-
Notifications
You must be signed in to change notification settings - Fork 2
/
main.c
2222 lines (1879 loc) · 54.7 KB
/
main.c
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
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2010-2018 Intel Corporation
*/
#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 <unistd.h>
#include <signal.h>
#include <rte_common.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_malloc.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_eal.h>
#include <rte_launch.h>
#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_lcore.h>
#include <rte_per_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
#include <rte_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_string_fns.h>
#include <rte_timer.h>
#include <rte_power.h>
#include <rte_spinlock.h>
#include <rte_power_empty_poll.h>
#include "perf_core.h"
#include "main.h"
#define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1
#define MAX_PKT_BURST 32
#define MIN_ZERO_POLL_COUNT 10
/* 100 ms interval */
#define TIMER_NUMBER_PER_SECOND 10
/* (10ms) */
#define INTERVALS_PER_SECOND 100
/* 100000 us */
#define SCALING_PERIOD (1000000/TIMER_NUMBER_PER_SECOND)
#define SCALING_DOWN_TIME_RATIO_THRESHOLD 0.25
#define APP_LOOKUP_EXACT_MATCH 0
#define APP_LOOKUP_LPM 1
#define DO_RFC_1812_CHECKS
#ifndef APP_LOOKUP_METHOD
#define APP_LOOKUP_METHOD APP_LOOKUP_LPM
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#include <rte_hash.h>
#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
#include <rte_lpm.h>
#else
#error "APP_LOOKUP_METHOD set to incorrect value"
#endif
#ifndef IPv6_BYTES
#define IPv6_BYTES_FMT "%02x%02x:%02x%02x:%02x%02x:%02x%02x:"\
"%02x%02x:%02x%02x:%02x%02x:%02x%02x"
#define IPv6_BYTES(addr) \
addr[0], addr[1], addr[2], addr[3], \
addr[4], addr[5], addr[6], addr[7], \
addr[8], addr[9], addr[10], addr[11],\
addr[12], addr[13],addr[14], addr[15]
#endif
#define MAX_JUMBO_PKT_LEN 9600
#define IPV6_ADDR_LEN 16
#define MEMPOOL_CACHE_SIZE 256
/*
* This expression is used to calculate the number of mbufs needed depending on
* user input, taking into account memory for rx and tx hardware rings, cache
* per lcore and mtable per port per lcore. RTE_MAX is used to ensure that
* NB_MBUF never goes below a minimum value of 8192.
*/
#define NB_MBUF RTE_MAX ( \
(nb_ports*nb_rx_queue*nb_rxd + \
nb_ports*nb_lcores*MAX_PKT_BURST + \
nb_ports*n_tx_queue*nb_txd + \
nb_lcores*MEMPOOL_CACHE_SIZE), \
(unsigned)8192)
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
#define NB_SOCKETS 8
/* Configure how many packets ahead to prefetch, when reading packets */
#define PREFETCH_OFFSET 3
/*
* Configurable number of RX/TX ring descriptors
*/
#define RTE_TEST_RX_DESC_DEFAULT 1024
#define RTE_TEST_TX_DESC_DEFAULT 1024
/*
* These two thresholds were decided on by running the training algorithm on
* a 2.5GHz Xeon. These defaults can be overridden by supplying non-zero values
* for the med_threshold and high_threshold parameters on the command line.
