diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index ea353264..c7910ada 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -63,10 +63,6 @@ int amdgpu_cs_ctx_create(amdgpu_device_handle dev,
 
 	gpu_context->dev = dev;
 
-	r = pthread_mutex_init(&gpu_context->sequence_mutex, NULL);
-	if (r)
-		goto error;
-
 	/* Create the context */
 	memset(&args, 0, sizeof(args));
 	args.in.op = AMDGPU_CTX_OP_ALLOC_CTX;
@@ -80,7 +76,6 @@ int amdgpu_cs_ctx_create(amdgpu_device_handle dev,
 	return 0;
 
 error:
-	pthread_mutex_destroy(&gpu_context->sequence_mutex);
 	free(gpu_context);
 	return r;
 }
@@ -101,8 +96,6 @@ int amdgpu_cs_ctx_free(amdgpu_context_handle context)
 	if (NULL == context)
 		return -EINVAL;
 
-	pthread_mutex_destroy(&context->sequence_mutex);
-
 	/* now deal with kernel side */
 	memset(&args, 0, sizeof(args));
 	args.in.op = AMDGPU_CTX_OP_FREE_CTX;
@@ -200,8 +193,6 @@ static int amdgpu_cs_submit_one(amdgpu_context_handle context,
 		chunk_data[i].ib_data.flags = ib->flags;
 	}
 
-	pthread_mutex_lock(&context->sequence_mutex);
-
 	if (user_fence) {
 		i = cs.in.num_chunks++;
 
@@ -254,7 +245,6 @@ static int amdgpu_cs_submit_one(amdgpu_context_handle context,
 	ibs_request->seq_no = cs.out.handle;
 
 error_unlock:
-	pthread_mutex_unlock(&context->sequence_mutex);
 	free(dependencies);
 	return r;
 }
diff --git a/amdgpu/amdgpu_internal.h b/amdgpu/amdgpu_internal.h
index 5d866030..7dd5c1c7 100644
--- a/amdgpu/amdgpu_internal.h
+++ b/amdgpu/amdgpu_internal.h
@@ -111,9 +111,6 @@ struct amdgpu_bo_list {
 
 struct amdgpu_context {
 	struct amdgpu_device *dev;
-	/** Mutex for accessing fences and to maintain command submissions
-	    in good sequence. */
-	pthread_mutex_t sequence_mutex;
 	/* context id*/
 	uint32_t id;
 };