debug lockups: Improve lockup detection

When debugging a recent lockup bug i found various deficiencies
in how our current lockup detection helpers work:

- SysRq-L is not very efficient as it uses a workqueue, hence
it cannot punch through hard lockups and cannot see through
most soft lockups either.

- The SysRq-L code depends on the NMI watchdog - which is off
by default.

- We dont print backtraces from the RCU code's built-in
'RCU state machine is stuck' debug code. This debug
code tends to be one of the first (and only) mechanisms
that show that a lockup has occured.

This patch changes the code so taht we:

- Trigger the NMI backtrace code from SysRq-L instead of using
a workqueue (which cannot punch through hard lockups)

- Trigger print-all-CPU-backtraces from the RCU lockup detection
code

Also decouple the backtrace printing code from the NMI watchdog:

- Dont use variable size cpumasks (it might not be initialized
and they are a bit more fragile anyway)

- Trigger an NMI immediately via an IPI, instead of waiting
for the NMI tick to occur. This is a lot faster and can
produce more relevant backtraces. It will also work if the
NMI watchdog is disabled.

- Dont print the 'dazed and confused' message when we print
a backtrace from the NMI

- Do a show_regs() plus a dump_stack() to get maximum info
out of the dump. Worst-case we get two stacktraces - which
is not a big deal. Sometimes, if register content is
corrupted, the precise stack walker in show_regs() wont
give us a full backtrace - in this case dump_stack() will
do it.

Cc: Paul E. McKenney <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <[e-mail]>

arch/x86/kernel/apic/nmi.c

···
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
 
-static cpumask_var_t backtrace_mask;
+static cpumask_t backtrace_mask __read_mostly;
 
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
···
 	if (!prev_nmi_count)
 		goto error;
 
-	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
···
 	}
 
 	/* We can be called before check_nmi_watchdog, hence NULL check. */
-	if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) {
+	if (cpumask_test_cpu(cpu, &backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
 		dump_stack();
 		spin_unlock(&lock);
-		cpumask_clear_cpu(cpu, backtrace_mask);
+		cpumask_clear_cpu(cpu, &backtrace_mask);
+
+		rc = 1;
 	}
 
 	/* Could check oops_in_progress here too, but it's safer not to */
···
 {
 	int i;
 
-	cpumask_copy(backtrace_mask, cpu_online_mask);
+	cpumask_copy(&backtrace_mask, cpu_online_mask);
+
+	printk(KERN_INFO "sending NMI to all CPUs:\n");
+	apic->send_IPI_all(NMI_VECTOR);
+
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
-		if (cpumask_empty(backtrace_mask))
+		if (cpumask_empty(&backtrace_mask))
 			break;
 		mdelay(1);
 	}

drivers/char/sysrq.c

···
 #include <linux/sysrq.h>
 #include <linux/kbd_kern.h>
 #include <linux/proc_fs.h>
+#include <linux/nmi.h>
 #include <linux/quotaops.h>
 #include <linux/perf_counter.h>
 #include <linux/kernel.h>
···
 
 static void sysrq_handle_showallcpus(int key, struct tty_struct *tty)
 {
-	struct pt_regs *regs = get_irq_regs();
-	if (regs) {
-		printk(KERN_INFO "CPU%d:\n", smp_processor_id());
-		show_regs(regs);
-	}
-	schedule_work(&sysrq_showallcpus);
+	trigger_all_cpu_backtrace();
 }
 
 static struct sysrq_key_op sysrq_showallcpus_op = {

kernel/rcutree.c

···
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/nmi.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
···
 	}
 	printk(" (detected by %d, t=%ld jiffies)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
+	trigger_all_cpu_backtrace();
+
 	force_quiescent_state(rsp, 0);  /* Kick them all. */
 }
 
···
 
 	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
 			smp_processor_id(), jiffies - rsp->gp_start);
-	dump_stack();
+	trigger_all_cpu_backtrace();
+
 	spin_lock_irqsave(&rnp->lock, flags);
 	if ((long)(jiffies - rsp->jiffies_stall) >= 0)
 		rsp->jiffies_stall =
 			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
 	spin_unlock_irqrestore(&rnp->lock, flags);
+
 	set_need_resched();  /* kick ourselves to get things going. */
 }