Merge branch 'perf/core' into oprofile/master

Merge reason: Resolve conflicts with Don's NMI rework:

    commit 9c48f1c629ecfa114850c03f875c6691003214de
    Author: Don Zickus <dzickus@redhat.com>
    Date:   Fri Sep 30 15:06:21 2011 -0400
    x86, nmi: Wire up NMI handlers to new routines

Conflicts:
	arch/x86/oprofile/nmi_timer_int.c

Signed-off-by: Robert Richter <robert.richter@amd.com>

22 files changed, 605 insertions, 379 deletions

diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 4886a68f267..53610957fea 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -22,25 +22,23 @@ void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
-/*
- * Define some priorities for the nmi notifier call chain.
- *
- * Create a local nmi bit that has a higher priority than
- * external nmis, because the local ones are more frequent.
- *
- * Also setup some default high/normal/low settings for
- * subsystems to registers with.  Using 4 bits to separate
- * the priorities.  This can go a lot higher if needed be.
- */
-
-#define NMI_LOCAL_SHIFT		16	/* randomly picked */
-#define NMI_LOCAL_BIT		(1ULL << NMI_LOCAL_SHIFT)
-#define NMI_HIGH_PRIOR		(1ULL << 8)
-#define NMI_NORMAL_PRIOR	(1ULL << 4)
-#define NMI_LOW_PRIOR		(1ULL << 0)
-#define NMI_LOCAL_HIGH_PRIOR	(NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
-#define NMI_LOCAL_NORMAL_PRIOR	(NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
-#define NMI_LOCAL_LOW_PRIOR	(NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+#define NMI_FLAG_FIRST	1
+
+enum {
+	NMI_LOCAL=0,
+	NMI_UNKNOWN,
+	NMI_MAX
+};
+
+#define NMI_DONE	0
+#define NMI_HANDLED	1
+
+typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
+
+int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long,
+			 const char *);
+
+void unregister_nmi_handler(unsigned int, const char *);
 
 void stop_nmi(void);
 void restart_nmi(void);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 094fb30817a..e47cb6167e8 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,6 +29,9 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
+#define AMD_PERFMON_EVENTSEL_GUESTONLY			(1ULL << 40)
+#define AMD_PERFMON_EVENTSEL_HOSTONLY			(1ULL << 41)
+
 #define AMD64_EVENTSEL_EVENT	\
 	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
 #define INTEL_ARCH_EVENT_MASK	\
@@ -159,7 +162,19 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	);							\
 }
 
+struct perf_guest_switch_msr {
+	unsigned msr;
+	u64 host, guest;
+};
+
+extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 #else
+static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+	*nr = 0;
+	return NULL;
+}
+
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 3250e3d605d..92f297069e8 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -23,7 +23,7 @@ void machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
-typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
 
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 82f2912155a..8baca3c4871 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -19,7 +19,7 @@ endif
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time.o ioport.o ldt.o dumpstack.o
+obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d5e57db0f7b..31cb9ae992b 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -60,22 +60,10 @@ void arch_trigger_all_cpu_backtrace(void)
 }
 
 static int __kprobes
-arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
-			 unsigned long cmd, void *__args)
+arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = __args;
-	struct pt_regs *regs;
 	int cpu;
 
-	switch (cmd) {
-	case DIE_NMI:
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
-	regs = args->regs;
 	cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
@@ -86,21 +74,16 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 		show_regs(regs);
 		arch_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
-		return NOTIFY_STOP;
+		return NMI_HANDLED;
 	}
 
-	return NOTIFY_DONE;
+	return NMI_DONE;
 }
 
-static __read_mostly struct notifier_block backtrace_notifier = {
-	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
-	.next                   = NULL,
-	.priority               = NMI_LOCAL_LOW_PRIOR,
-};
-
 static int __init register_trigger_all_cpu_backtrace(void)
 {
-	register_die_notifier(&backtrace_notifier);
+	register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler,
+				0, "arch_bt");
 	return 0;
 }
 early_initcall(register_trigger_all_cpu_backtrace);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 34b18594e72..75be00ecfff 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -672,18 +672,11 @@ void __cpuinit uv_cpu_init(void)
 /*
  * When NMI is received, print a stack trace.
  */
-int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
+int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 {
 	unsigned long real_uv_nmi;
 	int bid;
 
