X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fsoftlockup.c;h=11df812263c8fd3eed16f4f1a57d36a68f6eaedc;hb=a3aaabd6b402d8b0ede5aa4a040e9fdbbfdf9116;hp=50afeb813305d76435e8c6852a80b5b9dc5c8cd9;hpb=a12f66fccf2e266ad197df142b5ebafc6a169a8c;p=linux-2.6

diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 50afeb8133..11df812263 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -10,17 +10,21 @@
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
 
+#include <asm/irq_regs.h>
+
 static DEFINE_SPINLOCK(print_lock);
 
 static DEFINE_PER_CPU(unsigned long, touch_timestamp);
 static DEFINE_PER_CPU(unsigned long, print_timestamp);
 static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 
-static int did_panic = 0;
+static int did_panic;
+int softlockup_thresh = 10;
 
 static int
 softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
@@ -34,12 +38,34 @@ static struct notifier_block panic_block = {
 	.notifier_call = softlock_panic,
 };
 
+/*
+ * Returns seconds, approximately.  We don't need nanosecond
+ * resolution, and we don't need to waste time with a big divide when
+ * 2^30ns == 1.074s.
+ */
+static unsigned long get_timestamp(int this_cpu)
+{
+	return cpu_clock(this_cpu) >> 30;  /* 2^30 ~= 10^9 */
+}
+
 void touch_softlockup_watchdog(void)
 {
-	__raw_get_cpu_var(touch_timestamp) = jiffies;
+	int this_cpu = raw_smp_processor_id();
+
+	__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
+void touch_all_softlockup_watchdogs(void)
+{
+	int cpu;
+
+	/* Cause each CPU to re-update its timestamp rather than complain */
+	for_each_online_cpu(cpu)
+		per_cpu(touch_timestamp, cpu) = 0;
+}
+EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
+
 /*
  * This callback runs from the timer interrupt, and checks
  * whether the watchdog thread has hung or not:
@@ -48,12 +74,23 @@ void softlockup_tick(void)
 {
 	int this_cpu = smp_processor_id();
 	unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+	unsigned long print_timestamp;
+	struct pt_regs *regs = get_irq_regs();
+	unsigned long now;
+
+	if (touch_timestamp == 0) {
+		touch_softlockup_watchdog();
+		return;
+	}
 
-	/* prevent double reports: */
-	if (per_cpu(print_timestamp, this_cpu) == touch_timestamp ||
-		did_panic ||
-			!per_cpu(watchdog_task, this_cpu))
+	print_timestamp = per_cpu(print_timestamp, this_cpu);
+
+	/* report at most once a second */
+	if ((print_timestamp >= touch_timestamp &&
+			print_timestamp < (touch_timestamp + 1)) ||
+			did_panic || !per_cpu(watchdog_task, this_cpu)) {
 		return;
+	}
 
 	/* do not print during early bootup: */
 	if (unlikely(system_state != SYSTEM_RUNNING)) {
@@ -61,31 +98,40 @@ void softlockup_tick(void)
 		return;
 	}
 
+	now = get_timestamp(this_cpu);
+
 	/* Wake up the high-prio watchdog task every second: */
-	if (time_after(jiffies, touch_timestamp + HZ))
+	if (now > (touch_timestamp + 1))
 		wake_up_process(per_cpu(watchdog_task, this_cpu));
 
 	/* Warn about unreasonable 10+ seconds delays: */
-	if (time_after(jiffies, touch_timestamp + 10*HZ)) {
-		per_cpu(print_timestamp, this_cpu) = touch_timestamp;
+	if (now <= (touch_timestamp + softlockup_thresh))
+		return;
+
+	per_cpu(print_timestamp, this_cpu) = touch_timestamp;
 
-		spin_lock(&print_lock);
-		printk(KERN_ERR "BUG: soft lockup detected on CPU#%d!\n",
-			this_cpu);
+	spin_lock(&print_lock);
+	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
+			this_cpu, now - touch_timestamp,
+			current->comm, task_pid_nr(current));
+	if (regs)
+		show_regs(regs);
+	else
 		dump_stack();
-		spin_unlock(&print_lock);
-	}
+	spin_unlock(&print_lock);
 }
 
 /*
  * The watchdog thread - runs every second and touches the timestamp.
  */
-static int watchdog(void * __bind_cpu)
+static int watchdog(void *__bind_cpu)
 {
-	struct sched_param param = { .sched_priority = 99 };
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
-	current->flags |= PF_NOFREEZE;
+
+	/* initialize timestamp */
+	touch_softlockup_watchdog();
 
 	/*
 	 * Run briefly once per second to reset the softlockup timestamp.
@@ -112,33 +158,37 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	switch (action) {
 	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		BUG_ON(per_cpu(watchdog_task, hotcpu));
 		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
 		if (IS_ERR(p)) {
-			printk("watchdog for %i failed\n", hotcpu);
+			printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
 		}
-  		per_cpu(touch_timestamp, hotcpu) = jiffies;
-  		per_cpu(watchdog_task, hotcpu) = p;
+		per_cpu(touch_timestamp, hotcpu) = 0;
+		per_cpu(watchdog_task, hotcpu) = p;
 		kthread_bind(p, hotcpu);
- 		break;
+		break;
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		wake_up_process(per_cpu(watchdog_task, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		if (!per_cpu(watchdog_task, hotcpu))
 			break;
 		/* Unbind so it can run.  Fall thru. */
 		kthread_bind(per_cpu(watchdog_task, hotcpu),
 			     any_online_cpu(cpu_online_map));
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		p = per_cpu(watchdog_task, hotcpu);
 		per_cpu(watchdog_task, hotcpu) = NULL;
 		kthread_stop(p);
 		break;
 #endif /* CONFIG_HOTPLUG_CPU */
- 	}
+	}
 	return NOTIFY_OK;
 }