summaryrefslogtreecommitdiffstats
path: root/lib/librte_mempool/rte_mempool.c
blob: 2e28e2e80e40d3debc2e778b07c95ff160bdd52f (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
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   Copyright(c) 2016 6WIND S.A.
 *   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 <string.h>
#include <stdint.h>
#include <stdarg.h>
#include <unistd.h>
#include <inttypes.h>
#include <errno.h>
#include <sys/queue.h>
#include <sys/mman.h>

#include <rte_common.h>
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_memory.h>
#include <rte_memzone.h>
#include <rte_malloc.h>
#include <rte_atomic.h>
#include <rte_launch.h>
#include <rte_eal.h>
#include <rte_eal_memconfig.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_ring.h>
#include <rte_errno.h>
#include <rte_string_fns.h>
#include <rte_spinlock.h>

#include "rte_mempool.h"

TAILQ_HEAD(rte_mempool_list, rte_tailq_entry);

static struct rte_tailq_elem rte_mempool_tailq = {
	.name = "RTE_MEMPOOL",
};
EAL_REGISTER_TAILQ(rte_mempool_tailq)

#define CACHE_FLUSHTHRESH_MULTIPLIER 1.5
#define CALC_CACHE_FLUSHTHRESH(c)	\
	((typeof(c))((c) * CACHE_FLUSHTHRESH_MULTIPLIER))

/*
 * return the greatest common divisor between a and b (fast algorithm)
 *
 */
static unsigned get_gcd(unsigned a, unsigned b)
{
	unsigned c;

	if (0 == a)
		return b;
	if (0 == b)
		return a;

	if (a < b) {
		c = a;
		a = b;
		b = c;
	}

	while (b != 0) {
		c = a % b;
		a = b;
		b = c;
	}

	return a;
}

/*
 * Depending on memory configuration, objects addresses are spread
 * between channels and ranks in RAM: the pool allocator will add
 * padding between objects. This function return the new size of the
 * object.
 */
static unsigned optimize_object_size(unsigned obj_size)
{
	unsigned nrank, nchan;
	unsigned new_obj_size;

	/* get number of channels */
	nchan = rte_memory_get_nchannel();
	if (nchan == 0)
		nchan = 4;

	nrank = rte_memory_get_nrank();
	if (nrank == 0)
		nrank = 1;

	/* process new object size */
	new_obj_size = (obj_size + RTE_MEMPOOL_ALIGN_MASK) / RTE_MEMPOOL_ALIGN;
	while (get_gcd(new_obj_size, nrank * nchan) != 1)
		new_obj_size++;
	return new_obj_size * RTE_MEMPOOL_ALIGN;
}

static void
mempool_add_elem(struct rte_mempool *mp, void *obj, phys_addr_t physaddr)
{
	struct rte_mempool_objhdr *hdr;
	struct rte_mempool_objtlr *tlr __rte_unused;

	/* set mempool ptr in header */
	hdr = RTE_PTR_SUB(obj, sizeof(*hdr));
	hdr->mp = mp;
	hdr->physaddr = physaddr;
	STAILQ_INSERT_TAIL(&mp->elt_list, hdr, next);
	mp->populated_size++;

#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	hdr->cookie = RTE_MEMPOOL_HEADER_COOKIE2;
	tlr = __mempool_get_trailer(obj);
	tlr->cookie = RTE_MEMPOOL_TRAILER_COOKIE;
#endif

	/* enqueue in ring */
	rte_mempool_ops_enqueue_bulk(mp, &obj, 1);
}

/* call obj_cb() for each mempool element */
uint32_t
rte_mempool_obj_iter(struct rte_mempool *mp,
	rte_mempool_obj_cb_t *obj_cb, void *obj_cb_arg)
{
	struct rte_mempool_objhdr *hdr;
	void *obj;
	unsigned n = 0;

	STAILQ_FOREACH(hdr, &mp->elt_list, next) {
		obj = (char *)hdr + sizeof(*hdr);
		obj_cb(mp, obj_cb_arg, obj, n);
		n++;
	}

	return n;
}

/* call mem_cb() for each mempool memory chunk */
uint32_t
rte_mempool_mem_iter(struct rte_mempool *mp,
	rte_mempool_mem_cb_t *mem_cb, void *mem_cb_arg)
{
	struct rte_mempool_memhdr *hdr;
	unsigned n = 0;

	STAILQ_FOREACH(hdr, &mp->mem_list, next) {
		mem_cb(mp, mem_cb_arg, hdr, n);
		n++;
	}

	return n;
}

/* get the header, trailer and total size of a mempool element. */
uint32_t
rte_mempool_calc_obj_size(uint32_t elt_size, uint32_t flags,
	struct rte_mempool_objsz *sz)
{
	struct rte_mempool_objsz lsz;

	sz = (sz != NULL) ? sz : &lsz;

	sz->header_size = sizeof(struct rte_mempool_objhdr);
	if ((flags & MEMPOOL_F_NO_CACHE_ALIGN) == 0)
		sz->header_size = RTE_ALIGN_CEIL(sz->header_size,
			RTE_MEMPOOL_ALIGN);

