diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 20724aee76f4..c4a02648c8af 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1585,12 +1585,16 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				break;
 
 			case IB_WR_LOCAL_INV:
+				ctrl->srcrb_flags |=
+					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
 				set_local_inv_seg(wqe, wr->ex.invalidate_rkey);
 				wqe  += sizeof (struct mlx4_wqe_local_inval_seg);
 				size += sizeof (struct mlx4_wqe_local_inval_seg) / 16;
 				break;
 
 			case IB_WR_FAST_REG_MR:
+				ctrl->srcrb_flags |=
+					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
 				set_fmr_seg(wqe, wr);
 				wqe  += sizeof (struct mlx4_wqe_fmr_seg);
 				size += sizeof (struct mlx4_wqe_fmr_seg) / 16;
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index bf8f11982dae..9f29d86e5dc9 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -165,6 +165,7 @@ enum {
 	MLX4_WQE_CTRL_IP_CSUM		= 1 << 4,
 	MLX4_WQE_CTRL_TCP_UDP_CSUM	= 1 << 5,
 	MLX4_WQE_CTRL_INS_VLAN		= 1 << 6,
+	MLX4_WQE_CTRL_STRONG_ORDER	= 1 << 7,
 };
 
 struct mlx4_wqe_ctrl_seg {