summaryrefslogtreecommitdiffstats
path: root/fs/namespace.c
blob: 3782923d6d4d583091e731f6b02cd6343de82636 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
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
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
/*
 *  linux/fs/namespace.c
 *
 * (C) Copyright Al Viro 2000, 2001
 *	Released under GPL v2.
 *
 * Based on code from fs/super.c, copyright Linus Torvalds and others.
 * Heavily rewritten.
 */

#include <linux/config.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/acct.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"

extern int __init init_rootfs(void);

#define CL_EXPIRE 	0x01

#ifdef CONFIG_SYSFS
extern int __init sysfs_init(void);
#else
static inline int sysfs_init(void)
{
	return 0;
}
#endif

/* spinlock for vfsmount related operations, inplace of dcache_lock */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);

static int event;

static struct list_head *mount_hashtable;
static int hash_mask __read_mostly, hash_bits __read_mostly;
static kmem_cache_t *mnt_cache;
static struct rw_semaphore namespace_sem;

static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
{
	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
	tmp = tmp + (tmp >> hash_bits);
	return tmp & hash_mask;
}

struct vfsmount *alloc_vfsmnt(const char *name)
{
	struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL);
	if (mnt) {
		memset(mnt, 0, sizeof(struct vfsmount));
		atomic_set(&mnt->mnt_count, 1);
		INIT_LIST_HEAD(&mnt->mnt_hash);
		INIT_LIST_HEAD(&mnt->mnt_child);
		INIT_LIST_HEAD(&mnt->mnt_mounts);
		INIT_LIST_HEAD(&mnt->mnt_list);
		INIT_LIST_HEAD(&mnt->mnt_expire);
		if (name) {
			int size = strlen(name) + 1;
			char *newname = kmalloc(size, GFP_KERNEL);
			if (newname) {
				memcpy(newname, name, size);
				mnt->mnt_devname = newname;
			}
		}
	}
	return mnt;
}

void free_vfsmnt(struct vfsmount *mnt)
{
	kfree(mnt->mnt_devname);
	kmem_cache_free(mnt_cache, mnt);
}

/*
 * Now, lookup_mnt increments the ref count before returning
 * the vfsmount struct.
 */
struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
	struct list_head *head = mount_hashtable + hash(mnt, dentry);
	struct list_head *tmp = head;
	struct vfsmount *p, *found = NULL;

	spin_lock(&vfsmount_lock);
	for (;;) {
		tmp = tmp->next;
		p = NULL;
		if (tmp == head)
			break;
		p = list_entry(tmp, struct vfsmount, mnt_hash);
		if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) {
			found = mntget(p);
			break;
		}
	}
	spin_unlock(&vfsmount_lock);
	return found;
}

static inline int check_mnt(struct vfsmount *mnt)
{
	return mnt->mnt_namespace == current->namespace;
}

static void touch_namespace(struct namespace *ns)
{
	if (ns) {
		ns->event = ++event;
		wake_up_interruptible(&ns->poll);
	}
}

static void __touch_namespace(struct namespace *ns)
{
	if (ns && ns->event != event) {
		ns->event = event;
		wake_up_interruptible(&ns->poll);
	}
}

static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
{
	old_nd->dentry = mnt->mnt_mountpoint;
	old_nd->mnt = mnt->mnt_parent;
	mnt->mnt_parent = mnt;
	mnt->mnt_mountpoint = mnt->mnt_root;
	list_del_init(&mnt->mnt_child);
	list_del_init(&mnt->mnt_hash);
	old_nd->dentry->d_mounted--;
}

static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd)
{
	mnt->mnt_parent = mntget(nd->mnt);
	mnt->mnt_mountpoint = dget(nd->dentry);
	list_add(&mnt->mnt_hash, mount_hashtable + hash(nd->mnt, nd->dentry));
	list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts);
	nd->dentry->d_mounted++;
}

static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root)
{
	struct list_head *next = p->mnt_mounts.next;
	if (next == &p->mnt_mounts) {
		while (1) {
			if (p == root)
				return NULL;
			next = p->mnt_child.next;
			if (next != &p->mnt_parent->mnt_mounts)
				break;
			p = p->mnt_parent;
		}
	}
	return list_entry(next, struct vfsmount, mnt_child);
}

static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
					int flag)
{
	struct super_block *sb = old->mnt_sb;
	struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);

	if (mnt) {
		mnt->mnt_flags = old->mnt_flags;
		atomic_inc(&sb->s_active);
		mnt->mnt_sb = sb;
		mnt->mnt_root = dget(root);
		mnt->mnt_mountpoint = mnt->mnt_root;
		mnt->mnt_parent = mnt;
		mnt->mnt_namespace = current->namespace;

