drm/i915: make gpu hangman more resilient

- reset the stop_rings infrastructure while resetting the hw to
  avoid angering the hangcheck right away (and potentially declaring
  the gpu permanently wedged).

- ignore reset failures when hanging due to the hangman - we don't
  have reset code for all generations.

v2: Ensure that we only ignore reset failures when the hw reset is not
implemented and not when it failed.

Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 27630842bdccef91abf1b79046ba457a6a5b5185..dbe0f88ad3d007ecc5e2dbb1a04e8c1e46f24fc7 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -770,6 +770,7 @@ static int gen6_do_reset(struct drm_device *dev, u8 flags)
 
 static int intel_gpu_reset(struct drm_device *dev, u8 flags)
 {
+       struct drm_i915_private *dev_priv = dev->dev_private;
        int ret = -ENODEV;
 
        switch (INTEL_INFO(dev)->gen) {
@@ -788,6 +789,17 @@ static int intel_gpu_reset(struct drm_device *dev, u8 flags)
                break;
        }
 
+       /* Also reset the gpu hangman. */
+       if (dev_priv->stop_rings) {
+               DRM_DEBUG("Simulated gpu hang, resetting stop_rings\n");
+               dev_priv->stop_rings = 0;
+               if (ret == -ENODEV) {
+                       DRM_ERROR("Reset not implemented, but ignoring "
+                                 "error for simulated gpu hangs\n");
+                       ret = 0;
+               }
+       }
+
        return ret;
 }