[PATCH 4/7] drm/xe: Add new exec queue trace points

[Stuart Summers <stuart.summers@intel.com>]

Add an exec queue and guc exec queue trace point
to separate out which part of the stack is executing.

This is helpful because several of the guc specific
paths rely on responses from guc which is interesting
to view separately in the event the guc stops responding
in the middle of an operation that would expect a
response from guc otherwise.

Also add in the exec queue pointer information to
the trace events for easier tracking. Contexts (guc_ids)
can get re-used, so this just makes grepping a little
easier in this type of debug.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c |  4 ++++
 drivers/gpu/drm/xe/xe_guc_submit.c | 11 +++++++----
 drivers/gpu/drm/xe/xe_trace.h      | 22 ++++++++++++++++++++--
 3 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 90cbc95f8e2e..a2ef381cf6d9 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -377,6 +377,8 @@ void xe_exec_queue_destroy(struct kref *ref)
 	struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount);
 	struct xe_exec_queue *eq, *next;
 
+	trace_xe_exec_queue_destroy(q);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 
@@ -953,6 +955,8 @@ void xe_exec_queue_kill(struct xe_exec_queue *q)
 {
 	struct xe_exec_queue *eq = q, *next;
 
+	trace_xe_exec_queue_kill(q);
+
 	list_for_each_entry_safe(eq, next, &eq->multi_gt_list,
 				 multi_gt_link) {
 		q->ops->kill(eq);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index e9aa0625ce60..5ec1e4a83d68 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1003,9 +1003,12 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 	}
 
 	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (xe_exec_queue_get_unless_zero(q))
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		if (xe_exec_queue_get_unless_zero(q)) {
 			set_exec_queue_wedged(q);
+			trace_xe_exec_queue_wedge(q);
+		}
+	}
 	mutex_unlock(&guc->submission_state.lock);
 }
 
@@ -1455,7 +1458,7 @@ static void __guc_exec_queue_destroy_async(struct work_struct *w)
 	struct xe_guc *guc = exec_queue_to_guc(q);
 
 	xe_pm_runtime_get(guc_to_xe(guc));
-	trace_xe_exec_queue_destroy(q);
+	trace_xe_guc_exec_queue_destroy(q);
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
@@ -1716,7 +1719,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 
 static void guc_exec_queue_kill(struct xe_exec_queue *q)
 {
-	trace_xe_exec_queue_kill(q);
+	trace_xe_guc_exec_queue_kill(q);
 	set_exec_queue_killed(q);
 	__suspend_fence_signal(q);
 	xe_guc_exec_queue_trigger_cleanup(q);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 314f42fcbcbd..a5dd0c48d894 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -71,6 +71,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 
 		    TP_STRUCT__entry(
 			     __string(dev, __dev_name_eq(q))
+			     __field(struct xe_exec_queue *, q)
 			     __field(enum xe_engine_class, class)
 			     __field(u32, logical_mask)
 			     __field(u8, gt_id)
@@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 
 		    TP_fast_assign(
 			   __assign_str(dev);
+			   __entry->q = q;
 			   __entry->class = q->class;
 			   __entry->logical_mask = q->logical_mask;
 			   __entry->gt_id = q->gt->info.id;
@@ -91,8 +93,9 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 			   __entry->flags = q->flags;
 			   ),
 
-		    TP_printk("dev=%s, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
-			      __get_str(dev), __entry->class, __entry->logical_mask,
+		    TP_printk("dev=%s, %p, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
+			      __get_str(dev), __entry->q,
+			      __entry->class, __entry->logical_mask,
 			      __entry->gt_id, __entry->width, __entry->guc_id,
 			      __entry->guc_state, __entry->flags)
 );
@@ -147,11 +150,21 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_close,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_exec_queue_wedge,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_kill,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_kill,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_cleanup_entity,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
@@ -162,6 +175,11 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_destroy,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_destroy,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_reset,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
-- 
2.34.1