*/
#define EMPTY_POLL_MED_THRESHOLD 350000UL
#define EMPTY_POLL_HGH_THRESHOLD 580000UL
static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;
/* ethernet addresses of ports */
static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
/* ethernet addresses of ports */
static rte_spinlock_t locks[RTE_MAX_ETHPORTS];
/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
/* Ports set in promiscuous mode off by default. */
static int promiscuous_on = 0;
/* NUMA is enabled by default. */
static int numa_on = 1;
/* emptypoll is disabled by default. */
static bool empty_poll_on;
static bool empty_poll_train;
volatile bool empty_poll_stop;
static struct ep_params *ep_params;
static struct ep_policy policy;
static long ep_med_edpi, ep_hgh_edpi;
static int parse_ptype; /**< Parse packet type using rx callback, and */
/**< disabled by default */
enum freq_scale_hint_t
{
FREQ_LOWER = -1,
FREQ_CURRENT = 0,
FREQ_HIGHER = 1,
FREQ_HIGHEST = 2
};
struct lcore_rx_queue {
uint16_t port_id;
uint8_t queue_id;
enum freq_scale_hint_t freq_up_hint;
uint32_t zero_rx_packet_count;
uint32_t idle_hint;
} __rte_cache_aligned;
#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS
#define MAX_RX_QUEUE_PER_PORT 128
#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16
struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
static struct lcore_params lcore_params_array_default[] = {
{0, 0, 2},
{0, 1, 2},
{0, 2, 2},
{1, 0, 2},
{1, 1, 2},
{1, 2, 2},
{2, 0, 2},
{3, 0, 3},
{3, 1, 3},
};
struct lcore_params *lcore_params = lcore_params_array_default;
uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
sizeof(lcore_params_array_default[0]);
static struct rte_eth_conf port_conf = {
.rxmode = {
.mq_mode = ETH_MQ_RX_RSS,
.max_rx_pkt_len = ETHER_MAX_LEN,
.split_hdr_size = 0,
.offloads = DEV_RX_OFFLOAD_CHECKSUM,
},
.rx_adv_conf = {
.rss_conf = {
.rss_key = NULL,
.rss_hf = ETH_RSS_UDP,
},
},
.txmode = {
.mq_mode = ETH_MQ_TX_NONE,
},
.intr_conf = {
.rxq = 1,
},
};
static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#ifdef RTE_ARCH_X86
#include <rte_hash_crc.h>
#define DEFAULT_HASH_FUNC rte_hash_crc
#else
#include <rte_jhash.h>
#define DEFAULT_HASH_FUNC rte_jhash
#endif
struct ipv4_5tuple {
uint32_t ip_dst;
uint32_t ip_src;
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
} __attribute__((__packed__));
struct ipv6_5tuple {
uint8_t ip_dst[IPV6_ADDR_LEN];
uint8_t ip_src[IPV6_ADDR_LEN];
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
} __attribute__((__packed__));
struct ipv4_l3fwd_route {
struct ipv4_5tuple key;
uint8_t if_out;
};
struct ipv6_l3fwd_route {
struct ipv6_5tuple key;
uint8_t if_out;
};
static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
{{IPv4(100,10,0,1), IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0},
{{IPv4(100,20,0,2), IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1},
{{IPv4(100,30,0,3), IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2},
{{IPv4(100,40,0,4), IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3},
};
static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = {
{
{
{0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
{0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x02, 0x1e, 0x67, 0xff, 0xfe, 0x0d, 0xb6, 0x0a},
1, 10, IPPROTO_UDP
}, 4
},
};
typedef struct rte_hash lookup_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS];
#define L3FWD_HASH_ENTRIES 1024
#define IPV4_L3FWD_NUM_ROUTES \
(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))
#define IPV6_L3FWD_NUM_ROUTES \
(sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0]))
static uint16_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
static uint16_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
struct ipv4_l3fwd_route {
uint32_t ip;
uint8_t depth;
uint8_t if_out;
};
static struct ipv4_l3fwd_route ipv4_l3fwd_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},
};
#define IPV4_L3FWD_NUM_ROUTES \
(sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))
#define IPV4_L3FWD_LPM_MAX_RULES 1024
typedef struct rte_lpm lookup_struct_t;
static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS];
#endif
struct lcore_conf {
uint16_t n_rx_queue;
struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
uint16_t n_tx_port;
uint16_t tx_port_id[RTE_MAX_ETHPORTS];
uint16_t tx_queue_id[RTE_MAX_ETHPORTS];
struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS];
lookup_struct_t * ipv4_lookup_struct;
lookup_struct_t * ipv6_lookup_struct;
} __rte_cache_aligned;
struct lcore_stats {
/* total sleep time in ms since last frequency scaling down */
uint32_t sleep_time;
/* number of long sleep recently */
uint32_t nb_long_sleep;
/* freq. scaling up trend */
uint32_t trend;
/* total packet processed recently */
uint64_t nb_rx_processed;
/* total iterations looped recently */
uint64_t nb_iteration_looped;
uint32_t padding[9];
} __rte_cache_aligned;
static struct lcore_conf lcore_conf[RTE_MAX_LCORE] __rte_cache_aligned;
static struct lcore_stats stats[RTE_MAX_LCORE] __rte_cache_aligned;
static struct rte_timer power_timers[RTE_MAX_LCORE];
static inline uint32_t power_idle_heuristic(uint32_t zero_rx_packet_count);
static inline enum freq_scale_hint_t power_freq_scaleup_heuristic( \
unsigned int lcore_id, uint16_t port_id, uint16_t queue_id);
/*
* These defaults are using the max frequency index (1), a medium index (9)
* and a typical low frequency index (14). These can be adjusted to use
* different indexes using the relevant command line parameters.