-	if (reason != DIE_NMIUNKNOWN)
-		return NOTIFY_OK;
-
-	if (in_crash_kexec)
-		/* do nothing if entering the crash kernel */
-		return NOTIFY_OK;
-
 	/*
 	 * Each blade has an MMR that indicates when an NMI has been sent
 	 * to cpus on the blade. If an NMI is detected, atomically
@@ -704,7 +697,7 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 	}
 
 	if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
-		return NOTIFY_DONE;
+		return NMI_DONE;
 
 	__get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
 
@@ -717,17 +710,12 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 	dump_stack();
 	spin_unlock(&uv_nmi_lock);
 
-	return NOTIFY_STOP;
+	return NMI_HANDLED;
 }
 
-static struct notifier_block uv_dump_stack_nmi_nb = {
-	.notifier_call	= uv_handle_nmi,
-	.priority = NMI_LOCAL_LOW_PRIOR - 1,
-};
-
 void uv_register_nmi_notifier(void)
 {
-	if (register_die_notifier(&uv_dump_stack_nmi_nb))
+	if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv"))
 		printk(KERN_WARNING "UV NMI handler failed to register\n");
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 0ed633c5048..6199232161c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -78,27 +78,20 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
 
 static cpumask_var_t mce_inject_cpumask;
 
-static int mce_raise_notify(struct notifier_block *self,
-			    unsigned long val, void *data)
+static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = (struct die_args *)data;
 	int cpu = smp_processor_id();
 	struct mce *m = &__get_cpu_var(injectm);
-	if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
-		return NOTIFY_DONE;
+	if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
+		return NMI_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
 	if (m->inject_flags & MCJ_EXCEPTION)
-		raise_exception(m, args->regs);
+		raise_exception(m, regs);
 	else if (m->status)
 		raise_poll(m);
-	return NOTIFY_STOP;
+	return NMI_HANDLED;
 }
 
-static struct notifier_block mce_raise_nb = {
-	.notifier_call = mce_raise_notify,
-	.priority = NMI_LOCAL_NORMAL_PRIOR,
-};
-
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
@@ -216,7 +209,8 @@ static int inject_init(void)
 		return -ENOMEM;
 	printk(KERN_INFO "Machine check injector initialized\n");
 	mce_chrdev_ops.write = mce_write;
-	register_die_notifier(&mce_raise_nb);
+	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
+				"mce_notify");
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 08363b04212..fce51ad1f36 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -908,9 +908,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	percpu_inc(mce_exception_count);
 
-	if (notify_die(DIE_NMI, "machine check", regs, error_code,
-			   18, SIGKILL) == NOTIFY_STOP)
-		goto out;
 	if (!banks)
 		goto out;
 
@@ -1140,6 +1137,15 @@ static void mce_start_timer(unsigned long data)
 	add_timer_on(t, smp_processor_id());
 }
 
+/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+static void mce_timer_delete_all(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		del_timer_sync(&per_cpu(mce_timer, cpu));
+}
+
 static void mce_do_trigger(struct work_struct *work)
 {
 	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
@@ -1750,7 +1756,6 @@ static struct syscore_ops mce_syscore_ops = {
 
 static void mce_cpu_restart(void *data)
 {
-	del_timer_sync(&__get_cpu_var(mce_timer));
 	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
@@ -1760,16 +1765,15 @@ static void mce_cpu_restart(void *data)
 /* Reinit MCEs after user configuration changes */
 static void mce_restart(void)
 {
+	mce_timer_delete_all();
 	on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
 /* Toggle features for corrected errors */
-static void mce_disable_ce(void *all)
+static void mce_disable_cmci(void *data)
 {
 	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
-	if (all)
-		del_timer_sync(&__get_cpu_var(mce_timer));
 	cmci_clear();
 }
 
