summaryrefslogtreecommitdiffstats
path: root/common/api-parent/pom.xml
blob: 8fe25b329aa7bf3455bd465db04e4ddc798ce117 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
<?xml version="1.0" encoding="UTF-8"?>
<!--
 Copyright (c) 2015 Cisco and/or its affiliates.
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at:

     http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
-->
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">

  <parent>
    <groupId>io.fd.honeycomb.common</groupId>
    <artifactId>honeycomb-parent</artifactId>
    <version>1.18.10-SNAPSHOT</version>
    <relativePath>../honeycomb-parent</relativePath>
  </parent>

  <modelVersion>4.0.0</modelVersion>
  <artifactId>api-parent</artifactId>
  <name>${project.artifactId}</name>
  <version>1.18.10-SNAPSHOT</version>
  <packaging>pom</packaging>

  <properties>
    <annotations.version>3.0.0</annotations.version>
  </properties>

  <build>
    <pluginManagement>
      <plugins>
        <!-- Yangtools, generate yang -->
        <plugin>
          <groupId>org.opendaylight.yangtools</groupId>
          <artifactId>yang-maven-plugin</artifactId>
          <version>${odl.yangtools.version}</version>
          <dependencies>
            <dependency>
              <groupId>org.opendaylight.mdsal</groupId>
              <artifactId>maven-sal-api-gen-plugin</artifactId>
              <version>${odl.salGenerator.version}</version>
              <type>jar</type>
            </dependency>
          </dependencies>
          <executions>
            <execution>
              <id>binding</id>
              <goals>
                <goal>generate-sources</goal>
              </goals>
              <configuration>
                <codeGenerators>
                  <generator>
                    <codeGeneratorClass>org.opendaylight.mdsal.binding.maven.api.gen.plugin.CodeGeneratorImpl</codeGeneratorClass>
                    <outputBaseDir>${salGeneratorPath}</outputBaseDir>
                  </generator>
                </codeGenerators>
                <inspectDependencies>true</inspectDependencies>
              </configuration>
            </execution>
          </executions>
        </plugin>
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <configuration>
            <filesets>
              <fileset>
                <directory>${salGeneratorPath}</directory>
                <includes>
                  <include>**</include>
                </includes>
              </fileset>
            </filesets>
          </configuration>
        </plugin>
        <!-- add generated yang classes to build -->
        <plugin>
          <groupId>org.codehaus.mojo</groupId>
          <artifactId>build-helper-maven-plugin</artifactId>
          <executions>
            <execution>
              <id>add-yang-sources</id>
              <phase>generate-sources</phase>
              <goals>
                <goal>add-source</goal>
              </goals>
              <configuration>
                <sources>
                  <source>${salGeneratorPath}</source>
                </sources>
              </configuration>
            </execution>
          </executions>
        </plugin>
      </plugins>
    </pluginManagement>
    <plugins>
      <plugin>
        <groupId>org.opendaylight.yangtools</groupId>
        <artifactId>yang-maven-plugin</artifactId>
      </plugin>
      <plugin>
        <groupId>org.codehaus.mojo</groupId>
        <artifactId>build-helper-maven-plugin</artifactId>
      </plugin>
    </plugins>
  </build>

