aboutsummaryrefslogtreecommitdiffstats
path: root/lib/librte_eal/common/eal_common_proc.c
blob: 707d8ab30a78c2a9f6d94bee74d595777ac851ae (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2016-2018 Intel Corporation
 */

#include <dirent.h>
#include <errno.h>
#include <fcntl.h>
#include <fnmatch.h>
#include <inttypes.h>
#include <libgen.h>
#include <limits.h>
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/file.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <unistd.h>

#include <rte_common.h>
#include <rte_cycles.h>
#include <rte_eal.h>
#include <rte_errno.h>
#include <rte_lcore.h>
#include <rte_log.h>
#include <rte_tailq.h>

#include "eal_private.h"
#include "eal_filesystem.h"
#include "eal_internal_cfg.h"

static int mp_fd = -1;
static char mp_filter[PATH_MAX];   /* Filter for secondary process sockets */
static char mp_dir_path[PATH_MAX]; /* The directory path for all mp sockets */
static pthread_mutex_t mp_mutex_action = PTHREAD_MUTEX_INITIALIZER;

struct action_entry {
	TAILQ_ENTRY(action_entry) next;
	char action_name[RTE_MP_MAX_NAME_LEN];
	rte_mp_t action;
};

/** Double linked list of actions. */
TAILQ_HEAD(action_entry_list, action_entry);

static struct action_entry_list action_entry_list =
	TAILQ_HEAD_INITIALIZER(action_entry_list);

enum mp_type {
	MP_MSG, /* Share message with peers, will not block */
	MP_REQ, /* Request for information, Will block for a reply */
	MP_REP, /* Response to previously-received request */
	MP_IGN, /* Response telling requester to ignore this response */
};

struct mp_msg_internal {
	int type;
	struct rte_mp_msg msg;
};

struct async_request_param {
	rte_mp_async_reply_t clb;
	struct rte_mp_reply user_reply;
	struct timespec end;
	int n_responses_processed;
};

struct pending_request {
	TAILQ_ENTRY(pending_request) next;
	enum {
		REQUEST_TYPE_SYNC,
		REQUEST_TYPE_ASYNC
	} type;
	char dst[PATH_MAX];
	struct rte_mp_msg *request;
	struct rte_mp_msg *reply;
	int reply_received;
	RTE_STD_C11
	union {
		struct {
			struct async_request_param *param;
		} async;
		struct {
			pthread_cond_t cond;
		} sync;
	};
};

TAILQ_HEAD(pending_request_list, pending_request);

static struct {
	struct pending_request_list requests;
	pthread_mutex_t lock;
	pthread_cond_t async_cond;
} pending_requests = {
	.requests = TAILQ_HEAD_INITIALIZER(pending_requests.requests),
	.lock = PTHREAD_MUTEX_INITIALIZER,
	.async_cond = PTHREAD_COND_INITIALIZER
	/**< used in async requests only */
};

/* forward declarations */
static int
mp_send(struct rte_mp_msg *msg, const char *peer, int type);


static struct pending_request *
find_pending_request(const char *dst, const char *act_name)
{
	struct pending_request *r;

	TAILQ_FOREACH(r, &pending_requests.requests, next) {
		if (!strcmp(r->dst, dst) &&
		    !strcmp(r->request->name, act_name))
			break;
	}

	return r;
}

static void
create_socket_path(const char *name, char *buf, int len)
{
	const char *prefix = eal_mp_socket_path();

	if (strlen(name) > 0)
		snprintf(buf, len, "%s_%s", prefix, name);
	else
		strlcpy(buf, prefix, len);
}

int
rte_eal_primary_proc_alive(const char *config_file_path)
{
	int config_fd;

	if (config_file_path)
		config_fd = open(config_file_path, O_RDONLY);
	else {
		const char *path;

		path = eal_runtime_config_path();
		config_fd = open(path, O_RDONLY);
	}
	if (config_fd < 0)
		return 0;

	int ret = lockf(config_fd, F_TEST, 0);
	close(config_fd);

	return !!ret;
}

static struct action_entry *
find_action_entry_by_name(const char *name)
{
	struct action_entry *entry;

