diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
index f9b293964..c2a21b22f 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
@@ -514,8 +514,8 @@ void gk20a_channel_abort_clean_up(struct channel_gk20a *ch)
 		while (tmp_get != put) {
 			job = &ch->joblist.pre_alloc.jobs[tmp_get];
 			if (job->post_fence->semaphore) {
-				gk20a_semaphore_release(
-						job->post_fence->semaphore);
+				__gk20a_semaphore_release(
+					job->post_fence->semaphore, true);
 				released_job_semaphore = true;
 			}
 			tmp_get = (tmp_get + 1) % ch->joblist.pre_alloc.length;
@@ -524,8 +524,8 @@ void gk20a_channel_abort_clean_up(struct channel_gk20a *ch)
 		list_for_each_entry_safe(job, n,
 				&ch->joblist.dynamic.jobs, list) {
 			if (job->post_fence->semaphore) {
-				gk20a_semaphore_release(
-						job->post_fence->semaphore);
+				__gk20a_semaphore_release(
+					job->post_fence->semaphore, true);
 				released_job_semaphore = true;
 			}
 		}
diff --git a/drivers/gpu/nvgpu/gk20a/semaphore_gk20a.h b/drivers/gpu/nvgpu/gk20a/semaphore_gk20a.h
index c73d3c057..cf724fdb4 100644
--- a/drivers/gpu/nvgpu/gk20a/semaphore_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/semaphore_gk20a.h
@@ -249,9 +249,11 @@ static inline u32 gk20a_semaphore_next_value(struct gk20a_semaphore *s)
 }
 
 /*
- * Note - if you call this then any prior semaphores will also be released.
+ * If @force is set then this will not wait for the underlying semaphore to
+ * catch up to the passed semaphore.
  */
-static inline void gk20a_semaphore_release(struct gk20a_semaphore *s)
+static inline void __gk20a_semaphore_release(struct gk20a_semaphore *s,
+					     bool force)
 {
 	u32 current_val;
 	u32 val = gk20a_semaphore_get_value(s);
@@ -264,6 +266,8 @@ static inline void gk20a_semaphore_release(struct gk20a_semaphore *s)
 	 * TODO: tune the wait a little better.
 	 */
 	while ((current_val = gk20a_semaphore_read(s)) < (val - 1)) {
+		if (force)
+			break;
 		msleep(100);
 		attempts += 1;
 		if (attempts > 100) {
@@ -285,6 +289,11 @@ static inline void gk20a_semaphore_release(struct gk20a_semaphore *s)
 			     s->hw_sema->ch->hw_chid, val);
 }
 
+static inline void gk20a_semaphore_release(struct gk20a_semaphore *s)
+{
+	__gk20a_semaphore_release(s, false);
+}
+
 /*
  * Configure a software based increment on this semaphore. This is useful for
  * when we want the GPU to wait on a SW event before processing a channel.