drm/i915: Add support for per engine reset recovery

This change implements support for per-engine reset as an initial, less
intrusive hang recovery option to be attempted before falling back to the
legacy full GPU reset recovery mode if necessary. This is only supported
from Gen8 onwards.

Hangchecker determines which engines are hung and invokes error handler to
recover from it. Error handler schedules recovery for each of those engines
that are hung. The recovery procedure is as follows,
 - identifies the request that caused the hang and it is dropped
 - force engine to idle: this is done by issuing a reset request
 - reset the engine
 - re-init the engine to resume submissions.

If engine reset fails then we fall back to heavy weight full gpu reset
which resets all engines and reinitiazes complete state of HW and SW.

v2: Rebase.
v3: s/*engine_reset*/*reset_engine*/; freeze engine and irqs before
calling i915_gem_reset_engine (Chris).
v4: Rebase, modify i915_gem_reset_prepare to use a ring mask and
reuse the function for reset_engine.
v5: intel_reset_engine_start/cancel instead of request/unrequest_reset.
v6: Clean up reset_engine function to not require mutex, i.e. no need to call
revoke/restore_fences and _retire_requests (Chris).
v7: Remove leftovers from v5, i.e. no need to disable irq, hold
forcewake or wakeup the handoff bit (Chris).
v8: engine_retire_requests should be (and it was) static; explain that
we have to re-init the engine after reset, which is why the init_hw call
is needed; check reset-in-progress flag (Chris).
v9: Rebase, include code to pass the active request to gem_reset_engine
(as it is already done in full reset). Remove unnecessary
intel_reset_engine_start/cancel, these are executed as part of the
reset.
v10: Rebase, use the right I915_RESET_ENGINE flag.
v11: Fixup to call reset_finish_engine even on error.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170615201828.23144-6-michel.thierry@intel.comReviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620095751.13127-6-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_drv.c

@@ -1923,11 +1923,57 @@ void i915_reset(struct drm_i915_private *dev_priv)
  *
  * Reset a specific GPU engine. Useful if a hang is detected.
  * Returns zero on successful reset or otherwise an error code.
+ *
+ * Procedure is:
+ *  - identifies the request that caused the hang and it is dropped
+ *  - reset engine (which will force the engine to idle)
+ *  - re-init/configure engine
  */
 int i915_reset_engine(struct intel_engine_cs *engine)
 {
-	/* FIXME: replace me with engine reset sequence */
-	return -ENODEV;
+	struct i915_gpu_error *error = &engine->i915->gpu_error;
+	struct drm_i915_gem_request *active_request;
+	int ret;
+
+	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
+
+	DRM_DEBUG_DRIVER("resetting %s\n", engine->name);
+
+	active_request = i915_gem_reset_prepare_engine(engine);
+	if (IS_ERR(active_request)) {
+		DRM_DEBUG_DRIVER("Previous reset failed, promote to full reset\n");
+		ret = PTR_ERR(active_request);
+		goto out;
+	}
+
+	/*
+	 * The request that caused the hang is stuck on elsp, we know the
+	 * active request and can drop it, adjust head to skip the offending
+	 * request to resume executing remaining requests in the queue.
+	 */
+	i915_gem_reset_engine(engine, active_request);
+
+	/* Finally, reset just this engine. */
+	ret = intel_gpu_reset(engine->i915, intel_engine_flag(engine));
+
+	i915_gem_reset_finish_engine(engine);
+
+	if (ret) {
+		/* If we fail here, we expect to fallback to a global reset */
+		DRM_DEBUG_DRIVER("Failed to reset %s, ret=%d\n",
+				 engine->name, ret);
+		goto out;
+	}
+
+	/*
+	 * The engine and its registers (and workarounds in case of render)
+	 * have been reset to their default values. Follow the init_ring
+	 * process to program RING_MODE, HWSP and re-enable submission.
+	 */
+	ret = engine->init_hw(engine);
+
+out:
+	return ret;
 }
 
 static int i915_pm_suspend(struct device *kdev)

drivers/gpu/drm/i915/i915_drv.h

@@ -3474,11 +3474,16 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return READ_ONCE(error->reset_count);
 }
 
+struct drm_i915_gem_request *
+i915_gem_reset_prepare_engine(struct intel_engine_cs *engine);
 int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
 void i915_gem_reset(struct drm_i915_private *dev_priv);
+void i915_gem_reset_finish_engine(struct intel_engine_cs *engine);
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
 void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
 bool i915_gem_unset_wedged(struct drm_i915_private *dev_priv);
+void i915_gem_reset_engine(struct intel_engine_cs *engine,
+			   struct drm_i915_gem_request *request);
 
 void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/i915_gem.c

@@ -2831,14 +2831,13 @@ static bool engine_stalled(struct intel_engine_cs *engine)
 	return true;
 }
 
-int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
+/*
+ * Ensure irq handler finishes, and not run again.
+ * Also return the active request so that we only search for it once.
+ */
+struct drm_i915_gem_request *
+i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 {
-	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) {
 	struct drm_i915_gem_request *request = NULL;
 
 	/* Prevent the signaler thread from updating the request
@@ -2869,7 +2868,24 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	if (engine_stalled(engine)) {
 		request = i915_gem_find_active_request(engine);
 		if (request && request->fence.error == -EIO)
-				err = -EIO; /* Previous reset failed! */
+			request = ERR_PTR(-EIO); /* Previous reset failed! */
+	}
+
+	return request;
+}
+
+int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+	struct drm_i915_gem_request *request;
+	enum intel_engine_id id;
+	int err = 0;
+
+	for_each_engine(engine, dev_priv, id) {
+		request = i915_gem_reset_prepare_engine(engine);
+		if (IS_ERR(request)) {
+			err = PTR_ERR(request);
+			continue;
 		}
 
 		engine->hangcheck.active_request = request;
@@ -2960,7 +2976,7 @@ static bool i915_gem_reset_request(struct drm_i915_gem_request *request)
 	return guilty;
 }
 
-static void i915_gem_reset_engine(struct intel_engine_cs *engine,
+void i915_gem_reset_engine(struct intel_engine_cs *engine,
 			   struct drm_i915_gem_request *request)
 {
 	if (request && i915_gem_reset_request(request)) {
@@ -3004,6 +3020,12 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 	}
 }
 
+void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
+{
+	tasklet_enable(&engine->irq_tasklet);
+	kthread_unpark(engine->breadcrumbs.signaler);
+}
+
 void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
@@ -3013,8 +3035,7 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
 
 	for_each_engine(engine, dev_priv, id) {
 		engine->hangcheck.active_request = NULL;
-		tasklet_enable(&engine->irq_tasklet);
-		kthread_unpark(engine->breadcrumbs.signaler);
+		i915_gem_reset_finish_engine(engine);
 	}
 }