	TAILQ_FOREACH(entry, &action_entry_list, next) {
		if (strncmp(entry->action_name, name, RTE_MP_MAX_NAME_LEN) == 0)
			break;
	}

	return entry;
}

static int
validate_action_name(const char *name)
{
	if (name == NULL) {
		RTE_LOG(ERR, EAL, "Action name cannot be NULL\n");
		rte_errno = EINVAL;
		return -1;
	}
	if (strnlen(name, RTE_MP_MAX_NAME_LEN) == 0) {
		RTE_LOG(ERR, EAL, "Length of action name is zero\n");
		rte_errno = EINVAL;
		return -1;
	}
	if (strnlen(name, RTE_MP_MAX_NAME_LEN) == RTE_MP_MAX_NAME_LEN) {
		rte_errno = E2BIG;
		return -1;
	}
	return 0;
}

int __rte_experimental
rte_mp_action_register(const char *name, rte_mp_t action)
{
	struct action_entry *entry;

	if (validate_action_name(name))
		return -1;

	entry = malloc(sizeof(struct action_entry));
	if (entry == NULL) {
		rte_errno = ENOMEM;
		return -1;
	}
	strlcpy(entry->action_name, name, sizeof(entry->action_name));
	entry->action = action;

	pthread_mutex_lock(&mp_mutex_action);
	if (find_action_entry_by_name(name) != NULL) {
		pthread_mutex_unlock(&mp_mutex_action);
		rte_errno = EEXIST;
		free(entry);
		return -1;
	}
	TAILQ_INSERT_TAIL(&action_entry_list, entry, next);
	pthread_mutex_unlock(&mp_mutex_action);
	return 0;
}

void __rte_experimental
rte_mp_action_unregister(const char *name)
{
	struct action_entry *entry;

	if (validate_action_name(name))
		return;

	pthread_mutex_lock(&mp_mutex_action);
	entry = find_action_entry_by_name(name);
	if (entry == NULL) {
		pthread_mutex_unlock(&mp_mutex_action);
		return;
	}
	TAILQ_REMOVE(&action_entry_list, entry, next);
	pthread_mutex_unlock(&mp_mutex_action);
	free(entry);
}

static int
read_msg(struct mp_msg_internal *m, struct sockaddr_un *s)
{
	int msglen;
	struct iovec iov;
	struct msghdr msgh;
	char control[CMSG_SPACE(sizeof(m->msg.fds))];
	struct cmsghdr *cmsg;
	int buflen = sizeof(*m) - sizeof(m->msg.fds);

	memset(&msgh, 0, sizeof(msgh));
	iov.iov_base = m;
	iov.iov_len  = buflen;

	msgh.msg_name = s;
	msgh.msg_namelen = sizeof(*s);
	msgh.msg_iov = &iov;
	msgh.msg_iovlen = 1;
	msgh.msg_control = control;
	msgh.msg_controllen = sizeof(control);

	msglen = recvmsg(mp_fd, &msgh, 0);
	if (msglen < 0) {
		RTE_LOG(ERR, EAL, "recvmsg failed, %s\n", strerror(errno));
		return -1;
	}

	if (msglen != buflen || (msgh.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
		RTE_LOG(ERR, EAL, "truncted msg\n");
		return -1;
	}

	/* read auxiliary FDs if any */
	for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL;
		cmsg = CMSG_NXTHDR(&msgh, cmsg)) {
		if ((cmsg->cmsg_level == SOL_SOCKET) &&
			(cmsg->cmsg_type == SCM_RIGHTS)) {
			memcpy(m->msg.fds, CMSG_DATA(cmsg), sizeof(m->msg.fds));
			break;
		}
	}

	return 0;
}

static void
process_msg(struct mp_msg_internal *m, struct sockaddr_un *s)
{
	struct pending_request *pending_req;
	struct action_entry *entry;
	struct rte_mp_msg *msg = &m->msg;
	rte_mp_t action = NULL;

	RTE_LOG(DEBUG, EAL, "msg: %s\n", msg->name);

	if (m->type == MP_REP || m->type == MP_IGN) {
		pthread_mutex_lock(&pending_requests.lock);
		pending_req = find_pending_request(s->sun_path, msg->name);
		if (pending_req) {
			memcpy(pending_req->reply, msg, sizeof(*msg));
			/* -1 indicates that we've been asked to ignore */
			pending_req->reply_received =
				m->type == MP_REP ? 1 : -1;

			if (pending_req->type == REQUEST_TYPE_SYNC)
				pthread_cond_signal(&pending_req->sync.cond);
			else if (pending_req->type == REQUEST_TYPE_ASYNC)
				pthread_cond_signal(
					&pending_requests.async_cond);
		} else
			RTE_LOG(ERR, EAL, "Drop mp reply: %s\n", msg->name);
		pthread_mutex_unlock(&pending_requests.lock);
		return;
	}

	pthread_mutex_lock(&mp_mutex_action);
	entry = find_action_entry_by_name(msg->name);
	if (entry != NULL)
		action = entry->action;
	pthread_mutex_unlock(&mp_mutex_action);

