Quoting Tvrtko Ursulin (2018-03-29 10:34:40)
> From: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
>
> Contexts executing when reset triggers are potentialy corrupt so trying to
> use them from a subsequent test (like the default context) can hang the
> GPU or even the driver.
>
> Workaround that by always creating a dedicated context which will be
> running when GPU reset happens.
>
> v2:
> * Export and use gem_reopen_device so the test works on old gens as well.
> (Chris Wilson)
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxx>
Matches what I wrote^W imagined (as if you believe I would have bothered
with the export rather than cut'n'paste ;)
Have a conditional
Reviewed-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
on the condition that you throw in a test that reused a few contexts a few
times. I think something like
for (nctx in prime(1, next_prime(MAX_ELSP))) {
while (loop) {
for (ctx = nctx) {
for_each_engine() {
add-spin(ctx, engine);
}
end-spin.
}
// something, something inject wedge
}
?
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
