oprofile: convert oprofile from timer_hook to hrtimer

Oprofile is currently broken on systems running with NOHZ enabled.
A maximum of 1 tick is accounted via the timer_hook if a cpu sleeps
for a longer period of time. This does bad things to the percentages
in the profiler output. To solve this problem convert oprofile to
use a restarting hrtimer instead of the timer_hook.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>

drivers/oprofile/oprof.c

@@ -253,22 +253,26 @@ static int __init oprofile_init(void)
 	int err;
 
 	err = oprofile_arch_init(&oprofile_ops);
-
 	if (err < 0 || timer) {
 		printk(KERN_INFO "oprofile: using timer interrupt.\n");
-		oprofile_timer_init(&oprofile_ops);
+		err = oprofile_timer_init(&oprofile_ops);
+		if (err)
+			goto out_arch;
 	}
-
 	err = oprofilefs_register();
 	if (err)
-		oprofile_arch_exit();
+		goto out_arch;
+	return 0;
 
+out_arch:
+	oprofile_arch_exit();
 	return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
+	oprofile_timer_exit();
 	oprofilefs_unregister();
 	oprofile_arch_exit();
 }

drivers/oprofile/oprof.h

@@ -34,7 +34,8 @@ struct super_block;
 struct dentry;
 
 void oprofile_create_files(struct super_block *sb, struct dentry *root);
-void oprofile_timer_init(struct oprofile_operations *ops);
+int oprofile_timer_init(struct oprofile_operations *ops);
+void oprofile_timer_exit(void);
 
 int oprofile_set_backtrace(unsigned long depth);
 int oprofile_set_timeout(unsigned long time);

drivers/oprofile/timer_int.c

@@ -13,34 +13,94 @@
 #include <linux/oprofile.h>
 #include <linux/profile.h>
 #include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <asm/irq_regs.h>
 #include <asm/ptrace.h>
 
 #include "oprof.h"
 
-static int timer_notify(struct pt_regs *regs)
+static DEFINE_PER_CPU(struct hrtimer, oprofile_hrtimer);
+
+static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
+{
+	oprofile_add_sample(get_irq_regs(), 0);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(TICK_NSEC));
+	return HRTIMER_RESTART;
+}
+
+static void __oprofile_hrtimer_start(void *unused)
+{
+	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = oprofile_hrtimer_notify;
+
+	hrtimer_start(hrtimer, ns_to_ktime(TICK_NSEC),
+		      HRTIMER_MODE_REL_PINNED);
+}
+
+static int oprofile_hrtimer_start(void)
 {
-	oprofile_add_sample(regs, 0);
+	on_each_cpu(__oprofile_hrtimer_start, NULL, 1);
 	return 0;
 }
 
-static int timer_start(void)
+static void __oprofile_hrtimer_stop(int cpu)
 {
-	return register_timer_hook(timer_notify);
+	struct hrtimer *hrtimer = &per_cpu(oprofile_hrtimer, cpu);
+
+	hrtimer_cancel(hrtimer);
 }
 
+static void oprofile_hrtimer_stop(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		__oprofile_hrtimer_stop(cpu);
+}
 
-static void timer_stop(void)
+static int __cpuinit oprofile_cpu_notify(struct notifier_block *self,
+					 unsigned long action, void *hcpu)
 {
-	unregister_timer_hook(timer_notify);
+	long cpu = (long) hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		smp_call_function_single(cpu, __oprofile_hrtimer_start,
+					 NULL, 1);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		__oprofile_hrtimer_stop(cpu);
+		break;
+	}
+	return NOTIFY_OK;
 }
 
+static struct notifier_block __refdata oprofile_cpu_notifier = {
+	.notifier_call = oprofile_cpu_notify,
+};
 
-void __init oprofile_timer_init(struct oprofile_operations *ops)
+int __init oprofile_timer_init(struct oprofile_operations *ops)
 {
+	int rc;
+
+	rc = register_hotcpu_notifier(&oprofile_cpu_notifier);
+	if (rc)
+		return rc;
 	ops->create_files = NULL;
 	ops->setup = NULL;
 	ops->shutdown = NULL;
-	ops->start = timer_start;
-	ops->stop = timer_stop;
+	ops->start = oprofile_hrtimer_start;
+	ops->stop = oprofile_hrtimer_stop;
 	ops->cpu_type = "timer";
+	return 0;
+}
+
+void __exit oprofile_timer_exit(void)
+{
+	unregister_hotcpu_notifier(&oprofile_cpu_notifier);
 }