summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/python.c
blob: 02460362256d17f5833320cbb6db5ebe0768907e (plain) (blame)
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
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
// SPDX-License-Identifier: GPL-2.0
#include <Python.h>
#include <structmember.h>
#include <inttypes.h>
#include <poll.h>
#include <linux/err.h>
#include <perf/cpumap.h>
#include <traceevent/event-parse.h>
#include "evlist.h"
#include "callchain.h"
#include "evsel.h"
#include "event.h"
#include "print_binary.h"
#include "thread_map.h"
#include "trace-event.h"
#include "mmap.h"
#include "util/env.h"
#include <internal/lib.h>
#include "../perf-sys.h"

#if PY_MAJOR_VERSION < 3
#define _PyUnicode_FromString(arg) \
  PyString_FromString(arg)
#define _PyUnicode_AsString(arg) \
  PyString_AsString(arg)
#define _PyUnicode_FromFormat(...) \
  PyString_FromFormat(__VA_ARGS__)
#define _PyLong_FromLong(arg) \
  PyInt_FromLong(arg)

#else

#define _PyUnicode_FromString(arg) \
  PyUnicode_FromString(arg)
#define _PyUnicode_FromFormat(...) \
  PyUnicode_FromFormat(__VA_ARGS__)
#define _PyLong_FromLong(arg) \
  PyLong_FromLong(arg)
#endif

#ifndef Py_TYPE
#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
#endif

/*
 * Provide these two so that we don't have to link against callchain.c and
 * start dragging hist.c, etc.
 */
struct callchain_param callchain_param;

int parse_callchain_record(const char *arg __maybe_unused,
			   struct callchain_param *param __maybe_unused)
{
	return 0;
}

/*
 * Add this one here not to drag util/env.c
 */
struct perf_env perf_env;

/*
 * Support debug printing even though util/debug.c is not linked.  That means
 * implementing 'verbose' and 'eprintf'.
 */
int verbose;

int eprintf(int level, int var, const char *fmt, ...);

int eprintf(int level, int var, const char *fmt, ...)
{
	va_list args;
	int ret = 0;

	if (var >= level) {
		va_start(args, fmt);
		ret = vfprintf(stderr, fmt, args);
		va_end(args);
	}

	return ret;
}

/* Define PyVarObject_HEAD_INIT for python 2.5 */
#ifndef PyVarObject_HEAD_INIT
# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
#endif

#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initperf(void);
#else
PyMODINIT_FUNC PyInit_perf(void);
#endif

#define member_def(type, member, ptype, help) \
	{ #member, ptype, \
	  offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
	  0, help }

#define sample_member_def(name, member, ptype, help) \
	{ #name, ptype, \
	  offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \
	  0, help }

struct pyrf_event {
	PyObject_HEAD
	struct evsel *evsel;
	struct perf_sample sample;
	union perf_event   event;
};

#define sample_members \
	sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"),			 \
	sample_member_def(sample_pid, pid, T_INT, "event pid"),			 \
	sample_member_def(sample_tid, tid, T_INT, "event tid"),			 \
	sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"),		 \
	sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"),		 \
	sample_member_def(sample_id, id, T_ULONGLONG, "event id"),			 \
	sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
	sample_member_def(sample_period, period, T_ULONGLONG, "event period"),		 \
	sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),

static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");

static PyMemberDef pyrf_mmap_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	member_def(perf_event_header, misc, T_UINT, "event misc"),
	member_def(perf_record_mmap, pid, T_UINT, "event pid"),
	member_def(perf_record_mmap, tid, T_UINT, "event tid"),
	member_def(perf_record_mmap, start, T_ULONGLONG, "start of the map"),
	member_def(perf_record_mmap, len, T_ULONGLONG, "map length"),
	member_def(perf_record_mmap, pgoff, T_ULONGLONG, "page offset"),
	member_def(perf_record_mmap, filename, T_STRING_INPLACE, "backing store"),
	{ .name = NULL, },
};

static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
{
	PyObject *ret;
	char *s;

	if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRI_lx64 ", "
			 "length: %#" PRI_lx64 ", offset: %#" PRI_lx64 ", "
			 "filename: %s }",
		     pevent->event.mmap.pid, pevent->event.mmap.tid,
		     pevent->event.mmap.start, pevent->event.mmap.len,
		     pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
		ret = PyErr_NoMemory();
	} else {
		ret = _PyUnicode_FromString(s);
		free(s);
	}
	return ret;
}

static PyTypeObject pyrf_mmap_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.mmap_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_mmap_event__doc,
	.tp_members	= pyrf_mmap_event__members,
	.tp_repr	= (reprfunc)pyrf_mmap_event__repr,
};

static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");

static PyMemberDef pyrf_task_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	member_def(perf_record_fork, pid, T_UINT, "event pid"),
	member_def(perf_record_fork, ppid, T_UINT, "event ppid"),
	member_def(perf_record_fork, tid, T_UINT, "event tid"),
	member_def(perf_record_fork, ptid, T_UINT, "event ptid"),
	member_def(perf_record_fork, time, T_ULONGLONG, "timestamp"),
	{ .name = NULL, },
};

static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
{
	return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
				   "ptid: %u, time: %" PRI_lu64 "}",
				   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
				   pevent->event.fork.pid,
				   pevent->event.fork.ppid,
				   pevent->event.fork.tid,
				   pevent->event.fork.ptid,
				   pevent->event.fork.time);
}

static PyTypeObject pyrf_task_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.task_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_task_event__doc,
	.tp_members	= pyrf_task_event__members,
	.tp_repr	= (reprfunc)pyrf_task_event__repr,
};

static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");

static PyMemberDef pyrf_comm_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	member_def(perf_record_comm, pid, T_UINT, "event pid"),
	member_def(perf_record_comm, tid, T_UINT, "event tid"),
	member_def(perf_record_comm, comm, T_STRING_INPLACE, "process name"),
	{ .name = NULL, },
};

static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
{
	return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
				   pevent->event.comm.pid,
				   pevent->event.comm.tid,
				   pevent->event.comm.comm);
}

static PyTypeObject pyrf_comm_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.comm_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_comm_event__doc,
	.tp_members	= pyrf_comm_event__members,
	.tp_repr	= (reprfunc)pyrf_comm_event__repr,
};

static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object.");

static PyMemberDef pyrf_throttle_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	member_def(perf_record_throttle, time, T_ULONGLONG, "timestamp"),
	member_def(perf_record_throttle, id, T_ULONGLONG, "event id"),
	member_def(perf_record_throttle, stream_id, T_ULONGLONG, "event stream id"),
	{ .name = NULL, },
};

static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
{
	struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1);

	return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64
				   ", stream_id: %" PRI_lu64 " }",
				   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
				   te->time, te->id, te->stream_id);
}

static PyTypeObject pyrf_throttle_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.throttle_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_throttle_event__doc,
	.tp_members	= pyrf_throttle_event__members,
	.tp_repr	= (reprfunc)pyrf_throttle_event__repr,
};

static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object.");

static PyMemberDef pyrf_lost_event__members[] = {
	sample_members
	member_def(perf_record_lost, id, T_ULONGLONG, "event id"),
	member_def(perf_record_lost, lost, T_ULONGLONG, "number of lost events"),
	{ .name = NULL, },
};

static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
{
	PyObject *ret;
	char *s;

	if (asprintf(&s, "{ type: lost, id: %#" PRI_lx64 ", "
			 "lost: %#" PRI_lx64 " }",
		     pevent->event.lost.id, pevent->event.lost.lost) < 0) {
		ret = PyErr_NoMemory();
	} else {
		ret = _PyUnicode_FromString(s);
		free(s);
	}
	return ret;
}

static PyTypeObject pyrf_lost_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.lost_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_lost_event__doc,
	.tp_members	= pyrf_lost_event__members,
	.tp_repr	= (reprfunc)pyrf_lost_event__repr,
};

static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object.");

static PyMemberDef pyrf_read_event__members[] = {
	sample_members
	member_def(perf_record_read, pid, T_UINT, "event pid"),
	member_def(perf_record_read, tid, T_UINT, "event tid"),
	{ .name = NULL, },
};

static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent)
{
	return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }",
				   pevent->event.read.pid,
				   pevent->event.read.tid);
	/*
 	 * FIXME: return the array of read values,
 	 * making this method useful ;-)
 	 */
}

static PyTypeObject pyrf_read_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.read_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_read_event__doc,
	.tp_members	= pyrf_read_event__members,
	.tp_repr	= (reprfunc)pyrf_read_event__repr,
};

static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object.");

static PyMemberDef pyrf_sample_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	{ .name = NULL, },
};

static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
{
	PyObject *ret;
	char *s;

	if (asprintf(&s, "{ type: sample }") < 0) {
		ret = PyErr_NoMemory();
	} else {
		ret = _PyUnicode_FromString(s);
		free(s);
	}
	return ret;
}

static bool is_tracepoint(struct pyrf_event *pevent)
{
	return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT;
}

static PyObject*
tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
{
	struct tep_handle *pevent = field->event->tep;
	void *data = pe->sample.raw_data;
	PyObject *ret = NULL;
	unsigned long long val;
	unsigned int offset, len;

	if (field->flags & TEP_FIELD_IS_ARRAY) {
		offset = field->offset;
		len    = field->size;
		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
			val     = tep_read_number(pevent, data + offset, len);
			offset  = val;
			len     = offset >> 16;
			offset &= 0xffff;
		}
		if (field->flags & TEP_FIELD_IS_STRING &&
		    is_printable_array(data + offset, len)) {
			ret = _PyUnicode_FromString((char *)data + offset);
		} else {
			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
			field->flags &= ~TEP_FIELD_IS_STRING;
		}
	} else {
		val = tep_read_number(pevent, data + field->offset,
				      field->size);
		if (field->flags & TEP_FIELD_IS_POINTER)
			ret = PyLong_FromUnsignedLong((unsigned long) val);
		else if (field->flags & TEP_FIELD_IS_SIGNED)
			ret = PyLong_FromLong((long) val);
		else
			ret = PyLong_FromUnsignedLong((unsigned long) val);
	}

	return ret;
}

static PyObject*
get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
{
	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
	struct evsel *evsel = pevent->evsel;
	struct tep_format_field *field;

	if (!evsel->tp_format) {
		struct tep_event *tp_format;

		tp_format = trace_event__tp_format_id(evsel->core.attr.config);
		if (!tp_format)
			return NULL;

		evsel->tp_format = tp_format;
	}

	field = tep_find_any_field(evsel->tp_format, str);
	if (!field)
		return NULL;

	return tracepoint_field(pevent, field);
}

static PyObject*
pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
{
	PyObject *obj = NULL;

	if (is_tracepoint(pevent))
		obj = get_tracepoint_field(pevent, attr_name);

	return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name);
}

static PyTypeObject pyrf_sample_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.sample_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_sample_event__doc,
	.tp_members	= pyrf_sample_event__members,
	.tp_repr	= (reprfunc)pyrf_sample_event__repr,
	.tp_getattro	= (getattrofunc) pyrf_sample_event__getattro,
};

static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object.");

static PyMemberDef pyrf_context_switch_event__members[] = {
	sample_members
	member_def(perf_event_header, type, T_UINT, "event type"),
	member_def(perf_record_switch, next_prev_pid, T_UINT, "next/prev pid"),
	member_def(perf_record_switch, next_prev_tid, T_UINT, "next/prev tid"),
	{ .name = NULL, },
};

static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent)
{
	PyObject *ret;
	char *s;

	if (asprintf(&s, "{ type: context_switch, next_prev_pid: %u, next_prev_tid: %u, switch_out: %u }",
		     pevent->event.context_switch.next_prev_pid,
		     pevent->event.context_switch.next_prev_tid,
		     !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) {
		ret = PyErr_NoMemory();
	} else {
		ret = _PyUnicode_FromString(s);
		free(s);
	}
	return ret;
}

static PyTypeObject pyrf_context_switch_event__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.context_switch_event",
	.tp_basicsize	= sizeof(struct pyrf_event),
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_context_switch_event__doc,
	.tp_members	= pyrf_context_switch_event__members,
	.tp_repr	= (reprfunc)pyrf_context_switch_event__repr,
};