#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	sz->trailer_size = sizeof(struct rte_mempool_objtlr);
#else
	sz->trailer_size = 0;
#endif

	/* element size is 8 bytes-aligned at least */
	sz->elt_size = RTE_ALIGN_CEIL(elt_size, sizeof(uint64_t));

	/* expand trailer to next cache line */
	if ((flags & MEMPOOL_F_NO_CACHE_ALIGN) == 0) {
		sz->total_size = sz->header_size + sz->elt_size +
			sz->trailer_size;
		sz->trailer_size += ((RTE_MEMPOOL_ALIGN -
				  (sz->total_size & RTE_MEMPOOL_ALIGN_MASK)) &
				 RTE_MEMPOOL_ALIGN_MASK);
	}

	/*
	 * increase trailer to add padding between objects in order to
	 * spread them across memory channels/ranks
	 */
	if ((flags & MEMPOOL_F_NO_SPREAD) == 0) {
		unsigned new_size;
		new_size = optimize_object_size(sz->header_size + sz->elt_size +
			sz->trailer_size);
		sz->trailer_size = new_size - sz->header_size - sz->elt_size;
	}

	/* this is the size of an object, including header and trailer */
	sz->total_size = sz->header_size + sz->elt_size + sz->trailer_size;

	return sz->total_size;
}


/*
 * Calculate maximum amount of memory required to store given number of objects.
 */
size_t
rte_mempool_xmem_size(uint32_t elt_num, size_t total_elt_sz, uint32_t pg_shift)
{
	size_t obj_per_page, pg_num, pg_sz;

	if (total_elt_sz == 0)
		return 0;

	if (pg_shift == 0)
		return total_elt_sz * elt_num;

	pg_sz = (size_t)1 << pg_shift;
	obj_per_page = pg_sz / total_elt_sz;
	if (obj_per_page == 0)
		return RTE_ALIGN_CEIL(total_elt_sz, pg_sz) * elt_num;

	pg_num = (elt_num + obj_per_page - 1) / obj_per_page;
	return pg_num << pg_shift;
}

/*
 * Calculate how much memory would be actually required with the
 * given memory footprint to store required number of elements.
 */
ssize_t
rte_mempool_xmem_usage(__rte_unused void *vaddr, uint32_t elt_num,
	size_t total_elt_sz, const phys_addr_t paddr[], uint32_t pg_num,
	uint32_t pg_shift)
{
	uint32_t elt_cnt = 0;
	phys_addr_t start, end;
	uint32_t paddr_idx;
	size_t pg_sz = (size_t)1 << pg_shift;

	/* if paddr is NULL, assume contiguous memory */
	if (paddr == NULL) {
		start = 0;
		end = pg_sz * pg_num;
		paddr_idx = pg_num;
	} else {
		start = paddr[0];
		end = paddr[0] + pg_sz;
		paddr_idx = 1;
	}
	while (elt_cnt < elt_num) {

		if (end - start >= total_elt_sz) {
			/* enough contiguous memory, add an object */
			start += total_elt_sz;
			elt_cnt++;
		} else if (paddr_idx < pg_num) {
			/* no room to store one obj, add a page */
			if (end == paddr[paddr_idx]) {
				end += pg_sz;
			} else {
				start = paddr[paddr_idx];
				end = paddr[paddr_idx] + pg_sz;
			}
			paddr_idx++;

		} else {
			/* no more page, return how many elements fit */
			return -(size_t)elt_cnt;
		}
	}

	return (size_t)paddr_idx << pg_shift;
}

/* free a memchunk allocated with rte_memzone_reserve() */
static void
rte_mempool_memchunk_mz_free(__rte_unused struct rte_mempool_memhdr *memhdr,
	void *opaque)
{
	const struct rte_memzone *mz = opaque;
	rte_memzone_free(mz);
}

/* Free memory chunks used by a mempool. Objects must be in pool */
static void
rte_mempool_free_memchunks(struct rte_mempool *mp)
{
	struct rte_mempool_memhdr *memhdr;
	void *elt;

	while (!STAILQ_EMPTY(&mp->elt_list)) {
		rte_mempool_ops_dequeue_bulk(mp, &elt, 1);
		(void)elt;
		STAILQ_REMOVE_HEAD(&mp->elt_list, next);
		mp->populated_size--;
	}

	while (!STAILQ_EMPTY(&mp->mem_list)) {
		memhdr = STAILQ_FIRST(&mp->mem_list);
		STAILQ_REMOVE_HEAD(&mp->mem_list, next);
		if (memhdr->free_cb != NULL)
			memhdr->free_cb(memhdr, memhdr->opaque);
		rte_free(memhdr);
		mp->nb_mem_chunks--;
	}
}

/* Add objects in the pool, using a physically contiguous memory
 * zone. Return the number of objects added, or a negative value
 * on error.
 */
int
rte_mempool_populate_phys(struct rte_mempool *mp, char *vaddr,
	phys_addr_t paddr, size_t len, rte_mempool_memchunk_free_cb_t *free_cb,
	void *opaque)
{
	unsigned total_elt_sz;
	unsigned i = 0;
	size_t off;
	struct rte_mempool_memhdr *memhdr;
	int ret;