@@ -1852,7 +1856,8 @@ static ssize_t set_ignore_ce(struct sys_device *s,
 	if (mce_ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
-			on_each_cpu(mce_disable_ce, (void *)1, 1);
+			mce_timer_delete_all();
+			on_each_cpu(mce_disable_cmci, NULL, 1);
 			mce_ignore_ce = 1;
 		} else {
 			/* enable ce features */
@@ -1875,7 +1880,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s,
 	if (mce_cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
-			on_each_cpu(mce_disable_ce, NULL, 1);
+			on_each_cpu(mce_disable_cmci, NULL, 1);
 			mce_cmci_disabled = 1;
 		} else {
 			/* enable cmci */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8ab89112f93..640891014b2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1058,76 +1058,15 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
-struct pmu_nmi_state {
-	unsigned int	marked;
-	int		handled;
-};
-
-static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
-
 static int __kprobes
-perf_event_nmi_handler(struct notifier_block *self,
-			 unsigned long cmd, void *__args)
+perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = __args;
-	unsigned int this_nmi;
-	int handled;
-
 	if (!atomic_read(&active_events))
-		return NOTIFY_DONE;
-
-	switch (cmd) {
-	case DIE_NMI:
-		break;
-	case DIE_NMIUNKNOWN:
-		this_nmi = percpu_read(irq_stat.__nmi_count);
-		if (this_nmi != __this_cpu_read(pmu_nmi.marked))
-			/* let the kernel handle the unknown nmi */
-			return NOTIFY_DONE;
-		/*
-		 * This one is a PMU back-to-back nmi. Two events
-		 * trigger 'simultaneously' raising two back-to-back
-		 * NMIs. If the first NMI handles both, the latter
-		 * will be empty and daze the CPU. So, we drop it to
-		 * avoid false-positive 'unknown nmi' messages.
-		 */
-		return NOTIFY_STOP;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	handled = x86_pmu.handle_irq(args->regs);
-	if (!handled)
-		return NOTIFY_DONE;
+		return NMI_DONE;
 
-	this_nmi = percpu_read(irq_stat.__nmi_count);
-	if ((handled > 1) ||
-		/* the next nmi could be a back-to-back nmi */
-	    ((__this_cpu_read(pmu_nmi.marked) == this_nmi) &&
-	     (__this_cpu_read(pmu_nmi.handled) > 1))) {
-		/*
-		 * We could have two subsequent back-to-back nmis: The
-		 * first handles more than one counter, the 2nd
-		 * handles only one counter and the 3rd handles no
-		 * counter.
-		 *
-		 * This is the 2nd nmi because the previous was
-		 * handling more than one counter. We will mark the
-		 * next (3rd) and then drop it if unhandled.
-		 */
-		__this_cpu_write(pmu_nmi.marked, this_nmi + 1);
-		__this_cpu_write(pmu_nmi.handled, handled);
-	}
-
-	return NOTIFY_STOP;
+	return x86_pmu.handle_irq(regs);
 }
 
-static __read_mostly struct notifier_block perf_event_nmi_notifier = {
-	.notifier_call		= perf_event_nmi_handler,
-	.next			= NULL,
-	.priority		= NMI_LOCAL_LOW_PRIOR,
-};
-
 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
 
@@ -1232,7 +1171,7 @@ static int __init init_hw_perf_events(void)
 		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
 
 	perf_events_lapic_init();
-	register_die_notifier(&perf_event_nmi_notifier);
+	register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
 
 	unconstrained = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fb330b0a816..b9698d40ac4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -131,6 +131,13 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 
 	/*
+	 * Intel host/guest exclude bits
+	 */
+	u64				intel_ctrl_guest_mask;
+	u64				intel_ctrl_host_mask;
+	struct perf_guest_switch_msr	guest_switch_msrs[X86_PMC_IDX_MAX];
+
+	/*
 	 * manage shared (per-core, per-cpu) registers
 	 * used on Intel NHM/WSM/SNB
 	 */
@@ -295,6 +302,11 @@ struct x86_pmu {
 	 */
 	struct extra_reg *extra_regs;
 	unsigned int er_flags;
+
+	/*
+	 * Intel host/guest support (KVM)
+	 */
+	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
 #define ERF_NO_HT_SHARING	1
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 384450d6712..db8e603ff0c 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -138,6 +138,19 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.exclude_host && event->attr.exclude_guest)
+		/*
+		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
+		 * and will count in both modes. We don't want to count in that
+		 * case so we emulate no-counting by setting US = OS = 0.
+		 */
+		event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
+				      ARCH_PERFMON_EVENTSEL_OS);
+	else if (event->attr.exclude_host)
+		event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY;
+	else if (event->attr.exclude_guest)
+		event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY;
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61fa35750b9..e09ca20e86e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -749,7 +749,8 @@ static void intel_pmu_enable_all(int added)
 
