lkml.org 
[lkml]   [2010]   [Mar]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 1/6] kill the broken and deadlockable cpuset_lock/cpuset_cpus_allowed_locked code
On 03/25, Miao Xie wrote:
>
> on 2010-3-25 18:14, Oleg Nesterov wrote:
> > On 03/25, Miao Xie wrote:
> >>
> >> The problem what you said don't exist, because the kernel already move T to
> >> the active cpu when preparing to turn off a CPU.
> >
> > we need cpuset_lock() to move T. please look at _cpu_down().
> >
> > OK.
> >
> > A task T holds callback_mutex, and it is bound to CPU 1.
> >
> > _cpu_down(cpu => 1) is called by the task X.
> >
> > _cpu_down()->stop_machine() spawns rt-threads for each cpu,
> > a thread running on CPU 1 preempts T and calls take_cpu_down()
> > which removes CPU 1 from online/active masks.
> >
> > X continues, and does raw_notifier_call_chain(CPU_DEAD), this
> > calls migration_call(CPU_DEAD), and _this_ is what move the
> > tasks from the dead CPU.
> >
> > migration_call(CPU_DEAD) calls cpuset_lock() and deadlocks.
> >
> > See?
>
> But when the kernel want to offline a cpu, it does
> raw_notifier_call_chain(CPU_DOWN_PREPARE)
> at first. this calls cpuset_track_online_cpus() to update cpuset's cpus
First of let me note that it is wrong to call scan_for_empty_cpusets()
at CPU_DOWN_PREPARE state. _cpu_down() can fail after that but we can't
revert the result of remove_tasks_in_empty_cpuset().

But this doesn't matter,

> and task->cpus_allowed, and then moves the task running on the dying cpu
> to the other online cpu.

No, it doesn't track task->cpus_allowed afaics. It only checks
cpumask_empty(cp->cpus_allowed) and does nothing otherwise.

And it is quite possible that the task belongs to some cpuset cs, bound
to a single cpu, but cs->cpus_allowed is "wide" and includes other online cpus.

> At that time, rt-threads for each cpu have not
> been created.

(doesn't matter, but the are already created and sleeping)

> And when the kernel does migration_call(CPU_DEAD), the rt-threads already
> exit.

No, there are sleeping, but this doesn't matter again.

> the task that holds callback_mutex can run as normal.

It can't afaics, please see above.


That said, let me remind. I read this code only once a long ago, during my
first attempt to fix these problems (all my attempts were ignored until
I rerouted my concerns to Peter). It is possible that I missed/forgot/both
something. But when I did the second version I bothered to actually test
my theory and the kernel hanged, see the changelog in
http://marc.info/?t=124910242400002

You was cc'ed too ;)

Oleg.



\
 
 \ /
  Last update: 2010-03-25 14:05    [W:0.040 / U:0.360 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site