[PATCH v6 5/6] drm/xe/xe_hw_engine: Update hw_engine_snapshot_capture for debugfs

[Alan Previn]

xe_hw_engine_print is called by debugfs to do an immediate raw
dump of the engine registers. It depends on hw_engine_snapshot_capture
that assumes a prior capture with a matching job is ready for printing.
However, for the debugfs case, there is no prior job so ensure
hw_engine_snapshot_capture can also invoke GuC-Err-Capture for
an immediate jobless snapshot.

Signed-off-by: Alan Previn <alan.previn.teres.alexis at intel.com>
---
 drivers/gpu/drm/xe/xe_guc_capture.c | 26 ++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_capture.h |  2 ++
 drivers/gpu/drm/xe/xe_hw_engine.c   | 15 +++++++++++++--
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index 6f40aad7e212..92ea8cb681bb 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -1583,6 +1583,32 @@ guc_capture_get_manual_snapshot(struct xe_guc *guc, struct xe_hw_engine *hwe)
 	return new;
 }
 
+/**
+ * xe_guc_capture_snapshot_store_and_get_manual_hwe - Generate and get manual engine register dump
+ * @guc: Target GuC for manual capture
+ * @hwe: The engine instance to capture from
+ *
+ * Generate a manual GuC-Error-Capture snapshot of engine instance + engine class registers
+ * without any queue association. This capture node is not stored in outlist or cachelist,
+ * Returns: New capture node and caller must "put"
+ */
+struct xe_guc_capture_snapshot *
+xe_guc_capture_snapshot_manual_hwe(struct xe_guc *guc, struct xe_hw_engine *hwe)
+{
+	struct xe_guc_capture_snapshot *new;
+
+	new = guc_capture_get_manual_snapshot(guc, hwe);
+	if (!new)
+		return NULL;
+
+	new->guc_id = 0;
+	new->lrca = 0;
+	new->is_partial = 0;
+	new->source = XE_ENGINE_CAPTURE_SOURCE_MANUAL;
+
+	return new;
+}
+
 /**
  * xe_guc_capture_snapshot_store_manual_job - Generate and store a manual engine register dump
  * @guc: Target GuC for manual capture
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.h b/drivers/gpu/drm/xe/xe_guc_capture.h
index 77ee35a3f205..5df4b5579d2b 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.h
+++ b/drivers/gpu/drm/xe/xe_guc_capture.h
@@ -54,6 +54,8 @@ struct xe_guc_capture_snapshot *
 xe_guc_capture_get_matching_and_lock(struct xe_exec_queue *q,
 				     enum xe_guc_capture_snapshot_source srctype);
 void xe_guc_capture_snapshot_store_manual_job(struct xe_guc *guc, struct xe_exec_queue *q);
+struct xe_guc_capture_snapshot *
+xe_guc_capture_snapshot_manual_hwe(struct xe_guc *guc, struct xe_hw_engine *hwe);
 void xe_guc_capture_snapshot_print(struct xe_guc *guc, struct xe_guc_capture_snapshot *node,
 				   struct drm_printer *p);
 void xe_guc_capture_steered_list_init(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 40c1f9814177..94a1d5dd2030 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -832,7 +832,7 @@ void xe_hw_engine_handle_irq(struct xe_hw_engine *hwe, u16 intr_vec)
 /**
  * hw_engine_snapshot_capture - Take a quick snapshot of the HW Engine.
  * @hwe: Xe HW Engine.
- * @q: The exec queue object.
+ * @q: The exec queue object. (can be NULL for debugfs engine-register dump)
  *
  * This can be printed out in a later stage like during dev_coredump
  * analysis.
@@ -845,9 +845,11 @@ hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_exec_queue *q)
 {
 	struct xe_hw_engine_snapshot *snapshot;
 	struct xe_guc_capture_snapshot *node;
+	struct xe_guc *guc;
 
 	if (!xe_hw_engine_is_valid(hwe))
 		return NULL;
+	guc = &hwe->gt->uc.guc;
 
 	snapshot = kzalloc(sizeof(*snapshot), GFP_ATOMIC);
 
@@ -876,12 +878,21 @@ hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_exec_queue *q)
 			xe_gt_dbg(hwe->gt, "No fw sourced GuC-Err-Capture for queue %s", q->name);
 			snapshot->matched_node = node;
 		} else if (node) {
-			xe_guc_capture_put_matched_nodes(&hwe->gt->uc.guc, node);
+			xe_guc_capture_put_matched_nodes(guc, node);
 		}
 		if (!snapshot->matched_node)
 			xe_gt_warn(hwe->gt, "Can't retrieve any GuC-Err-Capture node");
 	}
 
+	if (!snapshot->matched_node) {
+		/*
+		 * Fallback path - do an immediate jobless manual engine capture.
+		 * This will happen when debugfs is triggered to force an engine dump.
+		 */
+		snapshot->matched_node = xe_guc_capture_snapshot_manual_hwe(guc, hwe);
+		xe_gt_dbg(hwe->gt, "Fallback to jobless-manual-err-capture node");
+	}
+
 	return snapshot;
 }
 
-- 
2.34.1