 	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all();
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
+			x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
 		struct perf_event *event =
@@ -872,6 +873,7 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
@@ -879,6 +881,9 @@ static void intel_pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
+	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
+	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -924,6 +929,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -933,6 +939,11 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
+	if (event->attr.exclude_host)
+		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
+	if (event->attr.exclude_guest)
+		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_enable_fixed(hwc);
 		return;
@@ -1302,12 +1313,84 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+	if (x86_pmu.guest_get_msrs)
+		return x86_pmu.guest_get_msrs(nr);
+	*nr = 0;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
+
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+
+	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
+	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
+	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+
+	*nr = 1;
+	return arr;
+}
+
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++)  {
+		struct perf_event *event = cpuc->events[idx];
+
+		arr[idx].msr = x86_pmu_config_addr(idx);
+		arr[idx].host = arr[idx].guest = 0;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		arr[idx].host = arr[idx].guest =
+			event->hw.config | ARCH_PERFMON_EVENTSEL_ENABLE;
+
+		if (event->attr.exclude_host)
+			arr[idx].host &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+		else if (event->attr.exclude_guest)
+			arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+	}
+
+	*nr = x86_pmu.num_counters;
+	return arr;
+}
+
+static void core_pmu_enable_event(struct perf_event *event)
+{
+	if (!event->attr.exclude_host)
+		x86_pmu_enable_event(event);
+}
+
+static void core_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+
+		if (!test_bit(idx, cpuc->active_mask) ||
+				cpuc->events[idx]->attr.exclude_host)
+			continue;
+
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	}
+}
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
 	.hw_config		= x86_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
@@ -1325,6 +1408,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1431,6 +1515,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.guest_get_msrs		= intel_guest_get_msrs,
 };
 
 static void intel_clovertown_quirks(void)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 764c7c2b181..13ad89971d4 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -32,15 +32,12 @@ int in_crash_kexec;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
-static void kdump_nmi_callback(int cpu, struct die_args *args)
+static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 {
-	struct pt_regs *regs;
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
 #endif
 
-	regs = args->regs;
-
 #ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
 		crash_fixup_ss_esp(&fixed_regs, regs);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 00354d4919a..faba5771aca 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -511,28 +511,37 @@ single_step_cont(struct pt_regs *regs, struct die_args *args)
 
 static int was_in_debug_nmi[NR_CPUS];
 
-static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct pt_regs *regs = args->regs;
-
 	switch (cmd) {
-	case DIE_NMI:
+	case NMI_LOCAL:
 		if (atomic_read(&kgdb_active) != -1) {
 			/* KGDB CPU roundup */
 			kgdb_nmicallback(raw_smp_processor_id(), regs);
 			was_in_debug_nmi[raw_smp_processor_id()] = 1;
 			touch_nmi_watchdog();
-			return NOTIFY_STOP;
+			return NMI_HANDLED;
 		}
-		return NOTIFY_DONE;
+		break;
 
-	case DIE_NMIUNKNOWN:
+	case NMI_UNKNOWN:
 		if (was_in_debug_nmi[raw_smp_processor_id()]) {
 			was_in_debug_nmi[raw_smp_processor_id()] = 0;
-			return NOTIFY_STOP;
+			return NMI_HANDLED;
 		}
-		return NOTIFY_DONE;
+		break;
+	default:
+		/* do nothing */
+		break;
+	}
+	return NMI_DONE;
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+	struct pt_regs *regs = args->regs;
 
+	switch (cmd) {
 	case DIE_DEBUG:
 		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
@@ -590,11 +599,6 @@ kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
 
 static struct notifier_block kgdb_notifier = {
 	.notifier_call	= kgdb_notify,
-
-	/*
-	 * Lowest-prio notifier priority, we want to be notified last:
-	 */
-	.priority	= NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
@@ -605,7 +609,31 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
-	return register_die_notifier(&kgdb_notifier);
+	int retval;
+
+	retval = register_die_notifier(&kgdb_notifier);
+	if (retval)
+		goto out;
+
+	retval = register_nmi_handler(NMI_LOCAL, kgdb_nmi_handler,
+					0, "kgdb");
+	if (retval)
+		goto out1;
+
+	retval = register_nmi_handler(NMI_UNKNOWN, kgdb_nmi_handler,
+					0, "kgdb");
+
+	if (retval)
+		goto out2;
+
+	return retval;
+
+out2:
+	unregister_nmi_handler(NMI_LOCAL, "kgdb");
+out1:
+	unregister_die_notifier(&kgdb_notifier);
+out:
+	return retval;
 }
 