	if (!action) {
		if (m->type == MP_REQ && !internal_config.init_complete) {
			/* if this is a request, and init is not yet complete,
			 * and callback wasn't registered, we should tell the
			 * requester to ignore our existence because we're not
			 * yet ready to process this request.
			 */
			struct rte_mp_msg dummy;

			memset(&dummy, 0, sizeof(dummy));
			strlcpy(dummy.name, msg->name, sizeof(dummy.name));
			mp_send(&dummy, s->sun_path, MP_IGN);
		} else {
			RTE_LOG(ERR, EAL, "Cannot find action: %s\n",
				msg->name);
		}
	} else if (action(msg, s->sun_path) < 0) {
		RTE_LOG(ERR, EAL, "Fail to handle message: %s\n", msg->name);
	}
}

static void *
mp_handle(void *arg __rte_unused)
{
	struct mp_msg_internal msg;
	struct sockaddr_un sa;

	while (1) {
		if (read_msg(&msg, &sa) == 0)
			process_msg(&msg, &sa);
	}

	return NULL;
}

static int
timespec_cmp(const struct timespec *a, const struct timespec *b)
{
	if (a->tv_sec < b->tv_sec)
		return -1;
	if (a->tv_sec > b->tv_sec)
		return 1;
	if (a->tv_nsec < b->tv_nsec)
		return -1;
	if (a->tv_nsec > b->tv_nsec)
		return 1;
	return 0;
}

enum async_action {
	ACTION_NONE, /**< don't do anything */
	ACTION_FREE, /**< free the action entry, but don't trigger callback */
	ACTION_TRIGGER /**< trigger callback, then free action entry */
};

static enum async_action
process_async_request(struct pending_request *sr, const struct timespec *now)
{
	struct async_request_param *param;
	struct rte_mp_reply *reply;
	bool timeout, received, last_msg;

	param = sr->async.param;
	reply = &param->user_reply;

	/* did we timeout? */
	timeout = timespec_cmp(&param->end, now) <= 0;

	/* did we receive a response? */
	received = sr->reply_received != 0;

	/* if we didn't time out, and we didn't receive a response, ignore */
	if (!timeout && !received)
		return ACTION_NONE;

	/* if we received a response, adjust relevant data and copy mesasge. */
	if (sr->reply_received == 1 && sr->reply) {
		struct rte_mp_msg *msg, *user_msgs, *tmp;

		msg = sr->reply;
		user_msgs = reply->msgs;

		tmp = realloc(user_msgs, sizeof(*msg) *
				(reply->nb_received + 1));
		if (!tmp) {
			RTE_LOG(ERR, EAL, "Fail to alloc reply for request %s:%s\n",
				sr->dst, sr->request->name);
			/* this entry is going to be removed and its message
			 * dropped, but we don't want to leak memory, so
			 * continue.
			 */
		} else {
			user_msgs = tmp;
			reply->msgs = user_msgs;
			memcpy(&user_msgs[reply->nb_received],
					msg, sizeof(*msg));
			reply->nb_received++;
		}

		/* mark this request as processed */
		param->n_responses_processed++;
	} else if (sr->reply_received == -1) {
		/* we were asked to ignore this process */
		reply->nb_sent--;
	} else if (timeout) {
		/* count it as processed response, but don't increment
		 * nb_received.
		 */
		param->n_responses_processed++;
	}

	free(sr->reply);

	last_msg = param->n_responses_processed == reply->nb_sent;

	return last_msg ? ACTION_TRIGGER : ACTION_FREE;
}

static void
trigger_async_action(struct pending_request *sr)
{
	struct async_request_param *param;
	struct rte_mp_reply *reply;

	param = sr->async.param;
	reply = &param->user_reply;

	param->clb(sr->request, reply);

	/* clean up */
	free(sr->async.param->user_reply.msgs);
	free(sr->async.param);
	free(sr->request);
}

static struct pending_request *
check_trigger(struct timespec *ts)
{
	struct pending_request *next, *cur, *trigger = NULL;

	TAILQ_FOREACH_SAFE(cur, &pending_requests.requests, next, next) {
		enum async_action action;
		if (cur->type != REQUEST_TYPE_ASYNC)
			continue;

		action = process_async_request(cur, ts);
		if (action == ACTION_FREE) {
			TAILQ_REMOVE(&pending_requests.requests, cur, next);
			free(cur);
		} else if (action == ACTION_TRIGGER) {
			TAILQ_REMOVE(&pending_requests.requests, cur, next);
			trigger = cur;
			break;
		}
	}
	return trigger;
}

static void
wait_for_async_messages(void)
{
	struct pending_request *sr;
	struct timespec timeout;
	bool timedwait = false;
	bool nowait = false;
	int ret;

