drm/i915: Detect a failed GPU reset+recovery

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@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1484668747-9120-6-git-send-email-mika.kuoppala@intel.com

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fbad2b64b8905d129ca3cf53b4e4ece43873a59e..348dec48250216c0245702deb8c67a8a5847e302 100644 (file)
--- 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 1cd485c314e6e25084957e51b76cbd738198b8a3..e75e367f253a8830300b4926ad7d8b9c92671c2b 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3327,7 +3327,7 @@ 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 832ad092f4623750a62f51f46904451e1ce4c67f..3e10e810101488c1545fc8c2148a83aa07a1a4ac 100644 (file)
--- 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)