  <dependencies>
    <dependency>
      <groupId>org.opendaylight.mdsal</groupId>
      <artifactId>yang-binding</artifactId>
    </dependency>
    <dependency>
      <groupId>org.opendaylight.yangtools</groupId>
      <artifactId>yang-common</artifactId>
    </dependency>
    <dependency>
      <groupId>com.google.code.findbugs</groupId>
      <artifactId>annotations</artifactId>
      <version>${annotations.version}</version>
    </dependency>
  </dependencies>
</project>
Name.Variable */ .highlight .ow { color: #f92672 } /* Operator.Word */ .highlight .w { color: #f8f8f2 } /* Text.Whitespace */ .highlight .mb { color: #ae81ff } /* Literal.Number.Bin */ .highlight .mf { color: #ae81ff } /* Literal.Number.Float */ .highlight .mh { color: #ae81ff } /* Literal.Number.Hex */ .highlight .mi { color: #ae81ff } /* Literal.Number.Integer */ .highlight .mo { color: #ae81ff } /* Literal.Number.Oct */ .highlight .sa { color: #e6db74 } /* Literal.String.Affix */ .highlight .sb { color: #e6db74 } /* Literal.String.Backtick */ .highlight .sc { color: #e6db74 } /* Literal.String.Char */ .highlight .dl { color: #e6db74 } /* Literal.String.Delimiter */ .highlight .sd { color: #e6db74 } /* Literal.String.Doc */ .highlight .s2 { color: #e6db74 } /* Literal.String.Double */ .highlight .se { color: #ae81ff } /* Literal.String.Escape */ .highlight .sh { color: #e6db74 } /* Literal.String.Heredoc */ .highlight .si { color: #e6db74 } /* Literal.String.Interpol */ .highlight .sx { color: #e6db74 } /* Literal.String.Other */ .highlight .sr { color: #e6db74 } /* Literal.String.Regex */ .highlight .s1 { color: #e6db74 } /* Literal.String.Single */ .highlight .ss { color: #e6db74 } /* Literal.String.Symbol */ .highlight .bp { color: #f8f8f2 } /* Name.Builtin.Pseudo */ .highlight .fm { color: #a6e22e } /* Name.Function.Magic */ .highlight .vc { color: #f8f8f2 } /* Name.Variable.Class */ .highlight .vg { color: #f8f8f2 } /* Name.Variable.Global */ .highlight .vi { color: #f8f8f2 } /* Name.Variable.Instance */ .highlight .vm { color: #f8f8f2 } /* Name.Variable.Magic */ .highlight .il { color: #ae81ff } /* Literal.Number.Integer.Long */ } @media (prefers-color-scheme: light) { .highlight .hll { background-color: #ffffcc } .highlight .c { color: #888888 } /* Comment */ .highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */ .highlight .k { color: #008800; font-weight: bold } /* Keyword */ .highlight .ch { color: #888888 } /* Comment.Hashbang */ .highlight .cm { color: #888888 } /* Comment.Multiline */ .highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */ .highlight .cpf { color: #888888 } /* Comment.PreprocFile */ .highlight .c1 { color: #888888 } /* Comment.Single */ .highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */ .highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */ .highlight .ge { font-style: italic } /* Generic.Emph */ .highlight .gr { color: #aa0000 } /* Generic.Error */ .highlight .gh { color: #333333 } /* Generic.Heading */ .highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */ .highlight .go { color: #888888 } /* Generic.Output */ .highlight .gp { color: #555555 } /* Generic.Prompt */ .highlight .gs { font-weight: bold } /* Generic.Strong */ .highlight .gu { color: #666666 } /* Generic.Subheading */ .highlight .gt { color: #aa0000 } /* Generic.Traceback */ .highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */ .highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */ .highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */ .highlight .kp { color: #008800 } /* Keyword.Pseudo */ .highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */ .highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */ .highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */ .highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */ .highlight .na { color: #336699 } /* Name.Attribute */ .highlight .nb { color: #003388 } /* Name.Builtin */ .highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */ .highlight .no { color: #003366; font-weight: bold } /* Name.Constant */ .highlight .nd { color: #555555 } /* Name.Decorator */ .highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */ .highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */ .highlight .nl { color: #336699; font-style: italic } /* Name.Label */ .highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */ .highlight .py { color: #336699; font-weight: bold } /* Name.Property */ .highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */ .highlight .nv { color: #336699 } /* Name.Variable */ .highlight .ow { color: #008800 } /* Operator.Word */ .highlight .w { color: #bbbbbb } /* Text.Whitespace */ .highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */ .highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */ .highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */ .highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */ .highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */ .highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */ .highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */ .highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */ .highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */ .highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */ .highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */ .highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */ .highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */ .highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */ .highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */ .highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */ .highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */ .highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */ .highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */ .highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */ .highlight .vc { color: #336699 } /* Name.Variable.Class */ .highlight .vg { color: #dd7700 } /* Name.Variable.Global */ .highlight .vi { color: #3333bb } /* Name.Variable.Instance */ .highlight .vm { color: #336699 } /* Name.Variable.Magic */ .highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */ }
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdint.h>
#include <rte_ethdev.h>
#include <rte_malloc.h>