	/* create the internal ring if not already done */
	if ((mp->flags & MEMPOOL_F_POOL_CREATED) == 0) {
		ret = rte_mempool_ops_alloc(mp);
		if (ret != 0)
			return ret;
		mp->flags |= MEMPOOL_F_POOL_CREATED;
	}

	/* mempool is already populated */
	if (mp->populated_size >= mp->size)
		return -ENOSPC;

	total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;

	memhdr = rte_zmalloc("MEMPOOL_MEMHDR", sizeof(*memhdr), 0);
	if (memhdr == NULL)
		return -ENOMEM;

	memhdr->mp = mp;
	memhdr->addr = vaddr;
	memhdr->phys_addr = paddr;
	memhdr->len = len;
	memhdr->free_cb = free_cb;
	memhdr->opaque = opaque;

	if (mp->flags & MEMPOOL_F_NO_CACHE_ALIGN)
		off = RTE_PTR_ALIGN_CEIL(vaddr, 8) - vaddr;
	else
		off = RTE_PTR_ALIGN_CEIL(vaddr, RTE_CACHE_LINE_SIZE) - vaddr;

	while (off + total_elt_sz <= len && mp->populated_size < mp->size) {
		off += mp->header_size;
		if (paddr == RTE_BAD_PHYS_ADDR)
			mempool_add_elem(mp, (char *)vaddr + off,
				RTE_BAD_PHYS_ADDR);
		else
			mempool_add_elem(mp, (char *)vaddr + off, paddr + off);
		off += mp->elt_size + mp->trailer_size;
		i++;
	}

	/* not enough room to store one object */
	if (i == 0)
		return -EINVAL;

	STAILQ_INSERT_TAIL(&mp->mem_list, memhdr, next);
	mp->nb_mem_chunks++;
	return i;
}

/* Add objects in the pool, using a table of physical pages. Return the
 * number of objects added, or a negative value on error.
 */
int
rte_mempool_populate_phys_tab(struct rte_mempool *mp, char *vaddr,
	const phys_addr_t paddr[], uint32_t pg_num, uint32_t pg_shift,
	rte_mempool_memchunk_free_cb_t *free_cb, void *opaque)
{
	uint32_t i, n;
	int ret, cnt = 0;
	size_t pg_sz = (size_t)1 << pg_shift;

	/* mempool must not be populated */
	if (mp->nb_mem_chunks != 0)
		return -EEXIST;

	if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
		return rte_mempool_populate_phys(mp, vaddr, RTE_BAD_PHYS_ADDR,
			pg_num * pg_sz, free_cb, opaque);

	for (i = 0; i < pg_num && mp->populated_size < mp->size; i += n) {

		/* populate with the largest group of contiguous pages */
		for (n = 1; (i + n) < pg_num &&
			     paddr[i] + pg_sz == paddr[i+n]; n++)
			;

		ret = rte_mempool_populate_phys(mp, vaddr + i * pg_sz,
			paddr[i], n * pg_sz, free_cb, opaque);
		if (ret < 0) {
			rte_mempool_free_memchunks(mp);
			return ret;
		}
		/* no need to call the free callback for next chunks */
		free_cb = NULL;
		cnt += ret;
	}
	return cnt;
}

/* Populate the mempool with a virtual area. Return the number of
 * objects added, or a negative value on error.
 */
int
rte_mempool_populate_virt(struct rte_mempool *mp, char *addr,
	size_t len, size_t pg_sz, rte_mempool_memchunk_free_cb_t *free_cb,
	void *opaque)
{
	phys_addr_t paddr;
	size_t off, phys_len;
	int ret, cnt = 0;

	/* mempool must not be populated */
	if (mp->nb_mem_chunks != 0)
		return -EEXIST;
	/* address and len must be page-aligned */
	if (RTE_PTR_ALIGN_CEIL(addr, pg_sz) != addr)
		return -EINVAL;
	if (RTE_ALIGN_CEIL(len, pg_sz) != len)
		return -EINVAL;

	if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
		return rte_mempool_populate_phys(mp, addr, RTE_BAD_PHYS_ADDR,
			len, free_cb, opaque);

	for (off = 0; off + pg_sz <= len &&
		     mp->populated_size < mp->size; off += phys_len) {

		paddr = rte_mem_virt2phy(addr + off);
		/* required for xen_dom0 to get the machine address */
		paddr = rte_mem_phy2mch(-1, paddr);

		if (paddr == RTE_BAD_PHYS_ADDR) {
			ret = -EINVAL;
			goto fail;
		}

		/* populate with the largest group of contiguous pages */
		for (phys_len = pg_sz; off + phys_len < len; phys_len += pg_sz) {
			phys_addr_t paddr_tmp;

			paddr_tmp = rte_mem_virt2phy(addr + off + phys_len);
			paddr_tmp = rte_mem_phy2mch(-1, paddr_tmp);

			if (paddr_tmp != paddr + phys_len)
				break;
		}

		ret = rte_mempool_populate_phys(mp, addr + off, paddr,
			phys_len, free_cb, opaque);
		if (ret < 0)
			goto fail;
		/* no need to call the free callback for next chunks */
		free_cb = NULL;
		cnt += ret;
	}

	return cnt;

 fail:
	rte_mempool_free_memchunks(mp);
	return ret;
}

/* Default function to populate the mempool: allocate memory in memzones,
 * and populate them. Return the number of objects added, or a negative
 * value on error.
 */
int
rte_mempool_populate_default(struct rte_mempool *mp)
{
	int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
	char mz_name[RTE_MEMZONE_NAMESIZE];
	const struct rte_memzone *mz;
	size_t size, total_elt_sz, align, pg_sz, pg_shift;
	phys_addr_t paddr;
	unsigned mz_id, n;
	int ret;