	/* scan through the list and see if there are any timeouts that
	 * are earlier than our current timeout.
	 */
	TAILQ_FOREACH(sr, &pending_requests.requests, next) {
		if (sr->type != REQUEST_TYPE_ASYNC)
			continue;
		if (!timedwait || timespec_cmp(&sr->async.param->end,
				&timeout) < 0) {
			memcpy(&timeout, &sr->async.param->end,
				sizeof(timeout));
			timedwait = true;
		}

		/* sometimes, we don't even wait */
		if (sr->reply_received) {
			nowait = true;
			break;
		}
	}

	if (nowait)
		return;

	do {
		ret = timedwait ?
			pthread_cond_timedwait(
				&pending_requests.async_cond,
				&pending_requests.lock,
				&timeout) :
			pthread_cond_wait(
				&pending_requests.async_cond,
				&pending_requests.lock);
	} while (ret != 0 && ret != ETIMEDOUT);

	/* we've been woken up or timed out */
}

static void *
async_reply_handle(void *arg __rte_unused)
{
	struct timeval now;
	struct timespec ts_now;
	while (1) {
		struct pending_request *trigger = NULL;

		pthread_mutex_lock(&pending_requests.lock);

		/* we exit this function holding the lock */
		wait_for_async_messages();

		if (gettimeofday(&now, NULL) < 0) {
			pthread_mutex_unlock(&pending_requests.lock);
			RTE_LOG(ERR, EAL, "Cannot get current time\n");
			break;
		}
		ts_now.tv_nsec = now.tv_usec * 1000;
		ts_now.tv_sec = now.tv_sec;

		do {
			trigger = check_trigger(&ts_now);
			/* unlock request list */
			pthread_mutex_unlock(&pending_requests.lock);

			if (trigger) {
				trigger_async_action(trigger);
				free(trigger);

				/* we've triggered a callback, but there may be
				 * more, so lock the list and check again.
				 */
				pthread_mutex_lock(&pending_requests.lock);
			}
		} while (trigger);
	}

	RTE_LOG(ERR, EAL, "ERROR: asynchronous requests disabled\n");

	return NULL;
}

static int
open_socket_fd(void)
{
	char peer_name[PATH_MAX] = {0};
	struct sockaddr_un un;

	if (rte_eal_process_type() == RTE_PROC_SECONDARY)
		snprintf(peer_name, sizeof(peer_name),
				"%d_%"PRIx64, getpid(), rte_rdtsc());

	mp_fd = socket(AF_UNIX, SOCK_DGRAM, 0);
	if (mp_fd < 0) {
		RTE_LOG(ERR, EAL, "failed to create unix socket\n");
		return -1;
	}

	memset(&un, 0, sizeof(un));
	un.sun_family = AF_UNIX;

	create_socket_path(peer_name, un.sun_path, sizeof(un.sun_path));

	unlink(un.sun_path); /* May still exist since last run */

	if (bind(mp_fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
		RTE_LOG(ERR, EAL, "failed to bind %s: %s\n",
			un.sun_path, strerror(errno));
		close(mp_fd);
		return -1;
	}

	RTE_LOG(INFO, EAL, "Multi-process socket %s\n", un.sun_path);
	return mp_fd;
}

static int
unlink_sockets(const char *filter)
{
	int dir_fd;
	DIR *mp_dir;
	struct dirent *ent;

	mp_dir = opendir(mp_dir_path);
	if (!mp_dir) {
		RTE_LOG(ERR, EAL, "Unable to open directory %s\n", mp_dir_path);
		return -1;
	}
	dir_fd = dirfd(mp_dir);

	while ((ent = readdir(mp_dir))) {
		if (fnmatch(filter, ent->d_name, 0) == 0)
			unlinkat(dir_fd, ent->d_name, 0);
	}

	closedir(mp_dir);
	return 0;
}

int
rte_mp_channel_init(void)
{
	char path[PATH_MAX];
	int dir_fd;
	pthread_t mp_handle_tid, async_reply_handle_tid;

	/* create filter path */
	create_socket_path("*", path, sizeof(path));
	strlcpy(mp_filter, basename(path), sizeof(mp_filter));

	/* path may have been modified, so recreate it */
	create_socket_path("*", path, sizeof(path));
	strlcpy(mp_dir_path, dirname(path), sizeof(mp_dir_path));

