x86, nmi: Wire up NMI handlers to new routines

Just convert all the files that have an nmi handler to the new routines.
Most of it is straight forward conversion.  A couple of places needed some
tweaking like kgdb which separates the debug notifier from the nmi handler
and mce removes a call to notify_die.

[Thanks to Ying for finding out the history behind that mce call

https://lkml.org/lkml/2010/5/27/114

And Boris responding that he would like to remove that call because of it

https://lkml.org/lkml/2011/9/21/163]

The things that get converted are the registeration/unregistration routines
and the nmi handler itself has its args changed along with code removal
to check which list it is on (most are on one NMI list except for kgdb
which has both an NMI routine and an NMI Unknown routine).

Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Corey Minyard <minyard@acm.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Corey Minyard <minyard@acm.org>
Cc: Jack Steiner <steiner@sgi.com>
Link: http://lkml.kernel.org/r/1317409584-23662-4-git-send-email-dzickus@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 81 insertions, 157 deletions

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d5e57db0f7be..31cb9ae992b7 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 34b18594e724..75be00ecfff2 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 0ed633c5048b..6199232161cf 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 5b5cceec94c5..fce51ad1f362 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;
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8ab89112f93c..640891014b2a 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/crash.c b/arch/x86/kernel/crash.c
index 764c7c2b1811..13ad89971d47 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 00354d4919a9..faba5771acad 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
index 327748d4f6b0..e20f5e790599 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -1,6 +1,7 @@
 /*
  *  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
@@ -248,8 +249,10 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 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)
+	int handled;
+
+	handled = nmi_handle(NMI_UNKNOWN, regs);
+	if (handled)
 		return;
 #ifdef CONFIG_MCA
 	/*
@@ -274,13 +277,15 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 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.
 	 */
-	if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
+	handled = nmi_handle(NMI_LOCAL, regs);
+	if (handled)
 		return;
 
 	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9242436e9937..e334be1182b9 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