[PATCH 5/6] 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 actually
resetting it.

Once the reset is successful, i915 takes over again and handles 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 funtion 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);
use tasklet_schedule(&execlists->irq_tasklet) to resubmit; rebase.

Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
Signed-off-by: Jeff McGee <jeff.mcgee at intel.com>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c       |  9 +++++++--
 drivers/gpu/drm/i915/i915_drv.h       |  1 +
 drivers/gpu/drm/i915/intel_guc.c      | 28 ++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_guc_fwif.h |  1 +
 drivers/gpu/drm/i915/intel_uncore.c   |  5 -----
 5 files changed, 37 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f1e651703764..b7c86be39444 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1984,10 +1984,15 @@ 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_gpu_reset(engine->i915, intel_engine_flag(engine));
+	else
+		ret = i915_guc_reset_engine(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 af6be3b8f022..a6dad7fc15c7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3312,6 +3312,7 @@ 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 i915_guc_reset_engine(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 eaad2781cc07..3641579a088c 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)
 {
@@ -193,6 +194,33 @@ 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
+ * @engine:	engine to be reset
+ */
+int i915_guc_reset_engine(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	struct intel_guc *guc = &dev_priv->guc;
+	struct i915_gem_context *ctx;
+	u32 data[7];
+
+	if (!i915_modparams.enable_guc_submission)
+		return 0;
+
+	ctx = dev_priv->kernel_context;
+
+	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 1c0a2a3de121..b0ac91acacd4 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -547,6 +547,7 @@ union guc_log_control {
 /* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */
 enum intel_guc_action {
 	INTEL_GUC_ACTION_DEFAULT = 0x0,
+	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 0b19c3f58b3b..17d8fc0d6ee0 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1787,14 +1787,9 @@ 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);
 }
 
-- 
2.14.1