static int pyrf_event__setup_types(void)
{
	int err;
	pyrf_mmap_event__type.tp_new =
	pyrf_task_event__type.tp_new =
	pyrf_comm_event__type.tp_new =
	pyrf_lost_event__type.tp_new =
	pyrf_read_event__type.tp_new =
	pyrf_sample_event__type.tp_new =
	pyrf_context_switch_event__type.tp_new =
	pyrf_throttle_event__type.tp_new = PyType_GenericNew;
	err = PyType_Ready(&pyrf_mmap_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_lost_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_task_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_comm_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_throttle_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_read_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_sample_event__type);
	if (err < 0)
		goto out;
	err = PyType_Ready(&pyrf_context_switch_event__type);
	if (err < 0)
		goto out;
out:
	return err;
}

static PyTypeObject *pyrf_event__type[] = {
	[PERF_RECORD_MMAP]	 = &pyrf_mmap_event__type,
	[PERF_RECORD_LOST]	 = &pyrf_lost_event__type,
	[PERF_RECORD_COMM]	 = &pyrf_comm_event__type,
	[PERF_RECORD_EXIT]	 = &pyrf_task_event__type,
	[PERF_RECORD_THROTTLE]	 = &pyrf_throttle_event__type,
	[PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
	[PERF_RECORD_FORK]	 = &pyrf_task_event__type,
	[PERF_RECORD_READ]	 = &pyrf_read_event__type,
	[PERF_RECORD_SAMPLE]	 = &pyrf_sample_event__type,
	[PERF_RECORD_SWITCH]	 = &pyrf_context_switch_event__type,
	[PERF_RECORD_SWITCH_CPU_WIDE]  = &pyrf_context_switch_event__type,
};

static PyObject *pyrf_event__new(union perf_event *event)
{
	struct pyrf_event *pevent;
	PyTypeObject *ptype;

	if ((event->header.type < PERF_RECORD_MMAP ||
	     event->header.type > PERF_RECORD_SAMPLE) &&
	    !(event->header.type == PERF_RECORD_SWITCH ||
	      event->header.type == PERF_RECORD_SWITCH_CPU_WIDE))
		return NULL;

	ptype = pyrf_event__type[event->header.type];
	pevent = PyObject_New(struct pyrf_event, ptype);
	if (pevent != NULL)
		memcpy(&pevent->event, event, event->header.size);
	return (PyObject *)pevent;
}

struct pyrf_cpu_map {
	PyObject_HEAD

	struct perf_cpu_map *cpus;
};

static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
			      PyObject *args, PyObject *kwargs)
{
	static char *kwlist[] = { "cpustr", NULL };
	char *cpustr = NULL;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s",
					 kwlist, &cpustr))
		return -1;

	pcpus->cpus = perf_cpu_map__new(cpustr);
	if (pcpus->cpus == NULL)
		return -1;
	return 0;
}

static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
{
	perf_cpu_map__put(pcpus->cpus);
	Py_TYPE(pcpus)->tp_free((PyObject*)pcpus);
}

static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
{
	struct pyrf_cpu_map *pcpus = (void *)obj;

	return pcpus->cpus->nr;
}

static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
{
	struct pyrf_cpu_map *pcpus = (void *)obj;

	if (i >= pcpus->cpus->nr)
		return NULL;

	return Py_BuildValue("i", pcpus->cpus->map[i]);
}

static PySequenceMethods pyrf_cpu_map__sequence_methods = {
	.sq_length = pyrf_cpu_map__length,
	.sq_item   = pyrf_cpu_map__item,
};

static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object.");

static PyTypeObject pyrf_cpu_map__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.cpu_map",
	.tp_basicsize	= sizeof(struct pyrf_cpu_map),
	.tp_dealloc	= (destructor)pyrf_cpu_map__delete,
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_cpu_map__doc,
	.tp_as_sequence	= &pyrf_cpu_map__sequence_methods,
	.tp_init	= (initproc)pyrf_cpu_map__init,
};

static int pyrf_cpu_map__setup_types(void)
{
	pyrf_cpu_map__type.tp_new = PyType_GenericNew;
	return PyType_Ready(&pyrf_cpu_map__type);
}

struct pyrf_thread_map {
	PyObject_HEAD

	struct perf_thread_map *threads;
};

static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
				 PyObject *args, PyObject *kwargs)
{
	static char *kwlist[] = { "pid", "tid", "uid", NULL };
	int pid = -1, tid = -1, uid = UINT_MAX;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii",
					 kwlist, &pid, &tid, &uid))
		return -1;

	pthreads->threads = thread_map__new(pid, tid, uid);
	if (pthreads->threads == NULL)
		return -1;
	return 0;
}

static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
{
	perf_thread_map__put(pthreads->threads);
	Py_TYPE(pthreads)->tp_free((PyObject*)pthreads);
}

static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
{
	struct pyrf_thread_map *pthreads = (void *)obj;

	return pthreads->threads->nr;
}

static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i)
{
	struct pyrf_thread_map *pthreads = (void *)obj;

	if (i >= pthreads->threads->nr)
		return NULL;

	return Py_BuildValue("i", pthreads->threads->map[i]);
}

static PySequenceMethods pyrf_thread_map__sequence_methods = {
	.sq_length = pyrf_thread_map__length,
	.sq_item   = pyrf_thread_map__item,
};

static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object.");

static PyTypeObject pyrf_thread_map__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.thread_map",
	.tp_basicsize	= sizeof(struct pyrf_thread_map),
	.tp_dealloc	= (destructor)pyrf_thread_map__delete,
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_thread_map__doc,
	.tp_as_sequence	= &pyrf_thread_map__sequence_methods,
	.tp_init	= (initproc)pyrf_thread_map__init,
};

static int pyrf_thread_map__setup_types(void)
{
	pyrf_thread_map__type.tp_new = PyType_GenericNew;
	return PyType_Ready(&pyrf_thread_map__type);
}

struct pyrf_evsel {
	PyObject_HEAD

	struct evsel evsel;
};

static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
			    PyObject *args, PyObject *kwargs)
{
	struct perf_event_attr attr = {
		.type = PERF_TYPE_HARDWARE,
		.config = PERF_COUNT_HW_CPU_CYCLES,
		.sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID,
	};
	static char *kwlist[] = {
		"type",
		"config",
		"sample_freq",
		"sample_period",
		"sample_type",
		"read_format",
		"disabled",
		"inherit",
		"pinned",
		"exclusive",
		"exclude_user",
		"exclude_kernel",
		"exclude_hv",
		"exclude_idle",
		"mmap",
		"context_switch",
		"comm",
		"freq",
		"inherit_stat",
		"enable_on_exec",
		"task",
		"watermark",
		"precise_ip",
		"mmap_data",
		"sample_id_all",
		"wakeup_events",
		"bp_type",
		"bp_addr",
		"bp_len",
		 NULL
	};
	u64 sample_period = 0;
	u32 disabled = 0,
	    inherit = 0,
	    pinned = 0,
	    exclusive = 0,
	    exclude_user = 0,
	    exclude_kernel = 0,
	    exclude_hv = 0,
	    exclude_idle = 0,
	    mmap = 0,
	    context_switch = 0,
	    comm = 0,
	    freq = 1,
	    inherit_stat = 0,
	    enable_on_exec = 0,
	    task = 0,
	    watermark = 0,
	    precise_ip = 0,
	    mmap_data = 0,
	    sample_id_all = 1;
	int idx = 0;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs,
					 "|iKiKKiiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
					 &attr.type, &attr.config, &attr.sample_freq,
					 &sample_period, &attr.sample_type,
					 &attr.read_format, &disabled, &inherit,
					 &pinned, &exclusive, &exclude_user,
					 &exclude_kernel, &exclude_hv, &exclude_idle,
					 &mmap, &context_switch, &comm, &freq, &inherit_stat,
					 &enable_on_exec, &task, &watermark,
					 &precise_ip, &mmap_data, &sample_id_all,
					 &attr.wakeup_events, &attr.bp_type,
					 &attr.bp_addr, &attr.bp_len, &idx))
		return -1;

	/* union... */
	if (sample_period != 0) {
		if (attr.sample_freq != 0)
			return -1; /* FIXME: throw right exception */
		attr.sample_period = sample_period;
	}

	/* Bitfields */
	attr.disabled	    = disabled;
	attr.inherit	    = inherit;
	attr.pinned	    = pinned;
	attr.exclusive	    = exclusive;
	attr.exclude_user   = exclude_user;
	attr.exclude_kernel = exclude_kernel;
	attr.exclude_hv	    = exclude_hv;
	attr.exclude_idle   = exclude_idle;
	attr.mmap	    = mmap;
	attr.context_switch = context_switch;
	attr.comm	    = comm;
	attr.freq	    = freq;
	attr.inherit_stat   = inherit_stat;
	attr.enable_on_exec = enable_on_exec;
	attr.task	    = task;
	attr.watermark	    = watermark;
	attr.precise_ip	    = precise_ip;
	attr.mmap_data	    = mmap_data;
	attr.sample_id_all  = sample_id_all;
	attr.size	    = sizeof(attr);

	evsel__init(&pevsel->evsel, &attr, idx);
	return 0;
}

static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
{
	perf_evsel__exit(&pevsel->evsel);
	Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
}

static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
				  PyObject *args, PyObject *kwargs)
{
	struct evsel *evsel = &pevsel->evsel;
	struct perf_cpu_map *cpus = NULL;
	struct perf_thread_map *threads = NULL;
	PyObject *pcpus = NULL, *pthreads = NULL;
	int group = 0, inherit = 0;
	static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL };

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
					 &pcpus, &pthreads, &group, &inherit))
		return NULL;

	if (pthreads != NULL)
		threads = ((struct pyrf_thread_map *)pthreads)->threads;

	if (pcpus != NULL)
		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;

	evsel->core.attr.inherit = inherit;
	/*
	 * This will group just the fds for this single evsel, to group
	 * multiple events, use evlist.open().
	 */
	if (evsel__open(evsel, cpus, threads) < 0) {
		PyErr_SetFromErrno(PyExc_OSError);
		return NULL;
	}

	Py_INCREF(Py_None);
	return Py_None;
}

static PyMethodDef pyrf_evsel__methods[] = {
	{
		.ml_name  = "open",
		.ml_meth  = (PyCFunction)pyrf_evsel__open,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("open the event selector file descriptor table.")
	},
	{ .ml_name = NULL, }
};

static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");

static PyTypeObject pyrf_evsel__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.evsel",
	.tp_basicsize	= sizeof(struct pyrf_evsel),
	.tp_dealloc	= (destructor)pyrf_evsel__delete,
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_doc		= pyrf_evsel__doc,
	.tp_methods	= pyrf_evsel__methods,
	.tp_init	= (initproc)pyrf_evsel__init,
};

static int pyrf_evsel__setup_types(void)
{
	pyrf_evsel__type.tp_new = PyType_GenericNew;
	return PyType_Ready(&pyrf_evsel__type);
}

struct pyrf_evlist {
	PyObject_HEAD

	struct evlist evlist;
};

static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
			     PyObject *args, PyObject *kwargs __maybe_unused)
{
	PyObject *pcpus = NULL, *pthreads = NULL;
	struct perf_cpu_map *cpus;
	struct perf_thread_map *threads;

	if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
		return -1;

	threads = ((struct pyrf_thread_map *)pthreads)->threads;
	cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
	evlist__init(&pevlist->evlist, cpus, threads);
	return 0;
}

static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
{
	evlist__exit(&pevlist->evlist);
	Py_TYPE(pevlist)->tp_free((PyObject*)pevlist);
}

static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
				   PyObject *args, PyObject *kwargs)
{
	struct evlist *evlist = &pevlist->evlist;
	static char *kwlist[] = { "pages", "overwrite", NULL };
	int pages = 128, overwrite = false;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist,
					 &pages, &overwrite))
		return NULL;

	if (evlist__mmap(evlist, pages) < 0) {
		PyErr_SetFromErrno(PyExc_OSError);
		return NULL;
	}

