net/mlx5: fix vectorized mini-CQE prefetching

[dpdk.git] / drivers / net / mlx5 / mlx5_rxtx_vec_altivec.h

diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
index f5414ee..cb4ce1a 100644 (file)
--- a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
@@ -158,7 +158,6 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cq,
                for (i = 0; i < MLX5_VPMD_DESCS_PER_LOOP; ++i)
                        if (likely(pos + i < mcqe_n))
                                rte_prefetch0((void *)(cq + pos + i));
-
                /* A.1 load mCQEs into a 128bit register. */
                mcqe1 = (vector unsigned char)vec_vsx_ld(0,
                        (signed int const *)&mcq[pos % 8]);
@@ -287,6 +286,8 @@ rxq_cq_decompress_v(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cq,
                pos += MLX5_VPMD_DESCS_PER_LOOP;
                /* Move to next CQE and invalidate consumed CQEs. */
                if (!(pos & 0x7) && pos < mcqe_n) {
+                       if (pos + 8 < mcqe_n)
+                               rte_prefetch0((void *)(cq + pos + 8));
                        mcq = (void *)&(cq + pos)->pkt_info;
                        for (i = 0; i < 8; ++i)
                                cq[inv++].op_own = MLX5_CQE_INVALIDATE;