	/* mempool must not be populated */
	if (mp->nb_mem_chunks != 0)
		return -EEXIST;

	if (rte_xen_dom0_supported()) {
		pg_sz = RTE_PGSIZE_2M;
		pg_shift = rte_bsf32(pg_sz);
		align = pg_sz;
	} else if (rte_eal_has_hugepages()) {
		pg_shift = 0; /* not needed, zone is physically contiguous */
		pg_sz = 0;
		align = RTE_CACHE_LINE_SIZE;
	} else {
		pg_sz = getpagesize();
		pg_shift = rte_bsf32(pg_sz);
		align = pg_sz;
	}

	total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;
	for (mz_id = 0, n = mp->size; n > 0; mz_id++, n -= ret) {
		size = rte_mempool_xmem_size(n, total_elt_sz, pg_shift);

		ret = snprintf(mz_name, sizeof(mz_name),
			RTE_MEMPOOL_MZ_FORMAT "_%d", mp->name, mz_id);
		if (ret < 0 || ret >= (int)sizeof(mz_name)) {
			ret = -ENAMETOOLONG;
			goto fail;
		}

		mz = rte_memzone_reserve_aligned(mz_name, size,
			mp->socket_id, mz_flags, align);
		/* not enough memory, retry with the biggest zone we have */
		if (mz == NULL)
			mz = rte_memzone_reserve_aligned(mz_name, 0,
				mp->socket_id, mz_flags, align);
		if (mz == NULL) {
			ret = -rte_errno;
			goto fail;
		}

		if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
			paddr = RTE_BAD_PHYS_ADDR;
		else
			paddr = mz->phys_addr;

		if (rte_eal_has_hugepages() && !rte_xen_dom0_supported())
			ret = rte_mempool_populate_phys(mp, mz->addr,
				paddr, mz->len,
				rte_mempool_memchunk_mz_free,
				(void *)(uintptr_t)mz);
		else
			ret = rte_mempool_populate_virt(mp, mz->addr,
				mz->len, pg_sz,
				rte_mempool_memchunk_mz_free,
				(void *)(uintptr_t)mz);
		if (ret < 0)
			goto fail;
	}

	return mp->size;

 fail:
	rte_mempool_free_memchunks(mp);
	return ret;
}

/* return the memory size required for mempool objects in anonymous mem */
static size_t
get_anon_size(const struct rte_mempool *mp)
{
	size_t size, total_elt_sz, pg_sz, pg_shift;

	pg_sz = getpagesize();
	pg_shift = rte_bsf32(pg_sz);
	total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;
	size = rte_mempool_xmem_size(mp->size, total_elt_sz, pg_shift);

	return size;
}

/* unmap a memory zone mapped by rte_mempool_populate_anon() */
static void
rte_mempool_memchunk_anon_free(struct rte_mempool_memhdr *memhdr,
	void *opaque)
{
	munmap(opaque, get_anon_size(memhdr->mp));
}

/* populate the mempool with an anonymous mapping */
int
rte_mempool_populate_anon(struct rte_mempool *mp)
{
	size_t size;
	int ret;
	char *addr;

	/* mempool is already populated, error */
	if (!STAILQ_EMPTY(&mp->mem_list)) {
		rte_errno = EINVAL;
		return 0;
	}

	/* get chunk of virtually continuous memory */
	size = get_anon_size(mp);
	addr = mmap(NULL, size, PROT_READ | PROT_WRITE,
		MAP_SHARED | MAP_ANONYMOUS, -1, 0);
	if (addr == MAP_FAILED) {
		rte_errno = errno;
		return 0;
	}
	/* can't use MMAP_LOCKED, it does not exist on BSD */
	if (mlock(addr, size) < 0) {
		rte_errno = errno;
		munmap(addr, size);
		return 0;
	}

	ret = rte_mempool_populate_virt(mp, addr, size, getpagesize(),
		rte_mempool_memchunk_anon_free, addr);
	if (ret == 0)
		goto fail;

	return mp->populated_size;

 fail:
	rte_mempool_free_memchunks(mp);
	return 0;
}

/* free a mempool */
void
rte_mempool_free(struct rte_mempool *mp)
{
	struct rte_mempool_list *mempool_list = NULL;
	struct rte_tailq_entry *te;

	if (mp == NULL)
		return;