	Py_INCREF(Py_None);
	return Py_None;
}

static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
				   PyObject *args, PyObject *kwargs)
{
	struct evlist *evlist = &pevlist->evlist;
	static char *kwlist[] = { "timeout", NULL };
	int timeout = -1, n;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
		return NULL;

	n = evlist__poll(evlist, timeout);
	if (n < 0) {
		PyErr_SetFromErrno(PyExc_OSError);
		return NULL;
	}

	return Py_BuildValue("i", n);
}

static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
					 PyObject *args __maybe_unused,
					 PyObject *kwargs __maybe_unused)
{
	struct evlist *evlist = &pevlist->evlist;
        PyObject *list = PyList_New(0);
	int i;

	for (i = 0; i < evlist->core.pollfd.nr; ++i) {
		PyObject *file;
#if PY_MAJOR_VERSION < 3
		FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r");

		if (fp == NULL)
			goto free_list;

		file = PyFile_FromFile(fp, "perf", "r", NULL);
#else
		file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1,
				     NULL, NULL, NULL, 0);
#endif
		if (file == NULL)
			goto free_list;

		if (PyList_Append(list, file) != 0) {
			Py_DECREF(file);
			goto free_list;
		}

		Py_DECREF(file);
	}

	return list;
free_list:
	return PyErr_NoMemory();
}


static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
				  PyObject *args,
				  PyObject *kwargs __maybe_unused)
{
	struct evlist *evlist = &pevlist->evlist;
	PyObject *pevsel;
	struct evsel *evsel;

	if (!PyArg_ParseTuple(args, "O", &pevsel))
		return NULL;

	Py_INCREF(pevsel);
	evsel = &((struct pyrf_evsel *)pevsel)->evsel;
	evsel->idx = evlist->core.nr_entries;
	evlist__add(evlist, evsel);

	return Py_BuildValue("i", evlist->core.nr_entries);
}

static struct mmap *get_md(struct evlist *evlist, int cpu)
{
	int i;

	for (i = 0; i < evlist->core.nr_mmaps; i++) {
		struct mmap *md = &evlist->mmap[i];

		if (md->core.cpu == cpu)
			return md;
	}

	return NULL;
}

static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
					  PyObject *args, PyObject *kwargs)
{
	struct evlist *evlist = &pevlist->evlist;
	union perf_event *event;
	int sample_id_all = 1, cpu;
	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
	struct mmap *md;
	int err;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
					 &cpu, &sample_id_all))
		return NULL;

	md = get_md(evlist, cpu);
	if (!md)
		return NULL;

	if (perf_mmap__read_init(md) < 0)
		goto end;

	event = perf_mmap__read_event(md);
	if (event != NULL) {
		PyObject *pyevent = pyrf_event__new(event);
		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
		struct evsel *evsel;

		if (pyevent == NULL)
			return PyErr_NoMemory();

		evsel = perf_evlist__event2evsel(evlist, event);
		if (!evsel) {
			Py_INCREF(Py_None);
			return Py_None;
		}

		pevent->evsel = evsel;

		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);

		/* Consume the even only after we parsed it out. */
		perf_mmap__consume(md);

		if (err)
			return PyErr_Format(PyExc_OSError,
					    "perf: can't parse sample, err=%d", err);
		return pyevent;
	}
end:
	Py_INCREF(Py_None);
	return Py_None;
}

static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
				   PyObject *args, PyObject *kwargs)
{
	struct evlist *evlist = &pevlist->evlist;
	int group = 0;
	static char *kwlist[] = { "group", NULL };

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group))
		return NULL;

	if (group)
		perf_evlist__set_leader(evlist);

	if (evlist__open(evlist) < 0) {
		PyErr_SetFromErrno(PyExc_OSError);
		return NULL;
	}

	Py_INCREF(Py_None);
	return Py_None;
}

static PyMethodDef pyrf_evlist__methods[] = {
	{
		.ml_name  = "mmap",
		.ml_meth  = (PyCFunction)pyrf_evlist__mmap,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("mmap the file descriptor table.")
	},
	{
		.ml_name  = "open",
		.ml_meth  = (PyCFunction)pyrf_evlist__open,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("open the file descriptors.")
	},
	{
		.ml_name  = "poll",
		.ml_meth  = (PyCFunction)pyrf_evlist__poll,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("poll the file descriptor table.")
	},
	{
		.ml_name  = "get_pollfd",
		.ml_meth  = (PyCFunction)pyrf_evlist__get_pollfd,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("get the poll file descriptor table.")
	},
	{
		.ml_name  = "add",
		.ml_meth  = (PyCFunction)pyrf_evlist__add,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("adds an event selector to the list.")
	},
	{
		.ml_name  = "read_on_cpu",
		.ml_meth  = (PyCFunction)pyrf_evlist__read_on_cpu,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("reads an event.")
	},
	{ .ml_name = NULL, }
};

static Py_ssize_t pyrf_evlist__length(PyObject *obj)
{
	struct pyrf_evlist *pevlist = (void *)obj;

	return pevlist->evlist.core.nr_entries;
}

static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
{
	struct pyrf_evlist *pevlist = (void *)obj;
	struct evsel *pos;

	if (i >= pevlist->evlist.core.nr_entries)
		return NULL;

	evlist__for_each_entry(&pevlist->evlist, pos) {
		if (i-- == 0)
			break;
	}

	return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
}

static PySequenceMethods pyrf_evlist__sequence_methods = {
	.sq_length = pyrf_evlist__length,
	.sq_item   = pyrf_evlist__item,
};

static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object.");

static PyTypeObject pyrf_evlist__type = {
	PyVarObject_HEAD_INIT(NULL, 0)
	.tp_name	= "perf.evlist",
	.tp_basicsize	= sizeof(struct pyrf_evlist),
	.tp_dealloc	= (destructor)pyrf_evlist__delete,
	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
	.tp_as_sequence	= &pyrf_evlist__sequence_methods,
	.tp_doc		= pyrf_evlist__doc,
	.tp_methods	= pyrf_evlist__methods,
	.tp_init	= (initproc)pyrf_evlist__init,
};

static int pyrf_evlist__setup_types(void)
{
	pyrf_evlist__type.tp_new = PyType_GenericNew;
	return PyType_Ready(&pyrf_evlist__type);
}

#define PERF_CONST(name) { #name, PERF_##name }

static struct {
	const char *name;
	int	    value;
} perf__constants[] = {
	PERF_CONST(TYPE_HARDWARE),
	PERF_CONST(TYPE_SOFTWARE),
	PERF_CONST(TYPE_TRACEPOINT),
	PERF_CONST(TYPE_HW_CACHE),
	PERF_CONST(TYPE_RAW),
	PERF_CONST(TYPE_BREAKPOINT),

	PERF_CONST(COUNT_HW_CPU_CYCLES),
	PERF_CONST(COUNT_HW_INSTRUCTIONS),
	PERF_CONST(COUNT_HW_CACHE_REFERENCES),
	PERF_CONST(COUNT_HW_CACHE_MISSES),
	PERF_CONST(COUNT_HW_BRANCH_INSTRUCTIONS),
	PERF_CONST(COUNT_HW_BRANCH_MISSES),
	PERF_CONST(COUNT_HW_BUS_CYCLES),
	PERF_CONST(COUNT_HW_CACHE_L1D),
	PERF_CONST(COUNT_HW_CACHE_L1I),
	PERF_CONST(COUNT_HW_CACHE_LL),
	PERF_CONST(COUNT_HW_CACHE_DTLB),
	PERF_CONST(COUNT_HW_CACHE_ITLB),
	PERF_CONST(COUNT_HW_CACHE_BPU),
	PERF_CONST(COUNT_HW_CACHE_OP_READ),
	PERF_CONST(COUNT_HW_CACHE_OP_WRITE),
	PERF_CONST(COUNT_HW_CACHE_OP_PREFETCH),
	PERF_CONST(COUNT_HW_CACHE_RESULT_ACCESS),
	PERF_CONST(COUNT_HW_CACHE_RESULT_MISS),

	PERF_CONST(COUNT_HW_STALLED_CYCLES_FRONTEND),
	PERF_CONST(COUNT_HW_STALLED_CYCLES_BACKEND),

	PERF_CONST(COUNT_SW_CPU_CLOCK),
	PERF_CONST(COUNT_SW_TASK_CLOCK),
	PERF_CONST(COUNT_SW_PAGE_FAULTS),
	PERF_CONST(COUNT_SW_CONTEXT_SWITCHES),
	PERF_CONST(COUNT_SW_CPU_MIGRATIONS),
	PERF_CONST(COUNT_SW_PAGE_FAULTS_MIN),
	PERF_CONST(COUNT_SW_PAGE_FAULTS_MAJ),
	PERF_CONST(COUNT_SW_ALIGNMENT_FAULTS),
	PERF_CONST(COUNT_SW_EMULATION_FAULTS),
	PERF_CONST(COUNT_SW_DUMMY),

	PERF_CONST(SAMPLE_IP),
	PERF_CONST(SAMPLE_TID),
	PERF_CONST(SAMPLE_TIME),
	PERF_CONST(SAMPLE_ADDR),
	PERF_CONST(SAMPLE_READ),
	PERF_CONST(SAMPLE_CALLCHAIN),
	PERF_CONST(SAMPLE_ID),
	PERF_CONST(SAMPLE_CPU),
	PERF_CONST(SAMPLE_PERIOD),
	PERF_CONST(SAMPLE_STREAM_ID),
	PERF_CONST(SAMPLE_RAW),

	PERF_CONST(FORMAT_TOTAL_TIME_ENABLED),
	PERF_CONST(FORMAT_TOTAL_TIME_RUNNING),
	PERF_CONST(FORMAT_ID),
	PERF_CONST(FORMAT_GROUP),

	PERF_CONST(RECORD_MMAP),
	PERF_CONST(RECORD_LOST),
	PERF_CONST(RECORD_COMM),
	PERF_CONST(RECORD_EXIT),
	PERF_CONST(RECORD_THROTTLE),
	PERF_CONST(RECORD_UNTHROTTLE),
	PERF_CONST(RECORD_FORK),
	PERF_CONST(RECORD_READ),
	PERF_CONST(RECORD_SAMPLE),
	PERF_CONST(RECORD_MMAP2),
	PERF_CONST(RECORD_AUX),
	PERF_CONST(RECORD_ITRACE_START),
	PERF_CONST(RECORD_LOST_SAMPLES),
	PERF_CONST(RECORD_SWITCH),
	PERF_CONST(RECORD_SWITCH_CPU_WIDE),

	PERF_CONST(RECORD_MISC_SWITCH_OUT),
	{ .name = NULL, },
};

static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
				  PyObject *args, PyObject *kwargs)
{
	struct tep_event *tp_format;
	static char *kwlist[] = { "sys", "name", NULL };
	char *sys  = NULL;
	char *name = NULL;

	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss", kwlist,
					 &sys, &name))
		return NULL;

	tp_format = trace_event__tp_format(sys, name);
	if (IS_ERR(tp_format))
		return _PyLong_FromLong(-1);

	return _PyLong_FromLong(tp_format->id);
}

static PyMethodDef perf__methods[] = {
	{
		.ml_name  = "tracepoint",
		.ml_meth  = (PyCFunction) pyrf__tracepoint,
		.ml_flags = METH_VARARGS | METH_KEYWORDS,
		.ml_doc	  = PyDoc_STR("Get tracepoint config.")
	},
	{ .ml_name = NULL, }
};

#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initperf(void)
#else
PyMODINIT_FUNC PyInit_perf(void)
#endif
{
	PyObject *obj;
	int i;
	PyObject *dict;
#if PY_MAJOR_VERSION < 3
	PyObject *module = Py_InitModule("perf", perf__methods);
#else
	static struct PyModuleDef moduledef = {
		PyModuleDef_HEAD_INIT,
		"perf",			/* m_name */
		"",			/* m_doc */
		-1,			/* m_size */
		perf__methods,		/* m_methods */
		NULL,			/* m_reload */
		NULL,			/* m_traverse */
		NULL,			/* m_clear */
		NULL,			/* m_free */
	};
	PyObject *module = PyModule_Create(&moduledef);
#endif

	if (module == NULL ||
	    pyrf_event__setup_types() < 0 ||
	    pyrf_evlist__setup_types() < 0 ||
	    pyrf_evsel__setup_types() < 0 ||
	    pyrf_thread_map__setup_types() < 0 ||
	    pyrf_cpu_map__setup_types() < 0)
#if PY_MAJOR_VERSION < 3
		return;
#else
		return module;
#endif

	/* The page_size is placed in util object. */
	page_size = sysconf(_SC_PAGE_SIZE);

	Py_INCREF(&pyrf_evlist__type);
	PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type);

	Py_INCREF(&pyrf_evsel__type);
	PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);

	Py_INCREF(&pyrf_mmap_event__type);
	PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type);

	Py_INCREF(&pyrf_lost_event__type);
	PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type);

	Py_INCREF(&pyrf_comm_event__type);
	PyModule_AddObject(module, "comm_event", (PyObject *)&pyrf_comm_event__type);

	Py_INCREF(&pyrf_task_event__type);
	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);