		/* stick the duplicate mount on the same expiry list
		 * as the original if that was on one */
		if (flag & CL_EXPIRE) {
			spin_lock(&vfsmount_lock);
			if (!list_empty(&old->mnt_expire))
				list_add(&mnt->mnt_expire, &old->mnt_expire);
			spin_unlock(&vfsmount_lock);
		}
	}
	return mnt;
}

static inline void __mntput(struct vfsmount *mnt)
{
	struct super_block *sb = mnt->mnt_sb;
	dput(mnt->mnt_root);
	free_vfsmnt(mnt);
	deactivate_super(sb);
}

void mntput_no_expire(struct vfsmount *mnt)
{
repeat:
	if (atomic_dec_and_lock(&mnt->mnt_count, &vfsmount_lock)) {
		if (likely(!mnt->mnt_pinned)) {
			spin_unlock(&vfsmount_lock);
			__mntput(mnt);
			return;
		}
		atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count);
		mnt->mnt_pinned = 0;
		spin_unlock(&vfsmount_lock);
		acct_auto_close_mnt(mnt);
		security_sb_umount_close(mnt);
		goto repeat;
	}
}

EXPORT_SYMBOL(mntput_no_expire);

void mnt_pin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	mnt->mnt_pinned++;
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_pin);

void mnt_unpin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	if (mnt->mnt_pinned) {
		atomic_inc(&mnt->mnt_count);
		mnt->mnt_pinned--;
	}
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_unpin);

/* iterator */
static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p;
	loff_t l = *pos;

	down_read(&namespace_sem);
	list_for_each(p, &n->list)
		if (!l--)
			return list_entry(p, struct vfsmount, mnt_list);
	return NULL;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p = ((struct vfsmount *)v)->mnt_list.next;
	(*pos)++;
	return p == &n->list ? NULL : list_entry(p, struct vfsmount, mnt_list);
}

static void m_stop(struct seq_file *m, void *v)
{
	up_read(&namespace_sem);
}

static inline void mangle(struct seq_file *m, const char *s)
{
	seq_escape(m, s, " \t\n\\");
}

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = v;
	int err = 0;
	static struct proc_fs_info {
		int flag;
		char *str;
	} fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_DIRSYNC, ",dirsync" },
		{ MS_MANDLOCK, ",mand" },
		{ MS_NOATIME, ",noatime" },
		{ MS_NODIRATIME, ",nodiratime" },
		{ 0, NULL }
	};
	static struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ 0, NULL }
	};
	struct proc_fs_info *fs_infop;

	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_putc(m, ' ');
	seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
	seq_putc(m, ' ');
	mangle(m, mnt->mnt_sb->s_type->name);
	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_sb->s_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	if (mnt->mnt_sb->s_op->show_options)
		err = mnt->mnt_sb->s_op->show_options(m, mnt);
	seq_puts(m, " 0 0\n");
	return err;
}

struct seq_operations mounts_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_vfsmnt
};

/**
 * may_umount_tree - check if a mount tree is busy
 * @mnt: root of mount tree
 *
 * This is called to check if a tree of mounts has any
 * open files, pwds, chroots or sub mounts that are
 * busy.
 */
int may_umount_tree(struct vfsmount *mnt)
{
	int actual_refs = 0;
	int minimum_refs = 0;
	struct vfsmount *p;

	spin_lock(&vfsmount_lock);
	for (p = mnt; p; p = next_mnt(p, mnt)) {
		actual_refs += atomic_read(&p->mnt_count);
		minimum_refs += 2;
	}
	spin_unlock(&vfsmount_lock);

	if (actual_refs > minimum_refs)
		return -EBUSY;

	return 0;
}

EXPORT_SYMBOL(may_umount_tree);

/**
 * may_umount - check if a mount point is busy
 * @mnt: root of mount
 *
 * This is called to check if a mount point has any
 * open files, pwds, chroots or sub mounts. If the
 * mount has sub mounts this will return busy
 * regardless of whether the sub mounts are busy.
 *
 * Doesn't take quota and stuff into account. IOW, in some cases it will
 * give false negatives. The main reason why it's here is that we need
 * a non-destructive way to look for easily umountable filesystems.
 */
int may_umount(struct vfsmount *mnt)
{
	if (atomic_read(&mnt->mnt_count) > 2)
		return -EBUSY;
	return 0;
}

EXPORT_SYMBOL(may_umount);

static void release_mounts(struct list_head *head)
{
	struct vfsmount *mnt;
	while(!list_empty(head)) {
		mnt = list_entry(head->next, struct vfsmount, mnt_hash);
		list_del_init(&mnt->mnt_hash);
		if (mnt->mnt_parent != mnt) {
			struct dentry *dentry;
			struct vfsmount *m;
			spin_lock(&vfsmount_lock);
			dentry = mnt->mnt_mountpoint;
			m = mnt->mnt_parent;
			mnt->mnt_mountpoint = mnt->mnt_root;
			mnt->mnt_parent = mnt;
			spin_unlock(&vfsmount_lock);
			dput(dentry);
			mntput(m);
		}
		mntput(mnt);
	}
}

static void umount_tree(struct vfsmount *mnt, struct list_head *kill)
{
	struct vfsmount *p;

	for (p = mnt; p; p = next_mnt(p, mnt)) {
		list_del(&p->mnt_hash);
		list_add(&p->mnt_hash, kill);
	}

	list_for_each_entry(p, kill, mnt_hash) {
		list_del_init(&p->mnt_expire);
		list_del_init(&p->mnt_list);
		__touch_namespace(p->mnt_namespace);
		p->mnt_namespace = NULL;
		list_del_init(&p->mnt_child);
		if (p->mnt_parent != p)
			mnt->mnt_mountpoint->d_mounted--;
	}
}

static int do_umount(struct vfsmount *mnt, int flags)
{
	struct super_block *sb = mnt->mnt_sb;
	int retval;
	LIST_HEAD(umount_list);

	retval = security_sb_umount(mnt, flags);
	if (retval)
		return retval;