*/
static uint8_t freq_tlb[] = {14, 9, 1};
static int is_done(void)
{
return empty_poll_stop;
}
/* exit signal handler */
static void
signal_exit_now(int sigtype)
{
unsigned lcore_id;
unsigned int portid;
int ret;
if (sigtype == SIGINT) {
if (empty_poll_on)
empty_poll_stop = true;
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
if (rte_lcore_is_enabled(lcore_id) == 0)
continue;
/* init power management library */
ret = rte_power_exit(lcore_id);
if (ret)
rte_exit(EXIT_FAILURE, "Power management "
"library de-initialization failed on "
"core%u\n", lcore_id);
}
if (!empty_poll_on) {
RTE_ETH_FOREACH_DEV(portid) {
if ((enabled_port_mask & (1 << portid)) == 0)
continue;
rte_eth_dev_stop(portid);
rte_eth_dev_close(portid);
}
}
}
if (!empty_poll_on)
rte_exit(EXIT_SUCCESS, "User forced exit\n");
}
/* Freqency scale down timer callback */
static void
power_timer_cb(__attribute__((unused)) struct rte_timer *tim,
__attribute__((unused)) void *arg)
{
uint64_t hz;
float sleep_time_ratio;
unsigned lcore_id = rte_lcore_id();
/* accumulate total execution time in us when callback is invoked */
sleep_time_ratio = (float)(stats[lcore_id].sleep_time) /
(float)SCALING_PERIOD;
/**
* check whether need to scale down frequency a step if it sleep a lot.
*/
if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD) {
if (rte_power_freq_down)
rte_power_freq_down(lcore_id);
}
else if ( (unsigned)(stats[lcore_id].nb_rx_processed /
stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST) {
/**
* scale down a step if average packet per iteration less
* than expectation.
*/
if (rte_power_freq_down)
rte_power_freq_down(lcore_id);
}
/**
* initialize another timer according to current frequency to ensure
* timer interval is relatively fixed.
*/
hz = rte_get_timer_hz();
rte_timer_reset(&power_timers[lcore_id], hz/TIMER_NUMBER_PER_SECOND,
SINGLE, lcore_id, power_timer_cb, NULL);
stats[lcore_id].nb_rx_processed = 0;
stats[lcore_id].nb_iteration_looped = 0;
stats[lcore_id].sleep_time = 0;
}
/* Enqueue a single packet, and send burst if queue is filled */
static inline int
send_single_packet(struct rte_mbuf *m, uint16_t port)
{
uint32_t lcore_id;
struct lcore_conf *qconf;
lcore_id = rte_lcore_id();
qconf = &lcore_conf[lcore_id];
rte_eth_tx_buffer(port, qconf->tx_queue_id[port],
qconf->tx_buffer[port], m);
return 0;
}
#ifdef DO_RFC_1812_CHECKS
static inline int
is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len)
{
/* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */
/*
* 1. The packet length reported by the Link Layer must be large
* enough to hold the minimum length legal IP datagram (20 bytes).
*/
if (link_len < sizeof(struct ipv4_hdr))
return -1;
/* 2. The IP checksum must be correct. */
/* this is checked in H/W */
/*
* 3. The IP version number must be 4. If the version number is not 4
* then the packet may be another version of IP, such as IPng or
* ST-II.
*/
if (((pkt->version_ihl) >> 4) != 4)
return -3;
/*
* 4. The IP header length field must be large enough to hold the
* minimum length legal IP datagram (20 bytes = 5 words).
*/
if ((pkt->version_ihl & 0xf) < 5)
return -4;
/*
* 5. The IP total length field must be large enough to hold the IP
* datagram header, whose length is specified in the IP header length
* field.