	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
	rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
	/* find out tailq entry */
	TAILQ_FOREACH(te, mempool_list, next) {
		if (te->data == (void *)mp)
			break;
	}

	if (te != NULL) {
		TAILQ_REMOVE(mempool_list, te, next);
		rte_free(te);
	}
	rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);

	rte_mempool_free_memchunks(mp);
	rte_mempool_ops_free(mp);
	rte_memzone_free(mp->mz);
}

static void
mempool_cache_init(struct rte_mempool_cache *cache, uint32_t size)
{
	cache->size = size;
	cache->flushthresh = CALC_CACHE_FLUSHTHRESH(size);
	cache->len = 0;
}

/*
 * Create and initialize a cache for objects that are retrieved from and
 * returned to an underlying mempool. This structure is identical to the
 * local_cache[lcore_id] pointed to by the mempool structure.
 */
struct rte_mempool_cache *
rte_mempool_cache_create(uint32_t size, int socket_id)
{
	struct rte_mempool_cache *cache;

	if (size == 0 || size > RTE_MEMPOOL_CACHE_MAX_SIZE) {
		rte_errno = EINVAL;
		return NULL;
	}

	cache = rte_zmalloc_socket("MEMPOOL_CACHE", sizeof(*cache),
				  RTE_CACHE_LINE_SIZE, socket_id);
	if (cache == NULL) {
		RTE_LOG(ERR, MEMPOOL, "Cannot allocate mempool cache.\n");
		rte_errno = ENOMEM;
		return NULL;
	}

	mempool_cache_init(cache, size);

	return cache;
}

/*
 * Free a cache. It's the responsibility of the user to make sure that any
 * remaining objects in the cache are flushed to the corresponding
 * mempool.
 */
void
rte_mempool_cache_free(struct rte_mempool_cache *cache)
{
	rte_free(cache);
}

/* create an empty mempool */
struct rte_mempool *
rte_mempool_create_empty(const char *name, unsigned n, unsigned elt_size,
	unsigned cache_size, unsigned private_data_size,
	int socket_id, unsigned flags)
{
	char mz_name[RTE_MEMZONE_NAMESIZE];
	struct rte_mempool_list *mempool_list;
	struct rte_mempool *mp = NULL;
	struct rte_tailq_entry *te = NULL;
	const struct rte_memzone *mz = NULL;
	size_t mempool_size;
	int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
	struct rte_mempool_objsz objsz;
	unsigned lcore_id;
	int ret;

	/* compilation-time checks */
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
			  RTE_CACHE_LINE_MASK) != 0);
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
			  RTE_CACHE_LINE_MASK) != 0);
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_debug_stats) &
			  RTE_CACHE_LINE_MASK) != 0);
	RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, stats) &
			  RTE_CACHE_LINE_MASK) != 0);
#endif

	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);

	/* asked cache too big */
	if (cache_size > RTE_MEMPOOL_CACHE_MAX_SIZE ||
	    CALC_CACHE_FLUSHTHRESH(cache_size) > n) {
		rte_errno = EINVAL;
		return NULL;
	}

	/* "no cache align" imply "no spread" */
	if (flags & MEMPOOL_F_NO_CACHE_ALIGN)
		flags |= MEMPOOL_F_NO_SPREAD;

	/* calculate mempool object sizes. */
	if (!rte_mempool_calc_obj_size(elt_size, flags, &objsz)) {
		rte_errno = EINVAL;
		return NULL;
	}

	rte_rwlock_write_lock(RTE_EAL_MEMPOOL_RWLOCK);

	/*
	 * reserve a memory zone for this mempool: private data is
	 * cache-aligned
	 */
	private_data_size = (private_data_size +
			     RTE_MEMPOOL_ALIGN_MASK) & (~RTE_MEMPOOL_ALIGN_MASK);


	/* try to allocate tailq entry */
	te = rte_zmalloc("MEMPOOL_TAILQ_ENTRY", sizeof(*te), 0);
	if (te == NULL) {
		RTE_LOG(ERR, MEMPOOL, "Cannot allocate tailq entry!\n");
		goto exit_unlock;
	}

	mempool_size = MEMPOOL_HEADER_SIZE(mp, cache_size);
	mempool_size += private_data_size;
	mempool_size = RTE_ALIGN_CEIL(mempool_size, RTE_MEMPOOL_ALIGN);

	ret = snprintf(mz_name, sizeof(mz_name), RTE_MEMPOOL_MZ_FORMAT, name);
	if (ret < 0 || ret >= (int)sizeof(mz_name)) {
		rte_errno = ENAMETOOLONG;
		goto exit_unlock;
	}

	mz = rte_memzone_reserve(mz_name, mempool_size, socket_id, mz_flags);
	if (mz == NULL)
		goto exit_unlock;

