Blob Blame History Raw
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 7 Feb 2018 11:15:45 +0000
Subject: drm/i915: Tidy up some error messages around reset failure
Git-commit: 8177e1125235a40c1af110e37febf6bb1e7b3f81
Patch-mainline: v4.17-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

On blb and pnv, we are seeing sporadic

  i915 0000:00:02.0: Resetting chip after gpu hang
  [drm:intel_gpu_reset [i915]] rcs0: timed out on STOP_RING
  [drm:i915_reset [i915]] *ERROR* Failed hw init on reset -5

which notably lack the actual root cause of the error. Ostensibly it
should be the init_ring_common() that failed, but it's error paths are
covered by DRM_ERROR.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180207111545.17078-1-chris@chris-wilson.co.uk

Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/i915/i915_drv.c         |    6 ++++--
 drivers/gpu/drm/i915/i915_gem.c         |   11 ++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |   18 +++++++++---------
 3 files changed, 21 insertions(+), 14 deletions(-)

--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1945,7 +1945,8 @@ void i915_reset(struct drm_i915_private
 	 */
 	ret = i915_ggtt_enable_hw(i915);
 	if (ret) {
-		DRM_ERROR("Failed to re-enable GGTT following reset %d\n", ret);
+		DRM_ERROR("Failed to re-enable GGTT following reset (%d)\n",
+			  ret);
 		goto error;
 	}
 
@@ -1962,7 +1963,8 @@ void i915_reset(struct drm_i915_private
 	 */
 	ret = i915_gem_init_hw(i915);
 	if (ret) {
-		DRM_ERROR("Failed hw init on reset %d\n", ret);
+		DRM_ERROR("Failed to initialise HW following reset (%d)\n",
+			  ret);
 		goto error;
 	}
 
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5077,8 +5077,11 @@ static int __i915_gem_restart_engines(vo
 
 	for_each_engine(engine, i915, id) {
 		err = engine->init_hw(engine);
-		if (err)
+		if (err) {
+			DRM_ERROR("Failed to restart %s (%d)\n",
+				  engine->name, err);
 			return err;
+		}
 	}
 
 	return 0;
@@ -5130,14 +5133,16 @@ int i915_gem_init_hw(struct drm_i915_pri
 
 	ret = i915_ppgtt_init_hw(dev_priv);
 	if (ret) {
-		DRM_ERROR("PPGTT enable HW failed %d\n", ret);
+		DRM_ERROR("Enabling PPGTT failed (%d)\n", ret);
 		goto out;
 	}
 
 	/* We can't enable contexts until all firmware is loaded */
 	ret = intel_uc_init_hw(dev_priv);
-	if (ret)
+	if (ret) {
+		DRM_ERROR("Enabling uc failed (%d)\n", ret);
 		goto out;
+	}
 
 	intel_mocs_init_l3cc_table(dev_priv);
 
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -453,13 +453,13 @@ static int init_ring_common(struct intel
 
 	if (!stop_ring(engine)) {
 		/* G45 ring initialization often fails to reset head to zero */
-		DRM_DEBUG_KMS("%s head not reset to zero "
-			      "ctl %08x head %08x tail %08x start %08x\n",
-			      engine->name,
-			      I915_READ_CTL(engine),
-			      I915_READ_HEAD(engine),
-			      I915_READ_TAIL(engine),
-			      I915_READ_START(engine));
+		DRM_DEBUG_DRIVER("%s head not reset to zero "
+				"ctl %08x head %08x tail %08x start %08x\n",
+				engine->name,
+				I915_READ_CTL(engine),
+				I915_READ_HEAD(engine),
+				I915_READ_TAIL(engine),
+				I915_READ_START(engine));
 
 		if (!stop_ring(engine)) {
 			DRM_ERROR("failed to set %s head to zero "
@@ -492,8 +492,8 @@ static int init_ring_common(struct intel
 
 	/* WaClearRingBufHeadRegAtInit:ctg,elk */
 	if (I915_READ_HEAD(engine))
-		DRM_DEBUG("%s initialization failed [head=%08x], fudging\n",
-			  engine->name, I915_READ_HEAD(engine));
+		DRM_DEBUG_DRIVER("%s initialization failed [head=%08x], fudging\n",
+				 engine->name, I915_READ_HEAD(engine));
 
 	intel_ring_update_space(ring);
 	I915_WRITE_HEAD(engine, ring->head);