diff mbox series

drm/i915/selftests: Exercise rc6 handling

Message ID 20191114083436.2261-1-chris@chris-wilson.co.uk (mailing list archive)
State New, archived
Headers show
Series drm/i915/selftests: Exercise rc6 handling | expand

Commit Message

Chris Wilson Nov. 14, 2019, 8:34 a.m. UTC
Reading from CTX_INFO upsets rc6, requiring us to detect and prevent
possible rc6 context corruption. Poke at the bear!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_rc6.c           |  4 +
 drivers/gpu/drm/i915/gt/selftest_gt_pm.c      | 13 +++
 drivers/gpu/drm/i915/gt/selftest_rc6.c        | 89 +++++++++++++++++++
 drivers/gpu/drm/i915/gt/selftest_rc6.h        | 12 +++
 .../drm/i915/selftests/i915_live_selftests.h  |  1 +
 5 files changed, 119 insertions(+)
 create mode 100644 drivers/gpu/drm/i915/gt/selftest_rc6.c
 create mode 100644 drivers/gpu/drm/i915/gt/selftest_rc6.h

Comments

Chris Wilson Nov. 14, 2019, 8:46 a.m. UTC | #1
Quoting Chris Wilson (2019-11-14 08:34:36)
> Reading from CTX_INFO upsets rc6, requiring us to detect and prevent
> possible rc6 context corruption. Poke at the bear!
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Imre Deak <imre.deak@intel.com>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_rc6.c           |  4 +
>  drivers/gpu/drm/i915/gt/selftest_gt_pm.c      | 13 +++
>  drivers/gpu/drm/i915/gt/selftest_rc6.c        | 89 +++++++++++++++++++
>  drivers/gpu/drm/i915/gt/selftest_rc6.h        | 12 +++
>  .../drm/i915/selftests/i915_live_selftests.h  |  1 +
>  5 files changed, 119 insertions(+)
>  create mode 100644 drivers/gpu/drm/i915/gt/selftest_rc6.c
>  create mode 100644 drivers/gpu/drm/i915/gt/selftest_rc6.h
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
> index f7c0baeb3793..0de35d18a2b2 100644
> --- a/drivers/gpu/drm/i915/gt/intel_rc6.c
> +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
> @@ -777,3 +777,7 @@ u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
>  {
>         return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
>  }
> +
> +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
> +#include "selftest_rc6.c"
> +#endif
> diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
> index d1752f15702a..1d5bf93d1258 100644
> --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
> +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
> @@ -6,6 +6,7 @@
>   */
>  
>  #include "selftest_llc.h"
> +#include "selftest_rc6.h"
>  
>  static int live_gt_resume(void *arg)
>  {
> @@ -58,3 +59,15 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
>  
>         return intel_gt_live_subtests(tests, &i915->gt);
>  }
> +
> +int intel_gt_pm_late_selftests(struct drm_i915_private *i915)
> +{
> +       static const struct i915_subtest tests[] = {
> +               SUBTEST(live_rc6_ctx),
> +       };
> +
> +       if (intel_gt_is_wedged(&i915->gt))
> +               return 0;
> +
> +       return intel_gt_live_subtests(tests, &i915->gt);
> +}
> diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
> new file mode 100644
> index 000000000000..9b02016c81a9
> --- /dev/null
> +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
> @@ -0,0 +1,89 @@
> +/*
> + * SPDX-License-Identifier: MIT
> + *
> + * Copyright © 2019 Intel Corporation
> + */
> +
> +#include "intel_context.h"
> +#include "intel_engine_pm.h"
> +#include "intel_gt_requests.h"
> +#include "intel_ring.h"
> +#include "selftest_rc6.h"
> +
> +static const u32 *__live_rc6_ctx(struct intel_context *ce)
> +{
> +       struct i915_request *rq;
> +       u32 const *result;
> +       u32 *cs;
> +
> +       rq = intel_context_create_request(ce);
> +       if (IS_ERR(rq))
> +               return ERR_CAST(rq);
> +
> +       cs = intel_ring_begin(rq, 4);
> +       if (IS_ERR(cs)) {
> +               i915_request_add(rq);
> +               return cs;
> +       }
> +
> +       *cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
> +       *cs++ = 0xA300; /* CTX_INFO */
> +       *cs++ = ce->timeline->hwsp_offset + 8;
> +       *cs++ = 0;
> +       intel_ring_advance(rq, cs);
> +
> +       result = rq->hwsp_seqno + 2;
> +       i915_request_add(rq);
> +
> +       return result;
> +}
> +
> +int live_rc6_ctx(void *arg)
> +{
> +       struct intel_gt *gt = arg;
> +       struct intel_engine_cs *engine;
> +       enum intel_engine_id id;
> +
> +       /* A read of CTX_INFO upsets rc6. Poke the bear! */
> +
> +       for_each_engine(engine, gt, id) {