	/* init the mempool structure */
	mp = mz->addr;
	memset(mp, 0, MEMPOOL_HEADER_SIZE(mp, cache_size));
	ret = snprintf(mp->name, sizeof(mp->name), "%s", name);
	if (ret < 0 || ret >= (int)sizeof(mp->name)) {
		rte_errno = ENAMETOOLONG;
		goto exit_unlock;
	}
	mp->mz = mz;
	mp->socket_id = socket_id;
	mp->size = n;
	mp->flags = flags;
	mp->socket_id = socket_id;
	mp->elt_size = objsz.elt_size;
	mp->header_size = objsz.header_size;
	mp->trailer_size = objsz.trailer_size;
	/* Size of default caches, zero means disabled. */
	mp->cache_size = cache_size;
	mp->private_data_size = private_data_size;
	STAILQ_INIT(&mp->elt_list);
	STAILQ_INIT(&mp->mem_list);

	/*
	 * local_cache pointer is set even if cache_size is zero.
	 * The local_cache points to just past the elt_pa[] array.
	 */
	mp->local_cache = (struct rte_mempool_cache *)
		RTE_PTR_ADD(mp, MEMPOOL_HEADER_SIZE(mp, 0));

	/* Init all default caches. */
	if (cache_size != 0) {
		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
			mempool_cache_init(&mp->local_cache[lcore_id],
					   cache_size);
	}

	te->data = mp;

	rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
	TAILQ_INSERT_TAIL(mempool_list, te, next);
	rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
	rte_rwlock_write_unlock(RTE_EAL_MEMPOOL_RWLOCK);

	return mp;

exit_unlock:
	rte_rwlock_write_unlock(RTE_EAL_MEMPOOL_RWLOCK);
	rte_free(te);
	rte_mempool_free(mp);
	return NULL;
}

/* create the mempool */
struct rte_mempool *
rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
	unsigned cache_size, unsigned private_data_size,
	rte_mempool_ctor_t *mp_init, void *mp_init_arg,
	rte_mempool_obj_cb_t *obj_init, void *obj_init_arg,
	int socket_id, unsigned flags)
{
	struct rte_mempool *mp;

	mp = rte_mempool_create_empty(name, n, elt_size, cache_size,
		private_data_size, socket_id, flags);
	if (mp == NULL)
		return NULL;

	/*
	 * Since we have 4 combinations of the SP/SC/MP/MC examine the flags to
	 * set the correct index into the table of ops structs.
	 */
	if (flags & (MEMPOOL_F_SP_PUT | MEMPOOL_F_SC_GET))
		rte_mempool_set_ops_byname(mp, "ring_sp_sc", NULL);
	else if (flags & MEMPOOL_F_SP_PUT)
		rte_mempool_set_ops_byname(mp, "ring_sp_mc", NULL);
	else if (flags & MEMPOOL_F_SC_GET)
		rte_mempool_set_ops_byname(mp, "ring_mp_sc", NULL);
	else
		rte_mempool_set_ops_byname(mp, "ring_mp_mc", NULL);

	/* call the mempool priv initializer */
	if (mp_init)
		mp_init(mp, mp_init_arg);

	if (rte_mempool_populate_default(mp) < 0)
		goto fail;

	/* call the object initializers */
	if (obj_init)
		rte_mempool_obj_iter(mp, obj_init, obj_init_arg);

	return mp;

 fail:
	rte_mempool_free(mp);
	return NULL;
}

/*
 * Create the mempool over already allocated chunk of memory.
 * That external memory buffer can consists of physically disjoint pages.
 * Setting vaddr to NULL, makes mempool to fallback to original behaviour
 * and allocate space for mempool and it's elements as one big chunk of
 * physically continuos memory.
 */
struct rte_mempool *
rte_mempool_xmem_create(const char *name, unsigned n, unsigned elt_size,
		unsigned cache_size, unsigned private_data_size,
		rte_mempool_ctor_t *mp_init, void *mp_init_arg,
		rte_mempool_obj_cb_t *obj_init, void *obj_init_arg,
		int socket_id, unsigned flags, void *vaddr,
		const phys_addr_t paddr[], uint32_t pg_num, uint32_t pg_shift)
{
	struct rte_mempool *mp = NULL;
	int ret;

	/* no virtual address supplied, use rte_mempool_create() */
	if (vaddr == NULL)
		return rte_mempool_create(name, n, elt_size, cache_size,
			private_data_size, mp_init, mp_init_arg,
			obj_init, obj_init_arg, socket_id, flags);

	/* check that we have both VA and PA */
	if (paddr == NULL) {
		rte_errno = EINVAL;
		return NULL;
	}

	/* Check that pg_shift parameter is valid. */
	if (pg_shift > MEMPOOL_PG_SHIFT_MAX) {
		rte_errno = EINVAL;
		return NULL;
	}

	mp = rte_mempool_create_empty(name, n, elt_size, cache_size,
		private_data_size, socket_id, flags);
	if (mp == NULL)
		return NULL;

	/* call the mempool priv initializer */
	if (mp_init)
		mp_init(mp, mp_init_arg);

	ret = rte_mempool_populate_phys_tab(mp, vaddr, paddr, pg_num, pg_shift,
		NULL, NULL);
	if (ret < 0 || ret != (int)mp->size)
		goto fail;

