[Intel-gfx] [PATCH 1/2] drm/i915/selftests: Add a cancel request selftest that triggers a reset
Matthew Brost
matthew.brost at intel.com
Thu Jan 13 17:34:08 UTC 2022
On Thu, Jan 13, 2022 at 09:33:12AM -0800, John Harrison wrote:
> On 1/11/2022 15:11, Matthew Brost wrote:
> > Add a cancel request selftest that results in an engine reset to cancel
> > the request as it is non-preemptable. Also insert a NOP request after
> > the cancelled request and confirm that it completes successfully.
> >
> > v2:
> > (Tvrtko)
> > - Skip test if preemption timeout compiled out
> > - Skip test if engine reset isn't supported
> > - Update debug prints to be more descriptive
> > v3:
> > - Add comment explaining test
> >
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> > ---
> > drivers/gpu/drm/i915/selftests/i915_request.c | 117 ++++++++++++++++++
> > 1 file changed, 117 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
> > index 7f66f6d299b26..f78de99d5ae1e 100644
> > --- a/drivers/gpu/drm/i915/selftests/i915_request.c
> > +++ b/drivers/gpu/drm/i915/selftests/i915_request.c
> > @@ -782,6 +782,115 @@ static int __cancel_completed(struct intel_engine_cs *engine)
> > return err;
> > }
> > +/*
> > + * Test to prove a non-preemptable request can be cancelled and a subsequent
> > + * request on the same context can successfully complete after cancallation.
> cancellation
>
Yep.
> > + *
> > + * Testing methodology is to create non-preemptable request and submit it,
> a non-preemptible
>
Yep.
> > + * wait for spinner to start, create a NOP request and submit it, cancel the
> > + * spinner, wait for spinner to complete and verify it failed with an error,
> > + * finally wait for NOP request to complete verify it succeeded without an
> > + * error. Preemption timeout also reduced / restored so test runs in a timely
> > + * maner.
> > + */
> > +static int __cancel_reset(struct drm_i915_private *i915,
> > + struct intel_engine_cs *engine)
> > +{
> > + struct intel_context *ce;
> > + struct igt_spinner spin;
> > + struct i915_request *rq, *nop;
> > + unsigned long preempt_timeout_ms;
> > + int err = 0;
> > +
> > + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT ||
> Does this matter? The test is overriding the default anyway.
>
Yes. Execlists don't try to preempt anything if
CONFIG_DRM_I915_PREEMPT_TIMEOUT is turned off. If we wan't to avoid the
cancelation doing a full GT reset, CONFIG_DRM_I915_PREEMPT_TIMEOUT
should be turned on.
> > + !intel_has_reset_engine(engine->gt))
> > + return 0;
> > +
> > + preempt_timeout_ms = engine->props.preempt_timeout_ms;
> > + engine->props.preempt_timeout_ms = 100;
> > +
> > + if (igt_spinner_init(&spin, engine->gt))
> > + goto out_restore;
> > +
> > + ce = intel_context_create(engine);
> > + if (IS_ERR(ce)) {
> > + err = PTR_ERR(ce);
> > + goto out_spin;
> > + }
> > +
> > + rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
> > + if (IS_ERR(rq)) {
> > + err = PTR_ERR(rq);
> > + goto out_ce;
> > + }
> > +
> > + pr_debug("%s: Cancelling active non-preemptable request\n",
> > + engine->name);
> > + i915_request_get(rq);
> > + i915_request_add(rq);
> > + if (!igt_wait_for_spinner(&spin, rq)) {
> > + struct drm_printer p = drm_info_printer(engine->i915->drm.dev);
> > +
> > + pr_err("Failed to start spinner on %s\n", engine->name);
> > + intel_engine_dump(engine, &p, "%s\n", engine->name);
> > + err = -ETIME;
> > + goto out_rq;
> > + }
> > +
> > + nop = intel_context_create_request(ce);
> > + if (IS_ERR(nop))
> > + goto out_nop;
> Should be out_rq?
>
Yes, it should.
Matt
> John.
>
>
> > + i915_request_get(nop);
> > + i915_request_add(nop);
> > +
> > + i915_request_cancel(rq, -EINTR);
> > +
> > + if (i915_request_wait(rq, 0, HZ) < 0) {
> > + struct drm_printer p = drm_info_printer(engine->i915->drm.dev);
> > +
> > + pr_err("%s: Failed to cancel hung request\n", engine->name);
> > + intel_engine_dump(engine, &p, "%s\n", engine->name);
> > + err = -ETIME;
> > + goto out_nop;
> > + }
> > +
> > + if (rq->fence.error != -EINTR) {
> > + pr_err("%s: fence not cancelled (%u)\n",
> > + engine->name, rq->fence.error);
> > + err = -EINVAL;
> > + goto out_nop;
> > + }
> > +
> > + if (i915_request_wait(nop, 0, HZ) < 0) {
> > + struct drm_printer p = drm_info_printer(engine->i915->drm.dev);
> > +
> > + pr_err("%s: Failed to complete nop request\n", engine->name);
> > + intel_engine_dump(engine, &p, "%s\n", engine->name);
> > + err = -ETIME;
> > + goto out_nop;
> > + }
> > +
> > + if (nop->fence.error != 0) {
> > + pr_err("%s: Nop request errored (%u)\n",
> > + engine->name, nop->fence.error);
> > + err = -EINVAL;
> > + }
> > +
> > +out_nop:
> > + i915_request_put(nop);
> > +out_rq:
> > + i915_request_put(rq);
> > +out_ce:
> > + intel_context_put(ce);
> > +out_spin:
> > + igt_spinner_fini(&spin);
> > +out_restore:
> > + engine->props.preempt_timeout_ms = preempt_timeout_ms;
> > + if (err)
> > + pr_err("%s: %s error %d\n", __func__, engine->name, err);
> > + return err;
> > +}
> > +
> > static int live_cancel_request(void *arg)
> > {
> > struct drm_i915_private *i915 = arg;
> > @@ -814,6 +923,14 @@ static int live_cancel_request(void *arg)
> > return err;
> > if (err2)
> > return err2;
> > +
> > + /* Expects reset so call outside of igt_live_test_* */
> > + err = __cancel_reset(i915, engine);
> > + if (err)
> > + return err;
> > +
> > + if (igt_flush_test(i915))
> > + return -EIO;
> > }
> > return 0;
>
More information about the Intel-gfx
mailing list