From patchwork Sun Apr 5 08:56:05 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jerin Jacob Kollanukkaran X-Patchwork-Id: 67843 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 05D9EA0577; Sun, 5 Apr 2020 11:01:04 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 07D951C0DC; Sun, 5 Apr 2020 10:57:37 +0200 (CEST) Received: from mx0b-0016f401.pphosted.com (mx0a-0016f401.pphosted.com [67.231.148.174]) by dpdk.org (Postfix) with ESMTP id C0D391BF54 for ; Sun, 5 Apr 2020 10:57:35 +0200 (CEST) Received: from pps.filterd (m0045849.ppops.net [127.0.0.1]) by mx0a-0016f401.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id 0358upNw029895; Sun, 5 Apr 2020 01:57:33 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=pfpt0818; bh=H/5nceb2EzAE+kdkryeBUwMuJIgDfFXMfHCy7TJL7so=; b=Cp+MLB3r21UmqVVb3+uxHZqvhN/TvLySNvXbYQg02cqYrfcwnxCCFoigE0iHjcJyUXRc Q46vNVDlExWhmW6CTPAfRi4Ur/L1WV2dOdtKJ86/iYxQBZc24qsb18P2ZdkZAX0elf0u DdlDMjPTzvrzcMbwDzxcLAjb9wkAR4t8Q+4wnlSfT/SCEfWuqGq+j6iDKUhXocuPYS9I 4bReD/TLVAag/zTWMsnDa3OJpG2Bn4lXmJYTh+dcbd09dDh1uOsQc9Y1/mrQ3y6Q/ogW koDPbSUWE1pBf+NrjHhZWQFfjPJMChmoDati1YwwxEga1Gx1OXYq7LbXzb8jwFmjMsU+ RQ== Received: from sc-exch01.marvell.com ([199.233.58.181]) by mx0a-0016f401.pphosted.com with ESMTP id 306qkqtmt7-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT); Sun, 05 Apr 2020 01:57:33 -0700 Received: from DC5-EXCH02.marvell.com (10.69.176.39) by SC-EXCH01.marvell.com (10.93.176.81) with Microsoft SMTP Server (TLS) id 15.0.1497.2; Sun, 5 Apr 2020 01:57:32 -0700 Received: from maili.marvell.com (10.69.176.80) by DC5-EXCH02.marvell.com (10.69.176.39) with Microsoft SMTP Server id 15.0.1497.2 via Frontend Transport; Sun, 5 Apr 2020 01:57:32 -0700 Received: from jerin-lab.marvell.com (jerin-lab.marvell.com [10.28.34.14]) by maili.marvell.com (Postfix) with ESMTP id 819E13F703F; Sun, 5 Apr 2020 01:57:29 -0700 (PDT) From: To: Nithin Dabilpuram , Pavan Nikhilesh CC: , , , , , , Date: Sun, 5 Apr 2020 14:26:05 +0530 Message-ID: <20200405085613.1336841-22-jerinj@marvell.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20200405085613.1336841-1-jerinj@marvell.com> References: <20200331192945.2466880-1-jerinj@marvell.com> <20200405085613.1336841-1-jerinj@marvell.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.138, 18.0.676 definitions=2020-04-05_01:2020-04-03, 2020-04-05 signatures=0 Subject: [dpdk-dev] [PATCH v4 21/29] node: ipv4 lookup for x86 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 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" From: Pavan Nikhilesh Add IPv4 lookup process function for ip4_lookup rte_node. This node performs LPM lookup using x86_64 vector supported RTE_LPM API on every packet received and forwards it to a next node that is identified by lookup result. Signed-off-by: Pavan Nikhilesh Signed-off-by: Nithin Dabilpuram Signed-off-by: Kiran Kumar K --- lib/librte_node/ip4_lookup.c | 2 + lib/librte_node/ip4_lookup_sse.h | 244 +++++++++++++++++++++++++++++++ 2 files changed, 246 insertions(+) create mode 100644 lib/librte_node/ip4_lookup_sse.h diff --git a/lib/librte_node/ip4_lookup.c b/lib/librte_node/ip4_lookup.c index e8732e31b..3a38f5ad8 100644 --- a/lib/librte_node/ip4_lookup.c +++ b/lib/librte_node/ip4_lookup.c @@ -30,6 +30,8 @@ struct ip4_lookup_node_main { #if defined(RTE_MACHINE_CPUFLAG_NEON) #include "ip4_lookup_neon.h" +#elif defined(RTE_ARCH_X86) +#include "ip4_lookup_sse.h" #else static uint16_t diff --git a/lib/librte_node/ip4_lookup_sse.h b/lib/librte_node/ip4_lookup_sse.h new file mode 100644 index 000000000..2efe48bf8 --- /dev/null +++ b/lib/librte_node/ip4_lookup_sse.