From 3a1aca384d3ac628dec8830714826e323f509dec Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Tue, 23 Feb 2021 11:10:58 +0800 Subject: [PATCH] net/iavf: fix VLAN tag extraction handling The new VIRTCHNL_VF_OFFLOAD_VLAN_V2 capability added support that allows the PF to set the location of the RX VLAN tag for stripping offloads. So the VF needs to extract the VLAN tag according to the location flags. Fixes: 1c301e8c3cff ("net/iavf: support new VLAN capabilities") Cc: stable@dpdk.org Signed-off-by: Haiyue Wang Signed-off-by: Leyi Rong Tested-by: Wei Xie Acked-by: Qi Zhang --- drivers/net/iavf/iavf_rxtx.c | 62 +++++---- drivers/net/iavf/iavf_rxtx.h | 3 + drivers/net/iavf/iavf_rxtx_vec_avx2.c | 179 ++++++++++++++++++++------ 3 files changed, 182 insertions(+), 62 deletions(-) diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c index af5a28d84d..41409e1525 100644 --- a/drivers/net/iavf/iavf_rxtx.c +++ b/drivers/net/iavf/iavf_rxtx.c @@ -543,6 +543,24 @@ iavf_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, rxq->proto_xtr = IAVF_PROTO_XTR_NONE; } + if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN_V2) { + struct virtchnl_vlan_supported_caps *stripping_support = + &vf->vlan_v2_caps.offloads.stripping_support; + uint32_t stripping_cap; + + if (stripping_support->outer) + stripping_cap = stripping_support->outer; + else + stripping_cap = stripping_support->inner; + + if (stripping_cap & VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1) + rxq->rx_flags = IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1; + else if (stripping_cap & VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2) + rxq->rx_flags = IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2; + } else { + rxq->rx_flags = IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1; + } + iavf_select_rxd_to_pkt_fields_handler(rxq, rxq->rxdid); rxq->mp = mp; @@ -972,31 +990,27 @@ iavf_rxd_to_vlan_tci(struct rte_mbuf *mb, volatile union iavf_rx_desc *rxdp) static inline void iavf_flex_rxd_to_vlan_tci(struct rte_mbuf *mb, - volatile union iavf_rx_flex_desc *rxdp) + volatile union iavf_rx_flex_desc *rxdp, + uint8_t rx_flags) { - if (rte_le_to_cpu_64(rxdp->wb.status_error0) & - (1 << IAVF_RX_FLEX_DESC_STATUS0_L2TAG1P_S)) { - mb->ol_flags |= PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED; - mb->vlan_tci = - rte_le_to_cpu_16(rxdp->wb.l2tag1); - } else { - mb->vlan_tci = 0; - } + uint16_t vlan_tci = 0; + + if (rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1 && + rte_le_to_cpu_64(rxdp->wb.status_error0) & + (1 << IAVF_RX_FLEX_DESC_STATUS0_L2TAG1P_S)) + vlan_tci = rte_le_to_cpu_16(rxdp->wb.l2tag1); #ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC - if (rte_le_to_cpu_16(rxdp->wb.status_error1) & - (1 << IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S)) { - mb->ol_flags |= PKT_RX_QINQ_STRIPPED | PKT_RX_QINQ | - PKT_RX_VLAN_STRIPPED | PKT_RX_VLAN; - mb->vlan_tci_outer = mb->vlan_tci; - mb->vlan_tci = rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd); - PMD_RX_LOG(DEBUG, "Descriptor l2tag2_1: %u, l2tag2_2: %u", - rte_le_to_cpu_16(rxdp->wb.l2tag2_1st), - rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd)); - } else { - mb->vlan_tci_outer = 0; - } + if (rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2 && + rte_le_to_cpu_16(rxdp->wb.status_error1) & + (1 << IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S)) + vlan_tci = rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd); #endif + + if (vlan_tci) { + mb->ol_flags |= PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED; + mb->vlan_tci = vlan_tci; + } } /* Translate the rx descriptor status and error fields to pkt flags */ @@ -1314,7 +1328,7 @@ iavf_recv_pkts_flex_rxd(void *rx_queue, rxm->ol_flags = 0; rxm->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M & rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)]; - iavf_flex_rxd_to_vlan_tci(rxm, &rxd); + iavf_flex_rxd_to_vlan_tci(rxm, &rxd, rxq->rx_flags); rxq->rxd_to_pkt_fields(rxq, rxm, &rxd); pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0); rxm->ol_flags |= pkt_flags; @@ -1455,7 +1469,7 @@ iavf_recv_scattered_pkts_flex_rxd(void *rx_queue, struct rte_mbuf **rx_pkts, first_seg->ol_flags = 0; first_seg->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M & rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)]; - iavf_flex_rxd_to_vlan_tci(first_seg, &rxd); + iavf_flex_rxd_to_vlan_tci(first_seg, &rxd, rxq->rx_flags); rxq->rxd_to_pkt_fields(rxq, first_seg, &rxd); pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0); @@ -1692,7 +1706,7 @@ iavf_rx_scan_hw_ring_flex_rxd(struct iavf_rx_queue *rxq) mb->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M & rte_le_to_cpu_16(rxdp[j].wb.ptype_flex_flags0)]; - iavf_flex_rxd_to_vlan_tci(mb, &rxdp[j]); + iavf_flex_rxd_to_vlan_tci(mb, &rxdp[j], rxq->rx_flags); rxq->rxd_to_pkt_fields(rxq, mb, &rxdp[j]); stat_err0 = rte_le_to_cpu_16(rxdp[j].wb.status_error0); pkt_flags = iavf_flex_rxd_error_to_pkt_flags(stat_err0); diff --git a/drivers/net/iavf/iavf_rxtx.h b/drivers/net/iavf/iavf_rxtx.h index d583badd98..922ddadad1 100644 --- a/drivers/net/iavf/iavf_rxtx.h +++ b/drivers/net/iavf/iavf_rxtx.h @@ -190,6 +190,9 @@ struct iavf_rx_queue { bool q_set; /* if rx queue has been configured */ bool rx_deferred_start; /* don't start this queue in dev start */ const struct iavf_rxq_ops *ops; + uint8_t rx_flags; +#define IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(0) +#define IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(1) uint8_t proto_xtr; /* protocol extraction type */ uint64_t xtr_ol_flag; /* flexible descriptor metadata extraction offload flag */ diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/iavf/iavf_rxtx_vec_avx2.c index 8f28afc8c5..f443300f54 100644 --- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c +++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c @@ -777,20 +777,32 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq, * If RSS(bit12)/VLAN(bit13) are set, * shuffle moves appropriate flags in place. */ - const __m256i rss_vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, + const __m256i rss_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, - PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, 0, /* end up 128-bits */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, - PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH, 0); + const __m256i vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + 0, 0, + /* end up 128-bits */ + 0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED, + 0, 0); + uint16_t i, received; for (i = 0, received = 0; i < nb_pkts; @@ -938,13 +950,24 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq, _mm256_srli_epi32(flag_bits, 4)); l3_l4_flags = _mm256_slli_epi32(l3_l4_flags, 1); l3_l4_flags = _mm256_and_si256(l3_l4_flags, cksum_mask); + /* set rss and vlan flags */ const __m256i rss_vlan_flag_bits = _mm256_srli_epi32(flag_bits, 12); - const __m256i rss_vlan_flags = - _mm256_shuffle_epi8(rss_vlan_flags_shuf, + const __m256i rss_flags = + _mm256_shuffle_epi8(rss_flags_shuf, rss_vlan_flag_bits); + __m256i vlan_flags = _mm256_setzero_si256(); + + if (rxq->rx_flags == IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG1) + vlan_flags = + _mm256_shuffle_epi8(vlan_flags_shuf, + rss_vlan_flag_bits); + + const __m256i rss_vlan_flags = + _mm256_or_si256(rss_flags, vlan_flags); + /* merge flags */ __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags, rss_vlan_flags); @@ -997,7 +1020,8 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq, * will cause performance drop to get into this context. */ if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads & - DEV_RX_OFFLOAD_RSS_HASH) { + DEV_RX_OFFLOAD_RSS_HASH || + rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { /* load bottom half of every 32B desc */ const __m128i raw_desc_bh7 = _mm_load_si128 @@ -1048,36 +1072,115 