#include "base/i40e_prototype.h"
#include "base/i40e_type.h"
#include "i40e_ethdev.h"
#include "i40e_rxtx.h"
#include "i40e_rxtx_vec_common.h"

#include <tmmintrin.h>

#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif

static inline void
i40e_rxq_rearm(struct i40e_rx_queue *rxq)
{
	int i;
	uint16_t rx_id;
	volatile union i40e_rx_desc *rxdp;
	struct i40e_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
	struct rte_mbuf *mb0, *mb1;
	__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
			RTE_PKTMBUF_HEADROOM);
	__m128i dma_addr0, dma_addr1;

	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) {
			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;
	}

	/* 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_physaddr(hi 64bit) */
		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);
	}

	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_WRITE(rxq->qrx_tail, rx_id);
}

static inline void
desc_to_olflags_v(struct i40e_rx_queue *rxq, __m128i descs[4] __rte_unused,
	struct rte_mbuf **rx_pkts)
{
	const __m128i mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer);
	__m128i rearm0, rearm1, rearm2, rearm3;

	__m128i vlan0, vlan1, rss, l3_l4e;

	/* mask everything except RSS, flow director and VLAN flags
	 * bit2 is for VLAN tag, bit11 for flow director indication
	 * bit13:12 for RSS indication.
	 */
	const __m128i rss_vlan_msk = _mm_set_epi32(
			0x1c03804, 0x1c03804, 0x1c03804, 0x1c03804);

	const __m128i cksum_mask = _mm_set_epi32(
			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
			PKT_RX_EIP_CKSUM_BAD,
			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
			PKT_RX_EIP_CKSUM_BAD,
			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
			PKT_RX_EIP_CKSUM_BAD,
			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
			PKT_RX_EIP_CKSUM_BAD);

	/* map rss and vlan type to rss hash and vlan flag */
	const __m128i vlan_flags = _mm_set_epi8(0, 0, 0, 0,
			0, 0, 0, 0,
			0, 0, 0, PKT_RX_VLAN_PKT | PKT_RX_VLAN_STRIPPED,
			0, 0, 0, 0);

	const __m128i rss_flags = _mm_set_epi8(0, 0, 0, 0,
			0, 0, 0, 0,
			PKT_RX_RSS_HASH | PKT_RX_FDIR, PKT_RX_RSS_HASH, 0, 0,
			0, 0, PKT_RX_FDIR, 0);

	const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
			/* shift right 1 bit to make sure it not exceed 255 */
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
			 PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
			 PKT_RX_L4_CKSUM_BAD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
			PKT_RX_IP_CKSUM_BAD >> 1,
			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1);

	vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]);
	vlan1 = _mm_unpackhi_epi32(descs[2], descs[3]);
	vlan0 = _mm_unpacklo_epi64(vlan0, vlan1);

	vlan1 = _mm_and_si128(vlan0, rss_vlan_msk);
	vlan0 = _mm_shuffle_epi8(vlan_flags, vlan1);

	rss = _mm_srli_epi32(vlan1, 11);
	rss = _mm_shuffle_epi8(rss_flags, rss);

	l3_l4e = _mm_srli_epi32(vlan1, 22);
	l3_l4e = _mm_shuffle_epi8(l3_l4e_flags, l3_l4e);
	/* then we shift left 1 bit */
	l3_l4e = _mm_slli_epi32(l3_l4e, 1);
	/* we need to mask out the reduntant bits */
	l3_l4e = _mm_and_si128(l3_l4e, cksum_mask);

	vlan0 = _mm_or_si128(vlan0, rss);
	vlan0 = _mm_or_si128(vlan0, l3_l4e);