*/
if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr))
return -5;
return 0;
}
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static void
print_ipv4_key(struct ipv4_5tuple key)
{
printf("IP dst = %08x, IP src = %08x, port dst = %d, port src = %d, "
"proto = %d\n", (unsigned)key.ip_dst, (unsigned)key.ip_src,
key.port_dst, key.port_src, key.proto);
}
static void
print_ipv6_key(struct ipv6_5tuple key)
{
printf( "IP dst = " IPv6_BYTES_FMT ", IP src = " IPv6_BYTES_FMT ", "
"port dst = %d, port src = %d, proto = %d\n",
IPv6_BYTES(key.ip_dst), IPv6_BYTES(key.ip_src),
key.port_dst, key.port_src, key.proto);
}
static inline uint16_t
get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid,
lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
struct ipv4_5tuple key;
struct tcp_hdr *tcp;
struct udp_hdr *udp;
int ret = 0;
key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr);
key.ip_src = rte_be_to_cpu_32(ipv4_hdr->src_addr);
key.proto = ipv4_hdr->next_proto_id;
switch (ipv4_hdr->next_proto_id) {
case IPPROTO_TCP:
tcp = (struct tcp_hdr *)((unsigned char *)ipv4_hdr +
sizeof(struct ipv4_hdr));
key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
key.port_src = rte_be_to_cpu_16(tcp->src_port);
break;
case IPPROTO_UDP:
udp = (struct udp_hdr *)((unsigned char *)ipv4_hdr +
sizeof(struct ipv4_hdr));
key.port_dst = rte_be_to_cpu_16(udp->dst_port);
key.port_src = rte_be_to_cpu_16(udp->src_port);
break;
default:
key.port_dst = 0;
key.port_src = 0;
break;
}
/* Find destination port */
ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
return ((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]);
}
static inline uint16_t
get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint16_t portid,
lookup_struct_t *ipv6_l3fwd_lookup_struct)
{
struct ipv6_5tuple key;
struct tcp_hdr *tcp;
struct udp_hdr *udp;
int ret = 0;
memcpy(key.ip_dst, ipv6_hdr->dst_addr, IPV6_ADDR_LEN);
memcpy(key.ip_src, ipv6_hdr->src_addr, IPV6_ADDR_LEN);
key.proto = ipv6_hdr->proto;
switch (ipv6_hdr->proto) {
case IPPROTO_TCP:
tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr +
sizeof(struct ipv6_hdr));
key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
key.port_src = rte_be_to_cpu_16(tcp->src_port);
break;
case IPPROTO_UDP:
udp = (struct udp_hdr *)((unsigned char *) ipv6_hdr +
sizeof(struct ipv6_hdr));
key.port_dst = rte_be_to_cpu_16(udp->dst_port);
key.port_src = rte_be_to_cpu_16(udp->src_port);
break;
default:
key.port_dst = 0;
key.port_src = 0;
break;
}
/* Find destination port */
ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
return ((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]);
}
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
static inline uint16_t
get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid,
lookup_struct_t *ipv4_l3fwd_lookup_struct)
{
uint32_t next_hop;
return ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)?