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq, (_mm256_castsi128_si256(raw_desc_bh0), raw_desc_bh1, 1); - /** - * to shift the 32b RSS hash value to the - * highest 32b of each 128b before mask - */ - __m256i rss_hash6_7 = - _mm256_slli_epi64(raw_desc_bh6_7, 32); - __m256i rss_hash4_5 = - _mm256_slli_epi64(raw_desc_bh4_5, 32); - __m256i rss_hash2_3 = - _mm256_slli_epi64(raw_desc_bh2_3, 32); - __m256i rss_hash0_1 = - _mm256_slli_epi64(raw_desc_bh0_1, 32); - - __m256i rss_hash_msk = - _mm256_set_epi32(0xFFFFFFFF, 0, 0, 0, - 0xFFFFFFFF, 0, 0, 0); - - rss_hash6_7 = _mm256_and_si256 - (rss_hash6_7, rss_hash_msk); - rss_hash4_5 = _mm256_and_si256 - (rss_hash4_5, rss_hash_msk); - rss_hash2_3 = _mm256_and_si256 - (rss_hash2_3, rss_hash_msk); - rss_hash0_1 = _mm256_and_si256 - (rss_hash0_1, rss_hash_msk); - - mb6_7 = _mm256_or_si256(mb6_7, rss_hash6_7); - mb4_5 = _mm256_or_si256(mb4_5, rss_hash4_5); - mb2_3 = _mm256_or_si256(mb2_3, rss_hash2_3); - mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1); + if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads & + DEV_RX_OFFLOAD_RSS_HASH) { + /** + * to shift the 32b RSS hash value to the + * highest 32b of each 128b before mask + */ + __m256i rss_hash6_7 = + _mm256_slli_epi64(raw_desc_bh6_7, 32); + __m256i rss_hash4_5 = + _mm256_slli_epi64(raw_desc_bh4_5, 32); + __m256i rss_hash2_3 = + _mm256_slli_epi64(raw_desc_bh2_3, 32); + __m256i rss_hash0_1 = + _mm256_slli_epi64(raw_desc_bh0_1, 32); + + const __m256i rss_hash_msk = + _mm256_set_epi32(0xFFFFFFFF, 0, 0, 0, + 0xFFFFFFFF, 0, 0, 0); + + rss_hash6_7 = _mm256_and_si256 + (rss_hash6_7, rss_hash_msk); + rss_hash4_5 = _mm256_and_si256 + (rss_hash4_5, rss_hash_msk); + rss_hash2_3 = _mm256_and_si256 + (rss_hash2_3, rss_hash_msk); + rss_hash0_1 = _mm256_and_si256 + (rss_hash0_1, rss_hash_msk); + + mb6_7 = _mm256_or_si256(mb6_7, rss_hash6_7); + mb4_5 = _mm256_or_si256(mb4_5, rss_hash4_5); + mb2_3 = _mm256_or_si256(mb2_3, rss_hash2_3); + mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1); + } + + if (rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + /* merge the status/error-1 bits into one register */ + const __m256i status1_4_7 = + _mm256_unpacklo_epi32(raw_desc_bh6_7, + raw_desc_bh4_5); + const __m256i status1_0_3 = + _mm256_unpacklo_epi32(raw_desc_bh2_3, + raw_desc_bh0_1); + + const __m256i status1_0_7 = + _mm256_unpacklo_epi64(status1_4_7, + status1_0_3); + + const __m256i l2tag2p_flag_mask = + _mm256_set1_epi32 + (1 << IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S); + + __m256i l2tag2p_flag_bits = + _mm256_and_si256 + (status1_0_7, l2tag2p_flag_mask); + + l2tag2p_flag_bits = + _mm256_srli_epi32(l2tag2p_flag_bits, + IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S); + + const __m256i l2tag2_flags_shuf = + _mm256_set_epi8(0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + /* end up 128-bits */ + 0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, + PKT_RX_VLAN | + PKT_RX_VLAN_STRIPPED, + 0); + + vlan_flags = + _mm256_shuffle_epi8(l2tag2_flags_shuf, + l2tag2p_flag_bits); + + /* merge with vlan_flags */ + mbuf_flags = _mm256_or_si256 + (mbuf_flags, vlan_flags); + + /* L2TAG2_2 */ + __m256i vlan_tci6_7 = + _mm256_slli_si256(raw_desc_bh6_7, 4); + __m256i vlan_tci4_5 = + _mm256_slli_si256(raw_desc_bh4_5, 4); + __m256i vlan_tci2_3 = + _mm256_slli_si256(raw_desc_bh2_3, 4); + __m256i vlan_tci0_1 = + _mm256_slli_si256(raw_desc_bh0_1, 4); + + const __m256i vlan_tci_msk = + _mm256_set_epi32(0, 0xFFFF0000, 0, 0, + 0, 0xFFFF0000, 0, 0); + + vlan_tci6_7 = _mm256_and_si256 + (vlan_tci6_7, vlan_tci_msk); + vlan_tci4_5 = _mm256_and_si256 + (vlan_tci4_5, vlan_tci_msk); + vlan_tci2_3 = _mm256_and_si256 + (vlan_tci2_3, vlan_tci_msk); + vlan_tci0_1 = _mm256_and_si256 + (vlan_tci0_1, vlan_tci_msk); + + mb6_7 = _mm256_or_si256(mb6_7, vlan_tci6_7); + mb4_5 = _mm256_or_si256(mb4_5, vlan_tci4_5); + mb2_3 = _mm256_or_si256(mb2_3, vlan_tci2_3); + mb0_1 = _mm256_or_si256(mb0_1, vlan_tci0_1); + } } /* if() on RSS hash parsing */ #endif -- 2.20.1