[Intel-gfx] [PATCH 6/7] drm/i915: Detect a failed GPU reset+recovery

[Mika Kuoppala]

From: Chris Wilson <chris at chris-wilson.co.uk>

If we can't recover the GPU after the reset, mark it as wedged to cancel
the outstanding tasks and to prevent new users from trying to use the
broken GPU.

v2: Check the same ring is hung again before declaring the reset broken.
v3: use engine_stalled (Mika)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk> (v2)
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c |  7 ++++++-
 drivers/gpu/drm/i915/i915_drv.h |  2 +-
 drivers/gpu/drm/i915/i915_gem.c | 16 ++++++++++++++--
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index bb747ae..5ee6297 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1761,7 +1761,12 @@ void i915_reset(struct drm_i915_private *dev_priv)
 
 	pr_notice("drm/i915: Resetting chip after gpu hang\n");
 	disable_irq(dev_priv->drm.irq);
-	i915_gem_reset_prepare(dev_priv);
+	ret = i915_gem_reset_prepare(dev_priv);
+	if (ret) {
+		DRM_ERROR("GPU recovery failed\n");
+		intel_gpu_reset(dev_priv, ALL_ENGINES);
+		goto error;
+	}
 
 	ret = intel_gpu_reset(dev_priv, ALL_ENGINES);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f861418..3850950 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3328,7 +3328,7 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return READ_ONCE(error->reset_count);
 }
 
-void i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
+int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
 void i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 832ad09..3e10e81 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2625,16 +2625,28 @@ static bool engine_stalled(struct intel_engine_cs *engine)
 	return true;
 }
 
-void i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
+int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	int err = 0;
 
 	/* Ensure irq handler finishes, and not run again. */
-	for_each_engine(engine, dev_priv, id)
+	for_each_engine(engine, dev_priv, id) {
+		struct drm_i915_gem_request *request;
+
 		tasklet_kill(&engine->irq_tasklet);
 
+		if (engine_stalled(engine)) {
+			request = i915_gem_find_active_request(engine);
+			if (request && request->fence.error == -EIO)
+				err = -EIO; /* Previous reset failed! */
+		}
+	}
+
 	i915_gem_revoke_fences(dev_priv);
+
+	return err;
 }
 
 static void skip_request(struct drm_i915_gem_request *request)
-- 
2.7.4