Use the context descriptor Tx vector paths from intel/common in ice driver to enable more offloads on the vector path for ice driver.
Signed-off-by: Bruce Richardson <[email protected]> --- doc/guides/rel_notes/release_26_11.rst | 6 ++++ drivers/net/intel/ice/ice_ethdev.h | 3 ++ drivers/net/intel/ice/ice_rxtx.c | 31 ++++++++++++++++++--- drivers/net/intel/ice/ice_rxtx.h | 11 ++++++++ drivers/net/intel/ice/ice_rxtx_vec_avx2.c | 24 ++++++++++++++++ drivers/net/intel/ice/ice_rxtx_vec_avx512.c | 24 ++++++++++++++++ 6 files changed, 95 insertions(+), 4 deletions(-) diff --git a/doc/guides/rel_notes/release_26_11.rst b/doc/guides/rel_notes/release_26_11.rst index 907f9013ff..47eccd9401 100644 --- a/doc/guides/rel_notes/release_26_11.rst +++ b/doc/guides/rel_notes/release_26_11.rst @@ -64,6 +64,12 @@ New Features * Renamed the ``enable_ptype_lldp`` devarg to ``enable_lldp``. The old name is no longer accepted. +* **Updated Intel ice driver.** + + * Added Tx context descriptor support to the AVX2 and AVX512 vector Tx + paths, enabling QinQ tag insertion and outer IPv4/UDP checksum + offloads on those paths. + Removed Items ------------- diff --git a/drivers/net/intel/ice/ice_ethdev.h b/drivers/net/intel/ice/ice_ethdev.h index 7ee3ea8a70..d357181a2a 100644 --- a/drivers/net/intel/ice/ice_ethdev.h +++ b/drivers/net/intel/ice/ice_ethdev.h @@ -213,8 +213,10 @@ enum ice_tx_func_type { ICE_TX_SIMPLE, ICE_TX_AVX2, ICE_TX_AVX2_OFFLOAD, + ICE_TX_AVX2_CTX_OFFLOAD, ICE_TX_AVX512, ICE_TX_AVX512_OFFLOAD, + ICE_TX_AVX512_CTX_OFFLOAD, ICE_TX_NEON, }; @@ -673,6 +675,7 @@ struct ice_adapter { bool rx_bulk_alloc_allowed; bool tx_vec_allowed; bool tx_simple_allowed; + bool use_ctx; enum ice_rx_func_type rx_func_type; enum ice_tx_func_type tx_func_type; /* ptype mapping table */ diff --git a/drivers/net/intel/ice/ice_rxtx.c b/drivers/net/intel/ice/ice_rxtx.c index 313cbd25d5..c6a464b2c1 100644 --- a/drivers/net/intel/ice/ice_rxtx.c +++ b/drivers/net/intel/ice/ice_rxtx.c @@ -883,6 +883,7 @@ ice_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id) /* record what kind of descriptor cleanup we need on teardown */ txq->use_vec_entry = ad->tx_vec_allowed || ad->tx_simple_allowed; + txq->use_ctx = ad->use_ctx; if (txq->tsq != NULL && txq->tsq->ts_flag > 0) { struct ice_aqc_set_txtime_qgrp *ts_elem; @@ -1193,7 +1194,7 @@ ice_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id) return -EINVAL; } - ci_txq_release_all_mbufs(txq, false); + ci_txq_release_all_mbufs(txq, txq->use_ctx); ice_reset_tx_queue(txq); dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED; @@ -1256,7 +1257,7 @@ ice_fdir_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id) return -EINVAL; } - ci_txq_release_all_mbufs(txq, false); + ci_txq_release_all_mbufs(txq, txq->use_ctx); txq->qtx_tail = NULL; return 0; @@ -1744,7 +1745,7 @@ ice_tx_queue_release(void *txq) return; } - ci_txq_release_all_mbufs(q, false); + ci_txq_release_all_mbufs(q, q->use_ctx); rte_free(q->sw_ring); rte_free(q->rs_last_id); if (q->tsq) { @@ -3526,7 +3527,8 @@ static const struct ci_tx_path_info ice_tx_path_infos[] = { .features = { .tx_offloads = ICE_TX_SCALAR_OFFLOADS }, - .pkt_prep = ice_prep_pkts + .pkt_prep = ice_prep_pkts, + .supports_ctx = true }, [ICE_TX_SIMPLE] = { .pkt_burst = ice_xmit_pkts_simple, @@ -3556,6 +3558,16 @@ static const struct ci_tx_path_info ice_tx_path_infos[] = { }, .pkt_prep = ice_prep_pkts }, + [ICE_TX_AVX2_CTX_OFFLOAD] = { + .pkt_burst = ice_xmit_pkts_vec_avx2_ctx_offload, + .info = "Offload Vector AVX2 Ctx", + .features = { + .tx_offloads = ICE_TX_VECTOR_CTX_OFFLOAD_OFFLOADS, + .simd_width = RTE_VECT_SIMD_256 + }, + .pkt_prep = ice_prep_pkts, + .supports_ctx = true + }, #ifdef CC_AVX512_SUPPORT [ICE_TX_AVX512] = { .pkt_burst = ice_xmit_pkts_vec_avx512, @@ -3575,6 +3587,16 @@ static const struct ci_tx_path_info ice_tx_path_infos[] = { }, .pkt_prep = ice_prep_pkts }, + [ICE_TX_AVX512_CTX_OFFLOAD] = { + .pkt_burst = ice_xmit_pkts_vec_avx512_ctx_offload, + .info = "Offload Vector AVX512 Ctx", + .features = { + .tx_offloads = ICE_TX_VECTOR_CTX_OFFLOAD_OFFLOADS, + .simd_width = RTE_VECT_SIMD_512 + }, + .pkt_prep = ice_prep_pkts, + .supports_ctx = true + }, #endif #elif defined(RTE_ARCH_ARM64) [ICE_TX_NEON] = { @@ -3788,6 +3810,7 @@ ice_set_tx_function(struct rte_eth_dev *dev) ad->tx_vec_allowed = (ice_tx_path_infos[ad->tx_func_type].features.simd_width >= RTE_VECT_SIMD_128); #endif + ad->use_ctx = ice_tx_path_infos[ad->tx_func_type].supports_ctx; dev->tx_pkt_burst = mbuf_check ? ice_xmit_pkts_check : ice_tx_path_infos[ad->tx_func_type].pkt_burst; diff --git a/drivers/net/intel/ice/ice_rxtx.h b/drivers/net/intel/ice/ice_rxtx.h index 999b6b30d6..bee8a464f5 100644 --- a/drivers/net/intel/ice/ice_rxtx.h +++ b/drivers/net/intel/ice/ice_rxtx.h @@ -135,6 +135,12 @@ RTE_ETH_TX_OFFLOAD_UDP_CKSUM | \ RTE_ETH_TX_OFFLOAD_TCP_CKSUM | \ RTE_ETH_TX_OFFLOAD_SCTP_CKSUM) +/* vector ctx offload path: QinQ outer tag + outer/tunnel checksum via ctx desc */ +#define ICE_TX_VECTOR_CTX_OFFLOAD_OFFLOADS ( \ + ICE_TX_VECTOR_OFFLOAD_OFFLOADS | \ + RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM | \ + RTE_ETH_TX_OFFLOAD_OUTER_UDP_CKSUM | \ + RTE_ETH_TX_OFFLOAD_QINQ_INSERT) /* Max header size can be 2K - 64 bytes */ #define ICE_RX_HDR_BUF_SIZE (2048 - 64) @@ -284,6 +290,8 @@ uint16_t ice_xmit_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts); uint16_t ice_xmit_pkts_vec_avx2_offload(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts); +uint16_t ice_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts, + uint16_t nb_pkts); uint16_t ice_recv_pkts_vec_avx512(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts); uint16_t ice_recv_pkts_vec_avx512_offload(void *rx_queue, @@ -300,6 +308,9 @@ uint16_t ice_xmit_pkts_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t ice_xmit_pkts_vec_avx512_offload(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts); +uint16_t ice_xmit_pkts_vec_avx512_ctx_offload(void *tx_queue, + struct rte_mbuf **tx_pkts, + uint16_t nb_pkts); int ice_fdir_programming(struct ice_pf *pf, struct ice_fltr_desc *fdir_desc); int ice_tx_done_cleanup(void *txq, uint32_t free_cnt); int ice_get_monitor_addr(void *rx_queue, struct rte_power_monitor_cond *pmc); diff --git a/drivers/net/intel/ice/ice_rxtx_vec_avx2.c b/drivers/net/intel/ice/ice_rxtx_vec_avx2.c index 00b5d51aab..056b2dc49b 100644 --- a/drivers/net/intel/ice/ice_rxtx_vec_avx2.c +++ b/drivers/net/intel/ice/ice_rxtx_vec_avx2.c @@ -810,6 +810,30 @@ ice_xmit_pkts_vec_avx2_offload(void *tx_queue, struct rte_mbuf **tx_pkts, return ice_xmit_pkts_vec_avx2_common(tx_queue, tx_pkts, nb_pkts, true); } +uint16_t +ice_xmit_pkts_vec_avx2_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts, + uint16_t nb_pkts) +{ + uint16_t nb_tx = 0; + struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue; + + while (nb_pkts) { + uint16_t ret, num; + + /* cross rs_thresh boundary is not allowed */ + num = (uint16_t)RTE_MIN(nb_pkts << 1, txq->tx_rs_thresh); + num = num >> 1; + ret = ci_xmit_fixed_burst_vec_ctx_avx2(tx_queue, &tx_pkts[nb_tx], num, + true, CI_TAG_IN_DATA_DESC, CI_TAG_IN_CTX_DESC, NULL); + nb_tx += ret; + nb_pkts -= ret; + if (ret < num) + break; + } + + return nb_tx; +} + int __rte_cold ice_rxq_vec_setup(struct ci_rx_queue *rxq) { diff --git a/drivers/net/intel/ice/ice_rxtx_vec_avx512.c b/drivers/net/intel/ice/ice_rxtx_vec_avx512.c index d8ede5cb42..0548c293bb 100644 --- a/drivers/net/intel/ice/ice_rxtx_vec_avx512.c +++ b/drivers/net/intel/ice/ice_rxtx_vec_avx512.c @@ -882,3 +882,27 @@ ice_xmit_pkts_vec_avx512_offload(void *tx_queue, struct rte_mbuf **tx_pkts, { return ice_xmit_pkts_vec_avx512_common(tx_queue, tx_pkts, nb_pkts, true); } + +uint16_t +ice_xmit_pkts_vec_avx512_ctx_offload(void *tx_queue, struct rte_mbuf **tx_pkts, + uint16_t nb_pkts) +{ + uint16_t nb_tx = 0; + struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue; + + while (nb_pkts) { + uint16_t ret, num; + + /* cross rs_thresh boundary is not allowed */ + num = (uint16_t)RTE_MIN(nb_pkts << 1, txq->tx_rs_thresh); + num = num >> 1; + ret = ci_xmit_fixed_burst_vec_ctx_avx512(tx_queue, &tx_pkts[nb_tx], num, + true, CI_TAG_IN_DATA_DESC, CI_TAG_IN_CTX_DESC, NULL); + nb_tx += ret; + nb_pkts -= ret; + if (ret < num) + break; + } + + return nb_tx; +} -- 2.53.0
