diff mbox series

[08/27] drm/i915/selftests: Add a cancel request selftest that triggers a reset

Message ID 20210826032327.18078-9-matthew.brost@intel.com (mailing list archive)
State New, archived
Headers show
Series Clean up GuC CI failures, simplify locking, and kernel DOC | expand

Commit Message

Matthew Brost Aug. 26, 2021, 3:23 a.m. UTC 
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 completely successfully.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 100 ++++++++++++++++++
 1 file changed, 100 insertions(+)

Comments

Tvrtko Ursulin Aug. 26, 2021, 9:32 a.m. UTC | #1 
On 26/08/2021 04:23, 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 completely successfully.

Which patch fixes a problem this exposes in the execlists implementation?

> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>   drivers/gpu/drm/i915/selftests/i915_request.c | 100 ++++++++++++++++++
>   1 file changed, 100 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
> index d67710d10615..e2c5db77f087 100644
> --- a/drivers/gpu/drm/i915/selftests/i915_request.c
> +++ b/drivers/gpu/drm/i915/selftests/i915_request.c
> @@ -772,6 +772,98 @@ static int __cancel_completed(struct intel_engine_cs *engine)
>   	return err;
>   }
>   
> +static int __cancel_reset(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;
> +

You may need to skip the test if preempt timeout is compiled out or if 
GPU reset is altogether disabled.

> +	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 request\n", engine->name);

"active non-preemptable" perhaps?

> +	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;
> +	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",

Maybe s/nop/innocent/ in the respective log messages?

> +		       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;
> @@ -804,6 +896,14 @@ static int live_cancel_request(void *arg)
>   			return err;
>   		if (err2)
>   			return err2;
> +
> +		/* Expects reset so call outside of igt_live_test_* */

Hm there are live tests like live_preempt_cancel which seemingly manage 
to do resets under the live test block.

Regards,

Tvrtko

> +		err = __cancel_reset(engine);
> +		if (err)
> +			return err;
> +
> +		if (igt_flush_test(i915))
> +			return -EIO;
>   	}
>   
>   	return 0;
>
Matthew Brost Aug. 26, 2021, 2 p.m. UTC | #2 
On Thu, Aug 26, 2021 at 10:32:54AM +0100, Tvrtko Ursulin wrote:
> 
> On 26/08/2021 04:23, 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 completely successfully.
> 
> Which patch fixes a problem this exposes in the execlists implementation?
> 

https://patchwork.freedesktop.org/patch/451421/?series=93704&rev=6

> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > ---
> >   drivers/gpu/drm/i915/selftests/i915_request.c | 100 ++++++++++++++++++
> >   1 file changed, 100 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
> > index d67710d10615..e2c5db77f087 100644
> > --- a/drivers/gpu/drm/i915/selftests/i915_request.c
> > +++ b/drivers/gpu/drm/i915/selftests/i915_request.c
> > @@ -772,6 +772,98 @@ static int __cancel_completed(struct intel_engine_cs *engine)
> >   	return err;
> >   }
> > +static int __cancel_reset(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;
> > +
> 
> You may need to skip the test if preempt timeout is compiled out or if GPU
> reset is altogether disabled.
>

Yes, probably. Will fix this.
 
> > +	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 request\n", engine->name);
> 
> "active non-preemptable" perhaps?
> 

Sure.

> > +	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;
> > +	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",
> 
> Maybe s/nop/innocent/ in the respective log messages?
> 

I kinda perfer NOP.

> > +		       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;
> > @@ -804,6 +896,14 @@ static int live_cancel_request(void *arg)
> >   			return err;
> >   		if (err2)
> >   			return err2;
> > +
> > +		/* Expects reset so call outside of igt_live_test_* */
> 
> Hm there are live tests like live_preempt_cancel which seemingly manage to
> do resets under the live test block.
>

You can increment t->reset_global if a GT reset is expected, problem is
only execlists do a GT while GuC submission does a GuC engine based
reset so we'd have to put in a statement like this if was within the
begin / end block:

if !guc
	t->reset_global++

I'd just rather leave it as is rather than baking in execlists / guc
backend specific knowledge into the test.

Matt

> Regards,
> 
> Tvrtko
> 
> > +		err = __cancel_reset(engine);
> > +		if (err)
> > +			return err;
> > +
> > +		if (igt_flush_test(i915))
> > +			return -EIO;
> >   	}
> >   	return 0;
> >
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index d67710d10615..e2c5db77f087 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -772,6 +772,98 @@  static int __cancel_completed(struct intel_engine_cs *engine)
 	return err;
 }
 
+static int __cancel_reset(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;
+
+	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 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;
+	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;
@@ -804,6 +896,14 @@  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(engine);
+		if (err)
+			return err;
+
+		if (igt_flush_test(i915))
+			return -EIO;
 	}
 
 	return 0;