[Intel-gfx] [CI 1/2] drm/i915/guc: Fix request re-submission after reset

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

In order to ensure no missed interrupts we must first re-direct
the interrupts to GuC, and only then re-submit the requests to
be replayed after a GPU reset. Otherwise context switch can fire
before GuC has been set up to receive it triggering more hangs.

v2: Rebase.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko at intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Oscar Mateo <oscar.mateo at intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble at intel.com>
Cc: Arkadiusz Hiler <arkadiusz.hiler at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_guc_submission.c | 32 ++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_guc_loader.c    | 21 --------------------
 2 files changed, 28 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index beb38e30d0e9..41f2dd87b413 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -936,6 +936,26 @@ static void guc_reset_wq(struct i915_guc_client *client)
 	client->wq_tail = 0;
 }
 
+static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int irqs;
+
+	/* tell all command streamers to forward interrupts (but not vblank) to GuC */
+	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
+	for_each_engine(engine, dev_priv, id)
+		I915_WRITE(RING_MODE_GEN7(engine), irqs);
+
+	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
+	irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
+	       GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
+	/* These three registers have the same bit definitions */
+	I915_WRITE(GUC_BCS_RCS_IER, ~irqs);
+	I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs);
+	I915_WRITE(GUC_WD_VECS_IER, ~irqs);
+}
+
 int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
@@ -953,13 +973,17 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 
 	/* Take over from manual control of ELSP (execlists) */
 	for_each_engine(engine, dev_priv, id) {
-		const int wqi_size = sizeof(struct guc_wq_item);
-		struct drm_i915_gem_request *rq;
-
 		engine->submit_request = i915_guc_submit;
 		engine->schedule = NULL;
+	}
+
+	guc_interrupts_capture(dev_priv);
+
+	/* Replay the current set of previously submitted requests */
+	for_each_engine(engine, dev_priv, id) {
+		const int wqi_size = sizeof(struct guc_wq_item);
+		struct drm_i915_gem_request *rq;
 
-		/* Replay the current set of previously submitted requests */
 		spin_lock_irq(&engine->timeline->lock);
 		list_for_each_entry(rq, &engine->timeline->requests, link) {
 			guc_client_update_wq_rsvd(client, wqi_size);
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index 64cdef479d1d..2e24712cf3ee 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -109,26 +109,6 @@ static void guc_interrupts_release(struct drm_i915_private *dev_priv)
 	I915_WRITE(GUC_WD_VECS_IER, 0);
 }
 
-static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int irqs;
-
-	/* tell all command streamers to forward interrupts (but not vblank) to GuC */
-	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MODE_GEN7(engine), irqs);
-
-	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
-	irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
-	       GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
-	/* These three registers have the same bit definitions */
-	I915_WRITE(GUC_BCS_RCS_IER, ~irqs);
-	I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs);
-	I915_WRITE(GUC_WD_VECS_IER, ~irqs);
-}
-
 static u32 get_gttype(struct drm_i915_private *dev_priv)
 {
 	/* XXX: GT type based on PCI device ID? field seems unused by fw */
@@ -503,7 +483,6 @@ int intel_guc_setup(struct drm_i915_private *dev_priv)
 		err = i915_guc_submission_enable(dev_priv);
 		if (err)
 			goto fail;
-		guc_interrupts_capture(dev_priv);
 	}
 
 	DRM_INFO("GuC %s (firmware %s [version %u.%u])\n",
-- 
2.9.3