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.com
Reviewed-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

1 files changed, 57 insertions, 36 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 37d1cbf..1353491 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2831,45 +2831,61 @@ static bool engine_stalled(struct intel_engine_cs *engine)
 	return true;
 }
 
+/*
+ * 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 drm_i915_gem_request *request = NULL;
+
+	/* Prevent the signaler thread from updating the request
+	 * state (by calling dma_fence_signal) as we are processing
+	 * the reset. The write from the GPU of the seqno is
+	 * asynchronous and the signaler thread may see a different
+	 * value to us and declare the request complete, even though
+	 * the reset routine have picked that request as the active
+	 * (incomplete) request. This conflict is not handled
+	 * gracefully!
+	 */
+	kthread_park(engine->breadcrumbs.signaler);
+
+	/* Prevent request submission to the hardware until we have
+	 * completed the reset in i915_gem_reset_finish(). If a request
+	 * is completed by one engine, it may then queue a request
+	 * to a second via its engine->irq_tasklet *just* as we are
+	 * calling engine->init_hw() and also writing the ELSP.
+	 * Turning off the engine->irq_tasklet until the reset is over
+	 * prevents the race.
+	 */
+	tasklet_kill(&engine->irq_tasklet);
+	tasklet_disable(&engine->irq_tasklet);
+
+	if (engine->irq_seqno_barrier)
+		engine->irq_seqno_barrier(engine);
+
+	if (engine_stalled(engine)) {
+		request = i915_gem_find_active_request(engine);
+		if (request && request->fence.error == -EIO)
+			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;
 
-	/* 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
-		 * state (by calling dma_fence_signal) as we are processing
-		 * the reset. The write from the GPU of the seqno is
-		 * asynchronous and the signaler thread may see a different
-		 * value to us and declare the request complete, even though
-		 * the reset routine have picked that request as the active
-		 * (incomplete) request. This conflict is not handled
-		 * gracefully!
-		 */
-		kthread_park(engine->breadcrumbs.signaler);
-
-		/* Prevent request submission to the hardware until we have
-		 * completed the reset in i915_gem_reset_finish(). If a request
-		 * is completed by one engine, it may then queue a request
-		 * to a second via its engine->irq_tasklet *just* as we are
-		 * calling engine->init_hw() and also writing the ELSP.
-		 * Turning off the engine->irq_tasklet until the reset is over
-		 * prevents the race.
-		 */
-		tasklet_kill(&engine->irq_tasklet);
-		tasklet_disable(&engine->irq_tasklet);
-
-		if (engine->irq_seqno_barrier)
-			engine->irq_seqno_barrier(engine);
-
-		if (engine_stalled(engine)) {
-			request = i915_gem_find_active_request(engine);
-			if (request && request->fence.error == -EIO)
-				err = -EIO; /* Previous reset failed! */
+		request = i915_gem_reset_prepare_engine(engine);
+		if (IS_ERR(request)) {
+			err = PTR_ERR(request);
+			continue;
 		}
 
 		engine->hangcheck.active_request = request;
@@ -2960,8 +2976,8 @@ 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,
-				  struct drm_i915_gem_request *request)
+void i915_gem_reset_engine(struct intel_engine_cs *engine,
+			   struct drm_i915_gem_request *request)
 {
 	if (request && i915_gem_reset_request(request)) {
 		DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n",
@@ -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);
 	}
 }