Quoting Mika Kuoppala (2019-10-24 09:06:30)
> Chris Wilson <ch...@chris-wilson.co.uk> writes:
>
> > Quoting Mika Kuoppala (2019-10-24 08:21:14)
> >> Chris Wilson <ch...@chris-wilson.co.uk> writes:
> >>
> >> > When setting up the system to perform the atomic reset, we need to
> >> > serialise with any ongoing interrupt tasklet or else:
> >> >
> >> > <0> [472.951428] i915_sel-4442 0d..1 466527056us :
> >> > __i915_request_submit: rcs0 fence 11659:2, current 0
> >> > <0> [472.951554] i915_sel-4442 0d..1 466527059us :
> >> > __execlists_submission_tasklet: rcs0: queue_priority_hint:-2147483648,
> >> > submit:yes
> >> > <0> [472.951681] i915_sel-4442 0d..1 466527061us : trace_ports: rcs0:
> >> > submit { 11659:2, 0:0 }
> >> > <0> [472.951805] i915_sel-4442 0.... 466527114us :
> >> > __igt_atomic_reset_engine: i915_reset_engine(rcs0:active) under hardirq
> >> > <0> [472.951932] i915_sel-4442 0d... 466527115us :
> >> > intel_engine_reset: rcs0 flags=11d
> >> > <0> [472.952056] i915_sel-4442 0d... 466527117us :
> >> > execlists_reset_prepare: rcs0: depth<-1
> >> > <0> [472.952179] i915_sel-4442 0d... 466527119us :
> >> > intel_engine_stop_cs: rcs0
> >> > <0> [472.952305] <idle>-0 1..s1 466527119us : process_csb: rcs0
> >> > cs-irq head=3, tail=4
> >>
> >> Racing and this shows from old world?
> >
> > We have the same CSB events being seen by process_csb() on two different
> > processors. One being issued by the reset in the test, the other by the
> > interrupt; this scenario is supposed to be prevented by flushing the
> > interrupt tasklet with tasklet_disable() before we enter the atomic
> > reset -- but I copied the code to use tasklet_disable_nosync() that is
> > meant to only used from inside the atomic reset after we had serialised
> > (or know we are inside the tasklet) with the tasklet. Basically this bug
> > is of our own invention because we are bypassing the usual setup in
> > order to do engine->reset() from unusual conditions.
>
> Some deepdiving into the trace format and tasklet_disable_nosync vs
> tasklet_disable and I agree with the trace and the patch.
>
> I don't know where you copied the nosync from but I did look
> at preempt_reset and it can pull the nosync trick as it
> is inside the submission.
A much older preempt timeout series :)
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