	/*
	 * Allow userspace to request a mountpoint be expired rather than
	 * unmounting unconditionally. Unmount only happens if:
	 *  (1) the mark is already set (the mark is cleared by mntput())
	 *  (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
	 */
	if (flags & MNT_EXPIRE) {
		if (mnt == current->fs->rootmnt ||
		    flags & (MNT_FORCE | MNT_DETACH))
			return -EINVAL;

		if (atomic_read(&mnt->mnt_count) != 2)
			return -EBUSY;

		if (!xchg(&mnt->mnt_expiry_mark, 1))
			return -EAGAIN;
	}

	/*
	 * If we may have to abort operations to get out of this
	 * mount, and they will themselves hold resources we must
	 * allow the fs to do things. In the Unix tradition of
	 * 'Gee thats tricky lets do it in userspace' the umount_begin
	 * might fail to complete on the first run through as other tasks
	 * must return, and the like. Thats for the mount program to worry
	 * about for the moment.
	 */

	lock_kernel();
	if ((flags & MNT_FORCE) && sb->s_op->umount_begin)
		sb->s_op->umount_begin(sb);
	unlock_kernel();

	/*
	 * No sense to grab the lock for this test, but test itself looks
	 * somewhat bogus. Suggestions for better replacement?
	 * Ho-hum... In principle, we might treat that as umount + switch
	 * to rootfs. GC would eventually take care of the old vfsmount.
	 * Actually it makes sense, especially if rootfs would contain a
	 * /reboot - static binary that would close all descriptors and
	 * call reboot(9). Then init(8) could umount root and exec /reboot.
	 */
	if (mnt == current->fs->rootmnt && !(flags & MNT_DETACH)) {
		/*
		 * Special case for "unmounting" root ...
		 * we just try to remount it readonly.
		 */
		down_write(&sb->s_umount);
		if (!(sb->s_flags & MS_RDONLY)) {
			lock_kernel();
			DQUOT_OFF(sb);
			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
			unlock_kernel();
		}
		up_write(&sb->s_umount);
		return retval;
	}

	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	event++;

	retval = -EBUSY;
	if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) {
		if (!list_empty(&mnt->mnt_list))
			umount_tree(mnt, &umount_list);
		retval = 0;
	}
	spin_unlock(&vfsmount_lock);
	if (retval)
		security_sb_umount_busy(mnt);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
	return retval;
}

/*
 * Now umount can handle mount points as well as block devices.
 * This is important for filesystems which use unnamed block devices.
 *
 * We now support a flag for forced unmount like the other 'big iron'
 * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
 */

asmlinkage long sys_umount(char __user * name, int flags)
{
	struct nameidata nd;
	int retval;

	retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
	if (retval)
		goto out;
	retval = -EINVAL;
	if (nd.dentry != nd.mnt->mnt_root)
		goto dput_and_out;
	if (!check_mnt(nd.mnt))
		goto dput_and_out;

	retval = -EPERM;
	if (!capable(CAP_SYS_ADMIN))
		goto dput_and_out;

	retval = do_umount(nd.mnt, flags);
dput_and_out:
	path_release_on_umount(&nd);
out:
	return retval;
}

#ifdef __ARCH_WANT_SYS_OLDUMOUNT

/*
 *	The 2.0 compatible umount. No flags.
 */
asmlinkage long sys_oldumount(char __user * name)
{
	return sys_umount(name, 0);
}

#endif

static int mount_is_safe(struct nameidata *nd)
{
	if (capable(CAP_SYS_ADMIN))
		return 0;
	return -EPERM;
#ifdef notyet
	if (S_ISLNK(nd->dentry->d_inode->i_mode))
		return -EPERM;
	if (nd->dentry->d_inode->i_mode & S_ISVTX) {
		if (current->uid != nd->dentry->d_inode->i_uid)
			return -EPERM;
	}
	if (permission(nd->dentry->d_inode, MAY_WRITE, nd))
		return -EPERM;
	return 0;
#endif
}

static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry)
{
	while (1) {
		if (d == dentry)
			return 1;
		if (d == NULL || d == d->d_parent)
			return 0;
		d = d->d_parent;
	}
}

static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
					int flag)
{
	struct vfsmount *res, *p, *q, *r, *s;
	struct nameidata nd;

	res = q = clone_mnt(mnt, dentry, flag);
	if (!q)
		goto Enomem;
	q->mnt_mountpoint = mnt->mnt_mountpoint;

