On 03/19/2014 03:42 PM, Oleg Nesterov wrote:
> On 03/19, Oleg Nesterov wrote:
>> On 03/19, Oleg Nesterov wrote:
>>> But please do not forget that the kernel crashes. Whatever else we do, this
>>> should be fixed anyway. And this should be fixed in driver.
>> drivers/message/fusion/ is obviously buggy.
> Perhaps this is the only problem and Tetsuo is right, this driver
> really needs more than 30 secs to probe...
>
> But if you have a bit of free time, perhaps you can try the stupid
> debugging patch below ;) Not sure it will help, but who knows.
>
> Oleg.
>
> diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
> index 00d339c..5ecc27e 100644
> --- a/drivers/message/fusion/mptsas.c
> +++ b/drivers/message/fusion/mptsas.c
> @@ -5400,12 +5400,16 @@ mptsas_init(void)
> {
> int error;
>
> + printk(KERN_CRIT "mptsas_init start\n");
> + current->flags |= 0x1;
> show_mptmod_ver(my_NAME, my_VERSION);
>
> mptsas_transport_template =
> sas_attach_transport(&mptsas_transport_functions);
> - if (!mptsas_transport_template)
> - return -ENODEV;
> + if (!mptsas_transport_template) {
> + error = -ENODEV;
> + goto out;
> + }
> mptsas_transport_template->eh_timed_out = mptsas_eh_timed_out;
>
> mptsasDoneCtx = mpt_register(mptscsih_io_done, MPTSAS_DRIVER,
> @@ -5428,6 +5432,9 @@ mptsas_init(void)
> if (error)
> sas_release_transport(mptsas_transport_template);
>
> +out:
> + current->flags &= ~0x1;
> + printk(KERN_CRIT "mptsas_init end\n");
> return error;
> }
>
> diff --git a/kernel/kthread.c b/kernel/kthread.c
> index b5ae3ee..78e643d 100644
> --- a/kernel/kthread.c
> +++ b/kernel/kthread.c
> @@ -291,6 +291,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
> * the OOM killer while kthreadd is trying to allocate memory for
> * new kernel thread.
> */
> +
> + if (current->flags & 1) {
> + pr_crit("mptsas no killable wait: %d %d\n",
> + signal_pending(current), __fatal_signal_pending(current));
> + goto wait;
> + }
> +
> if (unlikely(wait_for_completion_killable(&done))) {
> /*
> * If I was SIGKILLed before kthreadd (or new kernel thread)
> @@ -303,6 +310,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
> * kthreadd (or new kernel thread) will call complete()
> * shortly.
> */
> +wait:
> wait_for_completion(&done);
> }
> task = create->result;
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index b46131e..2b202bd 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2655,6 +2655,14 @@ static void __sched __schedule(void)
> unsigned long *switch_count;
> struct rq *rq;
> int cpu;
> + bool trace;
> +
> + trace = (current->flags & 1) && current->state && !(preempt_count() & PREEMPT_ACTIVE);
> + if (trace) {
> + pr_crit("mptsas sched: %lx %d %d\n", current->state,
> + signal_pending(current), __fatal_signal_pending(current));
> + show_stack(NULL, NULL);
> + }
>
> need_resched:
> preempt_disable();
> @@ -2733,6 +2741,11 @@ need_resched:
> sched_preempt_enable_no_resched();
> if (need_resched())
> goto need_resched;
> +
> + if (trace) {
> + pr_crit("mptsas wake: %d %d\n",
> + signal_pending(current), __fatal_signal_pending(current));
> + }
> }
>
> static inline void sched_submit_work(struct task_struct *tsk)
> diff --git a/kernel/signal.c b/kernel/signal.c
> index 52f881d..d121944 100644
> --- a/kernel/signal.c
> +++ b/kernel/signal.c
> @@ -1152,6 +1152,11 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
> {
> int from_ancestor_ns = 0;
>
> + if (t->flags & 1) {
> + pr_crit("mptsas killed %d\n", sig);
> + sched_show_task(t);
> + }
> +
> #ifdef CONFIG_PID_NS
> from_ancestor_ns = si_fromuser(info) &&
> !task_pid_nr_ns(current, task_active_pid_ns(t));
>
Thanks for the patch, Oleg. I built a test kernel and asked the bug
reporter to test it [0].
[0] https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1276705/comments/56
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
