aboutsummaryrefslogtreecommitdiffstats
path: root/examples/l3fwd/l3fwd_lpm.c
blob: 2d0e1724842449144e9c36da46a14ca7f15a7d01 (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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
/*-
 *   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.
 */

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <sys/types.h>
#include <string.h>
#include <sys/queue.h>
#include <stdarg.h>
#include <errno.h>
#include <getopt.h>
#include <stdbool.h>

#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_cycles.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_lpm.h>
#include <rte_lpm6.h>

#include "l3fwd.h"

struct ipv4_l3fwd_lpm_route {
	uint32_t ip;
	uint8_t  depth;
	uint8_t  if_out;
};

struct ipv6_l3fwd_lpm_route {
	uint8_t ip[16];
	uint8_t  depth;
	uint8_t  if_out;
};

static struct ipv4_l3fwd_lpm_route ipv4_l3fwd_lpm_route_array[] = {
	{IPv4(1, 1, 1, 0), 24, 0},
	{IPv4(2, 1, 1, 0), 24, 1},
	{IPv4(3, 1, 1, 0), 24, 2},
	{IPv4(4, 1, 1, 0), 24, 3},
	{IPv4(5, 1, 1, 0), 24, 4},
	{IPv4(6, 1, 1, 0), 24, 5},
	{IPv4(7, 1, 1, 0), 24, 6},
	{IPv4(8, 1, 1, 0), 24, 7},
};

static struct ipv6_l3fwd_lpm_route ipv6_l3fwd_lpm_route_array[] = {
	{{1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 0},
	{{2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 1},
	{{3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 2},
	{{4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 3},
	{{5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 4},
	{{6, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 5},
	{{7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 6},
	{{8, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1}, 48, 7},
};

#define IPV4_L3FWD_LPM_NUM_ROUTES \
	(sizeof(ipv4_l3fwd_lpm_route_array) / sizeof(ipv4_l3fwd_lpm_route_array[0]))
#define IPV6_L3FWD_LPM_NUM_ROUTES \
	(sizeof(ipv6_l3fwd_lpm_route_array) / sizeof(ipv6_l3fwd_lpm_route_array[0]))

#define IPV4_L3FWD_LPM_MAX_RULES         1024
#define IPV4_L3FWD_LPM_NUMBER_TBL8S (1 << 8)
#define IPV6_L3FWD_LPM_MAX_RULES         1024
#define IPV6_L3FWD_LPM_NUMBER_TBL8S (1 << 16)

struct rte_lpm *ipv4_l3fwd_lpm_lookup_struct[NB_SOCKETS];
struct rte_lpm6 *ipv6_l3fwd_lpm_lookup_struct[NB_SOCKETS];

static inline uint16_t
lpm_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct)
{
	uint32_t next_hop;
	struct rte_lpm *ipv4_l3fwd_lookup_struct =
		(struct rte_lpm *)lookup_struct;

	return (uint16_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
		rte_be_to_cpu_32(((struct ipv4_hdr *)ipv4_hdr)->dst_addr),
		&next_hop) == 0) ? next_hop : portid);
}

static inline uint16_t
lpm_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct)
{
	uint32_t next_hop;
	struct rte_lpm6 *ipv6_l3fwd_lookup_struct =
		(struct rte_lpm6 *)lookup_struct;

	return (uint16_t) ((rte_lpm6_lookup(ipv6_l3fwd_lookup_struct,
			((struct ipv6_hdr *)ipv6_hdr)->dst_addr,
			&next_hop) == 0) ?  next_hop : portid);
}

static __rte_always_inline uint16_t
lpm_get_dst_port(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
		uint16_t portid)
{
	struct ipv6_hdr *ipv6_hdr;
	struct ipv4_hdr *ipv4_hdr;
	struct ether_hdr *eth_hdr;

	if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) {

		eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
		ipv4_hdr = (struct ipv4_hdr *)(eth_hdr + 1);

		return lpm_get_ipv4_dst_port(ipv4_hdr, portid,
					     qconf->ipv4_lookup_struct);
	} else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) {

		eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
		ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1);

		return lpm_get_ipv6_dst_port(ipv6_hdr, portid,
					     qconf->ipv6_lookup_struct);
	}

	return portid;
}

/*
 * lpm_get_dst_port optimized routine for packets where dst_ipv4 is already
 * precalculated. If packet is ipv6 dst_addr is taken directly from packet
 * header and dst_ipv4 value is not used.
 */
static __rte_always_inline uint16_t
lpm_get_dst_port_with_ipv4(const struct lcore_conf *qconf, struct rte_mbuf *pkt,
	uint32_t dst_ipv4, uint16_t portid)
{
	uint32_t next_hop;
	struct ipv6_hdr *ipv6_hdr;
	struct ether_hdr *eth_hdr;

	if (RTE_ETH_IS_IPV4_HDR(pkt->packet_type)) {
		return (uint16_t) ((rte_lpm_lookup(qconf->ipv4_lookup_struct,
						   dst_ipv4, &next_hop) == 0)
				   ? next_hop : portid);