	p = mnt;
	list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
		if (!lives_below_in_same_fs(r->mnt_mountpoint, dentry))
			continue;

		for (s = r; s; s = next_mnt(s, r)) {
			while (p != s->mnt_parent) {
				p = p->mnt_parent;
				q = q->mnt_parent;
			}
			p = s;
			nd.mnt = q;
			nd.dentry = p->mnt_mountpoint;
			q = clone_mnt(p, p->mnt_root, flag);
			if (!q)
				goto Enomem;
			spin_lock(&vfsmount_lock);
			list_add_tail(&q->mnt_list, &res->mnt_list);
			attach_mnt(q, &nd);
			spin_unlock(&vfsmount_lock);
		}
	}
	return res;
Enomem:
	if (res) {
		LIST_HEAD(umount_list);
		spin_lock(&vfsmount_lock);
		umount_tree(res, &umount_list);
		spin_unlock(&vfsmount_lock);
		release_mounts(&umount_list);
	}
	return NULL;
}

static int graft_tree(struct vfsmount *mnt, struct nameidata *nd)
{
	int err;
	if (mnt->mnt_sb->s_flags & MS_NOUSER)
		return -EINVAL;

	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
		return -ENOTDIR;

	err = -ENOENT;
	down(&nd->dentry->d_inode->i_sem);
	if (IS_DEADDIR(nd->dentry->d_inode))
		goto out_unlock;

	err = security_sb_check_sb(mnt, nd);
	if (err)
		goto out_unlock;

	err = -ENOENT;
	spin_lock(&vfsmount_lock);
	if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) {
		struct list_head head;

		attach_mnt(mnt, nd);
		list_add_tail(&head, &mnt->mnt_list);
		list_splice(&head, current->namespace->list.prev);
		err = 0;
		touch_namespace(current->namespace);
	}
	spin_unlock(&vfsmount_lock);
out_unlock:
	up(&nd->dentry->d_inode->i_sem);
	if (!err)
		security_sb_post_addmount(mnt, nd);
	return err;
}

/*
 * recursively change the type of the mountpoint.
 */
static int do_change_type(struct nameidata *nd, int flag)
{
	struct vfsmount *m, *mnt = nd->mnt;
	int recurse = flag & MS_REC;
	int type = flag & ~MS_REC;

	if (nd->dentry != nd->mnt->mnt_root)
		return -EINVAL;

	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
		change_mnt_propagation(m, type);
	spin_unlock(&vfsmount_lock);
	up_write(&namespace_sem);
	return 0;
}

/*
 * do loopback mount.
 */
static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
{
	struct nameidata old_nd;
	struct vfsmount *mnt = NULL;
	int err = mount_is_safe(nd);
	if (err)
		return err;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
	if (err)
		return err;

	down_write(&namespace_sem);
	err = -EINVAL;
	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
		goto out;

	err = -ENOMEM;
	if (recurse)
		mnt = copy_tree(old_nd.mnt, old_nd.dentry, 0);
	else
		mnt = clone_mnt(old_nd.mnt, old_nd.dentry, 0);

	if (!mnt)
		goto out;

	err = graft_tree(mnt, nd);
	if (err) {
		LIST_HEAD(umount_list);
		spin_lock(&vfsmount_lock);
		umount_tree(mnt, &umount_list);
		spin_unlock(&vfsmount_lock);
		release_mounts(&umount_list);
	}

out:
	up_write(&namespace_sem);
	path_release(&old_nd);
	return err;
}

/*
 * change filesystem flags. dir should be a physical root of filesystem.
 * If you've mounted a non-root directory somewhere and want to do remount
 * on it - tough luck.
 */
static int do_remount(struct nameidata *nd, int flags, int mnt_flags,
		      void *data)
{
	int err;
	struct super_block *sb = nd->mnt->mnt_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!check_mnt(nd->mnt))
		return -EINVAL;

	if (nd->dentry != nd->mnt->mnt_root)
		return -EINVAL;

	down_write(&sb->s_umount);
	err = do_remount_sb(sb, flags, data, 0);
	if (!err)
		nd->mnt->mnt_flags = mnt_flags;
	up_write(&sb->s_umount);
	if (!err)
		security_sb_post_remount(nd->mnt, flags, data);
	return err;
}

static int do_move_mount(struct nameidata *nd, char *old_name)
{
	struct nameidata old_nd, parent_nd;
	struct vfsmount *p;
	int err = 0;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!old_name || !*old_name)
		return -EINVAL;
	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
	if (err)
		return err;

	down_write(&namespace_sem);
	while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
		goto out;

	err = -ENOENT;
	down(&nd->dentry->d_inode->i_sem);
	if (IS_DEADDIR(nd->dentry->d_inode))
		goto out1;

	spin_lock(&vfsmount_lock);
	if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))
		goto out2;

	err = -EINVAL;
	if (old_nd.dentry != old_nd.mnt->mnt_root)
		goto out2;

	if (old_nd.mnt == old_nd.mnt->mnt_parent)
		goto out2;