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(C) 2020 Marvell International Ltd. + */ + +#ifndef __INCLUDE_IP4_LOOKUP_SSE_H__ +#define __INCLUDE_IP4_LOOKUP_SSE_H__ + +/* X86 SSE */ +static uint16_t +ip4_lookup_node_process(struct rte_graph *graph, struct rte_node *node, + void **objs, uint16_t nb_objs) +{ + struct rte_mbuf *mbuf0, *mbuf1, *mbuf2, *mbuf3, **pkts; + rte_edge_t next0, next1, next2, next3, next_index; + struct rte_ipv4_hdr *ipv4_hdr; + uint32_t ip0, ip1, ip2, ip3; + void **to_next, **from; + uint16_t last_spec = 0; + uint16_t n_left_from; + struct rte_lpm *lpm; + uint16_t held = 0; + uint32_t drop_nh; + rte_xmm_t dst; + __m128i dip; /* SSE register */ + int rc, i; + + /* Speculative next */ + next_index = RTE_NODE_IP4_LOOKUP_NEXT_REWRITE; + /* Drop node */ + drop_nh = ((uint32_t)RTE_NODE_IP4_LOOKUP_NEXT_PKT_DROP) << 16; + + /* Get socket specific LPM from ctx */ + lpm = *((struct rte_lpm **)node->ctx); + + pkts = (struct rte_mbuf **)objs; + from = objs; + n_left_from = nb_objs; + + if (n_left_from >= 4) { + for (i = 0; i < 4; i++) + rte_prefetch0(rte_pktmbuf_mtod_offset(pkts[i], void *, + sizeof(struct rte_ether_hdr))); + } + + /* Get stream for the speculated next node */ + to_next = rte_node_next_stream_get(graph, node, next_index, nb_objs); + while (n_left_from >= 4) { + /* Prefetch next-next mbufs */ + if (likely(n_left_from > 11)) { + rte_prefetch0(pkts[8]); + rte_prefetch0(pkts[9]); + rte_prefetch0(pkts[10]); + rte_prefetch0(pkts[11]); + } + + /* Prefetch next mbuf data */ + if (likely(n_left_from > 7)) { + rte_prefetch0(rte_pktmbuf_mtod_offset(pkts[4], void *, + sizeof(struct rte_ether_hdr))); + rte_prefetch0(rte_pktmbuf_mtod_offset(pkts[5], void *, + sizeof(struct rte_ether_hdr))); + rte_prefetch0(rte_pktmbuf_mtod_offset(pkts[6], void *, + sizeof(struct rte_ether_hdr))); + rte_prefetch0(rte_pktmbuf_mtod_offset(pkts[7], void *, + sizeof(struct rte_ether_hdr))); + } + + mbuf0 = pkts[0]; + mbuf1 = pkts[1]; + mbuf2 = pkts[2]; + mbuf3 = pkts[3]; + + pkts += 4; + n_left_from -= 4; + + /* Extract DIP of mbuf0 */ + ipv4_hdr = rte_pktmbuf_mtod_offset(mbuf0, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); + ip0 = ipv4_hdr->dst_addr; + /* Extract cksum, ttl as ipv4 hdr is in cache */ + rte_node_mbuf_priv1(mbuf0)->cksum = ipv4_hdr->hdr_checksum; + rte_node_mbuf_priv1(mbuf0)->ttl = ipv4_hdr->time_to_live; + + /* Extract DIP of mbuf1 */ + ipv4_hdr = rte_pktmbuf_mtod_offset(mbuf1, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); + ip1 = ipv4_hdr->dst_addr; + /* Extract cksum, ttl as ipv4 hdr is in cache */ + rte_node_mbuf_priv1(mbuf1)->cksum = ipv4_hdr->hdr_checksum; + rte_node_mbuf_priv1(mbuf1)->ttl = ipv4_hdr->time_to_live; + + /* Extract DIP of mbuf2 */ + ipv4_hdr = rte_pktmbuf_mtod_offset(mbuf2, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); + ip2 = ipv4_hdr->dst_addr; + /* Extract cksum, ttl as ipv4 hdr is in cache */ + rte_node_mbuf_priv1(mbuf2)->cksum = ipv4_hdr->hdr_checksum; + rte_node_mbuf_priv1(mbuf2)->ttl = ipv4_hdr->time_to_live; + + /* Extract DIP of mbuf3 */ + ipv4_hdr = rte_pktmbuf_mtod_offset(mbuf3, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); + ip3 = ipv4_hdr->dst_addr; + + /* Prepare for lookup x4 */ + dip = _mm_set_epi32(ip3, ip2, ip1, ip0); + + /* Byte swap 4 IPV4 addresses. */ + const __m128i bswap_mask = _mm_set_epi8( + 12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3); + dip = _mm_shuffle_epi8(dip, bswap_mask); + + /* Extract cksum, ttl as ipv4 hdr is in cache */ + rte_node_mbuf_priv1(mbuf3)->cksum = ipv4_hdr->hdr_checksum; + rte_node_mbuf_priv1(mbuf3)->ttl = ipv4_hdr->time_to_live; + + /* Perform LPM lookup to get NH and next node */ + rte_lpm_lookupx4(lpm, dip, dst.u32, drop_nh); + + /* Extract next node id and NH */ + rte_node_mbuf_priv1(mbuf0)->nh = dst.u32[0] & 0xFFFF; + next0 = (dst.u32[0] >> 16); + + rte_node_mbuf_priv1(mbuf1)->nh = dst.u32[1] & 0xFFFF; + next1 = (dst.u32[1] >> 16); + + rte_node_mbuf_priv1(mbuf2)->nh = dst.u32[2] & 0xFFFF; + next2 = (dst.u32[2] >> 16); + + rte_node_mbuf_priv1(mbuf3)->nh = dst.u32[3] & 0xFFFF; + next3 = (dst.u32[3] >> 16); + + /* Enqueue four to next node */ + rte_edge_t fix_spec = + (next_index ^ next0) | (next_index ^ next1) | + (next_index ^ next2) | (next_index ^ next3); + + if (unlikely(fix_spec)) { + /* Copy things successfully speculated till now */ + rte_memcpy(to_next, from, last_spec * sizeof(from[0])); + from += last_spec; + to_next += last_spec; + held += last_spec; + last_spec = 0; + + /* Next0 */ + if (next_index == next0) { + to_next[0] = from[0]; + to_next++; + held++; + } else { + rte_node_enqueue_x1(graph, node, next0, + from[0]); + } + + /* Next1 */ + if (next_index == next1) { + to_next[0] = from[1]; + to_next++; + held++; + } else { + rte_node_enqueue_x1(graph, node, next1, + from[1]); + } + + /* Next2 */ + if (next_index == next2) { + to_next[0] = from[2]; + to_next++; + held++; + } else { + rte_node_enqueue_x1(graph, node, next2, + from[2]); + } + + /* Next3 */ + if (next_index == next3) { + to_next[0] = from[3]; + to_next++; + held++; + } else { + rte_node_enqueue_x1(graph, node, next3, + from[3]); + } + + from += 4; + + } else { + last_spec += 4; + } + } + + while (n_left_from > 0) { + uint32_t next_hop; + + mbuf0 = pkts[0]; + + pkts += 1; + n_left_from -= 1; + + /* Extract DIP of mbuf0 */ + ipv4_hdr = rte_pktmbuf_mtod_offset(mbuf0, struct rte_ipv4_hdr *, + sizeof(struct rte_ether_hdr)); + /* Extract cksum, ttl as ipv4 hdr is in cache */ + rte_node_mbuf_priv1(mbuf0)->cksum = ipv4_hdr->hdr_checksum; + rte_node_mbuf_priv1(mbuf0)->ttl = ipv4_hdr->time_to_live; + + rc = rte_lpm_lookup(lpm, rte_be_to_cpu_32(ipv4_hdr->dst_addr), + &next_hop); + next_hop = (rc == 0) ? next_hop : drop_nh; + + rte_node_mbuf_priv1(mbuf0)->nh = next_hop & 0xFFFF; + next0 = (next_hop >> 16); + + if (unlikely(next_index ^ next0)) { + /* Copy things successfully speculated till now */ + rte_memcpy(to_next, from, last_spec * sizeof(from[0])); + from += last_spec; + to_next += last_spec; + held += last_spec; + last_spec = 0; + + rte_node_enqueue_x1(graph, node, next0, from[0]); + from += 1; + } else { + last_spec += 1; + } + } + + /* !!! Home run !!! */ + if (likely(last_spec == nb_objs)) { + rte_node_next_stream_move(graph, node, next_index); + return nb_objs; + } + + held += last_spec; + /* Copy things successfully speculated till now */ + rte_memcpy(to_next, from, last_spec * sizeof(from[0])); + rte_node_next_stream_put(graph, node, next_index, held); + + return nb_objs; +} + +#endif /* __INCLUDE_IP4_LOOKUP_SSE_H__ */