	} else if (RTE_ETH_IS_IPV6_HDR(pkt->packet_type)) {

		eth_hdr = rte_pktmbuf_mtod(pkt, struct ether_hdr *);
		ipv6_hdr = (struct ipv6_hdr *)(eth_hdr + 1);

		return (uint16_t) ((rte_lpm6_lookup(qconf->ipv6_lookup_struct,
				ipv6_hdr->dst_addr, &next_hop) == 0)
				? next_hop : portid);

	}

	return portid;
}

#if defined(RTE_ARCH_X86)
#include "l3fwd_lpm_sse.h"
#elif defined RTE_MACHINE_CPUFLAG_NEON
#include "l3fwd_lpm_neon.h"
#elif defined(RTE_ARCH_PPC_64)
#include "l3fwd_lpm_altivec.h"
#else
#include "l3fwd_lpm.h"
#endif

/* main processing loop */
int
lpm_main_loop(__attribute__((unused)) void *dummy)
{
	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
	unsigned lcore_id;
	uint64_t prev_tsc, diff_tsc, cur_tsc;
	int i, nb_rx;
	uint16_t portid;
	uint8_t queueid;
	struct lcore_conf *qconf;
	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
		US_PER_S * BURST_TX_DRAIN_US;

	prev_tsc = 0;

	lcore_id = rte_lcore_id();
	qconf = &lcore_conf[lcore_id];

	if (qconf->n_rx_queue == 0) {
		RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id);
		return 0;
	}

	RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id);

	for (i = 0; i < qconf->n_rx_queue; i++) {

		portid = qconf->rx_queue_list[i].port_id;
		queueid = qconf->rx_queue_list[i].queue_id;
		RTE_LOG(INFO, L3FWD,
			" -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
			lcore_id, portid, queueid);
	}

	while (!force_quit) {

		cur_tsc = rte_rdtsc();

		/*
		 * TX burst queue drain
		 */
		diff_tsc = cur_tsc - prev_tsc;
		if (unlikely(diff_tsc > drain_tsc)) {

			for (i = 0; i < qconf->n_tx_port; ++i) {
				portid = qconf->tx_port_id[i];
				if (qconf->tx_mbufs[portid].len == 0)
					continue;
				send_burst(qconf,
					qconf->tx_mbufs[portid].len,
					portid);
				qconf->tx_mbufs[portid].len = 0;
			}

			prev_tsc = cur_tsc;
		}

		/*
		 * Read packet from RX queues
		 */
		for (i = 0; i < qconf->n_rx_queue; ++i) {
			portid = qconf->rx_queue_list[i].port_id;
			queueid = qconf->rx_queue_list[i].queue_id;
			nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
				MAX_PKT_BURST);
			if (nb_rx == 0)
				continue;

#if defined RTE_ARCH_X86 || defined RTE_MACHINE_CPUFLAG_NEON \
			 || defined RTE_ARCH_PPC_64
			l3fwd_lpm_send_packets(nb_rx, pkts_burst,
						portid, qconf);
#else
			l3fwd_lpm_no_opt_send_packets(nb_rx, pkts_burst,
							portid, qconf);
#endif /* X86 */
		}
	}

	return 0;
}

void
setup_lpm(const int socketid)
{
	struct rte_lpm6_config config;
	struct rte_lpm_config config_ipv4;
	unsigned i;
	int ret;
	char s[64];

	/* create the LPM table */
	config_ipv4.max_rules = IPV4_L3FWD_LPM_MAX_RULES;
	config_ipv4.number_tbl8s = IPV4_L3FWD_LPM_NUMBER_TBL8S;
	config_ipv4.flags = 0;
	snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid);
	ipv4_l3fwd_lpm_lookup_struct[socketid] =
			rte_lpm_create(s, socketid, &config_ipv4);
	if (ipv4_l3fwd_lpm_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE,
			"Unable to create the l3fwd LPM table on socket %d\n",
			socketid);