	Py_INCREF(&pyrf_throttle_event__type);
	PyModule_AddObject(module, "throttle_event", (PyObject *)&pyrf_throttle_event__type);

	Py_INCREF(&pyrf_task_event__type);
	PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);

	Py_INCREF(&pyrf_read_event__type);
	PyModule_AddObject(module, "read_event", (PyObject *)&pyrf_read_event__type);

	Py_INCREF(&pyrf_sample_event__type);
	PyModule_AddObject(module, "sample_event", (PyObject *)&pyrf_sample_event__type);

	Py_INCREF(&pyrf_context_switch_event__type);
	PyModule_AddObject(module, "switch_event", (PyObject *)&pyrf_context_switch_event__type);

	Py_INCREF(&pyrf_thread_map__type);
	PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);

	Py_INCREF(&pyrf_cpu_map__type);
	PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);

	dict = PyModule_GetDict(module);
	if (dict == NULL)
		goto error;

	for (i = 0; perf__constants[i].name != NULL; i++) {
		obj = _PyLong_FromLong(perf__constants[i].value);
		if (obj == NULL)
			goto error;
		PyDict_SetItemString(dict, perf__constants[i].name, obj);
		Py_DECREF(obj);
	}

error:
	if (PyErr_Occurred())
		PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
#if PY_MAJOR_VERSION >= 3
	return module;
#endif
}

/*
 * Dummy, to avoid dragging all the test_attr infrastructure in the python
 * binding.
 */
void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
                     int fd, int group_fd, unsigned long flags)
{
}
9 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586






















                                                                 
                           





                              
                       


































































































































































































































                                                                                














                                                                     
















                                                                         


























































                                                                             
                                  

 











                                                      















































































































































































                                                                                                      




                              
                                                                           

                  
                     
                                             
 
                                       
                              
 

                                  


                                                                
                                          
                          


                                                         
                                                                            
         

                          



                     















                                                                             






                                                                
                                                                         







                                                    
                                                           




                                    
                                         

                              

                   
                            
                         

























                                                             
















                                                                               
                                                                       
 



                                                                     
                              

                               
                                                  
         




                                                             
                                                              




                                            
                              

                               





                                                  
                                                      


                                        
                                                

                                              

                                                      




                                                        

                                                                





                                                  

                                             



                                                    
                                                           

                                            

                                 
         
                                            

 

















                                                                           
                             





















                                                   

                                                                      
  

                                                                    






















                                                                             
                                             
                                                      

                                                           
































                                                                               
                                                  













                                                                          



                                                    









                                               
                                                        








                                                    

                                                     

















                                                                 
                                                  












                                                                          


                                                                          
                                                        


                                                    

                                                     


































                                                                            
                                     











































                                                                   



                                                                      






























































                                                                                         
                                                                         

                                                                                    
                       











                                                                          
                                                                










                                                       
    

                                                                 
                                                              


                      











































                                                                                 


                                                                          

















                                                                                      











































                                                                                                   
                                                 
 
                                                        






















                                                                                
                                                














































































































                                                                                       








                                                          


































































                                                                  
                   
                                                          

















                                                           
                                             


















































                                                                              
                                                                                    


























                                                                               
                            
                         




                                  



                                                                         




                                                               



                                                   
                                                                                 







                                               
                                                                            














                                                                        
                                      
                           

        

                                     




                                                   
                                    

                                                    
                                                                        

                                         
                                         
















                                                                      
                                    
                               

                                       

                        
                                  
                               
                                                                                  

                             
                                     
                        
                                                                          







                                             
                             
     

                                          

















                                                                              
                                                            

                               
                                            


                                    
                                       
                        



                                          
                                         



                          
                                         



                                   
                                      
                           
                                 









                                                                   

                                                  


                                                              
                                                 

                                          



                                                            


                                       



                               
                                 

                           






                                                                        








                                                                       
                                 



















                                                                            
                   
                                                          




































































                                                                               
                   
                                                         























































































                                                                            

































                                                       
                                  




































                                                                           
                                 
         
 



























                                                                           
                                  










































                                                                                        
                   
                                                          




































































                                                                                         
                   
                                                              
















































































                                                                                  

                                                                           


































                                                                                        
                   
                                              


                     

                                                                             



















                                                                                        











                                                                
                             




















                                                                

                                                                  




                                                                                
                                                               

                                                                           
         

                                        

































                                                                       
                                         


















                                                                             
                                         



































































                                                                                          

                     
                     


                                                                                 
                                                    

                                                                             
         
                               









































                                                                                
                                                                         
 
                                 
                                                     
                    

 
                                                                             
 


                                   

                                         


































































                                                                           
                              
                               













                                  
/*
 *  linux/fs/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * Some corrections by tytso.
 */

/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
 * lookup logic.
 */
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
#include <linux/smp_lock.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/file.h>
#include <asm/namei.h>
#include <asm/uaccess.h>

#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])

/* [Feb-1997 T. Schoebel-Theuer]
 * Fundamental changes in the pathname lookup mechanisms (namei)
 * were necessary because of omirr.  The reason is that omirr needs
 * to know the _real_ pathname, not the user-supplied one, in case
 * of symlinks (and also when transname replacements occur).
 *
 * The new code replaces the old recursive symlink resolution with
 * an iterative one (in case of non-nested symlink chains).  It does
 * this with calls to <fs>_follow_link().
 * As a side effect, dir_namei(), _namei() and follow_link() are now 
 * replaced with a single function lookup_dentry() that can handle all 
 * the special cases of the former code.
 *
 * With the new dcache, the pathname is stored at each inode, at least as
 * long as the refcount of the inode is positive.  As a side effect, the
 * size of the dcache depends on the inode cache and thus is dynamic.
 *
 * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
 * resolution to correspond with current state of the code.
 *
 * Note that the symlink resolution is not *completely* iterative.
 * There is still a significant amount of tail- and mid- recursion in
 * the algorithm.  Also, note that <fs>_readlink() is not used in
 * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
 * may return different results than <fs>_follow_link().  Many virtual
 * filesystems (including /proc) exhibit this behavior.
 */

/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
 * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
 * and the name already exists in form of a symlink, try to create the new
 * name indicated by the symlink. The old code always complained that the
 * name already exists, due to not following the symlink even if its target
 * is nonexistent.  The new semantics affects also mknod() and link() when
 * the name is a symlink pointing to a non-existant name.
 *
 * I don't know which semantics is the right one, since I have no access
 * to standards. But I found by trial that HP-UX 9.0 has the full "new"
 * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
 * "old" one. Personally, I think the new semantics is much more logical.
 * Note that "ln old new" where "new" is a symlink pointing to a non-existing
 * file does succeed in both HP-UX and SunOs, but not in Solaris
 * and in the old Linux semantics.
 */

/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
 * semantics.  See the comments in "open_namei" and "do_link" below.
 *
 * [10-Sep-98 Alan Modra] Another symlink change.
 */

/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
 *	inside the path - always follow.
 *	in the last component in creation/removal/renaming - never follow.
 *	if LOOKUP_FOLLOW passed - follow.
 *	if the pathname has trailing slashes - follow.
 *	otherwise - don't follow.
 * (applied in that order).
 *
 * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
 * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
 * During the 2.4 we need to fix the userland stuff depending on it -
 * hopefully we will be able to get rid of that wart in 2.5. So far only
 * XEmacs seems to be relying on it...
 */
/*
 * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
 * implemented.  Let's see if raised priority of ->s_vfs_rename_sem gives
 * any extra contention...
 */

/* In order to reduce some races, while at the same time doing additional
 * checking and hopefully speeding things up, we copy filenames to the
 * kernel data space before using them..
 *
 * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
 * PATH_MAX includes the nul terminator --RR.
 */
static inline int do_getname(const char __user *filename, char *page)
{
	int retval;
	unsigned long len = PATH_MAX;

	if (!segment_eq(get_fs(), KERNEL_DS)) {
		if ((unsigned long) filename >= TASK_SIZE)
			return -EFAULT;
		if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
			len = TASK_SIZE - (unsigned long) filename;
	}

	retval = strncpy_from_user(page, filename, len);
	if (retval > 0) {
		if (retval < len)
			return 0;
		return -ENAMETOOLONG;
	} else if (!retval)
		retval = -ENOENT;
	return retval;
}

char * getname(const char __user * filename)
{
	char *tmp, *result;

	result = ERR_PTR(-ENOMEM);
	tmp = __getname();
	if (tmp)  {
		int retval = do_getname(filename, tmp);

		result = tmp;
		if (retval < 0) {
			__putname(tmp);
			result = ERR_PTR(retval);
		}
	}
	audit_getname(result);
	return result;
}

#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
	if (unlikely(current->audit_context))
		audit_putname(name);
	else
		__putname(name);
}
EXPORT_SYMBOL(putname);
#endif


/**
 * generic_permission  -  check for access rights on a Posix-like filesystem
 * @inode:	inode to check access rights for
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 * @check_acl:	optional callback to check for Posix ACLs
 *
 * Used to check for read/write/execute permissions on a file.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things..
 */
int generic_permission(struct inode *inode, int mask,
		int (*check_acl)(struct inode *inode, int mask))
{
	umode_t			mode = inode->i_mode;

	if (current->fsuid == inode->i_uid)
		mode >>= 6;
	else {
		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
			int error = check_acl(inode, mask);
			if (error == -EACCES)
				goto check_capabilities;
			else if (error != -EAGAIN)
				return error;
		}

		if (in_group_p(inode->i_gid))
			mode >>= 3;
	}

	/*
	 * If the DACs are ok we don't need any capability check.
	 */
	if (((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask))
		return 0;

 check_capabilities:
	/*
	 * Read/write DACs are always overridable.
	 * Executable DACs are overridable if at least one exec bit is set.
	 */
	if (!(mask & MAY_EXEC) ||
	    (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
		if (capable(CAP_DAC_OVERRIDE))
			return 0;

	/*
	 * Searching includes executable on directories, else just read.
	 */
	if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
		if (capable(CAP_DAC_READ_SEARCH))
			return 0;

	return -EACCES;
}

int permission(struct inode *inode, int mask, struct nameidata *nd)
{
	int retval, submask;

	if (mask & MAY_WRITE) {
		umode_t mode = inode->i_mode;

		/*
		 * Nobody gets write access to a read-only fs.
		 */
		if (IS_RDONLY(inode) &&
		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
			return -EROFS;

		/*
		 * Nobody gets write access to an immutable file.
		 */
		if (IS_IMMUTABLE(inode))
			return -EACCES;
	}


	/* Ordinary permission routines do not understand MAY_APPEND. */
	submask = mask & ~MAY_APPEND;
	if (inode->i_op && inode->i_op->permission)
		retval = inode->i_op->permission(inode, submask, nd);
	else
		retval = generic_permission(inode, submask, NULL);
	if (retval)
		return retval;

	return security_inode_permission(inode, mask, nd);
}

/**
 * vfs_permission  -  check for access rights to a given path
 * @nd:		lookup result that describes the path
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Used to check for read/write/execute permissions on a path.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things.
 */
int vfs_permission(struct nameidata *nd, int mask)
{
	return permission(nd->dentry->d_inode, mask, nd);
}

/**
 * file_permission  -  check for additional access rights to a given file
 * @file:	file to check access rights for
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Used to check for read/write/execute permissions on an already opened
 * file.
 *
 * Note:
 *	Do not use this function in new code.  All access checks should
 *	be done using vfs_permission().
 */
int file_permission(struct file *file, int mask)
{
	return permission(file->f_dentry->d_inode, mask, NULL);
}

/*
 * get_write_access() gets write permission for a file.
 * put_write_access() releases this write permission.
 * This is used for regular files.
 * We cannot support write (and maybe mmap read-write shared) accesses and
 * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
 * can have the following values:
 * 0: no writers, no VM_DENYWRITE mappings
 * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
 * > 0: (i_writecount) users are writing to the file.
 *
 * Normally we operate on that counter with atomic_{inc,dec} and it's safe
 * except for the cases where we don't hold i_writecount yet. Then we need to
 * use {get,deny}_write_access() - these functions check the sign and refuse
 * to do the change if sign is wrong. Exclusion between them is provided by
 * the inode->i_lock spinlock.
 */

int get_write_access(struct inode * inode)
{
	spin_lock(&inode->i_lock);
	if (atomic_read(&inode->i_writecount) < 0) {
		spin_unlock(&inode->i_lock);
		return -ETXTBSY;
	}
	atomic_inc(&inode->i_writecount);
	spin_unlock(&inode->i_lock);

	return 0;
}

int deny_write_access(struct file * file)
{
	struct inode *inode = file->f_dentry->d_inode;

	spin_lock(&inode->i_lock);
	if (atomic_read(&inode->i_writecount) > 0) {
		spin_unlock(&inode->i_lock);
		return -ETXTBSY;
	}
	atomic_dec(&inode->i_writecount);
	spin_unlock(&inode->i_lock);

	return 0;
}

void path_release(struct nameidata *nd)
{
	dput(nd->dentry);
	mntput(nd->mnt);
}

/*
 * umount() mustn't call path_release()/mntput() as that would clear
 * mnt_expiry_mark
 */
void path_release_on_umount(struct nameidata *nd)
{
	dput(nd->dentry);
	mntput_no_expire(nd->mnt);
}

