cpu_unplug_begin() should be called before CPU_DOWN_PREPARE,
because at CPU_DOWN_PREPARE cpu_active is cleared and sched_domain
is rebuilt, it will finally lead to thread 'sync_unplug' will
be running on the cpu on which it's created.
I found by an incorrect warning on smp_processor_id() called by
sync_unplug/1, and trace shows below:
(echo 1 > /sys/device/system/cpu/cpu1/online)
bash-1664 [000] 83.136620: _cpu_down: Bind sync_unplug to cpu 1
bash-1664 [000] 83.136623: sched_wait_task: comm=sync_unplug/1 pid=1724 prio=120
bash-1664 [000] 83.136624: _cpu_down: Wake sync_unplug
bash-1664 [000] 83.136629: sched_wakeup: comm=sync_unplug/1 pid=1724 prio=120 success=1 target_cpu=000
Signed-off-by: Yong Zhang <yong.zhang0@xxxxxxxxx>
---
kernel/cpu.c | 16 +++++++---------
1 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 83fb084..13066a3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -337,22 +337,20 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
return -EBUSY;
}
- err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
+ cpu_hotplug_begin();
+ err = cpu_unplug_begin(cpu);
if (err) {
- nr_calls--;
- __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
- printk("%s: attempt to take down CPU %u failed\n",
- __func__, cpu);
+ printk("cpu_unplug_begin(%d) failed\n", cpu);
goto out_cancel;
}
- cpu_hotplug_begin();
- err = cpu_unplug_begin(cpu);
+ err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
if (err) {
nr_calls--;
__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
- printk("cpu_unplug_begin(%d) failed\n", cpu);
- goto out_cancel;
+ printk("%s: attempt to take down CPU %u failed\n",
+ __func__, cpu);
+ goto out_release;
}
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