	/* populate the LPM table */
	for (i = 0; i < IPV4_L3FWD_LPM_NUM_ROUTES; i++) {

		/* skip unused ports */
		if ((1 << ipv4_l3fwd_lpm_route_array[i].if_out &
				enabled_port_mask) == 0)
			continue;

		ret = rte_lpm_add(ipv4_l3fwd_lpm_lookup_struct[socketid],
			ipv4_l3fwd_lpm_route_array[i].ip,
			ipv4_l3fwd_lpm_route_array[i].depth,
			ipv4_l3fwd_lpm_route_array[i].if_out);

		if (ret < 0) {
			rte_exit(EXIT_FAILURE,
				"Unable to add entry %u to the l3fwd LPM table on socket %d\n",
				i, socketid);
		}

		printf("LPM: Adding route 0x%08x / %d (%d)\n",
			(unsigned)ipv4_l3fwd_lpm_route_array[i].ip,
			ipv4_l3fwd_lpm_route_array[i].depth,
			ipv4_l3fwd_lpm_route_array[i].if_out);
	}

	/* create the LPM6 table */
	snprintf(s, sizeof(s), "IPV6_L3FWD_LPM_%d", socketid);

	config.max_rules = IPV6_L3FWD_LPM_MAX_RULES;
	config.number_tbl8s = IPV6_L3FWD_LPM_NUMBER_TBL8S;
	config.flags = 0;
	ipv6_l3fwd_lpm_lookup_struct[socketid] = rte_lpm6_create(s, socketid,
				&config);
	if (ipv6_l3fwd_lpm_lookup_struct[socketid] == NULL)
		rte_exit(EXIT_FAILURE,
			"Unable to create the l3fwd LPM table on socket %d\n",
			socketid);

	/* populate the LPM table */
	for (i = 0; i < IPV6_L3FWD_LPM_NUM_ROUTES; i++) {

		/* skip unused ports */
		if ((1 << ipv6_l3fwd_lpm_route_array[i].if_out &
				enabled_port_mask) == 0)
			continue;

		ret = rte_lpm6_add(ipv6_l3fwd_lpm_lookup_struct[socketid],
			ipv6_l3fwd_lpm_route_array[i].ip,
			ipv6_l3fwd_lpm_route_array[i].depth,
			ipv6_l3fwd_lpm_route_array[i].if_out);

		if (ret < 0) {
			rte_exit(EXIT_FAILURE,
				"Unable to add entry %u to the l3fwd LPM table on socket %d\n",
				i, socketid);
		}

		printf("LPM: Adding route %s / %d (%d)\n",
			"IPV6",
			ipv6_l3fwd_lpm_route_array[i].depth,
			ipv6_l3fwd_lpm_route_array[i].if_out);
	}
}

int
lpm_check_ptype(int portid)
{
	int i, ret;
	int ptype_l3_ipv4 = 0, ptype_l3_ipv6 = 0;
	uint32_t ptype_mask = RTE_PTYPE_L3_MASK;

	ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0);
	if (ret <= 0)
		return 0;

	uint32_t ptypes[ret];

	ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret);
	for (i = 0; i < ret; ++i) {
		if (ptypes[i] & RTE_PTYPE_L3_IPV4)
			ptype_l3_ipv4 = 1;
		if (ptypes[i] & RTE_PTYPE_L3_IPV6)
			ptype_l3_ipv6 = 1;
	}

	if (ptype_l3_ipv4 == 0)
		printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid);

	if (ptype_l3_ipv6 == 0)
		printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid);

	if (ptype_l3_ipv4 && ptype_l3_ipv6)
		return 1;

	return 0;

}

static inline void
lpm_parse_ptype(struct rte_mbuf *m)
{
	struct ether_hdr *eth_hdr;
	uint32_t packet_type = RTE_PTYPE_UNKNOWN;
	uint16_t ether_type;

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
	ether_type = eth_hdr->ether_type;
	if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4))
		packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
	else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6))
		packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;

	m->packet_type = packet_type;
}

uint16_t
lpm_cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused,
		   struct rte_mbuf *pkts[], uint16_t nb_pkts,
		   uint16_t max_pkts __rte_unused,
		   void *user_param __rte_unused)
{
	unsigned i;

	for (i = 0; i < nb_pkts; ++i)
		lpm_parse_ptype(pkts[i]);

	return nb_pkts;
}

/* Return ipv4/ipv6 lpm fwd lookup struct. */
void *
lpm_get_ipv4_l3fwd_lookup_struct(const int socketid)
{
	return ipv4_l3fwd_lpm_lookup_struct[socketid];
}

void *
lpm_get_ipv6_l3fwd_lookup_struct(const int socketid)
{
	return ipv6_l3fwd_lpm_lookup_struct[socketid];
}