	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
	      S_ISDIR(old_nd.dentry->d_inode->i_mode))
		goto out2;

	err = -ELOOP;
	for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent)
		if (p == old_nd.mnt)
			goto out2;
	err = 0;

	detach_mnt(old_nd.mnt, &parent_nd);
	attach_mnt(old_nd.mnt, nd);
	touch_namespace(current->namespace);

	/* if the mount is moved, it should no longer be expire
	 * automatically */
	list_del_init(&old_nd.mnt->mnt_expire);
out2:
	spin_unlock(&vfsmount_lock);
out1:
	up(&nd->dentry->d_inode->i_sem);
out:
	up_write(&namespace_sem);
	if (!err)
		path_release(&parent_nd);
	path_release(&old_nd);
	return err;
}

/*
 * create a new mount for userspace and request it to be added into the
 * namespace's tree
 */
static int do_new_mount(struct nameidata *nd, char *type, int flags,
			int mnt_flags, char *name, void *data)
{
	struct vfsmount *mnt;

	if (!type || !memchr(type, 0, PAGE_SIZE))
		return -EINVAL;

	/* we need capabilities... */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	mnt = do_kern_mount(type, flags, name, data);
	if (IS_ERR(mnt))
		return PTR_ERR(mnt);

	return do_add_mount(mnt, nd, mnt_flags, NULL);
}

/*
 * add a mount into a namespace's mount tree
 * - provide the option of adding the new mount to an expiration list
 */
int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
		 int mnt_flags, struct list_head *fslist)
{
	int err;

	down_write(&namespace_sem);
	/* Something was mounted here while we slept */
	while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
		;
	err = -EINVAL;
	if (!check_mnt(nd->mnt))
		goto unlock;

	/* Refuse the same filesystem on the same mount point */
	err = -EBUSY;
	if (nd->mnt->mnt_sb == newmnt->mnt_sb &&
	    nd->mnt->mnt_root == nd->dentry)
		goto unlock;

	err = -EINVAL;
	if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
		goto unlock;

	newmnt->mnt_flags = mnt_flags;
	if ((err = graft_tree(newmnt, nd)))
		goto unlock;

	if (fslist) {
		/* add to the specified expiration list */
		spin_lock(&vfsmount_lock);
		list_add_tail(&newmnt->mnt_expire, fslist);
		spin_unlock(&vfsmount_lock);
	}
	up_write(&namespace_sem);
	return 0;

unlock:
	up_write(&namespace_sem);
	mntput(newmnt);
	return err;
}

EXPORT_SYMBOL_GPL(do_add_mount);

static void expire_mount(struct vfsmount *mnt, struct list_head *mounts,
				struct list_head *umounts)
{
	spin_lock(&vfsmount_lock);

	/*
	 * Check if mount is still attached, if not, let whoever holds it deal
	 * with the sucker
	 */
	if (mnt->mnt_parent == mnt) {
		spin_unlock(&vfsmount_lock);
		return;
	}

	/*
	 * Check that it is still dead: the count should now be 2 - as
	 * contributed by the vfsmount parent and the mntget above
	 */
	if (atomic_read(&mnt->mnt_count) == 2) {
		/* delete from the namespace */
		touch_namespace(mnt->mnt_namespace);
		list_del_init(&mnt->mnt_list);
		mnt->mnt_namespace = NULL;
		umount_tree(mnt, umounts);
		spin_unlock(&vfsmount_lock);
	} else {
		/*
		 * Someone brought it back to life whilst we didn't have any
		 * locks held so return it to the expiration list
		 */
		list_add_tail(&mnt->mnt_expire, mounts);
		spin_unlock(&vfsmount_lock);
	}
}

/*
 * process a list of expirable mountpoints with the intent of discarding any
 * mountpoints that aren't in use and haven't been touched since last we came
 * here
 */
void mark_mounts_for_expiry(struct list_head *mounts)
{
	struct namespace *namespace;
	struct vfsmount *mnt, *next;
	LIST_HEAD(graveyard);

	if (list_empty(mounts))
		return;

	spin_lock(&vfsmount_lock);

	/* extract from the expiration list every vfsmount that matches the
	 * following criteria:
	 * - only referenced by its parent vfsmount
	 * - still marked for expiry (marked on the last call here; marks are
	 *   cleared by mntput())
	 */
	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
		    atomic_read(&mnt->mnt_count) != 1)
			continue;

		mntget(mnt);
		list_move(&mnt->mnt_expire, &graveyard);
	}

	/*
	 * go through the vfsmounts we've just consigned to the graveyard to
	 * - check that they're still dead
	 * - delete the vfsmount from the appropriate namespace under lock
	 * - dispose of the corpse
	 */
	while (!list_empty(&graveyard)) {
		LIST_HEAD(umounts);
		mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire);
		list_del_init(&mnt->mnt_expire);

