drm/xe: Wire devcoredump to LR TDR

LR queues can hang, cause engine reset, or cause IOMMU CAT errors.
Collect an error capture when this occurs.

v2:
 - s/queue's/queues (Jonathan)
v4:
 - Fix build (CI)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241114022522.1951351-8-matthew.brost@intel.com

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 985a21a72da484c1e198d4d025001d35822fa6c5..f9ecee5364d82c3e1d9487e3a587ba939414b67d 100644 (file)
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -896,13 +896,18 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
                                         !exec_queue_pending_disable(q) ||
                                         xe_guc_read_stopped(guc), HZ * 5);
                if (!ret) {
-                       xe_gt_warn(q->gt, "Schedule disable failed to respond\n");
+                       xe_gt_warn(q->gt, "Schedule disable failed to respond, guc_id=%d\n",
+                                  q->guc->id);
+                       xe_devcoredump(q, NULL);
                        xe_sched_submission_start(sched);
                        xe_gt_reset_async(q->gt);
                        return;
                }
        }
 
+       if (!exec_queue_killed(q) && !xe_lrc_ring_is_idle(q->lrc[0]))
+               xe_devcoredump(q, NULL);
+
        xe_sched_submission_start(sched);
 }