	/* call the object initializers */
	if (obj_init)
		rte_mempool_obj_iter(mp, obj_init, obj_init_arg);

	return mp;

 fail:
	rte_mempool_free(mp);
	return NULL;
}

/* Return the number of entries in the mempool */
unsigned int
rte_mempool_avail_count(const struct rte_mempool *mp)
{
	unsigned count;
	unsigned lcore_id;

	count = rte_mempool_ops_get_count(mp);

	if (mp->cache_size == 0)
		return count;

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
		count += mp->local_cache[lcore_id].len;

	/*
	 * due to race condition (access to len is not locked), the
	 * total can be greater than size... so fix the result
	 */
	if (count > mp->size)
		return mp->size;
	return count;
}

/* return the number of entries allocated from the mempool */
unsigned int
rte_mempool_in_use_count(const struct rte_mempool *mp)
{
	return mp->size - rte_mempool_avail_count(mp);
}

unsigned int
rte_mempool_count(const struct rte_mempool *mp)
{
	return rte_mempool_avail_count(mp);
}

/* dump the cache status */
static unsigned
rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
{
	unsigned lcore_id;
	unsigned count = 0;
	unsigned cache_count;

	fprintf(f, "  internal cache infos:\n");
	fprintf(f, "    cache_size=%"PRIu32"\n", mp->cache_size);

	if (mp->cache_size == 0)
		return count;

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		cache_count = mp->local_cache[lcore_id].len;
		fprintf(f, "    cache_count[%u]=%"PRIu32"\n",
			lcore_id, cache_count);
		count += cache_count;
	}
	fprintf(f, "    total_cache_count=%u\n", count);
	return count;
}

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

/* check and update cookies or panic (internal) */
void rte_mempool_check_cookies(const struct rte_mempool *mp,
	void * const *obj_table_const, unsigned n, int free)
{
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	struct rte_mempool_objhdr *hdr;
	struct rte_mempool_objtlr *tlr;
	uint64_t cookie;
	void *tmp;
	void *obj;
	void **obj_table;

	/* Force to drop the "const" attribute. This is done only when
	 * DEBUG is enabled */
	tmp = (void *) obj_table_const;
	obj_table = (void **) tmp;

	while (n--) {
		obj = obj_table[n];

		if (rte_mempool_from_obj(obj) != mp)
			rte_panic("MEMPOOL: object is owned by another "
				  "mempool\n");

		hdr = __mempool_get_header(obj);
		cookie = hdr->cookie;

		if (free == 0) {
			if (cookie != RTE_MEMPOOL_HEADER_COOKIE1) {
				RTE_LOG(CRIT, MEMPOOL,
					"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
					obj, (const void *) mp, cookie);
				rte_panic("MEMPOOL: bad header cookie (put)\n");
			}
			hdr->cookie = RTE_MEMPOOL_HEADER_COOKIE2;
		} else if (free == 1) {
			if (cookie != RTE_MEMPOOL_HEADER_COOKIE2) {
				RTE_LOG(CRIT, MEMPOOL,
					"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
					obj, (const void *) mp, cookie);
				rte_panic("MEMPOOL: bad header cookie (get)\n");
			}
			hdr->cookie = RTE_MEMPOOL_HEADER_COOKIE1;
		} else if (free == 2) {
			if (cookie != RTE_MEMPOOL_HEADER_COOKIE1 &&
			    cookie != RTE_MEMPOOL_HEADER_COOKIE2) {
				RTE_LOG(CRIT, MEMPOOL,
					"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
					obj, (const void *) mp, cookie);
				rte_panic("MEMPOOL: bad header cookie (audit)\n");
			}
		}
		tlr = __mempool_get_trailer(obj);
		cookie = tlr->cookie;
		if (cookie != RTE_MEMPOOL_TRAILER_COOKIE) {
			RTE_LOG(CRIT, MEMPOOL,
				"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
				obj, (const void *) mp, cookie);
			rte_panic("MEMPOOL: bad trailer cookie\n");
		}
	}
#else
	RTE_SET_USED(mp);
	RTE_SET_USED(obj_table_const);
	RTE_SET_USED(n);
	RTE_SET_USED(free);
#endif
}

#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
static void
mempool_obj_audit(struct rte_mempool *mp, __rte_unused void *opaque,
	void *obj, __rte_unused unsigned idx)
{
	__mempool_check_cookies(mp, &obj, 1, 2);
}

static void
mempool_audit_cookies(struct rte_mempool *mp)
{
	unsigned num;

	num = rte_mempool_obj_iter(mp, mempool_obj_audit, NULL);
	if (num != mp->size) {
		rte_panic("rte_mempool_obj_iter(mempool=%p, size=%u) "
			"iterated only over %u elements\n",
			mp, mp->size, num);
	}
}
#else
#define mempool_audit_cookies(mp) do {} while(0)
#endif

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

/* check cookies before and after objects */
static void
mempool_audit_cache(const struct rte_mempool *mp)
{
	/* check cache size consistency */
	unsigned lcore_id;

	if (mp->cache_size == 0)
		return;

	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		const struct rte_mempool_cache *cache;
		cache = &mp->local_cache[lcore_id];
		if (cache->len > cache->flushthresh) {
			RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
				lcore_id);
			rte_panic("MEMPOOL: invalid cache len\n");
		}
	}
}