I guess we really want to randomise this order so that we don't test the
same pattern of reads and fixup everytime.
-Chris
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index f7c0baeb3793..0de35d18a2b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -777,3 +777,7 @@  u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
 {
 	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_rc6.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index d1752f15702a..1d5bf93d1258 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -6,6 +6,7 @@ 
  */
 
 #include "selftest_llc.h"
+#include "selftest_rc6.h"
 
 static int live_gt_resume(void *arg)
 {
@@ -58,3 +59,15 @@  int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 
 	return intel_gt_live_subtests(tests, &i915->gt);
 }
+
+int intel_gt_pm_late_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_rc6_ctx),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
new file mode 100644
index 000000000000..9b02016c81a9
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -0,0 +1,89 @@ 
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_context.h"
+#include "intel_engine_pm.h"
+#include "intel_gt_requests.h"
+#include "intel_ring.h"
+#include "selftest_rc6.h"
+
+static const u32 *__live_rc6_ctx(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	u32 const *result;
+	u32 *cs;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return ERR_CAST(rq);
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return cs;
+	}
+
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+	*cs++ = 0xA300; /* CTX_INFO */
+	*cs++ = ce->timeline->hwsp_offset + 8;
+	*cs++ = 0;
+	intel_ring_advance(rq, cs);
+
+	result = rq->hwsp_seqno + 2;
+	i915_request_add(rq);
+
+	return result;
+}
+
+int live_rc6_ctx(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* A read of CTX_INFO upsets rc6. Poke the bear! */
+
+	for_each_engine(engine, gt, id) {
+		int pass;
+
+		for (pass = 0; pass < 2; pass++) {
+			struct intel_context *ce;
+			unsigned int resets =
+				i915_reset_engine_count(&gt->i915->gpu_error,
+							engine);
+			const u32 *res;
+
+			/* Use a sacrifical context */
+			ce = intel_context_create(engine->kernel_context->gem_context,
+						  engine);
+			if (IS_ERR(ce))
+				return PTR_ERR(ce);
+
+			intel_engine_pm_get(engine);
+			res = __live_rc6_ctx(ce);
+			intel_engine_pm_put(engine);
+			intel_context_put(ce);
+			if (IS_ERR(res))
+				return PTR_ERR(res);
+
+			intel_gt_retire_requests(gt);
+			intel_gt_pm_wait_for_idle(gt);
+
+			pr_debug("%s: CTX_INFO=%0x\n",
+				 engine->name, READ_ONCE(*res));
+			if (resets !=
+			    i915_reset_engine_count(&gt->i915->gpu_error,
+						    engine)) {
+				pr_err("%s: GPU reset required\n",
+				       engine->name);
+				add_taint_for_CI(TAINT_WARN);
+				return -EIO;
+			}
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.h b/drivers/gpu/drm/i915/gt/selftest_rc6.h
new file mode 100644
index 000000000000..230c6b4c7dc0
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.h
@@ -0,0 +1,12 @@ 
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef SELFTEST_RC6_H
+#define SELFTEST_RC6_H
+
+int live_rc6_ctx(void *arg);
+
+#endif /* SELFTEST_RC6_H */
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 4b3cac73e291..db5565679045 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -38,3 +38,4 @@  selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
 selftest(guc, intel_guc_live_selftest)
 selftest(perf, i915_perf_live_selftests)
+selftest(late_gt_pm, intel_gt_pm_late_selftests)