/**
 * release_open_intent - free up open intent resources
 * @nd: pointer to nameidata
 */
void release_open_intent(struct nameidata *nd)
{
	if (nd->intent.open.file->f_dentry == NULL)
		put_filp(nd->intent.open.file);
	else
		fput(nd->intent.open.file);
}

/*
 * Internal lookup() using the new generic dcache.
 * SMP-safe
 */
static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
{
	struct dentry * dentry = __d_lookup(parent, name);

	/* lockess __d_lookup may fail due to concurrent d_move() 
	 * in some unrelated directory, so try with d_lookup
	 */
	if (!dentry)
		dentry = d_lookup(parent, name);

	if (dentry && dentry->d_op && dentry->d_op->d_revalidate) {
		if (!dentry->d_op->d_revalidate(dentry, nd) && !d_invalidate(dentry)) {
			dput(dentry);
			dentry = NULL;
		}
	}
	return dentry;
}

/*
 * Short-cut version of permission(), for calling by
 * path_walk(), when dcache lock is held.  Combines parts
 * of permission() and generic_permission(), and tests ONLY for
 * MAY_EXEC permission.
 *
 * If appropriate, check DAC only.  If not appropriate, or
 * short-cut DAC fails, then call permission() to do more
 * complete permission check.
 */
static inline int exec_permission_lite(struct inode *inode,
				       struct nameidata *nd)
{
	umode_t	mode = inode->i_mode;

	if (inode->i_op && inode->i_op->permission)
		return -EAGAIN;

	if (current->fsuid == inode->i_uid)
		mode >>= 6;
	else if (in_group_p(inode->i_gid))
		mode >>= 3;

	if (mode & MAY_EXEC)
		goto ok;

	if ((inode->i_mode & S_IXUGO) && capable(CAP_DAC_OVERRIDE))
		goto ok;

	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_OVERRIDE))
		goto ok;

	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_READ_SEARCH))
		goto ok;

	return -EACCES;
ok:
	return security_inode_permission(inode, MAY_EXEC, nd);
}

/*
 * This is called when everything else fails, and we actually have
 * to go to the low-level filesystem to find out what we should do..
 *
 * We get the directory semaphore, and after getting that we also
 * make sure that nobody added the entry to the dcache in the meantime..
 * SMP-safe
 */
static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
{
	struct dentry * result;
	struct inode *dir = parent->d_inode;

	down(&dir->i_sem);
	/*
	 * First re-do the cached lookup just in case it was created
	 * while we waited for the directory semaphore..
	 *
	 * FIXME! This could use version numbering or similar to
	 * avoid unnecessary cache lookups.
	 *
	 * The "dcache_lock" is purely to protect the RCU list walker
	 * from concurrent renames at this point (we mustn't get false
	 * negatives from the RCU list walk here, unlike the optimistic
	 * fast walk).
	 *
	 * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
	 */
	result = d_lookup(parent, name);
	if (!result) {
		struct dentry * dentry = d_alloc(parent, name);
		result = ERR_PTR(-ENOMEM);
		if (dentry) {
			result = dir->i_op->lookup(dir, dentry, nd);
			if (result)
				dput(dentry);
			else
				result = dentry;
		}
		up(&dir->i_sem);
		return result;
	}

	/*
	 * Uhhuh! Nasty case: the cache was re-populated while
	 * we waited on the semaphore. Need to revalidate.
	 */
	up(&dir->i_sem);
	if (result->d_op && result->d_op->d_revalidate) {
		if (!result->d_op->d_revalidate(result, nd) && !d_invalidate(result)) {
			dput(result);
			result = ERR_PTR(-ENOENT);
		}
	}
	return result;
}

static int __emul_lookup_dentry(const char *, struct nameidata *);

/* SMP-safe */
static inline int
walk_init_root(const char *name, struct nameidata *nd)
{
	read_lock(&current->fs->lock);
	if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
		nd->mnt = mntget(current->fs->altrootmnt);
		nd->dentry = dget(current->fs->altroot);
		read_unlock(&current->fs->lock);
		if (__emul_lookup_dentry(name,nd))
			return 0;
		read_lock(&current->fs->lock);
	}
	nd->mnt = mntget(current->fs->rootmnt);
	nd->dentry = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	return 1;
}

static inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
	int res = 0;
	char *name;
	if (IS_ERR(link))
		goto fail;

	if (*link == '/') {
		path_release(nd);
		if (!walk_init_root(link, nd))
			/* weird __emul_prefix() stuff did it */
			goto out;
	}
	res = link_path_walk(link, nd);
out:
	if (nd->depth || res || nd->last_type!=LAST_NORM)
		return res;
	/*
	 * If it is an iterative symlinks resolution in open_namei() we
	 * have to copy the last component. And all that crap because of
	 * bloody create() on broken symlinks. Furrfu...
	 */
	name = __getname();
	if (unlikely(!name)) {
		path_release(nd);
		return -ENOMEM;
	}
	strcpy(name, nd->last.name);
	nd->last.name = name;
	return 0;
fail:
	path_release(nd);
	return PTR_ERR(link);
}

struct path {
	struct vfsmount *mnt;
	struct dentry *dentry;
};

static inline int __do_follow_link(struct path *path, struct nameidata *nd)
{
	int error;
	void *cookie;
	struct dentry *dentry = path->dentry;

	touch_atime(path->mnt, dentry);
	nd_set_link(nd, NULL);

	if (path->mnt == nd->mnt)
		mntget(path->mnt);
	cookie = dentry->d_inode->i_op->follow_link(dentry, nd);
	error = PTR_ERR(cookie);
	if (!IS_ERR(cookie)) {
		char *s = nd_get_link(nd);
		error = 0;
		if (s)
			error = __vfs_follow_link(nd, s);
		if (dentry->d_inode->i_op->put_link)
			dentry->d_inode->i_op->put_link(dentry, nd, cookie);
	}
	dput(dentry);
	mntput(path->mnt);

	return error;
}

static inline void dput_path(struct path *path, struct nameidata *nd)
{
	dput(path->dentry);
	if (path->mnt != nd->mnt)
		mntput(path->mnt);
}

static inline void path_to_nameidata(struct path *path, struct nameidata *nd)
{
	dput(nd->dentry);
	if (nd->mnt != path->mnt)
		mntput(nd->mnt);
	nd->mnt = path->mnt;
	nd->dentry = path->dentry;
}

/*
 * This limits recursive symlink follows to 8, while
 * limiting consecutive symlinks to 40.
 *
 * Without that kind of total limit, nasty chains of consecutive
 * symlinks can cause almost arbitrarily long lookups. 
 */
static inline int do_follow_link(struct path *path, struct nameidata *nd)
{
	int err = -ELOOP;
	if (current->link_count >= MAX_NESTED_LINKS)
		goto loop;
	if (current->total_link_count >= 40)
		goto loop;
	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
	cond_resched();
	err = security_inode_follow_link(path->dentry, nd);
	if (err)
		goto loop;
	current->link_count++;
	current->total_link_count++;
	nd->depth++;
	err = __do_follow_link(path, nd);
	current->link_count--;
	nd->depth--;
	return err;
loop:
	dput_path(path, nd);
	path_release(nd);
	return err;
}

int follow_up(struct vfsmount **mnt, struct dentry **dentry)
{
	struct vfsmount *parent;
	struct dentry *mountpoint;
	spin_lock(&vfsmount_lock);
	parent=(*mnt)->mnt_parent;
	if (parent == *mnt) {
		spin_unlock(&vfsmount_lock);
		return 0;
	}
	mntget(parent);
	mountpoint=dget((*mnt)->mnt_mountpoint);
	spin_unlock(&vfsmount_lock);
	dput(*dentry);
	*dentry = mountpoint;
	mntput(*mnt);
	*mnt = parent;
	return 1;
}

/* no need for dcache_lock, as serialization is taken care in
 * namespace.c
 */
static int __follow_mount(struct path *path)
{
	int res = 0;
	while (d_mountpoint(path->dentry)) {
		struct vfsmount *mounted = lookup_mnt(path->mnt, path->dentry);
		if (!mounted)
			break;
		dput(path->dentry);
		if (res)
			mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
		res = 1;
	}
	return res;
}

static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
{
	while (d_mountpoint(*dentry)) {
		struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
		if (!mounted)
			break;
		dput(*dentry);
		mntput(*mnt);
		*mnt = mounted;
		*dentry = dget(mounted->mnt_root);
	}
}

/* no need for dcache_lock, as serialization is taken care in
 * namespace.c
 */
int follow_down(struct vfsmount **mnt, struct dentry **dentry)
{
	struct vfsmount *mounted;

	mounted = lookup_mnt(*mnt, *dentry);
	if (mounted) {
		dput(*dentry);
		mntput(*mnt);
		*mnt = mounted;
		*dentry = dget(mounted->mnt_root);
		return 1;
	}
	return 0;
}

static inline void follow_dotdot(struct nameidata *nd)
{
	while(1) {
		struct vfsmount *parent;
		struct dentry *old = nd->dentry;

                read_lock(&current->fs->lock);
		if (nd->dentry == current->fs->root &&
		    nd->mnt == current->fs->rootmnt) {
                        read_unlock(&current->fs->lock);
			break;
		}
                read_unlock(&current->fs->lock);
		spin_lock(&dcache_lock);
		if (nd->dentry != nd->mnt->mnt_root) {
			nd->dentry = dget(nd->dentry->d_parent);
			spin_unlock(&dcache_lock);
			dput(old);
			break;
		}
		spin_unlock(&dcache_lock);
		spin_lock(&vfsmount_lock);
		parent = nd->mnt->mnt_parent;
		if (parent == nd->mnt) {
			spin_unlock(&vfsmount_lock);
			break;
		}
		mntget(parent);
		nd->dentry = dget(nd->mnt->mnt_mountpoint);
		spin_unlock(&vfsmount_lock);
		dput(old);
		mntput(nd->mnt);
		nd->mnt = parent;
	}
	follow_mount(&nd->mnt, &nd->dentry);
}

/*
 *  It's more convoluted than I'd like it to be, but... it's still fairly
 *  small and for now I'd prefer to have fast path as straight as possible.
 *  It _is_ time-critical.
 */
static int do_lookup(struct nameidata *nd, struct qstr *name,
		     struct path *path)
{
	struct vfsmount *mnt = nd->mnt;
	struct dentry *dentry = __d_lookup(nd->dentry, name);

	if (!dentry)
		goto need_lookup;
	if (dentry->d_op && dentry->d_op->d_revalidate)
		goto need_revalidate;
done:
	path->mnt = mnt;
	path->dentry = dentry;
	__follow_mount(path);
	return 0;

need_lookup:
	dentry = real_lookup(nd->dentry, name, nd);
	if (IS_ERR(dentry))
		goto fail;
	goto done;

need_revalidate:
	if (dentry->d_op->d_revalidate(dentry, nd))
		goto done;
	if (d_invalidate(dentry))
		goto done;
	dput(dentry);
	goto need_lookup;

fail:
	return PTR_ERR(dentry);
}

/*
 * Name resolution.
 * This is the basic name resolution function, turning a pathname into
 * the final dentry. We expect 'base' to be positive and a directory.
 *
 * Returns 0 and nd will have valid dentry and mnt on success.
 * Returns error and drops reference to input namei data on failure.
 */
static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
{
	struct path next;
	struct inode *inode;
	int err;
	unsigned int lookup_flags = nd->flags;
	
	while (*name=='/')
		name++;
	if (!*name)
		goto return_reval;

	inode = nd->dentry->d_inode;
	if (nd->depth)
		lookup_flags = LOOKUP_FOLLOW;

