[dpdk-dev] [PATCH v2 16/19] net/mlx5: add meta data support to Rx datapath

[Viacheslav Ovsiienko <viacheslavo@mellanox.com>]

This patch moves metadata from completion descriptor
to appropriate dynamic mbuf field.

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
---
 drivers/net/mlx5/mlx5_prm.h              |  6 ++++--
 drivers/net/mlx5/mlx5_rxtx.c             |  5 +++++
 drivers/net/mlx5/mlx5_rxtx_vec_altivec.h | 25 +++++++++++++++++++++++--
 drivers/net/mlx5/mlx5_rxtx_vec_neon.h    | 23 +++++++++++++++++++++++
 drivers/net/mlx5/mlx5_rxtx_vec_sse.h     | 27 +++++++++++++++++++++++----
 5 files changed, 78 insertions(+), 8 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h
index b405cb6..a0c37c8 100644
--- a/drivers/net/mlx5/mlx5_prm.h
+++ b/drivers/net/mlx5/mlx5_prm.h
@@ -357,12 +357,14 @@ struct mlx5_cqe {
 	uint16_t hdr_type_etc;
 	uint16_t vlan_info;
 	uint8_t lro_num_seg;
-	uint8_t rsvd3[11];
+	uint8_t rsvd3[3];
+	uint32_t flow_table_metadata;
+	uint8_t rsvd4[4];
 	uint32_t byte_cnt;
 	uint64_t timestamp;
 	uint32_t sop_drop_qpn;
 	uint16_t wqe_counter;
-	uint8_t rsvd4;
+	uint8_t rsvd5;
 	uint8_t op_own;
 };
 
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index 887e283..f28a909 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -26,6 +26,7 @@
 #include <rte_branch_prediction.h>
 #include <rte_ether.h>
 #include <rte_cycles.h>
+#include <rte_flow.h>
 
 #include "mlx5.h"
 #include "mlx5_utils.h"
@@ -1251,6 +1252,10 @@ enum mlx5_txcmp_code {
 			pkt->hash.fdir.hi = mlx5_flow_mark_get(mark);
 		}
 	}
+	if (rte_flow_dynf_metadata_avail() && cqe->flow_table_metadata) {
+		pkt->ol_flags |= PKT_RX_DYNF_METADATA;
+		*RTE_FLOW_DYNF_METADATA(pkt) = cqe->flow_table_metadata;
+	}
 	if (rxq->csum)
 		pkt->ol_flags |= rxq_cq_to_ol_flags(cqe);
 	if (rxq->vlan_strip &&
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
index 3be3a6d..8e79883 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
@@ -416,7 +416,6 @@
 			vec_cmpeq((vector unsigned int)flow_tag,
 			(vector unsigned int)pinfo_ft_mask)));
 	}
-
 	/*
 	 * Merge the two fields to generate the following:
 	 * bit[1]     = l3_ok
@@ -1011,7 +1010,29 @@
 			pkts[pos + 3]->timestamp =
 				rte_be_to_cpu_64(cq[pos + p3].timestamp);
 		}
-
+		if (rte_flow_dynf_metadata_avail()) {
+			uint64_t flag = rte_flow_dynf_metadata_mask;
+			int offs = rte_flow_dynf_metadata_offs;
+			uint32_t metadata;
+
+			/* This code is subject for futher optimization. */
+			metadata = cq[pos].flow_table_metadata;
+			*RTE_MBUF_DYNFIELD(pkts[pos], offs, uint32_t *) =
+								metadata;
+			pkts[pos]->ol_flags |= metadata ? flag : 0ULL;
+			metadata = cq[pos + 1].flow_table_metadata;
+			*RTE_MBUF_DYNFIELD(pkts[pos + 1], offs, uint32_t *) =
+								metadata;
+			pkts[pos + 1]->ol_flags |= metadata ? flag : 0ULL;
+			metadata = cq[pos + 2].flow_table_metadata;
+			*RTE_MBUF_DYNFIELD(pkts[pos + 2], offs, uint32_t *) =
+								metadata;
+			pkts[pos + 2]->ol_flags |= metadata ? flag : 0ULL;
+			metadata = cq[pos + 3].flow_table_metadata;
+			*RTE_MBUF_DYNFIELD(pkts[pos + 3], offs, uint32_t *) =
+								metadata;
+			pkts[pos + 3]->ol_flags |= metadata ? flag : 0ULL;
+		}
 #ifdef MLX5_PMD_SOFT_COUNTERS
 		/* Add up received bytes count. */
 		byte_cnt = vec_perm(op_own, zero, len_shuf_mask);
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index e914d01..86785c7 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -687,6 +687,29 @@
 					container_of(p3, struct mlx5_cqe,
 						     pkt_info)->timestamp);
 		}
+		if (rte_flow_dynf_metadata_avail()) {
+			/* This code is subject for futher optimization. */
+			*RTE_FLOW_DYNF_METADATA(elts[pos]) =
+				container_of(p0, struct mlx5_cqe,
+					     pkt_info)->flow_table_metadata;
+			*RTE_FLOW_DYNF_METADATA(elts[pos + 1]) =
+				container_of(p1, struct mlx5_cqe,
+					     pkt_info)->flow_table_metadata;
+			*RTE_FLOW_DYNF_METADATA(elts[pos + 2]) =
+				container_of(p2, struct mlx5_cqe,
+					     pkt_info)->flow_table_metadata;
+			*RTE_FLOW_DYNF_METADATA(elts[pos + 3]) =
+				container_of(p3, struct mlx5_cqe,
+					     pkt_info)->flow_table_metadata;
+			if (*RTE_FLOW_DYNF_METADATA(elts[pos]))
+				elts[pos]->ol_flags |= PKT_RX_DYNF_METADATA;
+			if (*RTE_FLOW_DYNF_METADATA(elts[pos + 1]))
+				elts[pos + 1]->ol_flags |= PKT_RX_DYNF_METADATA;
+			if (*RTE_FLOW_DYNF_METADATA(elts[pos + 2]))
+				elts[pos + 2]->ol_flags |= PKT_RX_DYNF_METADATA;
+			if (*RTE_FLOW_DYNF_METADATA(elts[pos + 3]))
+				elts[pos + 3]->ol_flags |= PKT_RX_DYNF_METADATA;
+		}
 #ifdef MLX5_PMD_SOFT_COUNTERS
 		/* Add up received bytes count. */
 		byte_cnt = vbic_u16(byte_cnt, invalid_mask);
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index ca8ed41..35b7761 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -537,8 +537,8 @@
 		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].rsvd3[9]);
-		cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos + p2].rsvd3[9]);
+		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. */
@@ -564,8 +564,8 @@
 		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].rsvd3[9]);
-		cqe_tmp1 = _mm_loadl_epi64((__m128i *)&cq[pos].rsvd3[9]);
+		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 +640,25 @@
 			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);
-- 
1.8.3.1