[Intel-gfx] [PATCH v6] drm/i915/guc: Add support for reset engine using GuC commands

[Michel Thierry]

This patch adds per engine reset and recovery (TDR) support when GuC is
used to submit workloads to GPU.

In the case of i915 directly submission to ELSP, driver manages hang
detection, recovery and resubmission. With GuC submission these tasks
are shared between driver and GuC. i915 is still responsible for detecting
a hang, and when it does it only requests GuC to reset that Engine. GuC
internally manages acquiring forcewake and idling the engine before
resetting it.

Once the reset is successful, i915 takes over again and handles the
resubmission. The scheduler in i915 knows which requests are pending so
after resetting a engine, pending workloads/requests are resubmitted
again.

v2: s/i915_guc_request_engine_reset/i915_guc_reset_engine/ to match the
non-guc function names.

v3: Removed debug message about engine restarting from which request,
since the new baseline do it regardless of submission mode. (Chris)

v4: Rebase.

v5: Do not pass unnecessary reporting flags to the fw (Jeff);
tasklet_schedule(&execlists->irq_tasklet) handles the resubmit; rebase.

v6: Rename the existing reset engine function and share a similar
interface between guc and non-guc paths (Chris).

Signed-off-by: Michel Thierry <michel.thierry at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.c       | 15 +++++++++++++--
 drivers/gpu/drm/i915/i915_drv.h       |  2 ++
 drivers/gpu/drm/i915/intel_guc.c      | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_guc_fwif.h |  1 +
 drivers/gpu/drm/i915/intel_uncore.c   |  5 -----
 5 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index af745749509c..359333a423cf 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1950,6 +1950,12 @@ void i915_reset(struct drm_i915_private *i915, unsigned int flags)
 	goto finish;
 }
 
+static inline int intel_gt_reset_engine(struct drm_i915_private *dev_priv,
+					struct intel_engine_cs *engine)
+{
+	return intel_gpu_reset(dev_priv, intel_engine_flag(engine));
+}
+
 /**
  * i915_reset_engine - reset GPU engine to recover from a hang
  * @engine: engine to reset
@@ -1984,10 +1990,15 @@ int i915_reset_engine(struct intel_engine_cs *engine, unsigned int flags)
 		goto out;
 	}
 
-	ret = intel_gpu_reset(engine->i915, intel_engine_flag(engine));
+	if (!engine->i915->guc.execbuf_client)
+		ret = intel_gt_reset_engine(engine->i915, engine);
+	else
+		ret = intel_guc_reset_engine(&engine->i915->guc, engine);
+
 	if (ret) {
 		/* If we fail here, we expect to fallback to a global reset */
-		DRM_DEBUG_DRIVER("Failed to reset %s, ret=%d\n",
+		DRM_DEBUG_DRIVER("%sFailed to reset %s, ret=%d\n",
+				 (engine->i915->guc.execbuf_client ? "GUC ":""),
 				 engine->name, ret);
 		goto out;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cff1b57598c3..ce2725696187 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3330,6 +3330,8 @@ extern int i915_reset_engine(struct intel_engine_cs *engine,
 
 extern bool intel_has_reset_engine(struct drm_i915_private *dev_priv);
 extern int intel_reset_guc(struct drm_i915_private *dev_priv);
+extern int intel_guc_reset_engine(struct intel_guc *guc,
+				  struct intel_engine_cs *engine);
 extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 extern void intel_hangcheck_init(struct drm_i915_private *dev_priv);
 extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index f74d50fdaeb0..9678630a1c70 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -24,6 +24,7 @@
 
 #include "intel_guc.h"
 #include "i915_drv.h"
+#include "i915_guc_submission.h"
 
 static void gen8_guc_raise_irq(struct intel_guc *guc)
 {
@@ -283,6 +284,29 @@ int intel_guc_suspend(struct drm_i915_private *dev_priv)
 	return intel_guc_send(guc, data, ARRAY_SIZE(data));
 }
 
+/**
+ * intel_guc_reset_engine() - ask GuC to reset an engine
+ * @guc:	intel_guc structure
+ * @engine:	engine to be reset
+ */
+int intel_guc_reset_engine(struct intel_guc *guc,
+			   struct intel_engine_cs *engine)
+{
+	u32 data[7];
+
+	GEM_BUG_ON(!guc->execbuf_client);
+
+	data[0] = INTEL_GUC_ACTION_REQUEST_ENGINE_RESET;
+	data[1] = engine->guc_id;
+	data[2] = 0;
+	data[3] = 0;
+	data[4] = 0;
+	data[5] = guc->execbuf_client->stage_id;
+	data[6] = guc_ggtt_offset(guc->shared_data);
+
+	return intel_guc_send(guc, data, ARRAY_SIZE(data));
+}
+
 /**
  * intel_guc_resume() - notify GuC resuming from suspend state
  * @dev_priv:	i915 device private
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index e24dbec2ead8..6a10aa6f04d3 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -574,6 +574,7 @@ struct guc_shared_ctx_data {
 enum intel_guc_action {
 	INTEL_GUC_ACTION_DEFAULT = 0x0,
 	INTEL_GUC_ACTION_REQUEST_PREEMPTION = 0x2,
+	INTEL_GUC_ACTION_REQUEST_ENGINE_RESET = 0x3,
 	INTEL_GUC_ACTION_SAMPLE_FORCEWAKE = 0x6,
 	INTEL_GUC_ACTION_ALLOCATE_DOORBELL = 0x10,
 	INTEL_GUC_ACTION_DEALLOCATE_DOORBELL = 0x20,
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index d629b2e40013..0564d87ad416 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1792,14 +1792,9 @@ bool intel_has_gpu_reset(struct drm_i915_private *dev_priv)
 	return intel_get_gpu_reset(dev_priv) != NULL;
 }
 
-/*
- * When GuC submission is enabled, GuC manages ELSP and can initiate the
- * engine reset too. For now, fall back to full GPU reset if it is enabled.
- */
 bool intel_has_reset_engine(struct drm_i915_private *dev_priv)
 {
 	return (dev_priv->info.has_reset_engine &&
-		!dev_priv->guc.execbuf_client &&
 		i915_modparams.reset >= 2);
 }
 
-- 
2.14.2