	/* At this point we know we have a real path component. */
	for(;;) {
		unsigned long hash;
		struct qstr this;
		unsigned int c;

		nd->flags |= LOOKUP_CONTINUE;
		err = exec_permission_lite(inode, nd);
		if (err == -EAGAIN)
			err = vfs_permission(nd, MAY_EXEC);
 		if (err)
			break;

		this.name = name;
		c = *(const unsigned char *)name;

		hash = init_name_hash();
		do {
			name++;
			hash = partial_name_hash(c, hash);
			c = *(const unsigned char *)name;
		} while (c && (c != '/'));
		this.len = name - (const char *) this.name;
		this.hash = end_name_hash(hash);

		/* remove trailing slashes? */
		if (!c)
			goto last_component;
		while (*++name == '/');
		if (!*name)
			goto last_with_slashes;

		/*
		 * "." and ".." are special - ".." especially so because it has
		 * to be able to know about the current root directory and
		 * parent relationships.
		 */
		if (this.name[0] == '.') switch (this.len) {
			default:
				break;
			case 2:	
				if (this.name[1] != '.')
					break;
				follow_dotdot(nd);
				inode = nd->dentry->d_inode;
				/* fallthrough */
			case 1:
				continue;
		}
		/*
		 * See if the low-level filesystem might want
		 * to use its own hash..
		 */
		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
			if (err < 0)
				break;
		}
		/* This does the actual lookups.. */
		err = do_lookup(nd, &this, &next);
		if (err)
			break;

		err = -ENOENT;
		inode = next.dentry->d_inode;
		if (!inode)
			goto out_dput;
		err = -ENOTDIR; 
		if (!inode->i_op)
			goto out_dput;

		if (inode->i_op->follow_link) {
			err = do_follow_link(&next, nd);
			if (err)
				goto return_err;
			err = -ENOENT;
			inode = nd->dentry->d_inode;
			if (!inode)
				break;
			err = -ENOTDIR; 
			if (!inode->i_op)
				break;
		} else
			path_to_nameidata(&next, nd);
		err = -ENOTDIR; 
		if (!inode->i_op->lookup)
			break;
		continue;
		/* here ends the main loop */

last_with_slashes:
		lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
last_component:
		nd->flags &= ~LOOKUP_CONTINUE;
		if (lookup_flags & LOOKUP_PARENT)
			goto lookup_parent;
		if (this.name[0] == '.') switch (this.len) {
			default:
				break;
			case 2:	
				if (this.name[1] != '.')
					break;
				follow_dotdot(nd);
				inode = nd->dentry->d_inode;
				/* fallthrough */
			case 1:
				goto return_reval;
		}
		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
			if (err < 0)
				break;
		}
		err = do_lookup(nd, &this, &next);
		if (err)
			break;
		inode = next.dentry->d_inode;
		if ((lookup_flags & LOOKUP_FOLLOW)
		    && inode && inode->i_op && inode->i_op->follow_link) {
			err = do_follow_link(&next, nd);
			if (err)
				goto return_err;
			inode = nd->dentry->d_inode;
		} else
			path_to_nameidata(&next, nd);
		err = -ENOENT;
		if (!inode)
			break;
		if (lookup_flags & LOOKUP_DIRECTORY) {
			err = -ENOTDIR; 
			if (!inode->i_op || !inode->i_op->lookup)
				break;
		}
		goto return_base;
lookup_parent:
		nd->last = this;
		nd->last_type = LAST_NORM;
		if (this.name[0] != '.')
			goto return_base;
		if (this.len == 1)
			nd->last_type = LAST_DOT;
		else if (this.len == 2 && this.name[1] == '.')
			nd->last_type = LAST_DOTDOT;
		else
			goto return_base;
return_reval:
		/*
		 * We bypassed the ordinary revalidation routines.
		 * We may need to check the cached dentry for staleness.
		 */
		if (nd->dentry && nd->dentry->d_sb &&
		    (nd->dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) {
			err = -ESTALE;
			/* Note: we do not d_invalidate() */
			if (!nd->dentry->d_op->d_revalidate(nd->dentry, nd))
				break;
		}
return_base:
		return 0;
out_dput:
		dput_path(&next, nd);
		break;
	}
	path_release(nd);
return_err:
	return err;
}

/*
 * Wrapper to retry pathname resolution whenever the underlying
 * file system returns an ESTALE.
 *
 * Retry the whole path once, forcing real lookup requests
 * instead of relying on the dcache.
 */
int fastcall link_path_walk(const char *name, struct nameidata *nd)
{
	struct nameidata save = *nd;
	int result;

	/* make sure the stuff we saved doesn't go away */
	dget(save.dentry);
	mntget(save.mnt);

	result = __link_path_walk(name, nd);
	if (result == -ESTALE) {
		*nd = save;
		dget(nd->dentry);
		mntget(nd->mnt);
		nd->flags |= LOOKUP_REVAL;
		result = __link_path_walk(name, nd);
	}

	dput(save.dentry);
	mntput(save.mnt);

	return result;
}

int fastcall path_walk(const char * name, struct nameidata *nd)
{
	current->total_link_count = 0;
	return link_path_walk(name, nd);
}

/* 
 * SMP-safe: Returns 1 and nd will have valid dentry and mnt, if
 * everything is done. Returns 0 and drops input nd, if lookup failed;
 */
static int __emul_lookup_dentry(const char *name, struct nameidata *nd)
{
	if (path_walk(name, nd))
		return 0;		/* something went wrong... */

	if (!nd->dentry->d_inode || S_ISDIR(nd->dentry->d_inode->i_mode)) {
		struct dentry *old_dentry = nd->dentry;
		struct vfsmount *old_mnt = nd->mnt;
		struct qstr last = nd->last;
		int last_type = nd->last_type;
		/*
		 * NAME was not found in alternate root or it's a directory.  Try to find
		 * it in the normal root:
		 */
		nd->last_type = LAST_ROOT;
		read_lock(&current->fs->lock);
		nd->mnt = mntget(current->fs->rootmnt);
		nd->dentry = dget(current->fs->root);
		read_unlock(&current->fs->lock);
		if (path_walk(name, nd) == 0) {
			if (nd->dentry->d_inode) {
				dput(old_dentry);
				mntput(old_mnt);
				return 1;
			}
			path_release(nd);
		}
		nd->dentry = old_dentry;
		nd->mnt = old_mnt;
		nd->last = last;
		nd->last_type = last_type;
	}
	return 1;
}

void set_fs_altroot(void)
{
	char *emul = __emul_prefix();
	struct nameidata nd;
	struct vfsmount *mnt = NULL, *oldmnt;
	struct dentry *dentry = NULL, *olddentry;
	int err;

	if (!emul)
		goto set_it;
	err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
	if (!err) {
		mnt = nd.mnt;
		dentry = nd.dentry;
	}
set_it:
	write_lock(&current->fs->lock);
	oldmnt = current->fs->altrootmnt;
	olddentry = current->fs->altroot;
	current->fs->altrootmnt = mnt;
	current->fs->altroot = dentry;
	write_unlock(&current->fs->lock);
	if (olddentry) {
		dput(olddentry);
		mntput(oldmnt);
	}
}

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd)
{
	int retval = 0;

	nd->last_type = LAST_ROOT; /* if there are only slashes... */
	nd->flags = flags;
	nd->depth = 0;

	read_lock(&current->fs->lock);
	if (*name=='/') {
		if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
			nd->mnt = mntget(current->fs->altrootmnt);
			nd->dentry = dget(current->fs->altroot);
			read_unlock(&current->fs->lock);
			if (__emul_lookup_dentry(name,nd))
				goto out; /* found in altroot */
			read_lock(&current->fs->lock);
		}
		nd->mnt = mntget(current->fs->rootmnt);
		nd->dentry = dget(current->fs->root);
	} else {
		nd->mnt = mntget(current->fs->pwdmnt);
		nd->dentry = dget(current->fs->pwd);
	}
	read_unlock(&current->fs->lock);
	current->total_link_count = 0;
	retval = link_path_walk(name, nd);
out:
	if (unlikely(current->audit_context
		     && nd && nd->dentry && nd->dentry->d_inode))
		audit_inode(name, nd->dentry->d_inode, flags);
	return retval;
}

static int __path_lookup_intent_open(const char *name, unsigned int lookup_flags,
		struct nameidata *nd, int open_flags, int create_mode)
{
	struct file *filp = get_empty_filp();
	int err;

	if (filp == NULL)
		return -ENFILE;
	nd->intent.open.file = filp;
	nd->intent.open.flags = open_flags;
	nd->intent.open.create_mode = create_mode;
	err = path_lookup(name, lookup_flags|LOOKUP_OPEN, nd);
	if (IS_ERR(nd->intent.open.file)) {
		if (err == 0) {
			err = PTR_ERR(nd->intent.open.file);
			path_release(nd);
		}
	} else if (err != 0)
		release_open_intent(nd);
	return err;
}

/**
 * path_lookup_open - lookup a file path with open intent
 * @name: pointer to file name
 * @lookup_flags: lookup intent flags
 * @nd: pointer to nameidata
 * @open_flags: open intent flags
 */
int path_lookup_open(const char *name, unsigned int lookup_flags,
		struct nameidata *nd, int open_flags)
{
	return __path_lookup_intent_open(name, lookup_flags, nd,
			open_flags, 0);
}

/**
 * path_lookup_create - lookup a file path with open + create intent
 * @name: pointer to file name
 * @lookup_flags: lookup intent flags
 * @nd: pointer to nameidata
 * @open_flags: open intent flags
 * @create_mode: create intent flags
 */
static int path_lookup_create(const char *name, unsigned int lookup_flags,
			      struct nameidata *nd, int open_flags,
			      int create_mode)
{
	return __path_lookup_intent_open(name, lookup_flags|LOOKUP_CREATE, nd,
			open_flags, create_mode);
}

int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags,
		struct nameidata *nd, int open_flags)
{
	char *tmp = getname(name);
	int err = PTR_ERR(tmp);

	if (!IS_ERR(tmp)) {
		err = __path_lookup_intent_open(tmp, lookup_flags, nd, open_flags, 0);
		putname(tmp);
	}
	return err;
}

/*
 * Restricted form of lookup. Doesn't follow links, single-component only,
 * needs parent already locked. Doesn't follow mounts.
 * SMP-safe.
 */
static struct dentry * __lookup_hash(struct qstr *name, struct dentry * base, struct nameidata *nd)
{
	struct dentry * dentry;
	struct inode *inode;
	int err;

	inode = base->d_inode;
	err = permission(inode, MAY_EXEC, nd);
	dentry = ERR_PTR(err);
	if (err)
		goto out;

	/*
	 * See if the low-level filesystem might want
	 * to use its own hash..
	 */
	if (base->d_op && base->d_op->d_hash) {
		err = base->d_op->d_hash(base, name);
		dentry = ERR_PTR(err);
		if (err < 0)
			goto out;
	}

	dentry = cached_lookup(base, name, nd);
	if (!dentry) {
		struct dentry *new = d_alloc(base, name);
		dentry = ERR_PTR(-ENOMEM);
		if (!new)
			goto out;
		dentry = inode->i_op->lookup(inode, new, nd);
		if (!dentry)
			dentry = new;
		else
			dput(new);
	}
out:
	return dentry;
}

struct dentry * lookup_hash(struct nameidata *nd)
{
	return __lookup_hash(&nd->last, nd->dentry, nd);
}

/* SMP-safe */
struct dentry * lookup_one_len(const char * name, struct dentry * base, int len)
{
	unsigned long hash;
	struct qstr this;
	unsigned int c;

	this.name = name;
	this.len = len;
	if (!len)
		goto access;

	hash = init_name_hash();
	while (len--) {
		c = *(const unsigned char *)name++;
		if (c == '/' || c == '\0')
			goto access;
		hash = partial_name_hash(c, hash);
	}
	this.hash = end_name_hash(hash);

	return __lookup_hash(&this, base, NULL);
access:
	return ERR_PTR(-EACCES);
}

/*
 *	namei()
 *
 * is used by most simple commands to get the inode of a specified name.
 * Open, link etc use their own routines, but this is enough for things
 * like 'chmod' etc.
 *
 * namei exists in two versions: namei/lnamei. The only difference is
 * that namei follows links, while lnamei does not.
 * SMP-safe
 */
int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
{
	char *tmp = getname(name);
	int err = PTR_ERR(tmp);

	if (!IS_ERR(tmp)) {
		err = path_lookup(tmp, flags, nd);
		putname(tmp);
	}
	return err;
}