	/*
	 * At this point, we have the 4 sets of flags in the low 16-bits
	 * of each 32-bit value in vlan0.
	 * We want to extract these, and merge them with the mbuf init data
	 * so we can do a single 16-byte write to the mbuf to set the flags
	 * and all the other initialization fields. Extracting the
	 * appropriate flags means that we have to do a shift and blend for
	 * each mbuf before we do the write.
	 */
	rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 8), 0x10);
	rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 4), 0x10);
	rearm2 = _mm_blend_epi16(mbuf_init, vlan0, 0x10);
	rearm3 = _mm_blend_epi16(mbuf_init, _mm_srli_si128(vlan0, 4), 0x10);
	_mm_store_si128((__m128i *)&rx_pkts[0]->rearm_data, rearm0);
	_mm_store_si128((__m128i *)&rx_pkts[1]->rearm_data, rearm1);
	_mm_store_si128((__m128i *)&rx_pkts[2]->rearm_data, rearm2);
	_mm_store_si128((__m128i *)&rx_pkts[3]->rearm_data, rearm3);
}

#define PKTLEN_SHIFT     10

static inline void
desc_to_ptype_v(__m128i descs[4], struct rte_mbuf **rx_pkts,
		uint32_t *ptype_tbl)
{
	__m128i ptype0 = _mm_unpackhi_epi64(descs[0], descs[1]);
	__m128i ptype1 = _mm_unpackhi_epi64(descs[2], descs[3]);

	ptype0 = _mm_srli_epi64(ptype0, 30);
	ptype1 = _mm_srli_epi64(ptype1, 30);

	rx_pkts[0]->packet_type = ptype_tbl[_mm_extract_epi8(ptype0, 0)];
	rx_pkts[1]->packet_type = ptype_tbl[_mm_extract_epi8(ptype0, 8)];
	rx_pkts[2]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 0)];
	rx_pkts[3]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 8)];
}

 /*
 * Notice:
 * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
 * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
 *   numbers of DD bits
 */
static inline uint16_t
_recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
		   uint16_t nb_pkts, uint8_t *split_packet)
{
	volatile union i40e_rx_desc *rxdp;
	struct i40e_rx_entry *sw_ring;
	uint16_t nb_pkts_recd;
	int pos;
	uint64_t var;
	__m128i shuf_msk;
	uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;

	__m128i crc_adjust = _mm_set_epi16(
				0, 0, 0,    /* ignore non-length fields */
				-rxq->crc_len, /* sub crc on data_len */
				0,          /* ignore high-16bits of pkt_len */
				-rxq->crc_len, /* sub crc on pkt_len */
				0, 0            /* ignore pkt_type field */
			);
	__m128i dd_check, eop_check;

	/* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
	nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);

	/* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);

	/* Just the act of getting into the function from the application is
	 * going to cost about 7 cycles
	 */
	rxdp = rxq->rx_ring + rxq->rx_tail;

	rte_prefetch0(rxdp);

	/* See if we need to rearm the RX queue - gives the prefetch a bit
	 * of time to act
	 */
	if (rxq->rxrearm_nb > RTE_I40E_RXQ_REARM_THRESH)
		i40e_rxq_rearm(rxq);

	/* Before we start moving massive data around, check to see if
	 * there is actually a packet available
	 */
	if (!(rxdp->wb.qword1.status_error_len &
			rte_cpu_to_le_32(1 << I40E_RX_DESC_STATUS_DD_SHIFT)))
		return 0;

	/* 4 packets DD mask */
	dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);

	/* 4 packets EOP mask */
	eop_check = _mm_set_epi64x(0x0000000200000002LL, 0x0000000200000002LL);

