5 files changed, 86 insertions, 122 deletions

diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c
index 5b96f03..736c76d 100644
--- a/arch/i386/kernel/crash.c
+++ b/arch/i386/kernel/crash.c
@@ -22,6 +22,8 @@
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/kdebug.h>
+
 #include <mach_ipi.h>
 
 
@@ -93,9 +95,18 @@ static void crash_save_self(struct pt_regs *regs)
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+static int crash_nmi_callback(struct notifier_block *self,
+			unsigned long val, void *data)
 {
+	struct pt_regs *regs;
 	struct pt_regs fixed_regs;
+	int cpu;
+
+	if (val != DIE_NMI)
+		return NOTIFY_OK;
+
+	regs = ((struct die_args *)data)->regs;
+	cpu = raw_smp_processor_id();
 
 	/* Don't do anything if this handler is invoked on crashing cpu.
 	 * Otherwise, system will completely hang. Crashing cpu can get
@@ -125,13 +136,18 @@ static void smp_send_nmi_allbutself(void)
 	send_IPI_allbutself(NMI_VECTOR);
 }
 
+static struct notifier_block crash_nmi_nb = {
+	.notifier_call = crash_nmi_callback,
+};
+
 static void nmi_shootdown_cpus(void)
 {
 	unsigned long msecs;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
 	/* Would it be better to replace the trap vector here? */
-	set_nmi_callback(crash_nmi_callback);
+	if (register_die_notifier(&crash_nmi_nb))
+		return;		/* return what? */
 	/* Ensure the new callback function is set before sending
 	 * out the NMI
 	 */
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index bd96ea4..acd3fde 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -42,20 +42,6 @@ static DEFINE_PER_CPU(unsigned long, evntsel_nmi_owner[3]);
  */
 #define NMI_MAX_COUNTER_BITS 66
 
-/*
- * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
- * - it may be reserved by some other driver, or not
- * - when not reserved by some other driver, it may be used for
- *   the NMI watchdog, or not
- *
- * This is maintained separately from nmi_active because the NMI
- * watchdog may also be driven from the I/O APIC timer.
- */
-static DEFINE_SPINLOCK(lapic_nmi_owner_lock);
-static unsigned int lapic_nmi_owner;
-#define LAPIC_NMI_WATCHDOG	(1<<0)
-#define LAPIC_NMI_RESERVED	(1<<1)
-
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
  * <0: the lapic NMI watchdog has not been set up, and cannot
@@ -325,33 +311,6 @@ static void enable_lapic_nmi_watchdog(void)
 	touch_nmi_watchdog();
 }
 
-int reserve_lapic_nmi(void)
-{
-	unsigned int old_owner;
-
-	spin_lock(&lapic_nmi_owner_lock);
-	old_owner = lapic_nmi_owner;
-	lapic_nmi_owner |= LAPIC_NMI_RESERVED;
-	spin_unlock(&lapic_nmi_owner_lock);
-	if (old_owner & LAPIC_NMI_RESERVED)
-		return -EBUSY;
-	if (old_owner & LAPIC_NMI_WATCHDOG)
-		disable_lapic_nmi_watchdog();
-	return 0;
-}
-
-void release_lapic_nmi(void)
-{
-	unsigned int new_owner;
-
-	spin_lock(&lapic_nmi_owner_lock);
-	new_owner = lapic_nmi_owner & ~LAPIC_NMI_RESERVED;
-	lapic_nmi_owner = new_owner;
-	spin_unlock(&lapic_nmi_owner_lock);
-	if (new_owner & LAPIC_NMI_WATCHDOG)
-		enable_lapic_nmi_watchdog();
-}
-
 void disable_timer_nmi_watchdog(void)
 {
 	BUG_ON(nmi_watchdog != NMI_IO_APIC);
@@ -866,6 +825,15 @@ done:
 	return rc;
 }
 
+int do_nmi_callback(struct pt_regs * regs, int cpu)
+{
+#ifdef CONFIG_SYSCTL
+	if (unknown_nmi_panic)
+		return unknown_nmi_panic_callback(regs, cpu);
+#endif
+	return 0;
+}
+
 #ifdef CONFIG_SYSCTL
 
