drm/xe: Add TLB invalidation fence ftrace

This will help debug issues with TLB invalidation fences.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c

@@ -7,6 +7,7 @@
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
+#include "xe_trace.h"
 
 static struct xe_gt *
 guc_to_gt(struct xe_guc *guc)
@@ -82,6 +83,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 		fence->seqno = seqno;
 		list_add_tail(&fence->link,
 			      &gt->tlb_invalidation.pending_fences);
+		trace_xe_gt_tlb_invalidation_fence_send(fence);
 	}
 	action[1] = seqno;
 	gt->tlb_invalidation.seqno = (gt->tlb_invalidation.seqno + 1) %
@@ -194,7 +196,10 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 
 	fence = list_first_entry_or_null(&gt->tlb_invalidation.pending_fences,
 					 typeof(*fence), link);
+	if (fence)
+		trace_xe_gt_tlb_invalidation_fence_recv(fence);
 	if (fence && tlb_invalidation_seqno_past(gt, fence->seqno)) {
+		trace_xe_gt_tlb_invalidation_fence_signal(fence);
 		list_del(&fence->link);
 		dma_fence_signal(&fence->base);
 		dma_fence_put(&fence->base);

drivers/gpu/drm/xe/xe_pt.c

@@ -13,6 +13,7 @@
 #include "xe_pt_walk.h"
 #include "xe_vm.h"
 #include "xe_res_cursor.h"
+#include "xe_trace.h"
 #include "xe_ttm_stolen_mgr.h"
 
 struct xe_pt_dir {
@@ -1493,6 +1494,7 @@ static void invalidation_fence_cb(struct dma_fence *fence,
 	struct invalidation_fence *ifence =
 		container_of(cb, struct invalidation_fence, cb);
 
+	trace_xe_gt_tlb_invalidation_fence_cb(&ifence->base);
 	queue_work(system_wq, &ifence->work);
 	dma_fence_put(ifence->fence);
 }
@@ -1502,6 +1504,7 @@ static void invalidation_fence_work_func(struct work_struct *w)
 	struct invalidation_fence *ifence =
 		container_of(w, struct invalidation_fence, work);
 
+	trace_xe_gt_tlb_invalidation_fence_work_func(&ifence->base);
 	xe_gt_tlb_invalidation(ifence->gt, &ifence->base);
 }
 
@@ -1511,6 +1514,8 @@ static int invalidation_fence_init(struct xe_gt *gt,
 {
 	int ret;
 
+	trace_xe_gt_tlb_invalidation_fence_create(&ifence->base);
+
 	spin_lock_irq(&gt->tlb_invalidation.lock);
 	dma_fence_init(&ifence->base.base, &invalidation_fence_ops,
 		       &gt->tlb_invalidation.lock,

drivers/gpu/drm/xe/xe_trace.h

@@ -16,10 +16,60 @@
 #include "xe_engine_types.h"
 #include "xe_gpu_scheduler_types.h"
 #include "xe_gt_types.h"
+#include "xe_gt_tlb_invalidation_types.h"
 #include "xe_guc_engine_types.h"
 #include "xe_sched_job.h"
 #include "xe_vm_types.h"
 
+DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
+		    TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+		    TP_ARGS(fence),
+
+		    TP_STRUCT__entry(
+			     __field(u64, fence)
+			     __field(int, seqno)
+			     ),
+
+		    TP_fast_assign(
+			   __entry->fence = (u64)fence;
+			   __entry->seqno = fence->seqno;
+			   ),
+
+		    TP_printk("fence=0x%016llx, seqno=%d",
+			      __entry->fence, __entry->seqno)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_create,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence,
+	     xe_gt_tlb_invalidation_fence_work_func,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_cb,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_send,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_recv,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
+DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_signal,
+	     TP_PROTO(struct xe_gt_tlb_invalidation_fence *fence),
+	     TP_ARGS(fence)
+);
+
 DECLARE_EVENT_CLASS(xe_bo,
 		    TP_PROTO(struct xe_bo *bo),
 		    TP_ARGS(bo),