Skip to contentSkip to conversation

softlockup: Make detector be aware of task switch of processes hogging cpu

PATCH In review Don Zickus 2 participants 3 messages Aug 28, 2014 – Aug 29, 2014

lore
Share & tools
lore

Don Zickus

author
#0 lore raw

PATCH 1/1 softlockup: Make detector be aware of task switch of processes hogging cpu

From: chai wen <[email protected]>

For now, soft lockup detector warns once for each case of process softlockup. But the thread 'watchdog/n' may not always get the cpu at the time slot between the task switch of two processes hogging that cpu to reset soft_watchdog_warn.

An example would be two processes hogging the cpu. Process A causes the softlockup warning and is killed manually by a user. Process B immediately becomes the new process hogging the cpu preventing the softlockup code from resetting the soft_watchdog_warn variable.

This case is a false negative of "warn only once for a process", as there may be a different process that is going to hog the cpu. Resolve this by saving/checking the task pointer of the hogging process and use that to reset soft_watchdog_warn too.

---
 kernel/watchdog.c |   16 +++++++++++++++-
 1 files changed, 15 insertions(+), 1 deletions(-)
kernel/watchdog.c +15 -1
index c3319bd..499f65f 100644
@@ -47,6 +47,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -331,8 +332,20 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			return HRTIMER_RESTART;
 
 		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true)
+		if (__this_cpu_read(soft_watchdog_warn) == true) {
+			/*
+			 * Handle the case where multiple processes are
+			 * causing softlockups but the duration is small
+			 * enough, the softlockup detector can not reset
+			 * itself in time.  Use task pointers to detect this.
+			 */
+			if (__this_cpu_read(softlockup_task_ptr_saved) !=
+			    current) {
+				__this_cpu_write(soft_watchdog_warn, false);
+				__touch_watchdog();
+			}
 			return HRTIMER_RESTART;
+		}
 
 		if (softlockup_all_cpu_backtrace) {
 			/* Prevent multiple soft-lockup reports if one cpu is already
@@ -348,6 +361,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
+		__this_cpu_write(softlockup_task_ptr_saved, current);
 		print_modules();
 		print_irqtrace_events(current);
 		if (regs)
Signature · 1 line
1.7.1
#1 lore raw
Quoted 11 lines · On Thu, 28 Aug 2014 00:52:24 -0400 Don Zickus <[email protected]> wrote:

From: chai wen <[email protected]>

For now, soft lockup detector warns once for each case of process softlockup. But the thread 'watchdog/n' may not always get the cpu at the time slot between the task switch of two processes hogging that cpu to reset soft_watchdog_warn.

An example would be two processes hogging the cpu. Process A causes the softlockup warning and is killed manually by a user. Process B immediately becomes the new process hogging the cpu preventing the softlockup code from resetting the soft_watchdog_warn variable.

Quoted 5 lines

This case is a false negative of "warn only once for a process", as there may be a different process that is going to hog the cpu. Resolve this by saving/checking the task pointer of the hogging process and use that to reset soft_watchdog_warn too.

OK, this should address the PID uniqueness issue which Ingo identified.

Quoted 12 lines
kernel/watchdog.c +1 -0
@@ -47,6 +47,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -331,8 +332,20 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			return HRTIMER_RESTART;

kernel/watchdog.c static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) · line 341

Quoted 10 lines
kernel/watchdog.c +7 -1
 
 		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true)
+		if (__this_cpu_read(soft_watchdog_warn) == true) {
+			/*
+			 * Handle the case where multiple processes are
+			 * causing softlockups but the duration is small
+			 * enough, the softlockup detector can not reset
+			 * itself in time.  Use task pointers to detect this.
+			 */

This comment is rather hard to follow ("the duration" of what?). Can you think of some words which are a bit more complete/clear?

author
#2 lore raw
Quoted 34 lines · Andrew Morton
Quoted 11 lines · On Thu, 28 Aug 2014 00:52:24 -0400 Don Zickus <[email protected]> wrote:

From: chai wen <[email protected]>

For now, soft lockup detector warns once for each case of process softlockup. But the thread 'watchdog/n' may not always get the cpu at the time slot between the task switch of two processes hogging that cpu to reset soft_watchdog_warn.

An example would be two processes hogging the cpu. Process A causes the softlockup warning and is killed manually by a user. Process B immediately becomes the new process hogging the cpu preventing the softlockup code from resetting the soft_watchdog_warn variable.

Quoted 5 lines

This case is a false negative of "warn only once for a process", as there may be a different process that is going to hog the cpu. Resolve this by saving/checking the task pointer of the hogging process and use that to reset soft_watchdog_warn too.

OK, this should address the PID uniqueness issue which Ingo identified.

Quoted 13 lines
kernel/watchdog.c +1 -0
@@ -47,6 +47,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -331,8 +332,20 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			return HRTIMER_RESTART;
 
Quoted 12 lines

kernel/watchdog.c static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) · line 341

Quoted 9 lines
kernel/watchdog.c +7 -1
 		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true)
+		if (__this_cpu_read(soft_watchdog_warn) == true) {
+			/*
+			 * Handle the case where multiple processes are
+			 * causing softlockups but the duration is small
+			 * enough, the softlockup detector can not reset
+			 * itself in time.  Use task pointers to detect this.
+			 */

This comment is rather hard to follow ("the duration" of what?). Can you think of some words which are a bit more complete/clear?

Agreed. Does this work better?

"
/*
* When multiple processes are causing softlockups
* the softlockup detector only warns on the first
* one because the code relies on a full quiet cycle
* to re-arm. The second process prevents the
* quiet cycle and never gets reported. Use task
* pointers to detect this.
*/

Cheers,
Don