/* check the consistency of mempool (size, cookies, ...) */
void
rte_mempool_audit(struct rte_mempool *mp)
{
	mempool_audit_cache(mp);
	mempool_audit_cookies(mp);

	/* For case where mempool DEBUG is not set, and cache size is 0 */
	RTE_SET_USED(mp);
}

/* dump the status of the mempool on the console */
void
rte_mempool_dump(FILE *f, struct rte_mempool *mp)
{
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	struct rte_mempool_debug_stats sum;
	unsigned lcore_id;
#endif
	struct rte_mempool_memhdr *memhdr;
	unsigned common_count;
	unsigned cache_count;
	size_t mem_len = 0;

	RTE_ASSERT(f != NULL);
	RTE_ASSERT(mp != NULL);

	fprintf(f, "mempool <%s>@%p\n", mp->name, mp);
	fprintf(f, "  flags=%x\n", mp->flags);
	fprintf(f, "  pool=%p\n", mp->pool_data);
	fprintf(f, "  phys_addr=0x%" PRIx64 "\n", mp->mz->phys_addr);
	fprintf(f, "  nb_mem_chunks=%u\n", mp->nb_mem_chunks);
	fprintf(f, "  size=%"PRIu32"\n", mp->size);
	fprintf(f, "  populated_size=%"PRIu32"\n", mp->populated_size);
	fprintf(f, "  header_size=%"PRIu32"\n", mp->header_size);
	fprintf(f, "  elt_size=%"PRIu32"\n", mp->elt_size);
	fprintf(f, "  trailer_size=%"PRIu32"\n", mp->trailer_size);
	fprintf(f, "  total_obj_size=%"PRIu32"\n",
	       mp->header_size + mp->elt_size + mp->trailer_size);

	fprintf(f, "  private_data_size=%"PRIu32"\n", mp->private_data_size);

	STAILQ_FOREACH(memhdr, &mp->mem_list, next)
		mem_len += memhdr->len;
	if (mem_len != 0) {
		fprintf(f, "  avg bytes/object=%#Lf\n",
			(long double)mem_len / mp->size);
	}

	cache_count = rte_mempool_dump_cache(f, mp);
	common_count = rte_mempool_ops_get_count(mp);
	if ((cache_count + common_count) > mp->size)
		common_count = mp->size - cache_count;
	fprintf(f, "  common_pool_count=%u\n", common_count);

	/* sum and dump statistics */
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	memset(&sum, 0, sizeof(sum));
	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
		sum.put_bulk += mp->stats[lcore_id].put_bulk;
		sum.put_objs += mp->stats[lcore_id].put_objs;
		sum.get_success_bulk += mp->stats[lcore_id].get_success_bulk;
		sum.get_success_objs += mp->stats[lcore_id].get_success_objs;
		sum.get_fail_bulk += mp->stats[lcore_id].get_fail_bulk;
		sum.get_fail_objs += mp->stats[lcore_id].get_fail_objs;
	}
	fprintf(f, "  stats:\n");
	fprintf(f, "    put_bulk=%"PRIu64"\n", sum.put_bulk);
	fprintf(f, "    put_objs=%"PRIu64"\n", sum.put_objs);
	fprintf(f, "    get_success_bulk=%"PRIu64"\n", sum.get_success_bulk);
	fprintf(f, "    get_success_objs=%"PRIu64"\n", sum.get_success_objs);
	fprintf(f, "    get_fail_bulk=%"PRIu64"\n", sum.get_fail_bulk);
	fprintf(f, "    get_fail_objs=%"PRIu64"\n", sum.get_fail_objs);
#else
	fprintf(f, "  no statistics available\n");
#endif

	rte_mempool_audit(mp);
}

/* dump the status of all mempools on the console */
void
rte_mempool_list_dump(FILE *f)
{
	struct rte_mempool *mp = NULL;
	struct rte_tailq_entry *te;
	struct rte_mempool_list *mempool_list;

	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);

	rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);

	TAILQ_FOREACH(te, mempool_list, next) {
		mp = (struct rte_mempool *) te->data;
		rte_mempool_dump(f, mp);
	}

	rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
}

/* search a mempool from its name */
struct rte_mempool *
rte_mempool_lookup(const char *name)
{
	struct rte_mempool *mp = NULL;
	struct rte_tailq_entry *te;
	struct rte_mempool_list *mempool_list;

	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);

	rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);

	TAILQ_FOREACH(te, mempool_list, next) {
		mp = (struct rte_mempool *) te->data;
		if (strncmp(name, mp->name, RTE_MEMPOOL_NAMESIZE) == 0)
			break;
	}

	rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);

	if (te == NULL) {
		rte_errno = ENOENT;
		return NULL;
	}

	return mp;
}

void rte_mempool_walk(void (*func)(struct rte_mempool *, void *),
		      void *arg)
{
	struct rte_tailq_entry *te = NULL;
	struct rte_mempool_list *mempool_list;
	void *tmp_te;

	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);

	rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);

	TAILQ_FOREACH_SAFE(te, mempool_list, next, tmp_te) {
		(*func)((struct rte_mempool *) te->data, arg);
	}

	rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
}