dev = &e820_pmem.dev;
-	struct nvdimm_bus *nvdimm_bus;
-	int rc, i;
-
-	rc = platform_device_register(&e820_pmem);
-	if (rc)
-		return rc;
-
-	nd_desc.attr_groups = e820_pmem_attribute_groups;
-	nd_desc.provider_name = "e820";
-	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
-	if (!nvdimm_bus)
-		goto err;
-	dev->platform_data = nvdimm_bus;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		struct resource res = {
-			.flags	= IORESOURCE_MEM,
-			.start	= ei->addr,
-			.end	= ei->addr + ei->size - 1,
-		};
-		struct nd_region_desc ndr_desc;
-
-		if (ei->type != E820_PRAM)
-			continue;
-
-		memset(&ndr_desc, 0, sizeof(ndr_desc));
-		ndr_desc.res = &res;
-		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
-		ndr_desc.numa_node = NUMA_NO_NODE;
-		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
-			goto err;
-	}
-
-	return 0;
-
- err:
-	dev_err(dev, "failed to register legacy persistent memory ranges\n");
-	platform_device_unregister(&e820_pmem);
-	return -ENXIO;
+	struct platform_device *pdev;
+
+	/*
+	 * See drivers/nvdimm/e820.c for the implementation, this is
+	 * simply here to trigger the module to load on demand.
+	 */
+	pdev = platform_device_alloc("e820_pmem", -1);
+	return platform_device_add(pdev);
 }
 device_initcall(register_e820_pmem);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 86db4bcd7ce5..02693dd9a079 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -673,7 +673,7 @@ struct machine_ops machine_ops = {
 	.emergency_restart = native_machine_emergency_restart,
 	.restart = native_machine_restart,
 	.halt = native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.crash_shutdown = native_machine_crash_shutdown,
 #endif
 };
@@ -703,7 +703,7 @@ void machine_halt(void)
 	machine_ops.halt();
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	machine_ops.crash_shutdown(regs);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b143c2d04420..fdb7f2a2d328 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -317,15 +317,12 @@ static u64 __init get_ramdisk_size(void)
 	return ramdisk_size;
 }
 
-#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
 	/* Assume only end is not page aligned */
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	unsigned long slop, clen, mapaddr;
-	char *p, *q;
 
 	/* We need to move the initrd down into directly mapped mem */
 	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
@@ -343,25 +340,8 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
 	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
-	q = (char *)initrd_start;
-
-	/* Copy the initrd */
-	while (ramdisk_size) {
-		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
-		if (clen > MAX_MAP_CHUNK-slop)
-			clen = MAX_MAP_CHUNK-slop;
-		mapaddr = ramdisk_image & PAGE_MASK;
-		p = early_memremap(mapaddr, clen+slop);
-		memcpy(q, p+slop, clen);
-		early_memunmap(p, clen+slop);
-		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
-	}
+	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
 
-	ramdisk_image = get_ramdisk_image();
-	ramdisk_size  = get_ramdisk_size();
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
@@ -498,7 +478,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
  * --------- Crashkernel reservation ------------------------------
  */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 79055cf2c497..c8d52cb4cb6e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -38,7 +38,7 @@ static int __read_mostly tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int __read_mostly tsc_disabled = -1;
 
-static struct static_key __use_tsc = STATIC_KEY_INIT;
+static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
@@ -274,7 +274,12 @@ done:
  */
 u64 native_sched_clock(void)
 {
-	u64 tsc_now;
+	if (static_branch_likely(&__use_tsc)) {
+		u64 tsc_now = rdtsc();
+
+		/* return the value in ns */
+		return cycles_2_ns(tsc_now);
+	}
 
 	/*
 	 * Fall back to jiffies if there's no TSC available:
@@ -284,16 +289,9 @@ u64 native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achieve it. )
 	 */
-	if (!static_key_false(&__use_tsc)) {
-		/* No locking but a rare wrong value is not a big deal: */
-		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
-	}
-
-	/* read the Time Stamp Counter: */
-	tsc_now = rdtsc();
 
-	/* return the value in ns */
-	return cycles_2_ns(tsc_now);
+	/* No locking but a rare wrong value is not a big deal: */
+	return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 }
 
 /*
@@ -1212,7 +1210,7 @@ void __init tsc_init(void)
 	/* now allow native_sched_clock() to use rdtsc */
 
 	tsc_disabled = 0;
-	static_key_slow_inc(&__use_tsc);
+	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 00bf300fd846..74e4bf11f562 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -364,7 +364,7 @@ INIT_PER_CPU(irq_stack_union);
 
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <asm/kexec.h>
 
 . = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,