Commit 8446f1d3 authored by Ingo Molnar's avatar Ingo Molnar Committed by Linus Torvalds
Browse files

[PATCH] detect soft lockups 



This patch adds a new kernel debug feature: CONFIG_DETECT_SOFTLOCKUP.

When enabled then per-CPU watchdog threads are started, which try to run
once per second.  If they get delayed for more than 10 seconds then a
callback from the timer interrupt detects this condition and prints out a
warning message and a stack dump (once per lockup incident).  The feature
is otherwise non-intrusive, it doesnt try to unlock the box in any way, it
only gets the debug info out, automatically, and on all CPUs affected by
the lockup.

Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
Signed-off-by: default avatarNishanth Aravamudan <nacc@us.ibm.com>
Signed-Off-By: default avatarMatthias Urlichs <smurf@smurf.noris.de>
Signed-off-by: default avatarRichard Purdie <rpurdie@rpsys.net>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent 4732efbe

arch/i386/kernel/nmi.c

+5 −0
Original line number Diff line number Diff line
@@ -478,6 +478,11 @@ void touch_nmi_watchdog (void) 
	 */

	for (i = 0; i < NR_CPUS; i++)

		alert_counter[i] = 0;



	/*

	 * Tickle the softlockup detector too:

	 */

	touch_softlockup_watchdog();

}



extern void die_nmi(struct pt_regs *, const char *msg);

arch/i386/kernel/time.c

+1 −0
Original line number Diff line number Diff line
@@ -422,6 +422,7 @@ static int timer_resume(struct sys_device *dev) 
		last_timer->resume();

	cur_timer = last_timer;

	last_timer = NULL;

	touch_softlockup_watchdog();

	return 0;

}

arch/x86_64/kernel/nmi.c

+2 −0
Original line number Diff line number Diff line
@@ -463,6 +463,8 @@ void touch_nmi_watchdog (void) 
	 */

	for (i = 0; i < NR_CPUS; i++)

		per_cpu(nmi_touch, i) = 1;



 	touch_softlockup_watchdog();

}



void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)

arch/x86_64/kernel/time.c

+1 −0
Original line number Diff line number Diff line
@@ -1041,6 +1041,7 @@ static int timer_resume(struct sys_device *dev) 
	write_sequnlock_irqrestore(&xtime_lock,flags);

	jiffies += sleep_length;

	wall_jiffies += sleep_length;

	touch_softlockup_watchdog();

	return 0;

}

drivers/mtd/nand/nand_base.c

+1 −0
Original line number Diff line number Diff line
@@ -526,6 +526,7 @@ static void nand_wait_ready(struct mtd_info *mtd) 
	do {

		if (this->dev_ready(mtd))

			return;

		touch_softlockup_watchdog();

	} while (time_before(jiffies, timeo));	

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE