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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
/*-
* BSD LICENSE
*
* Copyright(c) 2010-2016 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.
*/
#ifndef __L3FWD_LPM_SSE_H__
#define __L3FWD_LPM_SSE_H__
#include "l3fwd_sse.h"
/*
* Read packet_type and destination IPV4 addresses from 4 mbufs.
*/
static inline void
processx4_step1(struct rte_mbuf *pkt[FWDSTEP],
__m128i *dip,
uint32_t *ipv4_flag)
{
struct ipv4_hdr *ipv4_hdr;
struct ether_hdr *eth_hdr;
uint32_t x0, x1, x2, x3;
eth_hdr = rte_pktmbuf_mtod(pkt[0], struct ether_hdr *);
ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
x0 = ipv4_hdr->dst_addr;
ipv4_flag[0] = pkt[0]->packet_type & RTE_PTYPE_L3_IPV4;
eth_hdr = rte_pktmbuf_mtod(pkt[1], struct ether_hdr *);
ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
x1 = ipv4_hdr->dst_addr;
ipv4_flag[0] &= pkt[1]->packet_type;
eth_hdr = rte_pktmbuf_mtod(pkt[2], struct ether_hdr *);
ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
x2 = ipv4_hdr->dst_addr;
ipv4_flag[0] &= pkt[2]->packet_type;
eth_hdr = rte_pktmbuf_mtod(pkt[3], struct ether_hdr *);
ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);
x3 = ipv4_hdr->dst_addr;
ipv4_flag[0] &= pkt[3]->packet_type;
dip[0] = _mm_set_epi32(x3, x2, x1, x0);
}
/*
* Lookup into LPM for destination port.
* If lookup fails, use incoming port (portid) as destination port.
*/
static inline void
processx4_step2(const struct lcore_conf *qconf,
__m128i dip,
uint32_t ipv4_flag,
uint16_t portid,
struct rte_mbuf *pkt[FWDSTEP],
uint16_t dprt[FWDSTEP])
{
rte_xmm_t dst;
const __m128i bswap_mask = _mm_set_epi8(12, 13, 14, 15, 8, 9, 10, 11,
4, 5, 6, 7, 0, 1, 2, 3);
/* Byte swap 4 IPV4 addresses. */
dip = _mm_shuffle_epi8(dip, bswap_mask);
/* if all 4 packets are IPV4. */
if (likely(ipv4_flag)) {
rte_lpm_lookupx4(qconf->ipv4_lookup_struct, dip, dst.u32,
portid);
/* get rid of unused upper 16 bit for each dport. */
dst.x = _mm_packs_epi32(dst.x, dst.x);
*(uint64_t *)dprt = dst.u64[0];
} else {
dst.x = dip;
dprt[0] = lpm_get_dst_port_with_ipv4(qconf, pkt[0], dst.u32[0], portid);
dprt[1] = lpm_get_dst_port_with_ipv4(qconf, pkt[1], dst.u32[1], portid);
dprt[2] = lpm_get_dst_port_with_ipv4(qconf, pkt[2], dst.u32[2], portid);
dprt[3] = lpm_get_dst_port_with_ipv4(qconf, pkt[3], dst.u32[3], portid);
}
}
/*
* Buffer optimized handling of packets, invoked
* from main_loop.
*/
static inline void
l3fwd_lpm_send_packets(int nb_rx, struct rte_mbuf **pkts_burst,
uint16_t portid, struct lcore_conf *qconf)
{
int32_t j;
uint16_t dst_port[MAX_PKT_BURST];
__m128i dip[MAX_PKT_BURST / FWDSTEP];
uint32_t ipv4_flag[MAX_PKT_BURST / FWDSTEP];
const int32_t k = RTE_ALIGN_FLOOR(nb_rx, FWDSTEP);
for (j = 0; j != k; j += FWDSTEP)
processx4_step1(&pkts_burst[j], &dip[j / FWDSTEP],
&ipv4_flag[j / FWDSTEP]);
for (j = 0; j != k; j += FWDSTEP)
processx4_step2(qconf, dip[j / FWDSTEP],
ipv4_flag[j / FWDSTEP], portid, &pkts_burst[j], &dst_port[j]);
/* Classify last up to 3 packets one by one */
switch (nb_rx % FWDSTEP) {
case 3:
dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
j++;
/* fall-through */
case 2:
dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
j++;
/* fall-through */
case 1:
dst_port[j] = lpm_get_dst_port(qconf, pkts_burst[j], portid);
j++;
}
send_packets_multi(qconf, pkts_burst, dst_port, nb_rx);
}
#endif /* __L3FWD_LPM_SSE_H__ */
|