next_hop : portid);
}
#endif
static inline void
parse_ptype_one(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;
}
static uint16_t
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 int i;
for (i = 0; i < nb_pkts; ++i)
parse_ptype_one(pkts[i]);
return nb_pkts;
}
static int
add_cb_parse_ptype(uint16_t portid, uint16_t queueid)
{
printf("Port %d: softly parse packet type info\n", portid);
if (rte_eth_add_rx_callback(portid, queueid, cb_parse_ptype, NULL))
return 0;
printf("Failed to add rx callback: port=%d\n", portid);
return -1;
}
static inline void
l3fwd_simple_forward(struct rte_mbuf *m, uint16_t portid,
struct lcore_conf *qconf)
{
struct ether_hdr *eth_hdr;
struct ipv4_hdr *ipv4_hdr;
void *d_addr_bytes;
uint16_t dst_port;
eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) {
/* Handle IPv4 headers.*/
ipv4_hdr =
rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *,
sizeof(struct ether_hdr));
#ifdef DO_RFC_1812_CHECKS
/* Check to make sure the packet is valid (RFC1812) */
if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) {
rte_pktmbuf_free(m);
return;
}
#endif
dst_port = get_ipv4_dst_port(ipv4_hdr, portid,
qconf->ipv4_lookup_struct);
if (dst_port >= RTE_MAX_ETHPORTS ||
(enabled_port_mask & 1 << dst_port) == 0)
dst_port = portid;
/* 02:00:00:00:00:xx */
d_addr_bytes = ð_hdr->d_addr.addr_bytes[0];
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
#ifdef DO_RFC_1812_CHECKS
/* Update time to live and header checksum */
--(ipv4_hdr->time_to_live);
++(ipv4_hdr->hdr_checksum);
#endif
/* src addr */
ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr);
send_single_packet(m, dst_port);
} else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) {
/* Handle IPv6 headers.*/
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
struct ipv6_hdr *ipv6_hdr;
ipv6_hdr =
rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *,
sizeof(struct ether_hdr));
dst_port = get_ipv6_dst_port(ipv6_hdr, portid,
qconf->ipv6_lookup_struct);
if (dst_port >= RTE_MAX_ETHPORTS ||
(enabled_port_mask & 1 << dst_port) == 0)
dst_port = portid;
/* 02:00:00:00:00:xx */
d_addr_bytes = ð_hdr->d_addr.addr_bytes[0];
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
/* src addr */
ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr);
send_single_packet(m, dst_port);
#else
/* We don't currently handle IPv6 packets in LPM mode. */
rte_pktmbuf_free(m);
#endif
} else
rte_pktmbuf_free(m);
}
#define MINIMUM_SLEEP_TIME 1
#define SUSPEND_THRESHOLD 300
static inline uint32_t
power_idle_heuristic(uint32_t zero_rx_packet_count)
{
/* If zero count is less than 100, sleep 1us */
if (zero_rx_packet_count < SUSPEND_THRESHOLD)
return MINIMUM_SLEEP_TIME;
/* If zero count is less than 1000, sleep 100 us which is the
minimum latency switching from C3/C6 to C0
*/
else
return SUSPEND_THRESHOLD;
}
static inline enum freq_scale_hint_t
power_freq_scaleup_heuristic(unsigned lcore_id,
uint16_t port_id,
uint16_t queue_id)
{
uint32_t rxq_count = rte_eth_rx_queue_count(port_id, queue_id);
/**
* HW Rx queue size is 128 by default, Rx burst read at maximum 32 entries
* per iteration
*/
#define FREQ_GEAR1_RX_PACKET_THRESHOLD MAX_PKT_BURST
#define FREQ_GEAR2_RX_PACKET_THRESHOLD (MAX_PKT_BURST*2)
#define FREQ_GEAR3_RX_PACKET_THRESHOLD (MAX_PKT_BURST*3)
#define FREQ_UP_TREND1_ACC 1
#define FREQ_UP_TREND2_ACC 100
#define FREQ_UP_THRESHOLD 10000
if (likely(rxq_count > FREQ_GEAR3_RX_PACKET_THRESHOLD)) {
stats[lcore_id].trend = 0;
return FREQ_HIGHEST;
} else if (likely(rxq_count > FREQ_GEAR2_RX_PACKET_THRESHOLD))
stats[lcore_id].trend += FREQ_UP_TREND2_ACC;
else if (likely(rxq_count > FREQ_GEAR1_RX_PACKET_THRESHOLD))
stats[lcore_id].trend += FREQ_UP_TREND1_ACC;
if (likely(stats[lcore_id].trend > FREQ_UP_THRESHOLD)) {
stats[lcore_id].trend = 0;
return FREQ_HIGHER;
}
return FREQ_CURRENT;
}
/**
* force polling thread sleep until one-shot rx interrupt triggers
* @param port_id
* Port id.
* @param queue_id
* Rx queue id.