	/* mask to shuffle from desc. to mbuf */
	shuf_msk = _mm_set_epi8(
		7, 6, 5, 4,  /* octet 4~7, 32bits rss */
		3, 2,        /* octet 2~3, low 16 bits vlan_macip */
		15, 14,      /* octet 15~14, 16 bits data_len */
		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
		15, 14,      /* octet 15~14, low 16 bits pkt_len */
		0xFF, 0xFF,  /* pkt_type set as unknown */
		0xFF, 0xFF  /*pkt_type set as unknown */
		);

	/* Cache is empty -> need to scan the buffer rings, but first move
	 * the next 'n' mbufs into the cache
	 */
	sw_ring = &rxq->sw_ring[rxq->rx_tail];

	/* A. load 4 packet in one loop
	 * [A*. mask out 4 unused dirty field in desc]
	 * B. copy 4 mbuf point from swring to rx_pkts
	 * C. calc the number of DD bits among the 4 packets
	 * [C*. extract the end-of-packet bit, if requested]
	 * D. fill info. from desc to mbuf
	 */

	for (pos = 0, nb_pkts_recd = 0; pos < nb_pkts;
			pos += RTE_I40E_DESCS_PER_LOOP,
			rxdp += RTE_I40E_DESCS_PER_LOOP) {
		__m128i descs[RTE_I40E_DESCS_PER_LOOP];
		__m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
		__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
		/* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
		__m128i mbp1;
#if defined(RTE_ARCH_X86_64)
		__m128i mbp2;
#endif

		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
		/* Read desc statuses backwards to avoid race condition */
		/* A.1 load 4 pkts desc */
		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
		rte_compiler_barrier();

		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
		_mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);

#if defined(RTE_ARCH_X86_64)
		/* B.1 load 2 64 bit mbuf points */
		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos+2]);
#endif

		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
		rte_compiler_barrier();
		/* B.1 load 2 mbuf point */
		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
		rte_compiler_barrier();
		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));

#if defined(RTE_ARCH_X86_64)
		/* B.2 copy 2 mbuf point into rx_pkts  */
		_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
#endif

		if (split_packet) {
			rte_mbuf_prefetch_part2(rx_pkts[pos]);
			rte_mbuf_prefetch_part2(rx_pkts[pos + 1]);
			rte_mbuf_prefetch_part2(rx_pkts[pos + 2]);
			rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
		}

		/* avoid compiler reorder optimization */
		rte_compiler_barrier();

		/* pkt 3,4 shift the pktlen field to be 16-bit aligned*/
		const __m128i len3 = _mm_slli_epi32(descs[3], PKTLEN_SHIFT);
		const __m128i len2 = _mm_slli_epi32(descs[2], PKTLEN_SHIFT);

		/* merge the now-aligned packet length fields back in */
		descs[3] = _mm_blend_epi16(descs[3], len3, 0x80);
		descs[2] = _mm_blend_epi16(descs[2], len2, 0x80);

		/* D.1 pkt 3,4 convert format from desc to pktmbuf */
		pkt_mb4 = _mm_shuffle_epi8(descs[3], shuf_msk);
		pkt_mb3 = _mm_shuffle_epi8(descs[2], shuf_msk);

		/* C.1 4=>2 filter staterr info only */
		sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
		/* C.1 4=>2 filter staterr info only */
		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);

		desc_to_olflags_v(rxq, descs, &rx_pkts[pos]);

		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
		pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust);
		pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);

		/* pkt 1,2 shift the pktlen field to be 16-bit aligned*/
		const __m128i len1 = _mm_slli_epi32(descs[1], PKTLEN_SHIFT);
		const __m128i len0 = _mm_slli_epi32(descs[0], PKTLEN_SHIFT);

		/* merge the now-aligned packet length fields back in */
		descs[1] = _mm_blend_epi16(descs[1], len1, 0x80);
		descs[0] = _mm_blend_epi16(descs[0], len0, 0x80);

		/* D.1 pkt 1,2 convert format from desc to pktmbuf */
		pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
		pkt_mb1 = _mm_shuffle_epi8(descs[0], shuf_msk);

		/* C.2 get 4 pkts staterr value  */
		zero = _mm_xor_si128(dd_check, dd_check);
		staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);

		/* D.3 copy final 3,4 data to rx_pkts */
		_mm_storeu_si128((void *)&rx_pkts[pos+3]->rx_descriptor_fields1,
				 pkt_mb4);
		_mm_storeu_si128((void *)&rx_pkts[pos+2]->rx_descriptor_fields1,
				 pkt_mb3);

		/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
		pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
		pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);

		/* C* extract and record EOP bit */
		if (split_packet) {
			__m128i eop_shuf_mask = _mm_set_epi8(
					0xFF, 0xFF, 0xFF, 0xFF,
					0xFF, 0xFF, 0xFF, 0xFF,
					0xFF, 0xFF, 0xFF, 0xFF,
					0x04, 0x0C, 0x00, 0x08
					);

			/* and with mask to extract bits, flipping 1-0 */
			__m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
			/* the staterr values are not in order, as the count
			 * count of dd bits doesn't care. However, for end of
			 * packet tracking, we do care, so shuffle. This also
			 * compresses the 32-bit values to 8-bit
			 */
			eop_bits = _mm_shuffle_epi8(eop_bits, eop_shuf_mask);
			/* store the resulting 32-bit value */
			*(int *)split_packet = _mm_cvtsi128_si32(eop_bits);
			split_packet += RTE_I40E_DESCS_PER_LOOP;
		}

		/* C.3 calc available number of desc */
		staterr = _mm_and_si128(staterr, dd_check);
		staterr = _mm_packs_epi32(staterr, zero);

		/* D.3 copy final 1,2 data to rx_pkts */
		_mm_storeu_si128((void *)&rx_pkts[pos+1]->rx_descriptor_fields1,
				 pkt_mb2);
		_mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
				 pkt_mb1);
		desc_to_ptype_v(descs, &rx_pkts[pos], ptype_tbl);
		/* C.4 calc avaialbe number of desc */
		var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
		nb_pkts_recd += var;
		if (likely(var != RTE_I40E_DESCS_PER_LOOP))
			break;
	}

	/* Update our internal tail pointer */
	rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_pkts_recd);
	rxq->rx_tail = (uint16_t)(rxq->rx_tail & (rxq->nb_rx_desc - 1));
	rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);

	return nb_pkts_recd;
}

 /*
 * Notice:
 * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
 * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
 *   numbers of DD bits
 */
uint16_t
i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
		   uint16_t nb_pkts)
{
	return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}

 /* vPMD receive routine that reassembles scattered packets
 * Notice:
 * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
 * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
 *   numbers of DD bits
 */
uint16_t
i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
			     uint16_t nb_pkts)
{

	struct i40e_rx_queue *rxq = rx_queue;
	uint8_t split_flags[RTE_I40E_VPMD_RX_BURST] = {0};

	/* get some new buffers */
	uint16_t nb_bufs = _recv_raw_pkts_vec(rxq, rx_pkts, nb_pkts,
			split_flags);
	if (nb_bufs == 0)
		return 0;

	/* happy day case, full burst + no packets to be joined */
	const uint64_t *split_fl64 = (uint64_t *)split_flags;

	if (rxq->pkt_first_seg == NULL &&
			split_fl64[0] == 0 && split_fl64[1] == 0 &&
			split_fl64[2] == 0 && split_fl64[3] == 0)
		return nb_bufs;

