[PATCH v2 2/3] drm/xe: Forcefully tear down exec queues in GuC submit fini

[Matthew Brost <matthew.brost@intel.com>]

In GuC submit fini, forcefully tear down any exec queues by disabling
CTs, stopping the scheduler (which cleans up lost G2H), killing all
remaining queues, and resuming scheduling to allow any remaining cleanup
actions to complete and signal any remaining fences.

v2:
 - Fix VF failure (CI)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>

---

This fix will not apply outright to any stable kernel as it depeneds on
functions which have added in the KMD since the original commit. Likely
will have to manually send out patches to stable for kernel which we'd
like to fix.
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 071cbfec2401..58ec94439df1 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -289,6 +289,8 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 		 EXEC_QUEUE_STATE_BANNED));
 }
 
+static int __xe_guc_submit_reset_prepare(struct xe_guc *guc);
+
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
@@ -296,6 +298,12 @@ static void guc_submit_fini(struct drm_device *drm, void *arg)
 	struct xe_gt *gt = guc_to_gt(guc);
 	int ret;
 
+	/* Forcefully kill any remaining exec queues */
+	xe_guc_ct_stop(&guc->ct);
+	__xe_guc_submit_reset_prepare(guc);
+	xe_guc_submit_stop(guc);
+	xe_guc_submit_pause_abort(guc);
+
 	ret = wait_event_timeout(guc->submission_state.fini_wq,
 				 xa_empty(&guc->submission_state.exec_queue_lookup),
 				 HZ * 5);
@@ -2459,16 +2467,10 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 	}
 }
 
-int xe_guc_submit_reset_prepare(struct xe_guc *guc)
+static int __xe_guc_submit_reset_prepare(struct xe_guc *guc)
 {
 	int ret;
 
-	if (xe_gt_WARN_ON(guc_to_gt(guc), vf_recovery(guc)))
-		return 0;
-
-	if (!guc->submission_state.initialized)
-		return 0;
-
 	/*
 	 * Using an atomic here rather than submission_state.lock as this
 	 * function can be called while holding the CT lock (engine reset
@@ -2483,6 +2485,17 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 	return ret;
 }
 
+int xe_guc_submit_reset_prepare(struct xe_guc *guc)
+{
+	if (xe_gt_WARN_ON(guc_to_gt(guc), vf_recovery(guc)))
+		return 0;
+
+	if (!guc->submission_state.initialized)
+		return 0;
+
+	return __xe_guc_submit_reset_prepare(guc);
+}
+
 void xe_guc_submit_reset_wait(struct xe_guc *guc)
 {
 	wait_event(guc->ct.wq, xe_device_wedged(guc_to_xe(guc)) ||
-- 
2.34.1