* @return
* 0 on success
*/
static int
sleep_until_rx_interrupt(int num)
{
struct rte_epoll_event event[num];
int n, i;
uint16_t port_id;
uint8_t queue_id;
void *data;
RTE_LOG(INFO, L3FWD_POWER,
"lcore %u sleeps until interrupt triggers\n",
rte_lcore_id());
n = rte_epoll_wait(RTE_EPOLL_PER_THREAD, event, num, -1);
for (i = 0; i < n; i++) {
data = event[i].epdata.data;
port_id = ((uintptr_t)data) >> CHAR_BIT;
queue_id = ((uintptr_t)data) &
RTE_LEN2MASK(CHAR_BIT, uint8_t);
rte_spinlock_lock(&(locks[port_id]));
rte_eth_dev_rx_intr_disable(port_id, queue_id);
rte_spinlock_unlock(&(locks[port_id]));
RTE_LOG(INFO, L3FWD_POWER,
"lcore %u is waked up from rx interrupt on"
" port %d queue %d\n",
rte_lcore_id(), port_id, queue_id);
}
return 0;
}
static void turn_on_intr(struct lcore_conf *qconf)
{
int i;
struct lcore_rx_queue *rx_queue;
uint8_t queue_id;
uint16_t port_id;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
port_id = rx_queue->port_id;
queue_id = rx_queue->queue_id;
rte_spinlock_lock(&(locks[port_id]));
rte_eth_dev_rx_intr_enable(port_id, queue_id);
rte_spinlock_unlock(&(locks[port_id]));
}
}
static int event_register(struct lcore_conf *qconf)
{
struct lcore_rx_queue *rx_queue;
uint8_t queueid;
uint16_t portid;
uint32_t data;
int ret;
int i;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
portid = rx_queue->port_id;
queueid = rx_queue->queue_id;
data = portid << CHAR_BIT | queueid;
ret = rte_eth_dev_rx_intr_ctl_q(portid, queueid,
RTE_EPOLL_PER_THREAD,
RTE_INTR_EVENT_ADD,
(void *)((uintptr_t)data));
if (ret)
return ret;
}
return 0;
}
/* main processing loop */
static int
main_empty_poll_loop(__attribute__((unused)) void *dummy)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
unsigned int lcore_id;
uint64_t prev_tsc, diff_tsc, cur_tsc;
int i, j, nb_rx;
uint8_t queueid;
uint16_t portid;
struct lcore_conf *qconf;
struct lcore_rx_queue *rx_queue;
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_POWER, "lcore %u has nothing to do\n",
lcore_id);
return 0;
}
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_POWER, " -- lcoreid=%u portid=%u "
"rxqueueid=%hhu\n", lcore_id, portid, queueid);
}
while (!is_done()) {
stats[lcore_id].nb_iteration_looped++;
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];
rte_eth_tx_buffer_flush(portid,
qconf->tx_queue_id[portid],
qconf->tx_buffer[portid]);
}
prev_tsc = cur_tsc;
}
/*
* Read packet from RX queues
*/
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
rx_queue->idle_hint = 0;
portid = rx_queue->port_id;
queueid = rx_queue->queue_id;
nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
MAX_PKT_BURST);
stats[lcore_id].nb_rx_processed += nb_rx;
if (nb_rx == 0) {
rte_power_empty_poll_stat_update(lcore_id);
continue;
} else {
rte_power_poll_stat_update(lcore_id, nb_rx);
}
/* Prefetch first packets */
for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) {
rte_prefetch0(rte_pktmbuf_mtod(
pkts_burst[j], void *));
}
/* Prefetch and forward already prefetched packets */
for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[
j + PREFETCH_OFFSET],
void *));
l3fwd_simple_forward(pkts_burst[j], portid,
qconf);
}
/* Forward remaining prefetched packets */
for (; j < nb_rx; j++) {
l3fwd_simple_forward(pkts_burst[j], portid,
qconf);
}
}
}
return 0;
}
/* main processing loop */
static int
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, tim_res_tsc, hz;
uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power;
int i, j, nb_rx;
uint8_t queueid;
uint16_t portid;
struct lcore_conf *qconf;
struct lcore_rx_queue *rx_queue;
enum freq_scale_hint_t lcore_scaleup_hint;
uint32_t lcore_rx_idle_count = 0;
uint32_t lcore_idle_hint = 0;
int intr_en = 0;
const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
prev_tsc = 0;
hz = rte_get_timer_hz();
tim_res_tsc = hz/TIMER_NUMBER_PER_SECOND;
lcore_id = rte_lcore_id();