 static void kgdb_hw_overflow_handler(struct perf_event *event,
@@ -673,6 +701,8 @@ void kgdb_arch_exit(void)
 			breakinfo[i].pev = NULL;
 		}
 	}
+	unregister_nmi_handler(NMI_UNKNOWN, "kgdb");
+	unregister_nmi_handler(NMI_LOCAL, "kgdb");
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
new file mode 100644
index 00000000000..e20f5e79059
--- /dev/null
+++ b/arch/x86/kernel/nmi.c
@@ -0,0 +1,336 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ *  Copyright (C) 2011	Don Zickus Red Hat, Inc.
+ *
+ *  Pentium III FXSR, SSE support
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * Handle hardware traps and faults.
+ */
+#include <linux/spinlock.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <linux/slab.h>
+
+#if defined(CONFIG_EDAC)
+#include <linux/edac.h>
+#endif
+
+#include <linux/atomic.h>
+#include <asm/traps.h>
+#include <asm/mach_traps.h>
+#include <asm/nmi.h>
+
+#define NMI_MAX_NAMELEN	16
+struct nmiaction {
+	struct list_head list;
+	nmi_handler_t handler;
+	unsigned int flags;
+	char *name;
+};
+
+struct nmi_desc {
+	spinlock_t lock;
+	struct list_head head;
+};
+
+static struct nmi_desc nmi_desc[NMI_MAX] = 
+{
+	{
+		.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
+		.head = LIST_HEAD_INIT(nmi_desc[0].head),
+	},
+	{
+		.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
+		.head = LIST_HEAD_INIT(nmi_desc[1].head),
+	},
+
+};
+
+static int ignore_nmis;
+
+int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
+
+static int __init setup_unknown_nmi_panic(char *str)
+{
+	unknown_nmi_panic = 1;
+	return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
+#define nmi_to_desc(type) (&nmi_desc[type])
+
+static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	struct nmiaction *a;
+	int handled=0;
+
+	rcu_read_lock();
+
+	/*
+	 * NMIs are edge-triggered, which means if you have enough
+	 * of them concurrently, you can lose some because only one
+	 * can be latched at any given time.  Walk the whole list
+	 * to handle those situations.
+	 */
+	list_for_each_entry_rcu(a, &desc->head, list) {
+
+		handled += a->handler(type, regs);
+
+	}
+
+	rcu_read_unlock();
+
+	/* return total number of NMI events handled */
+	return handled;
+}
+
+static int __setup_nmi(unsigned int type, struct nmiaction *action)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	unsigned long flags;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	/*
+	 * some handlers need to be executed first otherwise a fake
+	 * event confuses some handlers (kdump uses this flag)
+	 */
+	if (action->flags & NMI_FLAG_FIRST)
+		list_add_rcu(&action->list, &desc->head);
+	else
+		list_add_tail_rcu(&action->list, &desc->head);
+	
+	spin_unlock_irqrestore(&desc->lock, flags);
+	return 0;
+}
+
+static struct nmiaction *__free_nmi(unsigned int type, const char *name)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	struct nmiaction *n;
+	unsigned long flags;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	list_for_each_entry_rcu(n, &desc->head, list) {
+		/*
+		 * the name passed in to describe the nmi handler
+		 * is used as the lookup key
+		 */
+		if (!strcmp(n->name, name)) {
+			WARN(in_nmi(),
+				"Trying to free NMI (%s) from NMI context!\n", n->name);
+			list_del_rcu(&n->list);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&desc->lock, flags);
+	synchronize_rcu();
+	return (n);
+}
+
+int register_nmi_handler(unsigned int type, nmi_handler_t handler,
+			unsigned long nmiflags, const char *devname)
+{
+	struct nmiaction *action;
+	int retval = -ENOMEM;
+
+	if (!handler)
+		return -EINVAL;
+
+	action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
+	if (!action)
+		goto fail_action;
+
+	action->handler = handler;
+	action->flags = nmiflags;
+	action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
+	if (!action->name)
+		goto fail_action_name;
+
+	retval = __setup_nmi(type, action);
+
+	if (retval)
+		goto fail_setup_nmi;
+
+	return retval;
+
+fail_setup_nmi:
+	kfree(action->name);
+fail_action_name:
+	kfree(action);
+fail_action:	
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(register_nmi_handler);
+
+void unregister_nmi_handler(unsigned int type, const char *name)
+{
+	struct nmiaction *a;
+
+	a = __free_nmi(type, name);
+	if (a) {
+		kfree(a->name);
+		kfree(a);
+	}
+}
+
+EXPORT_SYMBOL_GPL(unregister_nmi_handler);
+
+static notrace __kprobes void
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
+{
+	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+
+	/*
+	 * On some machines, PCI SERR line is used to report memory
+	 * errors. EDAC makes use of it.
+	 */
+#if defined(CONFIG_EDAC)
+	if (edac_handler_set()) {
+		edac_atomic_assert_error();
+		return;
+	}
+#endif
+
+	if (panic_on_unrecovered_nmi)
+		panic("NMI: Not continuing");
+
+	pr_emerg("Dazed and confused, but trying to continue\n");
+
+	/* Clear and disable the PCI SERR error line. */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+	outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+io_check_error(unsigned char reason, struct pt_regs *regs)
+{
+	unsigned long i;
+
+	pr_emerg(
+	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+	show_registers(regs);
+
+	if (panic_on_io_nmi)
+		panic("NMI IOCK error: Not continuing");
+
+	/* Re-enable the IOCK line, wait for a few seconds */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
+
+	i = 20000;
+	while (--i) {
+		touch_nmi_watchdog();
+		udelay(100);
+	}
+
+	reason &= ~NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
+{
+	int handled;
+
+	handled = nmi_handle(NMI_UNKNOWN, regs);
+	if (handled)
+		return;
+#ifdef CONFIG_MCA
+	/*
+	 * Might actually be able to figure out what the guilty party
+	 * is:
+	 */
+	if (MCA_bus) {
+		mca_handle_nmi();
+		return;
+	}
+#endif
+	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+
+	pr_emerg("Do you have a strange power saving mode enabled?\n");
+	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
+		panic("NMI: Not continuing");
+
+	pr_emerg("Dazed and confused, but trying to continue\n");
+}
+
+static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+{
+	unsigned char reason = 0;
+	int handled;
+
+	/*
+	 * CPU-specific NMI must be processed before non-CPU-specific
+	 * NMI, otherwise we may lose it, because the CPU-specific
+	 * NMI can not be detected/processed on other CPUs.
+	 */
+	handled = nmi_handle(NMI_LOCAL, regs);
+	if (handled)
+		return;
+
+	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+	raw_spin_lock(&nmi_reason_lock);
+	reason = get_nmi_reason();
+
+	if (reason & NMI_REASON_MASK) {
+		if (reason & NMI_REASON_SERR)
+			pci_serr_error(reason, regs);
+		else if (reason & NMI_REASON_IOCHK)
+			io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+		/*
+		 * Reassert NMI in case it became active
+		 * meanwhile as it's edge-triggered:
+		 */
+		reassert_nmi();
+#endif
+		raw_spin_unlock(&nmi_reason_lock);
+		return;
+	}
+	raw_spin_unlock(&nmi_reason_lock);
+
+	unknown_nmi_error(reason, regs);
+}
+
+dotraplinkage notrace __kprobes void
+do_nmi(struct pt_regs *regs, long error_code)
+{
+	nmi_enter();
+
+	inc_irq_stat(__nmi_count);
+
+	if (!ignore_nmis)
+		default_do_nmi(regs);
+
+	nmi_exit();
+}
+
+void stop_nmi(void)
+{
+	ignore_nmis++;
+}
+
+void restart_nmi(void)
+{
+	ignore_nmis--;
+}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9242436e993..e334be1182b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,7 +464,7 @@ static inline void kb_wait(void)
 	}
 }
 
