[Intel-gfx] [PATCH] drm/i915: Abandon the reset if we fail to stop the engines

[Chris Wilson]

Some machines, *cough* snb *cough*, fail catastrophically if asked to
reset the GPU under certain conditions. The initial guess is that this
is when the rings are still busy at the time of the reset request
(because that's a pattern we've seen elsewhere, hence why we do try
gen3_stop_engines() before reset) so abandon the reset and leave the
device wedged, if gen3_stop_engines() fails.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103240
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
---
Whee! Let's see how much breaks!
-Chris
---
 drivers/gpu/drm/i915/intel_uncore.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 20e3c65c0999..c9a254b6125f 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1372,20 +1372,23 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	return ret;
 }
 
-static void gen3_stop_engine(struct intel_engine_cs *engine)
+static bool gen3_stop_engine(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	const u32 base = engine->mmio_base;
 	const i915_reg_t mode = RING_MI_MODE(base);
 
+
 	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
 	if (intel_wait_for_register_fw(dev_priv,
 				       mode,
 				       MODE_IDLE,
 				       MODE_IDLE,
-				       500))
+				       500)) {
 		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
 				 engine->name);
+		return false;
+	}
 
 	I915_WRITE_FW(RING_CTL(base), 0);
 	I915_WRITE_FW(RING_HEAD(base), 0);
@@ -1395,19 +1398,32 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 	if (I915_READ_FW(RING_HEAD(base)) != 0)
 		DRM_DEBUG_DRIVER("%s: ring head not parked\n",
 				 engine->name);
+
+	return true;
 }
 
-static void i915_stop_engines(struct drm_i915_private *dev_priv,
-			      unsigned engine_mask)
+static int i915_stop_engines(struct drm_i915_private *dev_priv,
+			     unsigned engine_mask)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	bool idle;
 
 	if (INTEL_GEN(dev_priv) < 3)
-		return;
+		return true;
 
+	idle = true;
 	for_each_engine_masked(engine, dev_priv, engine_mask, id)
-		gen3_stop_engine(engine);
+		idle &= gen3_stop_engine(engine);
+	if (idle)
+		return idle;
+
+	dev_err(dev_priv->drm.dev, "Failed to stop all engines\n");
+	for_each_engine_masked(engine, dev_priv, engine_mask, id) {
+		struct drm_printer p = drm_debug_printer(__func__);
+		intel_engine_dump(engine, &p);
+	}
+	return false;
 }
 
 static bool i915_reset_complete(struct pci_dev *pdev)
@@ -1768,7 +1784,10 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 		 *
 		 * FIXME: Wa for more modern gens needs to be validated
 		 */
-		i915_stop_engines(dev_priv, engine_mask);
+		if (!i915_stop_engines(dev_priv, engine_mask)) {
+			ret = -EIO;
+			break;
+		}
 
 		ret = -ENODEV;
 		if (reset)
-- 
2.15.0.rc2