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
@@ -873,37 +841,8 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
 	unsigned char reason = get_nmi_reason();
 	char buf[64];
 
-	if (!(reason & 0xc0)) {
-		sprintf(buf, "NMI received for unknown reason %02x\n", reason);
-		die_nmi(regs, buf);
-	}
-	return 0;
-}
-
-/*
- * proc handler for /proc/sys/kernel/unknown_nmi_panic
- */
-int proc_unknown_nmi_panic(ctl_table *table, int write, struct file *file,
-			void __user *buffer, size_t *length, loff_t *ppos)
-{
-	int old_state;
-
-	old_state = unknown_nmi_panic;
-	proc_dointvec(table, write, file, buffer, length, ppos);
-	if (!!old_state == !!unknown_nmi_panic)
-		return 0;
-
-	if (unknown_nmi_panic) {
-		if (reserve_lapic_nmi() < 0) {
-			unknown_nmi_panic = 0;
-			return -EBUSY;
-		} else {
-			set_nmi_callback(unknown_nmi_panic_callback);
-		}
-	} else {
-		release_lapic_nmi();
-		unset_nmi_callback();
-	}
+	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+	die_nmi(regs, buf);
 	return 0;
 }
 
@@ -917,7 +856,5 @@ EXPORT_SYMBOL(reserve_perfctr_nmi);
 EXPORT_SYMBOL(release_perfctr_nmi);
 EXPORT_SYMBOL(reserve_evntsel_nmi);
 EXPORT_SYMBOL(release_evntsel_nmi);
-EXPORT_SYMBOL(reserve_lapic_nmi);
-EXPORT_SYMBOL(release_lapic_nmi);
 EXPORT_SYMBOL(disable_timer_nmi_watchdog);
 EXPORT_SYMBOL(enable_timer_nmi_watchdog);
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 282f0bd..7db664d 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -706,13 +706,6 @@ void die_nmi (struct pt_regs *regs, const char *msg)
 	do_exit(SIGSEGV);
 }
 
-static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
-{
-	return 0;
-}
-
-static nmi_callback_t nmi_callback = dummy_nmi_callback;
-
 static void default_do_nmi(struct pt_regs * regs)
 {
 	unsigned char reason = 0;
@@ -732,9 +725,10 @@ static void default_do_nmi(struct pt_regs * regs)
 		 */
 		if (nmi_watchdog_tick(regs, reason))
 			return;
+		if (!do_nmi_callback(regs, smp_processor_id()))
 #endif
-		if (!rcu_dereference(nmi_callback)(regs, smp_processor_id()))
 			unknown_nmi_error(reason, regs);
+
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
@@ -765,19 +759,6 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code)
 	nmi_exit();
 }
 
-void set_nmi_callback(nmi_callback_t callback)
-{
-	vmalloc_sync_all();
-	rcu_assign_pointer(nmi_callback, callback);
-}
-EXPORT_SYMBOL_GPL(set_nmi_callback);
-
-void unset_nmi_callback(void)
-{
-	nmi_callback = dummy_nmi_callback;
-}
-EXPORT_SYMBOL_GPL(unset_nmi_callback);
-
 #ifdef CONFIG_KPROBES
 fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c
index 8710ca0..b361018 100644
--- a/arch/i386/oprofile/nmi_int.c
+++ b/arch/i386/oprofile/nmi_int.c
@@ -17,14 +17,15 @@
 #include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
+#include <asm/kdebug.h>
  
 #include "op_counter.h"
 #include "op_x86_model.h"
- 
+
 static struct op_x86_model_spec const * model;
 static struct op_msrs cpu_msrs[NR_CPUS];
 static unsigned long saved_lvtpc[NR_CPUS];
- 
+
 static int nmi_start(void);
 static void nmi_stop(void);
 
@@ -82,13 +83,24 @@ static void exit_driverfs(void)
 #define exit_driverfs() do { } while (0)
 #endif /* CONFIG_PM */
 