-static void vmxoff_nmi(int cpu, struct die_args *args)
+static void vmxoff_nmi(int cpu, struct pt_regs *regs)
 {
 	cpu_emergency_vmxoff();
 }
@@ -736,14 +736,10 @@ static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct notifier_block *self,
-			unsigned long val, void *data)
+static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
 	int cpu;
 
-	if (val != DIE_NMI)
-		return NOTIFY_OK;
-
 	cpu = raw_smp_processor_id();
 
 	/* Don't do anything if this handler is invoked on crashing cpu.
@@ -751,10 +747,10 @@ static int crash_nmi_callback(struct notifier_block *self,
 	 * an NMI if system was initially booted with nmi_watchdog parameter.
 	 */
 	if (cpu == crashing_cpu)
-		return NOTIFY_STOP;
+		return NMI_HANDLED;
 	local_irq_disable();
 
-	shootdown_callback(cpu, (struct die_args *)data);
+	shootdown_callback(cpu, regs);
 
 	atomic_dec(&waiting_for_crash_ipi);
 	/* Assume hlt works */
@@ -762,7 +758,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 	for (;;)
 		cpu_relax();
 
-	return 1;
+	return NMI_HANDLED;
 }
 
 static void smp_send_nmi_allbutself(void)
@@ -770,12 +766,6 @@ static void smp_send_nmi_allbutself(void)
 	apic->send_IPI_allbutself(NMI_VECTOR);
 }
 