	/* lock the directory */
	dir_fd = open(mp_dir_path, O_RDONLY);
	if (dir_fd < 0) {
		RTE_LOG(ERR, EAL, "failed to open %s: %s\n",
			mp_dir_path, strerror(errno));
		return -1;
	}

	if (flock(dir_fd, LOCK_EX)) {
		RTE_LOG(ERR, EAL, "failed to lock %s: %s\n",
			mp_dir_path, strerror(errno));
		close(dir_fd);
		return -1;
	}

	if (rte_eal_process_type() == RTE_PROC_PRIMARY &&
			unlink_sockets(mp_filter)) {
		RTE_LOG(ERR, EAL, "failed to unlink mp sockets\n");
		close(dir_fd);
		return -1;
	}

	if (open_socket_fd() < 0) {
		close(dir_fd);
		return -1;
	}

	if (rte_ctrl_thread_create(&mp_handle_tid, "rte_mp_handle",
			NULL, mp_handle, NULL) < 0) {
		RTE_LOG(ERR, EAL, "failed to create mp thead: %s\n",
			strerror(errno));
		close(mp_fd);
		close(dir_fd);
		mp_fd = -1;
		return -1;
	}

	if (rte_ctrl_thread_create(&async_reply_handle_tid,
			"rte_mp_async", NULL,
			async_reply_handle, NULL) < 0) {
		RTE_LOG(ERR, EAL, "failed to create mp thead: %s\n",
			strerror(errno));
		close(mp_fd);
		close(dir_fd);
		mp_fd = -1;
		return -1;
	}

	/* unlock the directory */
	flock(dir_fd, LOCK_UN);
	close(dir_fd);

	return 0;
}

/**
 * Return -1, as fail to send message and it's caused by the local side.
 * Return 0, as fail to send message and it's caused by the remote side.
 * Return 1, as succeed to send message.
 *
 */
static int
send_msg(const char *dst_path, struct rte_mp_msg *msg, int type)
{
	int snd;
	struct iovec iov;
	struct msghdr msgh;
	struct cmsghdr *cmsg;
	struct sockaddr_un dst;
	struct mp_msg_internal m;
	int fd_size = msg->num_fds * sizeof(int);
	char control[CMSG_SPACE(fd_size)];

	m.type = type;
	memcpy(&m.msg, msg, sizeof(*msg));

	memset(&dst, 0, sizeof(dst));
	dst.sun_family = AF_UNIX;
	strlcpy(dst.sun_path, dst_path, sizeof(dst.sun_path));

	memset(&msgh, 0, sizeof(msgh));
	memset(control, 0, sizeof(control));

	iov.iov_base = &m;
	iov.iov_len = sizeof(m) - sizeof(msg->fds);

	msgh.msg_name = &dst;
	msgh.msg_namelen = sizeof(dst);
	msgh.msg_iov = &iov;
	msgh.msg_iovlen = 1;
	msgh.msg_control = control;
	msgh.msg_controllen = sizeof(control);

	cmsg = CMSG_FIRSTHDR(&msgh);
	cmsg->cmsg_len = CMSG_LEN(fd_size);
	cmsg->cmsg_level = SOL_SOCKET;
	cmsg->cmsg_type = SCM_RIGHTS;
	memcpy(CMSG_DATA(cmsg), msg->fds, fd_size);

	do {
		snd = sendmsg(mp_fd, &msgh, 0);
	} while (snd < 0 && errno == EINTR);

	if (snd < 0) {
		rte_errno = errno;
		/* Check if it caused by peer process exits */
		if (errno == ECONNREFUSED &&
				rte_eal_process_type() == RTE_PROC_PRIMARY) {
			unlink(dst_path);
			return 0;
		}
		if (errno == ENOBUFS) {
			RTE_LOG(ERR, EAL, "Peer cannot receive message %s\n",
				dst_path);
			return 0;
		}
		RTE_LOG(ERR, EAL, "failed to send to (%s) due to %s\n",
			dst_path, strerror(errno));
		return -1;
	}

	return 1;
}

static int
mp_send(struct rte_mp_msg *msg, const char *peer, int type)
{
	int dir_fd, ret = 0;
	DIR *mp_dir;
	struct dirent *ent;

	if (!peer && (rte_eal_process_type() == RTE_PROC_SECONDARY))
		peer = eal_mp_socket_path();

	if (peer) {
		if (send_msg(peer, msg, type) < 0)
			return -1;
		else
			return 0;
	}

