From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id F1D6AA0547; Wed, 29 Sep 2021 14:43:11 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id DC217410EE; Wed, 29 Sep 2021 14:43:11 +0200 (CEST) Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by mails.dpdk.org (Postfix) with ESMTP id 72F7340685; Wed, 29 Sep 2021 14:43:10 +0200 (CEST) X-IronPort-AV: E=McAfee;i="6200,9189,10121"; a="224586112" X-IronPort-AV: E=Sophos;i="5.85,332,1624345200"; d="scan'208";a="224586112" Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 29 Sep 2021 05:43:09 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.85,332,1624345200"; d="scan'208";a="519790817" Received: from dpdk-lrong-srv-04.sh.intel.com ([10.67.119.221]) by fmsmga008.fm.intel.com with ESMTP; 29 Sep 2021 05:43:07 -0700 From: Leyi Rong To: ferruh.yigit@intel.com, bruce.richardson@intel.com, qi.z.zhang@intel.com Cc: dev@dpdk.org, Leyi Rong , wenzhuo.lu@intel.com, stable@dpdk.org Date: Wed, 29 Sep 2021 20:13:08 +0800 Message-Id: <20210929121309.11766-1-leyi.rong@intel.com> X-Mailer: git-send-email 2.17.1 Subject: [dpdk-dev] [PATCH 1/2] net/i40e: fix generic build on FreeBSD X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" The common header file for vectorization is included in multiple files, and so must use macros for the current compilation unit, rather than the compiler-capability flag set for the whole driver. With the current, incorrect, macro, the AVX512 or AVX2 flags may be set when compiling up SSE code, leading to compilation errors. Changing from "CC_AVX*_SUPPORT" to the compiler-defined "__AVX*__" macros fixes this issue. In addition, splitting AVX-specific code into the new i40e_rxtx_common_avx.h header file to avoid such bugs. Bugzilla ID: 788 Fixes: 0604b1f2208f ("net/i40e: fix crash in AVX512") Cc: wenzhuo.lu@intel.com Cc: stable@dpdk.org Signed-off-by: Leyi Rong Signed-off-by: Bruce Richardson --- drivers/net/i40e/i40e_rxtx_common_avx.h | 214 ++++++++++++++++++++++++ drivers/net/i40e/i40e_rxtx_vec_common.h | 200 +--------------------- 2 files changed, 218 insertions(+), 196 deletions(-) create mode 100644 drivers/net/i40e/i40e_rxtx_common_avx.h diff --git a/drivers/net/i40e/i40e_rxtx_common_avx.h b/drivers/net/i40e/i40e_rxtx_common_avx.h new file mode 100644 index 0000000000..cfc1e63173 --- /dev/null +++ b/drivers/net/i40e/i40e_rxtx_common_avx.h @@ -0,0 +1,214 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2015 Intel Corporation + */ + +#ifndef _I40E_RXTX_COMMON_AVX_H_ +#define _I40E_RXTX_COMMON_AVX_H_ +#include +#include +#include + +#include "i40e_ethdev.h" +#include "i40e_rxtx.h" + +#ifndef __INTEL_COMPILER +#pragma GCC diagnostic ignored "-Wcast-qual" +#endif + +#ifdef __AVX2__ +static __rte_always_inline void +i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512) +{ + int i; + uint16_t rx_id; + volatile union i40e_rx_desc *rxdp; + struct i40e_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start]; + + rxdp = rxq->rx_ring + rxq->rxrearm_start; + + /* Pull 'n' more MBUFs into the software ring */ + if (rte_mempool_get_bulk(rxq->mp, + (void *)rxep, + RTE_I40E_RXQ_REARM_THRESH) < 0) { + if (rxq->rxrearm_nb + RTE_I40E_RXQ_REARM_THRESH >= + rxq->nb_rx_desc) { + __m128i dma_addr0; + dma_addr0 = _mm_setzero_si128(); + for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) { + rxep[i].mbuf = &rxq->fake_mbuf; + _mm_store_si128((__m128i *)&rxdp[i].read, + dma_addr0); + } + } + rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed += + RTE_I40E_RXQ_REARM_THRESH; + return; + } + +#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC + struct rte_mbuf *mb0, *mb1; + __m128i dma_addr0, dma_addr1; + __m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM, + RTE_PKTMBUF_HEADROOM); + /* Initialize the mbufs in vector, process 2 mbufs in one loop */ + for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; i += 2, rxep += 2) { + __m128i vaddr0, vaddr1; + + mb0 = rxep[0].mbuf; + mb1 = rxep[1].mbuf; + + /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ + RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != + offsetof(struct rte_mbuf, buf_addr) + 8); + vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); + vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); + + /* convert pa to dma_addr hdr/data */ + dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0); + dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1); + + /* add headroom to pa values */ + dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room); + dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room); + + /* flush desc with pa dma_addr */ + _mm_store_si128((__m128i *)&rxdp++->read, dma_addr0); + _mm_store_si128((__m128i *)&rxdp++->read, dma_addr1); + } +#else +#ifdef __AVX512VL__ + if (avx512) { + struct rte_mbuf *mb0, *mb1, *mb2, *mb3; + struct rte_mbuf *mb4, *mb5, *mb6, *mb7; + __m512i dma_addr0_3, dma_addr4_7; + __m512i hdr_room = _mm512_set1_epi64(RTE_PKTMBUF_HEADROOM); + /* Initialize the mbufs in vector, process 8 mbufs in one loop */ + for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; + i += 8, rxep += 8, rxdp += 8) { + __m128i vaddr0, vaddr1, vaddr2, vaddr3; + __m128i vaddr4, vaddr5, vaddr6, vaddr7; + __m256i vaddr0_1, vaddr2_3; + __m256i vaddr4_5, vaddr6_7; + __m512i vaddr0_3, vaddr4_7; + + mb0 = rxep[0].mbuf; + mb1 = rxep[1].mbuf; + mb2 = rxep[2].mbuf; + mb3 = rxep[3].mbuf; + mb4 = rxep[4].mbuf; + mb5 = rxep[5].mbuf; + mb6 = rxep[6].mbuf; + mb7 = rxep[7].mbuf; + + /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ + RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != + offsetof(struct rte_mbuf, buf_addr) + 8); + vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); + vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); + vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr); + vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr); + vaddr4 = _mm_loadu_si128((__m128i *)&mb4->buf_addr); + vaddr5 = _mm_loadu_si128((__m128i *)&mb5->buf_addr); + vaddr6 = _mm_loadu_si128((__m128i *)&mb6->buf_addr); + vaddr7 = _mm_loadu_si128((__m128i *)&mb7->buf_addr); + + /** + * merge 0 & 1, by casting 0 to 256-bit and inserting 1 + * into the high lanes. Similarly for 2 & 3, and so on. + */ + vaddr0_1 = + _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr0), + vaddr1, 1); + vaddr2_3 = + _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr2), + vaddr3, 1); + vaddr4_5 = + _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr4), + vaddr5, 1); + vaddr6_7 = + _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr6), + vaddr7, 1); + vaddr0_3 = + _mm512_inserti64x4(_mm512_castsi256_si512(vaddr0_1), + vaddr2_3, 1); + vaddr4_7 = + _mm512_inserti64x4(_mm512_castsi256_si512(vaddr4_5), + vaddr6_7, 1); + + /* convert pa to dma_addr hdr/data */ + dma_addr0_3 = _mm512_unpackhi_epi64(vaddr0_3, vaddr0_3); + dma_addr4_7 = _mm512_unpackhi_epi64(vaddr4_7, vaddr4_7); + + /* add headroom to pa values */ + dma_addr0_3 = _mm512_add_epi64(dma_addr0_3, hdr_room); + dma_addr4_7 = _mm512_add_epi64(dma_addr4_7, hdr_room); + + /* flush desc with pa dma_addr */ + _mm512_store_si512((__m512i *)&rxdp->read, dma_addr0_3); + _mm512_store_si512((__m512i *)&(rxdp + 4)->read, dma_addr4_7); + } + } else +#endif /* __AVX512VL__*/ + { + struct rte_mbuf *mb0, *mb1, *mb2, *mb3; + __m256i dma_addr0_1, dma_addr2_3; + __m256i hdr_room = _mm256_set1_epi64x(RTE_PKTMBUF_HEADROOM); + /* Initialize the mbufs in vector, process 4 mbufs in one loop */ + for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; + i += 4, rxep += 4, rxdp += 4) { + __m128i vaddr0, vaddr1, vaddr2, vaddr3; + __m256i vaddr0_1, vaddr2_3; + + mb0 = rxep[0].mbuf; + mb1 = rxep[1].mbuf; + mb2 = rxep[2].mbuf; + mb3 = rxep[3].mbuf; + + /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ + RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != + offsetof(struct rte_mbuf, buf_addr) + 8); + vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); + vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); + vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr); + vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr); + + /** + * merge 0 & 1, by casting 0 to 256-bit and inserting 1 + * into the high lanes. Similarly for 2 & 3 + */ + vaddr0_1 = _mm256_inserti128_si256 + (_mm256_castsi128_si256(vaddr0), vaddr1, 1); + vaddr2_3 = _mm256_inserti128_si256 + (_mm256_castsi128_si256(vaddr2), vaddr3, 1); + + /* convert pa to dma_addr hdr/data */ + dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1); + dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3); + + /* add headroom to pa values */ + dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room); + dma_addr2_3 = _mm256_add_epi64(dma_addr2_3, hdr_room); + + /* flush desc with pa dma_addr */ + _mm256_store_si256((__m256i *)&rxdp->read, dma_addr0_1); + _mm256_store_si256((__m256i *)&(rxdp + 2)->read, dma_addr2_3); + } + } + +#endif + + rxq->rxrearm_start += RTE_I40E_RXQ_REARM_THRESH; + if (rxq->rxrearm_start >= rxq->nb_rx_desc) + rxq->rxrearm_start = 0; + + rxq->rxrearm_nb -= RTE_I40E_RXQ_REARM_THRESH; + + rx_id = (uint16_t)((rxq->rxrearm_start == 0) ? + (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1)); + + /* Update the tail pointer on the NIC */ + I40E_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id); +} +#endif /* __AVX2__*/ + +#endif /*_I40E_RXTX_COMMON_AVX_H_*/ diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h index f52ed98d62..798d6a3e4a 100644 --- a/drivers/net/i40e/i40e_rxtx_vec_common.h +++ b/drivers/net/i40e/i40e_rxtx_vec_common.h @@ -15,6 +15,10 @@ #pragma GCC diagnostic ignored "-Wcast-qual" #endif +#ifdef __AVX2__ +#include "i40e_rxtx_common_avx.h" +#endif + static inline uint16_t reassemble_packets(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_bufs, uint16_t nb_bufs, uint8_t *split_flags) @@ -268,200 +272,4 @@ i40e_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev) #endif } -#ifdef CC_AVX2_SUPPORT -static __rte_always_inline void -i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512) -{ - int i; - uint16_t rx_id; - volatile union i40e_rx_desc *rxdp; - struct i40e_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start]; - - rxdp = rxq->rx_ring + rxq->rxrearm_start; - - /* Pull 'n' more MBUFs into the software ring */ - if (rte_mempool_get_bulk(rxq->mp, - (void *)rxep, - RTE_I40E_RXQ_REARM_THRESH) < 0) { - if (rxq->rxrearm_nb + RTE_I40E_RXQ_REARM_THRESH >= - rxq->nb_rx_desc) { - __m128i dma_addr0; - dma_addr0 = _mm_setzero_si128(); - for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) { - rxep[i].mbuf = &rxq->fake_mbuf; - _mm_store_si128((__m128i *)&rxdp[i].read, - dma_addr0); - } - } - rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed += - RTE_I40E_RXQ_REARM_THRESH; - return; - } - -#ifndef RTE_LIBRTE_I40E_16BYTE_RX_DESC - struct rte_mbuf *mb0, *mb1; - __m128i dma_addr0, dma_addr1; - __m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM, - RTE_PKTMBUF_HEADROOM); - /* Initialize the mbufs in vector, process 2 mbufs in one loop */ - for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; i += 2, rxep += 2) { - __m128i vaddr0, vaddr1; - - mb0 = rxep[0].mbuf; - mb1 = rxep[1].mbuf; - - /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ - RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != - offsetof(struct rte_mbuf, buf_addr) + 8); - vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); - vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); - - /* convert pa to dma_addr hdr/data */ - dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0); - dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1); - - /* add headroom to pa values */ - dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room); - dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room); - - /* flush desc with pa dma_addr */ - _mm_store_si128((__m128i *)&rxdp++->read, dma_addr0); - _mm_store_si128((__m128i *)&rxdp++->read, dma_addr1); - } -#else -#ifdef CC_AVX512_SUPPORT - if (avx512) { - struct rte_mbuf *mb0, *mb1, *mb2, *mb3; - struct rte_mbuf *mb4, *mb5, *mb6, *mb7; - __m512i dma_addr0_3, dma_addr4_7; - __m512i hdr_room = _mm512_set1_epi64(RTE_PKTMBUF_HEADROOM); - /* Initialize the mbufs in vector, process 8 mbufs in one loop */ - for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; - i += 8, rxep += 8, rxdp += 8) { - __m128i vaddr0, vaddr1, vaddr2, vaddr3; - __m128i vaddr4, vaddr5, vaddr6, vaddr7; - __m256i vaddr0_1, vaddr2_3; - __m256i vaddr4_5, vaddr6_7; - __m512i vaddr0_3, vaddr4_7; - - mb0 = rxep[0].mbuf; - mb1 = rxep[1].mbuf; - mb2 = rxep[2].mbuf; - mb3 = rxep[3].mbuf; - mb4 = rxep[4].mbuf; - mb5 = rxep[5].mbuf; - mb6 = rxep[6].mbuf; - mb7 = rxep[7].mbuf; - - /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ - RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != - offsetof(struct rte_mbuf, buf_addr) + 8); - vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); - vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); - vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr); - vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr); - vaddr4 = _mm_loadu_si128((__m128i *)&mb4->buf_addr); - vaddr5 = _mm_loadu_si128((__m128i *)&mb5->buf_addr); - vaddr6 = _mm_loadu_si128((__m128i *)&mb6->buf_addr); - vaddr7 = _mm_loadu_si128((__m128i *)&mb7->buf_addr); - - /** - * merge 0 & 1, by casting 0 to 256-bit and inserting 1 - * into the high lanes. Similarly for 2 & 3, and so on. - */ - vaddr0_1 = - _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr0), - vaddr1, 1); - vaddr2_3 = - _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr2), - vaddr3, 1); - vaddr4_5 = - _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr4), - vaddr5, 1); - vaddr6_7 = - _mm256_inserti128_si256(_mm256_castsi128_si256(vaddr6), - vaddr7, 1); - vaddr0_3 = - _mm512_inserti64x4(_mm512_castsi256_si512(vaddr0_1), - vaddr2_3, 1); - vaddr4_7 = - _mm512_inserti64x4(_mm512_castsi256_si512(vaddr4_5), - vaddr6_7, 1); - - /* convert pa to dma_addr hdr/data */ - dma_addr0_3 = _mm512_unpackhi_epi64(vaddr0_3, vaddr0_3); - dma_addr4_7 = _mm512_unpackhi_epi64(vaddr4_7, vaddr4_7); - - /* add headroom to pa values */ - dma_addr0_3 = _mm512_add_epi64(dma_addr0_3, hdr_room); - dma_addr4_7 = _mm512_add_epi64(dma_addr4_7, hdr_room); - - /* flush desc with pa dma_addr */ - _mm512_store_si512((__m512i *)&rxdp->read, dma_addr0_3); - _mm512_store_si512((__m512i *)&(rxdp + 4)->read, dma_addr4_7); - } - } else -#endif - { - struct rte_mbuf *mb0, *mb1, *mb2, *mb3; - __m256i dma_addr0_1, dma_addr2_3; - __m256i hdr_room = _mm256_set1_epi64x(RTE_PKTMBUF_HEADROOM); - /* Initialize the mbufs in vector, process 4 mbufs in one loop */ - for (i = 0; i < RTE_I40E_RXQ_REARM_THRESH; - i += 4, rxep += 4, rxdp += 4) { - __m128i vaddr0, vaddr1, vaddr2, vaddr3; - __m256i vaddr0_1, vaddr2_3; - - mb0 = rxep[0].mbuf; - mb1 = rxep[1].mbuf; - mb2 = rxep[2].mbuf; - mb3 = rxep[3].mbuf; - - /* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */ - RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) != - offsetof(struct rte_mbuf, buf_addr) + 8); - vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr); - vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr); - vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr); - vaddr3 = _mm_loadu_si128((__m128i *)&mb3->buf_addr); - - /* - * merge 0 & 1, by casting 0 to 256-bit and inserting 1 - * into the high lanes. Similarly for 2 & 3 - */ - vaddr0_1 = _mm256_inserti128_si256( - _mm256_castsi128_si256(vaddr0), vaddr1, 1); - vaddr2_3 = _mm256_inserti128_si256( - _mm256_castsi128_si256(vaddr2), vaddr3, 1); - - /* convert pa to dma_addr hdr/data */ - dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1); - dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3); - - /* add headroom to pa values */ - dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room); - dma_addr2_3 = _mm256_add_epi64(dma_addr2_3, hdr_room); - - /* flush desc with pa dma_addr */ - _mm256_store_si256((__m256i *)&rxdp->read, dma_addr0_1); - _mm256_store_si256((__m256i *)&(rxdp + 2)->read, dma_addr2_3); - } - } - -#endif - - rxq->rxrearm_start += RTE_I40E_RXQ_REARM_THRESH; - if (rxq->rxrearm_start >= rxq->nb_rx_desc) - rxq->rxrearm_start = 0; - - rxq->rxrearm_nb -= RTE_I40E_RXQ_REARM_THRESH; - - rx_id = (uint16_t)((rxq->rxrearm_start == 0) ? - (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1)); - - /* Update the tail pointer on the NIC */ - I40E_PCI_REG_WC_WRITE(rxq->qrx_tail, rx_id); -} -#endif - #endif -- 2.17.1