common/mlx5: introduce common library

[dpdk.git] / drivers / net / mlx5 / mlx5_rxtx_vec_sse.h

diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index 7bd254f..6e1b967 100644 (file)
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -16,13 +16,14 @@
 #include <rte_mempool.h>
 #include <rte_prefetch.h>
 
+#include <mlx5_prm.h>
+
+#include "mlx5_defs.h"
 #include "mlx5.h"
 #include "mlx5_utils.h"
 #include "mlx5_rxtx.h"
 #include "mlx5_rxtx_vec.h"
 #include "mlx5_autoconf.h"
-#include "mlx5_defs.h"
-#include "mlx5_prm.h"
 
 #ifndef __INTEL_COMPILER
 #pragma GCC diagnostic ignored "-Wcast-qual"
@@ -259,7 +260,7 @@ rxq_cq_to_ptype_oflags_v(struct mlx5_rxq_data *rxq, __m128i cqes[4],
                              PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD |
                              PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED);
        const __m128i mbuf_init =
-               _mm_loadl_epi64((__m128i *)&rxq->mbuf_initializer);
+               _mm_load_si128((__m128i *)&rxq->mbuf_initializer);
        __m128i rearm0, rearm1, rearm2, rearm3;
        uint8_t pt_idx0, pt_idx1, pt_idx2, pt_idx3;
 
@@ -533,12 +534,12 @@ rxq_burst_v(struct mlx5_rxq_data *rxq, struct rte_mbuf **pkts, uint16_t pkts_n,
                cqe_tmp1 = _mm_load_si128((__m128i *)&cq[pos + p2]);
                cqes[3] = _mm_blendv_epi8(cqes[3], cqe_tmp2, blend_mask);
                cqes[2] = _mm_blendv_epi8(cqes[2], cqe_tmp1, blend_mask);
-               cqe_tmp2 = _mm_loadu_si128((__m128i *)&cq[pos + p3].rsvd1[3]);
-               cqe_tmp1 = _mm_loadu_si128((__m128i *)&cq[pos + p2].rsvd1[3]);
+               cqe_tmp2 = _mm_loadu_si128((__m128i *)&cq[pos + p3].csum);
+               cqe_tmp1 = _mm_loadu_si128((__m128i *)&cq[pos + p2].csum);
                cqes[3] = _mm_blend_epi16(cqes[3], cqe_tmp2, 0x30);
                cqes[2] = _mm_blend_epi16(cqes[2], cqe_tmp1, 0x30);
-               cqe_tmp2 = _mm_loadl_epi64((__m128i *)&cq[pos + p3].rsvd2[10]);
-               cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos + p2].rsvd2[10]);
+               cqe_tmp2 = _mm_loadl_epi64((__m128i *)&cq[pos + p3].rsvd4[2]);
+               cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos + p2].rsvd4[2]);
                cqes[3] = _mm_blend_epi16(cqes[3], cqe_tmp2, 0x04);
                cqes[2] = _mm_blend_epi16(cqes[2], cqe_tmp1, 0x04);
                /* C.2 generate final structure for mbuf with swapping bytes. */
@@ -560,12 +561,12 @@ rxq_burst_v(struct mlx5_rxq_data *rxq, struct rte_mbuf **pkts, uint16_t pkts_n,
                cqe_tmp1 = _mm_load_si128((__m128i *)&cq[pos]);
                cqes[1] = _mm_blendv_epi8(cqes[1], cqe_tmp2, blend_mask);
                cqes[0] = _mm_blendv_epi8(cqes[0], cqe_tmp1, blend_mask);
-               cqe_tmp2 = _mm_loadu_si128((__m128i *)&cq[pos + p1].rsvd1[3]);
-               cqe_tmp1 = _mm_loadu_si128((__m128i *)&cq[pos].rsvd1[3]);
+               cqe_tmp2 = _mm_loadu_si128((__m128i *)&cq[pos + p1].csum);
+               cqe_tmp1 = _mm_loadu_si128((__m128i *)&cq[pos].csum);
                cqes[1] = _mm_blend_epi16(cqes[1], cqe_tmp2, 0x30);
                cqes[0] = _mm_blend_epi16(cqes[0], cqe_tmp1, 0x30);
-               cqe_tmp2 = _mm_loadl_epi64((__m128i *)&cq[pos + p1].rsvd2[10]);
-               cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos].rsvd2[10]);
+               cqe_tmp2 = _mm_loadl_epi64((__m128i *)&cq[pos + p1].rsvd4[2]);
+               cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos].rsvd4[2]);
                cqes[1] = _mm_blend_epi16(cqes[1], cqe_tmp2, 0x04);
                cqes[0] = _mm_blend_epi16(cqes[0], cqe_tmp1, 0x04);
                /* C.2 generate final structure for mbuf with swapping bytes. */
@@ -640,6 +641,25 @@ rxq_burst_v(struct mlx5_rxq_data *rxq, struct rte_mbuf **pkts, uint16_t pkts_n,
                        pkts[pos + 3]->timestamp =
                                rte_be_to_cpu_64(cq[pos + p3].timestamp);
                }
+               if (rte_flow_dynf_metadata_avail()) {
+                       /* This code is subject for futher optimization. */
+                       *RTE_FLOW_DYNF_METADATA(pkts[pos]) =
+                               cq[pos].flow_table_metadata;
+                       *RTE_FLOW_DYNF_METADATA(pkts[pos + 1]) =
+                               cq[pos + p1].flow_table_metadata;
+                       *RTE_FLOW_DYNF_METADATA(pkts[pos + 2]) =
+                               cq[pos + p2].flow_table_metadata;
+                       *RTE_FLOW_DYNF_METADATA(pkts[pos + 3]) =
+                               cq[pos + p3].flow_table_metadata;
+                       if (*RTE_FLOW_DYNF_METADATA(pkts[pos]))
+                               pkts[pos]->ol_flags |= PKT_RX_DYNF_METADATA;
+                       if (*RTE_FLOW_DYNF_METADATA(pkts[pos + 1]))
+                               pkts[pos + 1]->ol_flags |= PKT_RX_DYNF_METADATA;
+                       if (*RTE_FLOW_DYNF_METADATA(pkts[pos + 2]))
+                               pkts[pos + 2]->ol_flags |= PKT_RX_DYNF_METADATA;
+                       if (*RTE_FLOW_DYNF_METADATA(pkts[pos + 3]))
+                               pkts[pos + 3]->ol_flags |= PKT_RX_DYNF_METADATA;
+               }
 #ifdef MLX5_PMD_SOFT_COUNTERS
                /* Add up received bytes count. */
                byte_cnt = _mm_shuffle_epi8(op_own, len_shuf_mask);