/*
 * It's inline, so penalty for filesystems that don't use sticky bit is
 * minimal.
 */
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;
	if (inode->i_uid == current->fsuid)
		return 0;
	if (dir->i_uid == current->fsuid)
		return 0;
	return !capable(CAP_FOWNER);
}

/*
 *	Check whether we can remove a link victim from directory dir, check
 *  whether the type of victim is right.
 *  1. We can't do it if dir is read-only (done in permission())
 *  2. We should have write and exec permissions on dir
 *  3. We can't remove anything from append-only dir
 *  4. We can't do anything with immutable dir (done in permission())
 *  5. If the sticky bit on dir is set we should either
 *	a. be owner of dir, or
 *	b. be owner of victim, or
 *	c. have CAP_FOWNER capability
 *  6. If the victim is append-only or immutable we can't do antyhing with
 *     links pointing to it.
 *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
 *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
 *  9. We can't remove a root or mountpoint.
 * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
 *     nfs_async_unlink().
 */
static inline int may_delete(struct inode *dir,struct dentry *victim,int isdir)
{
	int error;

	if (!victim->d_inode)
		return -ENOENT;

	BUG_ON(victim->d_parent->d_inode != dir);

	error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
	if (error)
		return error;
	if (IS_APPEND(dir))
		return -EPERM;
	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
	    IS_IMMUTABLE(victim->d_inode))
		return -EPERM;
	if (isdir) {
		if (!S_ISDIR(victim->d_inode->i_mode))
			return -ENOTDIR;
		if (IS_ROOT(victim))
			return -EBUSY;
	} else if (S_ISDIR(victim->d_inode->i_mode))
		return -EISDIR;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	if (victim->d_flags & DCACHE_NFSFS_RENAMED)
		return -EBUSY;
	return 0;
}

/*	Check whether we can create an object with dentry child in directory
 *  dir.
 *  1. We can't do it if child already exists (open has special treatment for
 *     this case, but since we are inlined it's OK)
 *  2. We can't do it if dir is read-only (done in permission())
 *  3. We should have write and exec permissions on dir
 *  4. We can't do it if dir is immutable (done in permission())
 */
static inline int may_create(struct inode *dir, struct dentry *child,
			     struct nameidata *nd)
{
	if (child->d_inode)
		return -EEXIST;
	if (IS_DEADDIR(dir))
		return -ENOENT;
	return permission(dir,MAY_WRITE | MAY_EXEC, nd);
}

/* 
 * O_DIRECTORY translates into forcing a directory lookup.
 */
static inline int lookup_flags(unsigned int f)
{
	unsigned long retval = LOOKUP_FOLLOW;

	if (f & O_NOFOLLOW)
		retval &= ~LOOKUP_FOLLOW;
	
	if (f & O_DIRECTORY)
		retval |= LOOKUP_DIRECTORY;

	return retval;
}

/*
 * p1 and p2 should be directories on the same fs.
 */
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
	struct dentry *p;

	if (p1 == p2) {
		down(&p1->d_inode->i_sem);
		return NULL;
	}

	down(&p1->d_inode->i_sb->s_vfs_rename_sem);

	for (p = p1; p->d_parent != p; p = p->d_parent) {
		if (p->d_parent == p2) {
			down(&p2->d_inode->i_sem);
			down(&p1->d_inode->i_sem);
			return p;
		}
	}

	for (p = p2; p->d_parent != p; p = p->d_parent) {
		if (p->d_parent == p1) {
			down(&p1->d_inode->i_sem);
			down(&p2->d_inode->i_sem);
			return p;
		}
	}

	down(&p1->d_inode->i_sem);
	down(&p2->d_inode->i_sem);
	return NULL;
}

void unlock_rename(struct dentry *p1, struct dentry *p2)
{
	up(&p1->d_inode->i_sem);
	if (p1 != p2) {
		up(&p2->d_inode->i_sem);
		up(&p1->d_inode->i_sb->s_vfs_rename_sem);
	}
}

int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
		struct nameidata *nd)
{
	int error = may_create(dir, dentry, nd);

	if (error)
		return error;

	if (!dir->i_op || !dir->i_op->create)
		return -EACCES;	/* shouldn't it be ENOSYS? */
	mode &= S_IALLUGO;
	mode |= S_IFREG;
	error = security_inode_create(dir, dentry, mode);
	if (error)
		return error;
	DQUOT_INIT(dir);
	error = dir->i_op->create(dir, dentry, mode, nd);
	if (!error)
		fsnotify_create(dir, dentry->d_name.name);
	return error;
}

int may_open(struct nameidata *nd, int acc_mode, int flag)
{
	struct dentry *dentry = nd->dentry;
	struct inode *inode = dentry->d_inode;
	int error;

	if (!inode)
		return -ENOENT;

	if (S_ISLNK(inode->i_mode))
		return -ELOOP;
	
	if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE))
		return -EISDIR;

	error = vfs_permission(nd, acc_mode);
	if (error)
		return error;

	/*
	 * FIFO's, sockets and device files are special: they don't
	 * actually live on the filesystem itself, and as such you
	 * can write to them even if the filesystem is read-only.
	 */
	if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
	    	flag &= ~O_TRUNC;
	} else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) {
		if (nd->mnt->mnt_flags & MNT_NODEV)
			return -EACCES;

		flag &= ~O_TRUNC;
	} else if (IS_RDONLY(inode) && (flag & FMODE_WRITE))
		return -EROFS;
	/*
	 * An append-only file must be opened in append mode for writing.
	 */
	if (IS_APPEND(inode)) {
		if  ((flag & FMODE_WRITE) && !(flag & O_APPEND))
			return -EPERM;
		if (flag & O_TRUNC)
			return -EPERM;
	}

	/* O_NOATIME can only be set by the owner or superuser */
	if (flag & O_NOATIME)
		if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
			return -EPERM;

	/*
	 * Ensure there are no outstanding leases on the file.
	 */
	error = break_lease(inode, flag);
	if (error)
		return error;

	if (flag & O_TRUNC) {
		error = get_write_access(inode);
		if (error)
			return error;

		/*
		 * Refuse to truncate files with mandatory locks held on them.
		 */
		error = locks_verify_locked(inode);
		if (!error) {
			DQUOT_INIT(inode);
			
			error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL);
		}
		put_write_access(inode);
		if (error)
			return error;
	} else
		if (flag & FMODE_WRITE)
			DQUOT_INIT(inode);

	return 0;
}

/*
 *	open_namei()
 *
 * namei for open - this is in fact almost the whole open-routine.
 *
 * Note that the low bits of "flag" aren't the same as in the open
 * system call - they are 00 - no permissions needed
 *			  01 - read permission needed
 *			  10 - write permission needed
 *			  11 - read/write permissions needed
 * which is a lot more logical, and also allows the "no perm" needed
 * for symlinks (where the permissions are checked later).
 * SMP-safe
 */
int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd)
{
	int acc_mode, error;
	struct path path;
	struct dentry *dir;
	int count = 0;

	acc_mode = ACC_MODE(flag);

	/* O_TRUNC implies we need access checks for write permissions */
	if (flag & O_TRUNC)
		acc_mode |= MAY_WRITE;

	/* Allow the LSM permission hook to distinguish append 
	   access from general write access. */
	if (flag & O_APPEND)
		acc_mode |= MAY_APPEND;

	/*
	 * The simplest case - just a plain lookup.
	 */
	if (!(flag & O_CREAT)) {
		error = path_lookup_open(pathname, lookup_flags(flag), nd, flag);
		if (error)
			return error;
		goto ok;
	}

	/*
	 * Create - we need to know the parent.
	 */
	error = path_lookup_create(pathname, LOOKUP_PARENT, nd, flag, mode);
	if (error)
		return error;

	/*
	 * We have the parent and last component. First of all, check
	 * that we are not asked to creat(2) an obvious directory - that
	 * will not do.
	 */
	error = -EISDIR;
	if (nd->last_type != LAST_NORM || nd->last.name[nd->last.len])
		goto exit;

	dir = nd->dentry;
	nd->flags &= ~LOOKUP_PARENT;
	down(&dir->d_inode->i_sem);
	path.dentry = lookup_hash(nd);
	path.mnt = nd->mnt;

do_last:
	error = PTR_ERR(path.dentry);
	if (IS_ERR(path.dentry)) {
		up(&dir->d_inode->i_sem);
		goto exit;
	}

	/* Negative dentry, just create the file */
	if (!path.dentry->d_inode) {
		if (!IS_POSIXACL(dir->d_inode))
			mode &= ~current->fs->umask;
		error = vfs_create(dir->d_inode, path.dentry, mode, nd);
		up(&dir->d_inode->i_sem);
		dput(nd->dentry);
		nd->dentry = path.dentry;
		if (error)
			goto exit;
		/* Don't check for write permission, don't truncate */
		acc_mode = 0;
		flag &= ~O_TRUNC;
		goto ok;
	}

	/*
	 * It already exists.
	 */
	up(&dir->d_inode->i_sem);

	error = -EEXIST;
	if (flag & O_EXCL)
		goto exit_dput;

	if (__follow_mount(&path)) {
		error = -ELOOP;
		if (flag & O_NOFOLLOW)
			goto exit_dput;
	}
	error = -ENOENT;
	if (!path.dentry->d_inode)
		goto exit_dput;
	if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link)
		goto do_link;

	path_to_nameidata(&path, nd);
	error = -EISDIR;
	if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
		goto exit;
ok:
	error = may_open(nd, acc_mode, flag);
	if (error)
		goto exit;
	return 0;

exit_dput:
	dput_path(&path, nd);
exit:
	if (!IS_ERR(nd->intent.open.file))
		release_open_intent(nd);
	path_release(nd);
	return error;

do_link:
	error = -ELOOP;
	if (flag & O_NOFOLLOW)
		goto exit_dput;
	/*
	 * This is subtle. Instead of calling do_follow_link() we do the
	 * thing by hands. The reason is that this way we have zero link_count
	 * and path_walk() (called from ->follow_link) honoring LOOKUP_PARENT.
	 * After that we have the parent and last component, i.e.
	 * we are in the same situation as after the first path_walk().
	 * Well, almost - if the last component is normal we get its copy
	 * stored in nd->last.name and we will have to putname() it when we
	 * are done. Procfs-like symlinks just set LAST_BIND.
	 */
	nd->flags |= LOOKUP_PARENT;
	error = security_inode_follow_link(path.dentry, nd);
	if (error)
		goto exit_dput;
	error = __do_follow_link(&path, nd);
	if (error)
		return error;
	nd->flags &= ~LOOKUP_PARENT;
	if (nd->last_type == LAST_BIND)
		goto ok;
	error = -EISDIR;
	if (nd->last_type != LAST_NORM)
		goto exit;
	if (nd->last.name[nd->last.len]) {
		__putname(nd->last.name);
		goto exit;
	}
	error = -ELOOP;
	if (count++==32) {
		__putname(nd->last.name);
		goto exit;
	}
	dir = nd->dentry;
	down(&dir->d_inode->i_sem);
	path.dentry = lookup_hash(nd);
	path.mnt = nd->mnt;
	__putname(nd->last.name);
	goto do_last;
}

/**
 * lookup_create - lookup a dentry, creating it if it doesn't exist
 * @nd: nameidata info
 * @is_dir: directory flag
 *
 * Simple function to lookup and return a dentry and create it
 * if it doesn't exist.  Is SMP-safe.
 *
 * Returns with nd->dentry->d_inode->i_sem locked.
 */
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
	struct dentry *dentry = ERR_PTR(-EEXIST);

	down(&nd->dentry->d_inode->i_sem);
	/*
	 * Yucky last component or no last component at all?
	 * (foo/., foo/.., /////)
	 */
	if (nd->last_type != LAST_NORM)
		goto fail;
	nd->flags &= ~LOOKUP_PARENT;

	/*
	 * Do the final lookup.
	 */
	dentry = lookup_hash(nd);
	if (IS_ERR(dentry))
		goto fail;

	/*
	 * Special case - lookup gave negative, but... we had foo/bar/
	 * From the vfs_mknod() POV we just have a negative dentry -
	 * all is fine. Let's be bastards - you had / on the end, you've
	 * been asking for (non-existent) directory. -ENOENT for you.
	 */
	if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode)
		goto enoent;
	return dentry;
enoent:
	dput(dentry);
	dentry = ERR_PTR(-ENOENT);
fail:
	return dentry;
}
EXPORT_SYMBOL_GPL(lookup_create);

int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
	int error = may_create(dir, dentry, NULL);

	if (error)
		return error;

	if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
		return -EPERM;

	if (!dir->i_op || !dir->i_op->mknod)
		return -EPERM;

	error = security_inode_mknod(dir, dentry, mode, dev);
	if (error)
		return error;

