korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-24 04:34:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

wq: handle VM suspension in stall detection

Browse Source 
If VCPU is suspended (VM suspend) in wq_watchdog_timer_fn() then
once this VCPU resumes it will see the new jiffies value, while it
may take a while before IRQ detects PVCLOCK_GUEST_STOPPED on this
VCPU and updates all the watchdogs via pvclock_touch_watchdogs().
There is a small chance of misreported WQ stalls in the meantime,
because new jiffies is time_after() old 'ts + thresh'.

wq_watchdog_timer_fn()
{
	for_each_pool(pool, pi) {
		if (time_after(jiffies, ts + thresh)) {
			pr_emerg("BUG: workqueue lockup - pool");
		}
	}
}

Save jiffies at the beginning of this function and use that value
for stall detection. If VM gets suspended then we continue using
"old" jiffies value and old WQ touch timestamps. If IRQ at some
point restarts the stall detection cycle (pvclock_touch_watchdogs())
then old jiffies will always be before new 'ts + thresh'.

Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
This commit is contained in:
Sergey Senozhatsky 2021-05-20 19:14:22 +09:00 committed by Tejun Heo
parent c3d0e3fd41
commit 940d71c646
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
kernel/workqueue.c
View File

@ -50,6 +50,7 @@
#include <linux/uaccess.h> #include <linux/uaccess.h>
#include <linux/sched/isolation.h> #include <linux/sched/isolation.h>
#include <linux/nmi.h> #include <linux/nmi.h>
#include <linux/kvm_para.h>
#include "workqueue_internal.h" #include "workqueue_internal.h"
@ -5772,6 +5773,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
{ {
unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
bool lockup_detected = false; bool lockup_detected = false;
unsigned long now = jiffies;
struct worker_pool *pool; struct worker_pool *pool;
int pi; int pi;
@ -5786,6 +5788,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
if (list_empty(&pool->worklist)) if (list_empty(&pool->worklist))
continue; continue;
/*
* If a virtual machine is stopped by the host it can look to
* the watchdog like a stall.
*/
kvm_check_and_clear_guest_paused();
/* get the latest of pool and touched timestamps */ /* get the latest of pool and touched timestamps */
if (pool->cpu >= 0) if (pool->cpu >= 0)
touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
@ -5799,12 +5807,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
ts = touched; ts = touched;
/* did we stall? */ /* did we stall? */
if (time_after(jiffies, ts + thresh)) { if (time_after(now, ts + thresh)) {
lockup_detected = true; lockup_detected = true;
pr_emerg("BUG: workqueue lockup - pool"); pr_emerg("BUG: workqueue lockup - pool");
pr_cont_pool_info(pool); pr_cont_pool_info(pool);
pr_cont(" stuck for %us!\n", pr_cont(" stuck for %us!\n",
jiffies_to_msecs(jiffies - pool_ts) / 1000); jiffies_to_msecs(now - pool_ts) / 1000);
} }
} }