	/* broadcast to all secondary processes */
	mp_dir = opendir(mp_dir_path);
	if (!mp_dir) {
		RTE_LOG(ERR, EAL, "Unable to open directory %s\n",
				mp_dir_path);
		rte_errno = errno;
		return -1;
	}

	dir_fd = dirfd(mp_dir);
	/* lock the directory to prevent processes spinning up while we send */
	if (flock(dir_fd, LOCK_EX)) {
		RTE_LOG(ERR, EAL, "Unable to lock directory %s\n",
			mp_dir_path);
		rte_errno = errno;
		closedir(mp_dir);
		return -1;
	}

	while ((ent = readdir(mp_dir))) {
		char path[PATH_MAX];

		if (fnmatch(mp_filter, ent->d_name, 0) != 0)
			continue;

		snprintf(path, sizeof(path), "%s/%s", mp_dir_path,
			 ent->d_name);
		if (send_msg(path, msg, type) < 0)
			ret = -1;
	}
	/* unlock the dir */
	flock(dir_fd, LOCK_UN);

	/* dir_fd automatically closed on closedir */
	closedir(mp_dir);
	return ret;
}

static bool
check_input(const struct rte_mp_msg *msg)
{
	if (msg == NULL) {
		RTE_LOG(ERR, EAL, "Msg cannot be NULL\n");
		rte_errno = EINVAL;
		return false;
	}

	if (validate_action_name(msg->name))
		return false;

	if (msg->len_param > RTE_MP_MAX_PARAM_LEN) {
		RTE_LOG(ERR, EAL, "Message data is too long\n");
		rte_errno = E2BIG;
		return false;
	}

	if (msg->num_fds > RTE_MP_MAX_FD_NUM) {
		RTE_LOG(ERR, EAL, "Cannot send more than %d FDs\n",
			RTE_MP_MAX_FD_NUM);
		rte_errno = E2BIG;
		return false;
	}

	return true;
}

int __rte_experimental
rte_mp_sendmsg(struct rte_mp_msg *msg)
{
	if (!check_input(msg))
		return -1;

	RTE_LOG(DEBUG, EAL, "sendmsg: %s\n", msg->name);
	return mp_send(msg, NULL, MP_MSG);
}

static int
mp_request_async(const char *dst, struct rte_mp_msg *req,
		struct async_request_param *param)
{
	struct rte_mp_msg *reply_msg;
	struct pending_request *pending_req, *exist;
	int ret;

	pending_req = calloc(1, sizeof(*pending_req));
	reply_msg = calloc(1, sizeof(*reply_msg));
	if (pending_req == NULL || reply_msg == NULL) {
		RTE_LOG(ERR, EAL, "Could not allocate space for sync request\n");
		rte_errno = ENOMEM;
		ret = -1;
		goto fail;
	}

	pending_req->type = REQUEST_TYPE_ASYNC;
	strlcpy(pending_req->dst, dst, sizeof(pending_req->dst));
	pending_req->request = req;
	pending_req->reply = reply_msg;
	pending_req->async.param = param;

	/* queue already locked by caller */

	exist = find_pending_request(dst, req->name);
	if (exist) {
		RTE_LOG(ERR, EAL, "A pending request %s:%s\n", dst, req->name);
		rte_errno = EEXIST;
		ret = -1;
		goto fail;
	}

	ret = send_msg(dst, req, MP_REQ);
	if (ret < 0) {
		RTE_LOG(ERR, EAL, "Fail to send request %s:%s\n",
			dst, req->name);
		ret = -1;
		goto fail;
	} else if (ret == 0) {
		ret = 0;
		goto fail;
	}
	TAILQ_INSERT_TAIL(&pending_requests.requests, pending_req, next);

	param->user_reply.nb_sent++;

	return 0;
fail:
	free(pending_req);
	free(reply_msg);
	return ret;
}

static int
mp_request_sync(const char *dst, struct rte_mp_msg *req,
	       struct rte_mp_reply *reply, const struct timespec *ts)
{
	int ret;
	struct rte_mp_msg msg, *tmp;
	struct pending_request pending_req, *exist;

	pending_req.type = REQUEST_TYPE_SYNC;
	pending_req.reply_received = 0;
	strlcpy(pending_req.dst, dst, sizeof(pending_req.dst));
	pending_req.request = req;
	pending_req.reply = &msg;
	pthread_cond_init(&pending_req.sync.cond, NULL);

	exist = find_pending_request(dst, req->name);
	if (exist) {
		RTE_LOG(ERR, EAL, "A pending request %s:%s\n", dst, req->name);
		rte_errno = EEXIST;
		return -1;
	}

	ret = send_msg(dst, req, MP_REQ);
	if (ret < 0) {
		RTE_LOG(ERR, EAL, "Fail to send request %s:%s\n",
			dst, req->name);
		return -1;
	} else if (ret == 0)
		return 0;