	/* reassemble any packets that need reassembly*/
	unsigned i = 0;

	if (rxq->pkt_first_seg == NULL) {
		/* find the first split flag, and only reassemble then*/
		while (i < nb_bufs && !split_flags[i])
			i++;
		if (i == nb_bufs)
			return nb_bufs;
	}
	return i + reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
		&split_flags[i]);
}

static inline void
vtx1(volatile struct i40e_tx_desc *txdp,
		struct rte_mbuf *pkt, uint64_t flags)
{
	uint64_t high_qw = (I40E_TX_DESC_DTYPE_DATA |
			((uint64_t)flags  << I40E_TXD_QW1_CMD_SHIFT) |
			((uint64_t)pkt->data_len << I40E_TXD_QW1_TX_BUF_SZ_SHIFT));

	__m128i descriptor = _mm_set_epi64x(high_qw,
				pkt->buf_physaddr + pkt->data_off);
	_mm_store_si128((__m128i *)txdp, descriptor);
}

static inline void
vtx(volatile struct i40e_tx_desc *txdp,
		struct rte_mbuf **pkt, uint16_t nb_pkts,  uint64_t flags)
{
	int i;

	for (i = 0; i < nb_pkts; ++i, ++txdp, ++pkt)
		vtx1(txdp, *pkt, flags);
}

uint16_t
i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
			  uint16_t nb_pkts)
{
	struct i40e_tx_queue *txq = (struct i40e_tx_queue *)tx_queue;
	volatile struct i40e_tx_desc *txdp;
	struct i40e_tx_entry *txep;
	uint16_t n, nb_commit, tx_id;
	uint64_t flags = I40E_TD_CMD;
	uint64_t rs = I40E_TX_DESC_CMD_RS | I40E_TD_CMD;
	int i;

	/* cross rx_thresh boundary is not allowed */
	nb_pkts = RTE_MIN(nb_pkts, txq->tx_rs_thresh);

	if (txq->nb_tx_free < txq->tx_free_thresh)
		i40e_tx_free_bufs(txq);

	nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
	if (unlikely(nb_pkts == 0))
		return 0;

	tx_id = txq->tx_tail;
	txdp = &txq->tx_ring[tx_id];
	txep = &txq->sw_ring[tx_id];

	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);

	n = (uint16_t)(txq->nb_tx_desc - tx_id);
	if (nb_commit >= n) {
		tx_backlog_entry(txep, tx_pkts, n);

		for (i = 0; i < n - 1; ++i, ++tx_pkts, ++txdp)
			vtx1(txdp, *tx_pkts, flags);

		vtx1(txdp, *tx_pkts++, rs);

		nb_commit = (uint16_t)(nb_commit - n);

		tx_id = 0;
		txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);

		/* avoid reach the end of ring */
		txdp = &txq->tx_ring[tx_id];
		txep = &txq->sw_ring[tx_id];
	}

	tx_backlog_entry(txep, tx_pkts, nb_commit);

	vtx(txdp, tx_pkts, nb_commit, flags);

	tx_id = (uint16_t)(tx_id + nb_commit);
	if (tx_id > txq->tx_next_rs) {
		txq->tx_ring[txq->tx_next_rs].cmd_type_offset_bsz |=
			rte_cpu_to_le_64(((uint64_t)I40E_TX_DESC_CMD_RS) <<
						I40E_TXD_QW1_CMD_SHIFT);
		txq->tx_next_rs =
			(uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
	}

	txq->tx_tail = tx_id;

	I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);

	return nb_pkts;
}

void __attribute__((cold))
i40e_rx_queue_release_mbufs_vec(struct i40e_rx_queue *rxq)
{
	_i40e_rx_queue_release_mbufs_vec(rxq);
}

int __attribute__((cold))
i40e_rxq_vec_setup(struct i40e_rx_queue *rxq)
{
	return i40e_rxq_vec_setup_default(rxq);
}

int __attribute__((cold))
i40e_txq_vec_setup(struct i40e_tx_queue __rte_unused *txq)
{
	return 0;
}

int __attribute__((cold))
i40e_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
{
#ifndef RTE_LIBRTE_IEEE1588
	/* need SSE4.1 support */
	if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_1))
		return -1;
#endif

	return i40e_rx_vec_dev_conf_condition_check_default(dev);
}