-
-static int nmi_callback(struct pt_regs * regs, int cpu)
+int profile_exceptions_notify(struct notifier_block *self,
+				unsigned long val, void *data)
 {
-	return model->check_ctrs(regs, &cpu_msrs[cpu]);
+	struct die_args *args = (struct die_args *)data;
+	int ret = NOTIFY_DONE;
+	int cpu = smp_processor_id();
+
+	switch(val) {
+	case DIE_NMI:
+		if (model->check_ctrs(args->regs, &cpu_msrs[cpu]))
+			ret = NOTIFY_STOP;
+		break;
+	default:
+		break;
+	}
+	return ret;
 }
- 
- 
+
 static void nmi_cpu_save_registers(struct op_msrs * msrs)
 {
 	unsigned int const nr_ctrs = model->num_counters;
@@ -174,27 +186,29 @@ 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 = 0
+};
 
 static int nmi_setup(void)
 {
+	int err=0;
+
 	if (!allocate_msrs())
 		return -ENOMEM;
 
-	/* We walk a thin line between law and rape here.
-	 * We need to be careful to install our NMI handler
-	 * without actually triggering any NMIs as this will
-	 * break the core code horrifically.
-	 */
-	if (reserve_lapic_nmi() < 0) {
+	if ((err = register_die_notifier(&profile_exceptions_nb))){
 		free_msrs();
-		return -EBUSY;
+		return err;
 	}
+
 	/* We need to serialize save and setup for HT because the subset
 	 * of msrs are distinct for save and setup operations
 	 */
 	on_each_cpu(nmi_save_registers, NULL, 0, 1);
 	on_each_cpu(nmi_cpu_setup, NULL, 0, 1);
-	set_nmi_callback(nmi_callback);
 	nmi_enabled = 1;
 	return 0;
 }
@@ -250,8 +264,7 @@ static void nmi_shutdown(void)
 {
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
-	unset_nmi_callback();
-	release_lapic_nmi();
+	unregister_die_notifier(&profile_exceptions_nb);
 	free_msrs();
 }
 
diff --git a/arch/i386/oprofile/nmi_timer_int.c b/arch/i386/oprofile/nmi_timer_int.c
index a33a73b..93ca48f 100644
--- a/arch/i386/oprofile/nmi_timer_int.c
+++ b/arch/i386/oprofile/nmi_timer_int.c
@@ -17,32 +17,49 @@
 #include <asm/nmi.h>
 #include <asm/apic.h>
 #include <asm/ptrace.h>
+#include <asm/kdebug.h>
  
-static int nmi_timer_callback(struct pt_regs * regs, int cpu)
+int profile_timer_exceptions_notify(struct notifier_block *self,
+				unsigned long val, void *data)
 {
-	oprofile_add_sample(regs, 0);
-	return 1;
+	struct die_args *args = (struct die_args *)data;
+	int ret = NOTIFY_DONE;
+
+	switch(val) {
+	case DIE_NMI:
+		oprofile_add_sample(args->regs, 0);
+		ret = NOTIFY_STOP;
+		break;
+	default:
+		break;
+	}
+	return ret;
 }
 
+static struct notifier_block profile_timer_exceptions_nb = {
+	.notifier_call = profile_timer_exceptions_notify,
+	.next = NULL,
+	.priority = 0
+};
+
 static int timer_start(void)
 {
-	disable_timer_nmi_watchdog();
-	set_nmi_callback(nmi_timer_callback);
+	if (register_die_notifier(&profile_timer_exceptions_nb))
+		return 1;
 	return 0;
 }
 
 
 static void timer_stop(void)
 {
-	enable_timer_nmi_watchdog();
-	unset_nmi_callback();
+	unregister_die_notifier(&profile_timer_exceptions_nb);
 	synchronize_sched();  /* Allow already-started NMIs to complete. */
 }
 
 
 int __init op_nmi_timer_init(struct oprofile_operations * ops)
 {
-	if (atomic_read(&nmi_active) <= 0)
+	if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0))
 		return -ENODEV;
 
 	ops->start = timer_start;