-static struct notifier_block crash_nmi_nb = {
-	.notifier_call = crash_nmi_callback,
-	/* we want to be the first one called */
-	.priority = NMI_LOCAL_HIGH_PRIOR+1,
-};
-
 /* Halt all other CPUs, calling the specified function on each of them
  *
  * This function can be used to halt all other CPUs on crash
@@ -794,7 +784,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
 	/* Would it be better to replace the trap vector here? */
-	if (register_die_notifier(&crash_nmi_nb))
+	if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
+				 NMI_FLAG_FIRST, "crash"))
 		return;		/* return what? */
 	/* Ensure the new callback function is set before sending
 	 * out the NMI
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 3f2ad2640d8..ccdbc16b894 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -42,8 +42,11 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes, cmos_minutes;
 	unsigned char save_control, save_freq_select;
+	unsigned long flags;
 	int retval = 0;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	 /* tell the clock it's being set */
 	save_control = CMOS_READ(RTC_CONTROL);
 	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
@@ -93,12 +96,17 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	CMOS_WRITE(save_control, RTC_CONTROL);
 	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return retval;
 }
 
 unsigned long mach_get_cmos_time(void)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/*
 	 * If UIP is clear, then we have >= 244 microseconds before
@@ -125,6 +133,8 @@ unsigned long mach_get_cmos_time(void)
 	status = CMOS_READ(RTC_CONTROL);
 	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
 		sec = bcd2bin(sec);
 		min = bcd2bin(min);
@@ -169,24 +179,15 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	retval = x86_platform.set_wallclock(now.tv_sec);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return retval;
+	return x86_platform.set_wallclock(now.tv_sec);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval, flags;
+	unsigned long retval;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	retval = x86_platform.get_wallclock();
-	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	ts->tv_sec = retval;
 	ts->tv_nsec = 0;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 6913369c234..a8e3eb83466 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -81,15 +81,6 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, };
 DECLARE_BITMAP(used_vectors, NR_VECTORS);
 EXPORT_SYMBOL_GPL(used_vectors);
 
-static int ignore_nmis;
-
-int unknown_nmi_panic;
-/*
- * Prevent NMI reason port (0x61) being accessed simultaneously, can
- * only be used in NMI handler.
- */
-static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
-
 static inline void conditional_sti(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
@@ -307,152 +298,6 @@ gp_in_kernel:
 	die("general protection fault", regs, error_code);
 }
 
-static int __init setup_unknown_nmi_panic(char *str)
-{
-	unknown_nmi_panic = 1;
-	return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static notrace __kprobes void
-pci_serr_error(unsigned char reason, struct pt_regs *regs)
-{
-	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-
-	/*
-	 * On some machines, PCI SERR line is used to report memory
-	 * errors. EDAC makes use of it.
-	 */
-#if defined(CONFIG_EDAC)
-	if (edac_handler_set()) {
-		edac_atomic_assert_error();
-		return;
-	}
-#endif
-
-	if (panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
-
-	pr_emerg("Dazed and confused, but trying to continue\n");
-
-	/* Clear and disable the PCI SERR error line. */
-	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
-	outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-io_check_error(unsigned char reason, struct pt_regs *regs)
-{
-	unsigned long i;
-
-	pr_emerg(
-	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-	show_registers(regs);
-
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
-
-	/* Re-enable the IOCK line, wait for a few seconds */
-	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
-	outb(reason, NMI_REASON_PORT);
-
-	i = 20000;
-	while (--i) {
-		touch_nmi_watchdog();
-		udelay(100);
-	}
-
-	reason &= ~NMI_REASON_CLEAR_IOCHK;
-	outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
-{
-	if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
-			NOTIFY_STOP)
-		return;
-#ifdef CONFIG_MCA
-	/*
-	 * Might actually be able to figure out what the guilty party
-	 * is:
-	 */
-	if (MCA_bus) {
-		mca_handle_nmi();
-		return;
-	}
-#endif
-	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-
-	pr_emerg("Do you have a strange power saving mode enabled?\n");
-	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
-
-	pr_emerg("Dazed and confused, but trying to continue\n");
-}
-
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
-{
-	unsigned char reason = 0;
-
-	/*
-	 * CPU-specific NMI must be processed before non-CPU-specific
-	 * NMI, otherwise we may lose it, because the CPU-specific
-	 * NMI can not be detected/processed on other CPUs.
-	 */
-	if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
-	raw_spin_lock(&nmi_reason_lock);
-	reason = get_nmi_reason();
-
-	if (reason & NMI_REASON_MASK) {
-		if (reason & NMI_REASON_SERR)
-			pci_serr_error(reason, regs);
-		else if (reason & NMI_REASON_IOCHK)
-			io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-		/*
-		 * Reassert NMI in case it became active
-		 * meanwhile as it's edge-triggered:
-		 */
-		reassert_nmi();
-#endif
-		raw_spin_unlock(&nmi_reason_lock);
-		return;
-	}
-	raw_spin_unlock(&nmi_reason_lock);
-
-	unknown_nmi_error(reason, regs);
-}
-
-dotraplinkage notrace __kprobes void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_enter();
-
-	inc_irq_stat(__nmi_count);
-
-	if (!ignore_nmis)
-		default_do_nmi(regs);
-
-	nmi_exit();
-}
-
-void stop_nmi(void)
-{
-	ignore_nmis++;
-}
-
-void restart_nmi(void)
-{
-	ignore_nmis--;
-}
-
 /* May run on IST stack. */
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6f08bc940fa..8b4cc5f067d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3603,7 +3603,7 @@ done_prefixes:
 		break;
 	case Src2CL:
 		ctxt->src2.bytes = 1;
-		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8;
+		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff;
 		break;
 	case Src2ImmByte:
 		rc = decode_imm(ctxt, &ctxt->src2, 1, true);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1c5b69373a0..8e8da7960db 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -400,7 +400,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 
 	/* xchg acts as a barrier before the setting of the high bits */
 	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
-	orig.spte_high = ssptep->spte_high = sspte.spte_high;
+	orig.spte_high = ssptep->spte_high;
+	ssptep->spte_high = sspte.spte_high;
 	count_spte_clear(sptep, spte);
 
