[poll / rfc] kdb_stop_cpus

[Attilio Rao]

2011/6/3 Nathan Whitehorn <nwhitehorn at freebsd.org>:
> On 06/03/11 10:13, Andriy Gapon wrote:
>>
>> I wonder if anybody uses kdb_stop_cpus with non-default value.
>> If, yes, I am very interested to learn about your usecase for it.
>>
>> I think that the default kdb behavior is the correct one, so it doesn't
>> make sense
>> to have a knob to turn on incorrect behavior.
>> But I may be missing something obvious.
>>
>> The comment in the code doesn't really satisfy me:
>> /*
>>  * Flag indicating whether or not to IPI the other CPUs to stop them on
>>  * entering the debugger.  Sometimes, this will result in a deadlock as
>>  * stop_cpus() waits for the other cpus to stop, so we allow it to be
>>  * disabled.  In order to maximize the chances of success, use a hard
>>  * stop for that.
>>  */
>>
>> The hard stop should be sufficiently mighty.
>> Yes, I am aware of supposedly extremely rare situations where a deadlock
>> could
>> happen even when using hard stop.  But I'd rather fix that than have this
>> switch.
>>
>> Oh, the commit message (from 2004) explains it:
>>>
>>> Add a new sysctl, debug.kdb.stop_cpus, which controls whether or not we
>>> attempt to IPI other cpus when entering the debugger in order to stop
>>> them while in the debugger.  The default remains to issue the stop;
>>> however, that can result in a hang if another cpu has interrupts disabled
>>> and is spinning, since the IPI won't be received and the KDB will wait
>>> indefinitely.  We probably need to add a timeout, but this is a useful
>>> stopgap in the mean time.
>>
>> But that was before we started using hard stop in this context (in 2009).
>
> Some non-x86 platforms (e.g. PPC) don't support real NMIs, and so this still
> applies.

Well, if I get Andriy's proposal right, he just wants to trim off the
possibility to not stop the CPUs on entering KDB. I'm not entirely
sure why there is a sysctl for disabling that and I really don't want
it.

Note that the missing of the NMI/privileged Interrupt is not going to
be a factor on this request, unless you are worried a lot by the easy
deadlock that a normal stop operation may lead.
If that is the case, I think that the upcoming work on skipping
locking during KDB/panic entering is going to help a lot for this
case. At that point removing the possibility to turn off CPU stopping
will be a good idea, IMHO.

Attilio


-- 
Peace can only be achieved by understanding - A. Einstein