		/* don't do anything if the namespace is dead - all the
		 * vfsmounts from it are going away anyway */
		namespace = mnt->mnt_namespace;
		if (!namespace || !namespace->root)
			continue;
		get_namespace(namespace);

		spin_unlock(&vfsmount_lock);
		down_write(&namespace_sem);
		expire_mount(mnt, mounts, &umounts);
		up_write(&namespace_sem);
		release_mounts(&umounts);
		mntput(mnt);
		put_namespace(namespace);
		spin_lock(&vfsmount_lock);
	}

	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);

/*
 * Some copy_from_user() implementations do not return the exact number of
 * bytes remaining to copy on a fault.  But copy_mount_options() requires that.
 * Note that this function differs from copy_from_user() in that it will oops
 * on bad values of `to', rather than returning a short copy.
 */
static long exact_copy_from_user(void *to, const void __user * from,
				 unsigned long n)
{
	char *t = to;
	const char __user *f = from;
	char c;

	if (!access_ok(VERIFY_READ, from, n))
		return n;

	while (n) {
		if (__get_user(c, f)) {
			memset(t, 0, n);
			break;
		}
		*t++ = c;
		f++;
		n--;
	}
	return n;
}

int copy_mount_options(const void __user * data, unsigned long *where)
{
	int i;
	unsigned long page;
	unsigned long size;

	*where = 0;
	if (!data)
		return 0;

	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	/* We only care that *some* data at the address the user
	 * gave us is valid.  Just in case, we'll zero
	 * the remainder of the page.
	 */
	/* copy_from_user cannot cross TASK_SIZE ! */
	size = TASK_SIZE - (unsigned long)data;
	if (size > PAGE_SIZE)
		size = PAGE_SIZE;

	i = size - exact_copy_from_user((void *)page, data, size);
	if (!i) {
		free_page(page);
		return -EFAULT;
	}
	if (i != PAGE_SIZE)
		memset((char *)page + i, 0, PAGE_SIZE - i);
	*where = page;
	return 0;
}

/*
 * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
 * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
 *
 * data is a (void *) that can point to any structure up to
 * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
 * information (or be NULL).
 *
 * Pre-0.97 versions of mount() didn't have a flags word.
 * When the flags word was introduced its top half was required
 * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.
 * Therefore, if this magic number is present, it carries no information
 * and must be discarded.
 */
long do_mount(char *dev_name, char *dir_name, char *type_page,
		  unsigned long flags, void *data_page)
{
	struct nameidata nd;
	int retval = 0;
	int mnt_flags = 0;

	/* Discard magic */
	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
		flags &= ~MS_MGC_MSK;

	/* Basic sanity checks */

	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
		return -EINVAL;
	if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))
		return -EINVAL;

	if (data_page)
		((char *)data_page)[PAGE_SIZE - 1] = 0;

	/* Separate the per-mountpoint flags */
	if (flags & MS_NOSUID)
		mnt_flags |= MNT_NOSUID;
	if (flags & MS_NODEV)
		mnt_flags |= MNT_NODEV;
	if (flags & MS_NOEXEC)
		mnt_flags |= MNT_NOEXEC;
	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE);

	/* ... and get the mountpoint */
	retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd);
	if (retval)
		return retval;

	retval = security_sb_mount(dev_name, &nd, type_page, flags, data_page);
	if (retval)
		goto dput_out;

	if (flags & MS_REMOUNT)
		retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
				    data_page);
	else if (flags & MS_BIND)
		retval = do_loopback(&nd, dev_name, flags & MS_REC);
	else if (flags & MS_PRIVATE)
		retval = do_change_type(&nd, flags);
	else if (flags & MS_MOVE)
		retval = do_move_mount(&nd, dev_name);
	else
		retval = do_new_mount(&nd, type_page, flags, mnt_flags,
				      dev_name, data_page);
dput_out:
	path_release(&nd);
	return retval;
}

int copy_namespace(int flags, struct task_struct *tsk)
{
	struct namespace *namespace = tsk->namespace;
	struct namespace *new_ns;
	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
	struct fs_struct *fs = tsk->fs;
	struct vfsmount *p, *q;

	if (!namespace)
		return 0;

	get_namespace(namespace);

	if (!(flags & CLONE_NEWNS))
		return 0;

	if (!capable(CAP_SYS_ADMIN)) {
		put_namespace(namespace);
		return -EPERM;
	}

	new_ns = kmalloc(sizeof(struct namespace), GFP_KERNEL);
	if (!new_ns)
		goto out;

	atomic_set(&new_ns->count, 1);
	INIT_LIST_HEAD(&new_ns->list);
	init_waitqueue_head(&new_ns->poll);
	new_ns->event = 0;

	down_write(&namespace_sem);
	/* First pass: copy the tree topology */
	new_ns->root = copy_tree(namespace->root, namespace->root->mnt_root,
					CL_EXPIRE);
	if (!new_ns->root) {
		up_write(&namespace_sem);
		kfree(new_ns);
		goto out;
	}
	spin_lock(&vfsmount_lock);
	list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
	spin_unlock(&vfsmount_lock);