	DQUOT_INIT(dir);
	error = dir->i_op->mknod(dir, dentry, mode, dev);
	if (!error)
		fsnotify_create(dir, dentry->d_name.name);
	return error;
}

asmlinkage long sys_mknod(const char __user * filename, int mode, unsigned dev)
{
	int error = 0;
	char * tmp;
	struct dentry * dentry;
	struct nameidata nd;

	if (S_ISDIR(mode))
		return -EPERM;
	tmp = getname(filename);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	error = path_lookup(tmp, LOOKUP_PARENT, &nd);
	if (error)
		goto out;
	dentry = lookup_create(&nd, 0);
	error = PTR_ERR(dentry);

	if (!IS_POSIXACL(nd.dentry->d_inode))
		mode &= ~current->fs->umask;
	if (!IS_ERR(dentry)) {
		switch (mode & S_IFMT) {
		case 0: case S_IFREG:
			error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd);
			break;
		case S_IFCHR: case S_IFBLK:
			error = vfs_mknod(nd.dentry->d_inode,dentry,mode,
					new_decode_dev(dev));
			break;
		case S_IFIFO: case S_IFSOCK:
			error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0);
			break;
		case S_IFDIR:
			error = -EPERM;
			break;
		default:
			error = -EINVAL;
		}
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
	path_release(&nd);
out:
	putname(tmp);

	return error;
}

int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int error = may_create(dir, dentry, NULL);

	if (error)
		return error;

	if (!dir->i_op || !dir->i_op->mkdir)
		return -EPERM;

	mode &= (S_IRWXUGO|S_ISVTX);
	error = security_inode_mkdir(dir, dentry, mode);
	if (error)
		return error;

	DQUOT_INIT(dir);
	error = dir->i_op->mkdir(dir, dentry, mode);
	if (!error)
		fsnotify_mkdir(dir, dentry->d_name.name);
	return error;
}

asmlinkage long sys_mkdir(const char __user * pathname, int mode)
{
	int error = 0;
	char * tmp;

	tmp = getname(pathname);
	error = PTR_ERR(tmp);
	if (!IS_ERR(tmp)) {
		struct dentry *dentry;
		struct nameidata nd;

		error = path_lookup(tmp, LOOKUP_PARENT, &nd);
		if (error)
			goto out;
		dentry = lookup_create(&nd, 1);
		error = PTR_ERR(dentry);
		if (!IS_ERR(dentry)) {
			if (!IS_POSIXACL(nd.dentry->d_inode))
				mode &= ~current->fs->umask;
			error = vfs_mkdir(nd.dentry->d_inode, dentry, mode);
			dput(dentry);
		}
		up(&nd.dentry->d_inode->i_sem);
		path_release(&nd);
out:
		putname(tmp);
	}

	return error;
}

/*
 * We try to drop the dentry early: we should have
 * a usage count of 2 if we're the only user of this
 * dentry, and if that is true (possibly after pruning
 * the dcache), then we drop the dentry now.
 *
 * A low-level filesystem can, if it choses, legally
 * do a
 *
 *	if (!d_unhashed(dentry))
 *		return -EBUSY;
 *
 * if it cannot handle the case of removing a directory
 * that is still in use by something else..
 */
void dentry_unhash(struct dentry *dentry)
{
	dget(dentry);
	if (atomic_read(&dentry->d_count))
		shrink_dcache_parent(dentry);
	spin_lock(&dcache_lock);
	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count) == 2)
		__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
}

int vfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	int error = may_delete(dir, dentry, 1);

	if (error)
		return error;

	if (!dir->i_op || !dir->i_op->rmdir)
		return -EPERM;

	DQUOT_INIT(dir);

	down(&dentry->d_inode->i_sem);
	dentry_unhash(dentry);
	if (d_mountpoint(dentry))
		error = -EBUSY;
	else {
		error = security_inode_rmdir(dir, dentry);
		if (!error) {
			error = dir->i_op->rmdir(dir, dentry);
			if (!error)
				dentry->d_inode->i_flags |= S_DEAD;
		}
	}
	up(&dentry->d_inode->i_sem);
	if (!error) {
		d_delete(dentry);
	}
	dput(dentry);

	return error;
}

asmlinkage long sys_rmdir(const char __user * pathname)
{
	int error = 0;
	char * name;
	struct dentry *dentry;
	struct nameidata nd;

	name = getname(pathname);
	if(IS_ERR(name))
		return PTR_ERR(name);

	error = path_lookup(name, LOOKUP_PARENT, &nd);
	if (error)
		goto exit;

	switch(nd.last_type) {
		case LAST_DOTDOT:
			error = -ENOTEMPTY;
			goto exit1;
		case LAST_DOT:
			error = -EINVAL;
			goto exit1;
		case LAST_ROOT:
			error = -EBUSY;
			goto exit1;
	}
	down(&nd.dentry->d_inode->i_sem);
	dentry = lookup_hash(&nd);
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		error = vfs_rmdir(nd.dentry->d_inode, dentry);
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
exit1:
	path_release(&nd);
exit:
	putname(name);
	return error;
}

int vfs_unlink(struct inode *dir, struct dentry *dentry)
{
	int error = may_delete(dir, dentry, 0);

	if (error)
		return error;

	if (!dir->i_op || !dir->i_op->unlink)
		return -EPERM;

	DQUOT_INIT(dir);

	down(&dentry->d_inode->i_sem);
	if (d_mountpoint(dentry))
		error = -EBUSY;
	else {
		error = security_inode_unlink(dir, dentry);
		if (!error)
			error = dir->i_op->unlink(dir, dentry);
	}
	up(&dentry->d_inode->i_sem);

	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
		d_delete(dentry);
	}

	return error;
}

/*
 * Make sure that the actual truncation of the file will occur outside its
 * directory's i_sem.  Truncate can take a long time if there is a lot of
 * writeout happening, and we don't want to prevent access to the directory
 * while waiting on the I/O.
 */
asmlinkage long sys_unlink(const char __user * pathname)
{
	int error = 0;
	char * name;
	struct dentry *dentry;
	struct nameidata nd;
	struct inode *inode = NULL;

	name = getname(pathname);
	if(IS_ERR(name))
		return PTR_ERR(name);

	error = path_lookup(name, LOOKUP_PARENT, &nd);
	if (error)
		goto exit;
	error = -EISDIR;
	if (nd.last_type != LAST_NORM)
		goto exit1;
	down(&nd.dentry->d_inode->i_sem);
	dentry = lookup_hash(&nd);
	error = PTR_ERR(dentry);
	if (!IS_ERR(dentry)) {
		/* Why not before? Because we want correct error value */
		if (nd.last.name[nd.last.len])
			goto slashes;
		inode = dentry->d_inode;
		if (inode)
			atomic_inc(&inode->i_count);
		error = vfs_unlink(nd.dentry->d_inode, dentry);
	exit2:
		dput(dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
	if (inode)
		iput(inode);	/* truncate the inode here */
exit1:
	path_release(&nd);
exit:
	putname(name);
	return error;

slashes:
	error = !dentry->d_inode ? -ENOENT :
		S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
	goto exit2;
}

int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode)
{
	int error = may_create(dir, dentry, NULL);

	if (error)
		return error;

	if (!dir->i_op || !dir->i_op->symlink)
		return -EPERM;

	error = security_inode_symlink(dir, dentry, oldname);
	if (error)
		return error;

	DQUOT_INIT(dir);
	error = dir->i_op->symlink(dir, dentry, oldname);
	if (!error)
		fsnotify_create(dir, dentry->d_name.name);
	return error;
}

asmlinkage long sys_symlink(const char __user * oldname, const char __user * newname)
{
	int error = 0;
	char * from;
	char * to;

	from = getname(oldname);
	if(IS_ERR(from))
		return PTR_ERR(from);
	to = getname(newname);
	error = PTR_ERR(to);
	if (!IS_ERR(to)) {
		struct dentry *dentry;
		struct nameidata nd;

		error = path_lookup(to, LOOKUP_PARENT, &nd);
		if (error)
			goto out;
		dentry = lookup_create(&nd, 0);
		error = PTR_ERR(dentry);
		if (!IS_ERR(dentry)) {
			error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
			dput(dentry);
		}
		up(&nd.dentry->d_inode->i_sem);
		path_release(&nd);
out:
		putname(to);
	}
	putname(from);
	return error;
}

int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
{
	struct inode *inode = old_dentry->d_inode;
	int error;

	if (!inode)
		return -ENOENT;

	error = may_create(dir, new_dentry, NULL);
	if (error)
		return error;

	if (dir->i_sb != inode->i_sb)
		return -EXDEV;

	/*
	 * A link to an append-only or immutable file cannot be created.
	 */
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return -EPERM;
	if (!dir->i_op || !dir->i_op->link)
		return -EPERM;
	if (S_ISDIR(old_dentry->d_inode->i_mode))
		return -EPERM;

	error = security_inode_link(old_dentry, dir, new_dentry);
	if (error)
		return error;

	down(&old_dentry->d_inode->i_sem);
	DQUOT_INIT(dir);
	error = dir->i_op->link(old_dentry, dir, new_dentry);
	up(&old_dentry->d_inode->i_sem);
	if (!error)
		fsnotify_create(dir, new_dentry->d_name.name);
	return error;
}

/*
 * Hardlinks are often used in delicate situations.  We avoid
 * security-related surprises by not following symlinks on the
 * newname.  --KAB
 *
 * We don't follow them on the oldname either to be compatible
 * with linux 2.0, and to avoid hard-linking to directories
 * and other special files.  --ADM
 */
asmlinkage long sys_link(const char __user * oldname, const char __user * newname)
{
	struct dentry *new_dentry;
	struct nameidata nd, old_nd;
	int error;
	char * to;

	to = getname(newname);
	if (IS_ERR(to))
		return PTR_ERR(to);

	error = __user_walk(oldname, 0, &old_nd);
	if (error)
		goto exit;
	error = path_lookup(to, LOOKUP_PARENT, &nd);
	if (error)
		goto out;
	error = -EXDEV;
	if (old_nd.mnt != nd.mnt)
		goto out_release;
	new_dentry = lookup_create(&nd, 0);
	error = PTR_ERR(new_dentry);
	if (!IS_ERR(new_dentry)) {
		error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry);
		dput(new_dentry);
	}
	up(&nd.dentry->d_inode->i_sem);
out_release:
	path_release(&nd);
out:
	path_release(&old_nd);
exit:
	putname(to);

	return error;
}

/*
 * The worst of all namespace operations - renaming directory. "Perverted"
 * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
 * Problems:
 *	a) we can get into loop creation. Check is done in is_subdir().
 *	b) race potential - two innocent renames can create a loop together.
 *	   That's where 4.4 screws up. Current fix: serialization on
 *	   sb->s_vfs_rename_sem. We might be more accurate, but that's another
 *	   story.
 *	c) we have to lock _three_ objects - parents and victim (if it exists).
 *	   And that - after we got ->i_sem on parents (until then we don't know
 *	   whether the target exists).  Solution: try to be smart with locking
 *	   order for inodes.  We rely on the fact that tree topology may change
 *	   only under ->s_vfs_rename_sem _and_ that parent of the object we
 *	   move will be locked.  Thus we can rank directories by the tree
 *	   (ancestors first) and rank all non-directories after them.
 *	   That works since everybody except rename does "lock parent, lookup,
 *	   lock child" and rename is under ->s_vfs_rename_sem.
 *	   HOWEVER, it relies on the assumption that any object with ->lookup()
 *	   has no more than 1 dentry.  If "hybrid" objects will ever appear,
 *	   we'd better make sure that there's no link(2) for them.
 *	d) some filesystems don't support opened-but-unlinked directories,
 *	   either because of layout or because they are not ready to deal with
 *	   all cases correctly. The latter will be fixed (taking this sort of
 *	   stuff into VFS), but the former is not going away. Solution: the same
 *	   trick as in rmdir().
 *	e) conversion from fhandle to dentry may come in the wrong moment - when
 *	   we are removing the target. Solution: we will have to grab ->i_sem
 *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
 *	   ->i_sem on parents, which works but leads to some truely excessive