	TAILQ_INSERT_TAIL(&pending_requests.requests, &pending_req, next);

	reply->nb_sent++;

	do {
		ret = pthread_cond_timedwait(&pending_req.sync.cond,
				&pending_requests.lock, ts);
	} while (ret != 0 && ret != ETIMEDOUT);

	TAILQ_REMOVE(&pending_requests.requests, &pending_req, next);

	if (pending_req.reply_received == 0) {
		RTE_LOG(ERR, EAL, "Fail to recv reply for request %s:%s\n",
			dst, req->name);
		rte_errno = ETIMEDOUT;
		return -1;
	}
	if (pending_req.reply_received == -1) {
		RTE_LOG(DEBUG, EAL, "Asked to ignore response\n");
		/* not receiving this message is not an error, so decrement
		 * number of sent messages
		 */
		reply->nb_sent--;
		return 0;
	}

	tmp = realloc(reply->msgs, sizeof(msg) * (reply->nb_received + 1));
	if (!tmp) {
		RTE_LOG(ERR, EAL, "Fail to alloc reply for request %s:%s\n",
			dst, req->name);
		rte_errno = ENOMEM;
		return -1;
	}
	memcpy(&tmp[reply->nb_received], &msg, sizeof(msg));
	reply->msgs = tmp;
	reply->nb_received++;
	return 0;
}

int __rte_experimental
rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
		const struct timespec *ts)
{
	int dir_fd, ret = 0;
	DIR *mp_dir;
	struct dirent *ent;
	struct timeval now;
	struct timespec end;

	RTE_LOG(DEBUG, EAL, "request: %s\n", req->name);

	if (check_input(req) == false)
		return -1;
	if (gettimeofday(&now, NULL) < 0) {
		RTE_LOG(ERR, EAL, "Faile to get current time\n");
		rte_errno = errno;
		return -1;
	}

	end.tv_nsec = (now.tv_usec * 1000 + ts->tv_nsec) % 1000000000;
	end.tv_sec = now.tv_sec + ts->tv_sec +
			(now.tv_usec * 1000 + ts->tv_nsec) / 1000000000;

	reply->nb_sent = 0;
	reply->nb_received = 0;
	reply->msgs = NULL;

	/* for secondary process, send request to the primary process only */
	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
		pthread_mutex_lock(&pending_requests.lock);
		ret = mp_request_sync(eal_mp_socket_path(), req, reply, &end);
		pthread_mutex_unlock(&pending_requests.lock);
		return ret;
	}

	/* for primary process, broadcast request, and collect reply 1 by 1 */
	mp_dir = opendir(mp_dir_path);
	if (!mp_dir) {
		RTE_LOG(ERR, EAL, "Unable to open directory %s\n", mp_dir_path);
		rte_errno = errno;
		return -1;
	}

	dir_fd = dirfd(mp_dir);
	/* lock the directory to prevent processes spinning up while we send */
	if (flock(dir_fd, LOCK_EX)) {
		RTE_LOG(ERR, EAL, "Unable to lock directory %s\n",
			mp_dir_path);
		closedir(mp_dir);
		rte_errno = errno;
		return -1;
	}

	pthread_mutex_lock(&pending_requests.lock);
	while ((ent = readdir(mp_dir))) {
		char path[PATH_MAX];

		if (fnmatch(mp_filter, ent->d_name, 0) != 0)
			continue;

		snprintf(path, sizeof(path), "%s/%s", mp_dir_path,
			 ent->d_name);

		/* unlocks the mutex while waiting for response,
		 * locks on receive
		 */
		if (mp_request_sync(path, req, reply, &end))
			ret = -1;
	}
	pthread_mutex_unlock(&pending_requests.lock);
	/* unlock the directory */
	flock(dir_fd, LOCK_UN);

	/* dir_fd automatically closed on closedir */
	closedir(mp_dir);
	return ret;
}

int __rte_experimental
rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
		rte_mp_async_reply_t clb)
{
	struct rte_mp_msg *copy;
	struct pending_request *dummy;
	struct async_request_param *param;
	struct rte_mp_reply *reply;
	int dir_fd, ret = 0;
	DIR *mp_dir;
	struct dirent *ent;
	struct timeval now;
	struct timespec *end;
	bool dummy_used = false;