	/*
	 * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
	 * as belonging to new namespace.  We have already acquired a private
	 * fs_struct, so tsk->fs->lock is not needed.
	 */
	p = namespace->root;
	q = new_ns->root;
	while (p) {
		q->mnt_namespace = new_ns;
		if (fs) {
			if (p == fs->rootmnt) {
				rootmnt = p;
				fs->rootmnt = mntget(q);
			}
			if (p == fs->pwdmnt) {
				pwdmnt = p;
				fs->pwdmnt = mntget(q);
			}
			if (p == fs->altrootmnt) {
				altrootmnt = p;
				fs->altrootmnt = mntget(q);
			}
		}
		p = next_mnt(p, namespace->root);
		q = next_mnt(q, new_ns->root);
	}
	up_write(&namespace_sem);

	tsk->namespace = new_ns;

	if (rootmnt)
		mntput(rootmnt);
	if (pwdmnt)
		mntput(pwdmnt);
	if (altrootmnt)
		mntput(altrootmnt);

	put_namespace(namespace);
	return 0;

out:
	put_namespace(namespace);
	return -ENOMEM;
}

asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
			  char __user * type, unsigned long flags,
			  void __user * data)
{
	int retval;
	unsigned long data_page;
	unsigned long type_page;
	unsigned long dev_page;
	char *dir_page;

	retval = copy_mount_options(type, &type_page);
	if (retval < 0)
		return retval;

	dir_page = getname(dir_name);
	retval = PTR_ERR(dir_page);
	if (IS_ERR(dir_page))
		goto out1;

	retval = copy_mount_options(dev_name, &dev_page);
	if (retval < 0)
		goto out2;

	retval = copy_mount_options(data, &data_page);
	if (retval < 0)
		goto out3;

	lock_kernel();
	retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
			  flags, (void *)data_page);
	unlock_kernel();
	free_page(data_page);

out3:
	free_page(dev_page);
out2:
	putname(dir_page);
out1:
	free_page(type_page);
	return retval;
}

/*
 * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
 * It can block. Requires the big lock held.
 */
void set_fs_root(struct fs_struct *fs, struct vfsmount *mnt,
		 struct dentry *dentry)
{
	struct dentry *old_root;
	struct vfsmount *old_rootmnt;
	write_lock(&fs->lock);
	old_root = fs->root;
	old_rootmnt = fs->rootmnt;
	fs->rootmnt = mntget(mnt);
	fs->root = dget(dentry);
	write_unlock(&fs->lock);
	if (old_root) {
		dput(old_root);
		mntput(old_rootmnt);
	}
}

/*
 * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
 * It can block. Requires the big lock held.
 */
void set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
		struct dentry *dentry)
{
	struct dentry *old_pwd;
	struct vfsmount *old_pwdmnt;

	write_lock(&fs->lock);
	old_pwd = fs->pwd;
	old_pwdmnt = fs->pwdmnt;
	fs->pwdmnt = mntget(mnt);
	fs->pwd = dget(dentry);
	write_unlock(&fs->lock);

	if (old_pwd) {
		dput(old_pwd);
		mntput(old_pwdmnt);
	}
}

static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
{
	struct task_struct *g, *p;
	struct fs_struct *fs;

	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		task_lock(p);
		fs = p->fs;
		if (fs) {
			atomic_inc(&fs->count);
			task_unlock(p);
			if (fs->root == old_nd->dentry
			    && fs->rootmnt == old_nd->mnt)
				set_fs_root(fs, new_nd->mnt, new_nd->dentry);
			if (fs->pwd == old_nd->dentry
			    && fs->pwdmnt == old_nd->mnt)
				set_fs_pwd(fs, new_nd->mnt, new_nd->dentry);
			put_fs_struct(fs);
		} else
			task_unlock(p);
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);
}

/*
 * pivot_root Semantics:
 * Moves the root file system of the current process to the directory put_old,
 * makes new_root as the new root file system of the current process, and sets
 * root/cwd of all processes which had them on the current root to new_root.
 *
 * Restrictions:
 * The new_root and put_old must be directories, and  must not be on the
 * same file  system as the current process root. The put_old  must  be
 * underneath new_root,  i.e. adding a non-zero number of /.. to the string
 * pointed to by put_old must yield the same directory as new_root. No other
 * file system may be mounted on put_old. After all, new_root is a mountpoint.
 *
 * Notes:
 *  - we don't move root/cwd if they are not at the root (reason: if something
 *    cared enough to change them, it's probably wrong to force them elsewhere)
 *  - it's okay to pick a root that isn't the root of a file system, e.g.
 *    /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
 *    though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
 *    first.
 */
asmlinkage long sys_pivot_root(const char __user * new_root,
			       const char __user * put_old)
{
	struct vfsmount *tmp;
	struct nameidata new_nd, old_nd, parent_nd, root_parent, user_nd;
	int error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	lock_kernel();

	error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
			    &new_nd);
	if (error)
		goto out0;
	error = -EINVAL;
	if (!check_mnt(new_nd.mnt))
		goto out1;

	error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd);
	if (error)
		goto out1;