 	return orig.spte;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 7ca4d43e898..990c35bfa88 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -61,26 +61,15 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 }
 
 
-static int profile_exceptions_notify(struct notifier_block *self,
-				     unsigned long val, void *data)
+static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
 {
-	struct die_args *args = (struct die_args *)data;
-	int ret = NOTIFY_DONE;
-
-	switch (val) {
-	case DIE_NMI:
-		if (ctr_running)
-			model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
-		else if (!nmi_enabled)
-			break;
-		else
-			model->stop(&__get_cpu_var(cpu_msrs));
-		ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
-	}
-	return ret;
+	if (ctr_running)
+		model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+	else if (!nmi_enabled)
+		return NMI_DONE;
+	else
+		model->stop(&__get_cpu_var(cpu_msrs));
+	return NMI_HANDLED;
 }
 
 static void nmi_cpu_save_registers(struct op_msrs *msrs)
@@ -363,12 +352,6 @@ static void nmi_cpu_setup(void *dummy)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
-static struct notifier_block profile_exceptions_nb = {
-	.notifier_call = profile_exceptions_notify,
-	.next = NULL,
-	.priority = NMI_LOCAL_LOW_PRIOR,
-};
-
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
 {
 	struct op_msr *counters = msrs->counters;
@@ -508,7 +491,8 @@ static int nmi_setup(void)
 	ctr_running = 0;
 	/* make variables visible to the nmi handler: */
 	smp_mb();
-	err = register_die_notifier(&profile_exceptions_nb);
+	err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify,
+					0, "oprofile");
 	if (err)
 		goto fail;
 
@@ -538,7 +522,7 @@ static void nmi_shutdown(void)
 	put_online_cpus();
 	/* make variables visible to the nmi handler: */
 	smp_mb();
-	unregister_die_notifier(&profile_exceptions_nb);
+	unregister_nmi_handler(NMI_LOCAL, "oprofile");
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);
 	free_msrs();
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 73d70d65e76..6d5dbcdd444 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -58,8 +58,11 @@ EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 unsigned long vrtc_get_time(void)
 {
 	u8 sec, min, hour, mday, mon;
+	unsigned long flags;
 	u32 year;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP))
 		cpu_relax();
 
@@ -70,6 +73,8 @@ unsigned long vrtc_get_time(void)
 	mon = vrtc_cmos_read(RTC_MONTH);
 	year = vrtc_cmos_read(RTC_YEAR);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	/* vRTC YEAR reg contains the offset to 1960 */
 	year += 1960;
 
@@ -83,8 +88,10 @@ unsigned long vrtc_get_time(void)
 int vrtc_set_mmss(unsigned long nowtime)
 {
 	int real_sec, real_min;
+	unsigned long flags;
 	int vrtc_min;
 
+	spin_lock_irqsave(&rtc_lock, flags);
 	vrtc_min = vrtc_cmos_read(RTC_MINUTES);
 
 	real_sec = nowtime % 60;
@@ -95,6 +102,8 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 	vrtc_cmos_write(real_sec, RTC_SECONDS);
 	vrtc_cmos_write(real_min, RTC_MINUTES);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return 0;
 }