	RTE_LOG(DEBUG, EAL, "request: %s\n", req->name);

	if (check_input(req) == false)
		return -1;
	if (gettimeofday(&now, NULL) < 0) {
		RTE_LOG(ERR, EAL, "Faile to get current time\n");
		rte_errno = errno;
		return -1;
	}
	copy = calloc(1, sizeof(*copy));
	dummy = calloc(1, sizeof(*dummy));
	param = calloc(1, sizeof(*param));
	if (copy == NULL || dummy == NULL || param == NULL) {
		RTE_LOG(ERR, EAL, "Failed to allocate memory for async reply\n");
		rte_errno = ENOMEM;
		goto fail;
	}

	/* copy message */
	memcpy(copy, req, sizeof(*copy));

	param->n_responses_processed = 0;
	param->clb = clb;
	end = &param->end;
	reply = &param->user_reply;

	end->tv_nsec = (now.tv_usec * 1000 + ts->tv_nsec) % 1000000000;
	end->tv_sec = now.tv_sec + ts->tv_sec +
			(now.tv_usec * 1000 + ts->tv_nsec) / 1000000000;
	reply->nb_sent = 0;
	reply->nb_received = 0;
	reply->msgs = NULL;

	/* we have to lock the request queue here, as we will be adding a bunch
	 * of requests to the queue at once, and some of the replies may arrive
	 * before we add all of the requests to the queue.
	 */
	pthread_mutex_lock(&pending_requests.lock);

	/* we have to ensure that callback gets triggered even if we don't send
	 * anything, therefore earlier we have allocated a dummy request. fill
	 * it, and put it on the queue if we don't send any requests.
	 */
	dummy->type = REQUEST_TYPE_ASYNC;
	dummy->request = copy;
	dummy->reply = NULL;
	dummy->async.param = param;
	dummy->reply_received = 1; /* short-circuit the timeout */

	/* for secondary process, send request to the primary process only */
	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
		ret = mp_request_async(eal_mp_socket_path(), copy, param);

		/* if we didn't send anything, put dummy request on the queue */
		if (ret == 0 && reply->nb_sent == 0) {
			TAILQ_INSERT_TAIL(&pending_requests.requests, dummy,
					next);
			dummy_used = true;
		}

		pthread_mutex_unlock(&pending_requests.lock);

		/* if we couldn't send anything, clean up */
		if (ret != 0)
			goto fail;
		return 0;
	}

	/* for primary process, broadcast request */
	mp_dir = opendir(mp_dir_path);
	if (!mp_dir) {
		RTE_LOG(ERR, EAL, "Unable to open directory %s\n", mp_dir_path);
		rte_errno = errno;
		goto unlock_fail;
	}
	dir_fd = dirfd(mp_dir);

	/* lock the directory to prevent processes spinning up while we send */
	if (flock(dir_fd, LOCK_EX)) {
		RTE_LOG(ERR, EAL, "Unable to lock directory %s\n",
			mp_dir_path);
		rte_errno = errno;
		goto closedir_fail;
	}

	while ((ent = readdir(mp_dir))) {
		char path[PATH_MAX];

		if (fnmatch(mp_filter, ent->d_name, 0) != 0)
			continue;

		snprintf(path, sizeof(path), "%s/%s", mp_dir_path,
			 ent->d_name);

		if (mp_request_async(path, copy, param))
			ret = -1;
	}
	/* if we didn't send anything, put dummy request on the queue */
	if (ret == 0 && reply->nb_sent == 0) {
		TAILQ_INSERT_HEAD(&pending_requests.requests, dummy, next);
		dummy_used = true;
	}

	/* trigger async request thread wake up */
	pthread_cond_signal(&pending_requests.async_cond);

	/* finally, unlock the queue */
	pthread_mutex_unlock(&pending_requests.lock);

	/* unlock the directory */
	flock(dir_fd, LOCK_UN);

	/* dir_fd automatically closed on closedir */
	closedir(mp_dir);

	/* if dummy was unused, free it */
	if (!dummy_used)
		free(dummy);

	return ret;
closedir_fail:
	closedir(mp_dir);
unlock_fail:
	pthread_mutex_unlock(&pending_requests.lock);
fail:
	free(dummy);
	free(param);
	free(copy);
	return -1;
}

int __rte_experimental
rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
{
	RTE_LOG(DEBUG, EAL, "reply: %s\n", msg->name);

	if (check_input(msg) == false)
		return -1;

	if (peer == NULL) {
		RTE_LOG(ERR, EAL, "peer is not specified\n");
		rte_errno = EINVAL;
		return -1;
	}

	return mp_send(msg, peer, MP_REP);
}