	error = security_sb_pivotroot(&old_nd, &new_nd);
	if (error) {
		path_release(&old_nd);
		goto out1;
	}

	read_lock(&current->fs->lock);
	user_nd.mnt = mntget(current->fs->rootmnt);
	user_nd.dentry = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	down_write(&namespace_sem);
	down(&old_nd.dentry->d_inode->i_sem);
	error = -EINVAL;
	if (!check_mnt(user_nd.mnt))
		goto out2;
	error = -ENOENT;
	if (IS_DEADDIR(new_nd.dentry->d_inode))
		goto out2;
	if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry))
		goto out2;
	if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry))
		goto out2;
	error = -EBUSY;
	if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt)
		goto out2; /* loop, on the same file system  */
	error = -EINVAL;
	if (user_nd.mnt->mnt_root != user_nd.dentry)
		goto out2; /* not a mountpoint */
	if (user_nd.mnt->mnt_parent == user_nd.mnt)
		goto out2; /* not attached */
	if (new_nd.mnt->mnt_root != new_nd.dentry)
		goto out2; /* not a mountpoint */
	if (new_nd.mnt->mnt_parent == new_nd.mnt)
		goto out2; /* not attached */
	tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
	spin_lock(&vfsmount_lock);
	if (tmp != new_nd.mnt) {
		for (;;) {
			if (tmp->mnt_parent == tmp)
				goto out3; /* already mounted on put_old */
			if (tmp->mnt_parent == new_nd.mnt)
				break;
			tmp = tmp->mnt_parent;
		}
		if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry))
			goto out3;
	} else if (!is_subdir(old_nd.dentry, new_nd.dentry))
		goto out3;
	detach_mnt(new_nd.mnt, &parent_nd);
	detach_mnt(user_nd.mnt, &root_parent);
	attach_mnt(user_nd.mnt, &old_nd);     /* mount old root on put_old */
	attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */
	touch_namespace(current->namespace);
	spin_unlock(&vfsmount_lock);
	chroot_fs_refs(&user_nd, &new_nd);
	security_sb_post_pivotroot(&user_nd, &new_nd);
	error = 0;
	path_release(&root_parent);
	path_release(&parent_nd);
out2:
	up(&old_nd.dentry->d_inode->i_sem);
	up_write(&namespace_sem);
	path_release(&user_nd);
	path_release(&old_nd);
out1:
	path_release(&new_nd);
out0:
	unlock_kernel();
	return error;
out3:
	spin_unlock(&vfsmount_lock);
	goto out2;
}

static void __init init_mount_tree(void)
{
	struct vfsmount *mnt;
	struct namespace *namespace;
	struct task_struct *g, *p;

	mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
	if (IS_ERR(mnt))
		panic("Can't create rootfs");
	namespace = kmalloc(sizeof(*namespace), GFP_KERNEL);
	if (!namespace)
		panic("Can't allocate initial namespace");
	atomic_set(&namespace->count, 1);
	INIT_LIST_HEAD(&namespace->list);
	init_waitqueue_head(&namespace->poll);
	namespace->event = 0;
	list_add(&mnt->mnt_list, &namespace->list);
	namespace->root = mnt;
	mnt->mnt_namespace = namespace;

	init_task.namespace = namespace;
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		get_namespace(namespace);
		p->namespace = namespace;
	} while_each_thread(g, p);
	read_unlock(&tasklist_lock);

	set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root);
	set_fs_root(current->fs, namespace->root, namespace->root->mnt_root);
}

void __init mnt_init(unsigned long mempages)
{
	struct list_head *d;
	unsigned int nr_hash;
	int i;

	init_rwsem(&namespace_sem);

	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount),
			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL, NULL);

	mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);

	if (!mount_hashtable)
		panic("Failed to allocate mount hash table\n");

	/*
	 * Find the power-of-two list-heads that can fit into the allocation..
	 * We don't guarantee that "sizeof(struct list_head)" is necessarily
	 * a power-of-two.
	 */
	nr_hash = PAGE_SIZE / sizeof(struct list_head);
	hash_bits = 0;
	do {
		hash_bits++;
	} while ((nr_hash >> hash_bits) != 0);
	hash_bits--;

	/*
	 * Re-calculate the actual number of entries and the mask
	 * from the number of bits we can fit.
	 */
	nr_hash = 1UL << hash_bits;
	hash_mask = nr_hash - 1;

	printk("Mount-cache hash table entries: %d\n", nr_hash);

	/* And initialize the newly allocated array */
	d = mount_hashtable;
	i = nr_hash;
	do {
		INIT_LIST_HEAD(d);
		d++;
		i--;
	} while (i);
	sysfs_init();
	init_rootfs();
	init_mount_tree();
}

void __put_namespace(struct namespace *namespace)
{
	struct vfsmount *root = namespace->root;
	LIST_HEAD(umount_list);
	namespace->root = NULL;
	spin_unlock(&vfsmount_lock);
	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	umount_tree(root, &umount_list);
	spin_unlock(&vfsmount_lock);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
	kfree(namespace);
}