diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index f7d6640d3452..c9cc5842d65b 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -14,6 +14,7 @@
 #include "xe_guc_tlb_inval.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
+#include "xe_printk.h"
 #include "xe_tlb_inval.h"
 #include "xe_trace.h"
 
@@ -110,6 +111,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
 		}
 
 		timedout_seqno = fence->seqno;
+		if (!tlb_inval->timedout_seqno) {
+			tlb_inval->timedout_seqno = fence->seqno;
+			tlb_inval->timedout_inval_time = fence->inval_time;
+			tlb_inval->timedout_time = ktime_get();
+		}
 
 		fence->base.error = -ETIME;
 		xe_tlb_inval_fence_signal(fence);
@@ -242,6 +248,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
 	else
 		pending_seqno = tlb_inval->seqno - 1;
 	WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
+	tlb_inval->timedout_seqno = 0;
 
 	list_for_each_entry_safe(fence, next,
 				 &tlb_inval->pending_fences, link)
@@ -470,6 +477,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
 
 	WRITE_ONCE(tlb_inval->seqno_recv, seqno);
 
+	if (tlb_inval->timedout_seqno &&
+	    xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
+		ktime_t now = ktime_get();
+
+		xe_warn(xe,
+			"TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
+			tlb_inval->timedout_seqno, seqno,
+			ktime_ms_delta(now, tlb_inval->timedout_inval_time),
+			ktime_ms_delta(now, tlb_inval->timedout_time));
+		tlb_inval->timedout_seqno = 0;
+	}
+
 	list_for_each_entry_safe(fence, next,
 				 &tlb_inval->pending_fences, link) {
 		trace_xe_tlb_inval_fence_recv(xe, fence);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
index d77be1aedc91..80d2019fa20b 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
@@ -112,6 +112,23 @@ struct xe_tlb_inval {
 	 * @pending_lock: protects @pending_fences and updating @seqno_recv.
 	 */
 	spinlock_t pending_lock;
+	/**
+	 * @timedout_seqno: seqno of the most recent timed out TLB
+	 * invalidation, 0 if none. Used to measure how late the ack for a
+	 * timed out invalidation actually arrives. Protected by
+	 * @pending_lock.
+	 */
+	int timedout_seqno;
+	/**
+	 * @timedout_inval_time: request time of @timedout_seqno. Protected by
+	 * @pending_lock.
+	 */
+	ktime_t timedout_inval_time;
+	/**
+	 * @timedout_time: time @timedout_seqno was signaled with -ETIME.
+	 * Protected by @pending_lock.
+	 */
+	ktime_t timedout_time;
 	/**
 	 * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
 	 * the timeout interval is over.