summaryrefslogtreecommitdiffstats
path: root/fs/ceph/dir.c
blob: 96141ae3d8be3f301a576a7ab30fdba4cf6fde69 (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
#include <linux/ceph/ceph_debug.h>

#include <linux/spinlock.h>
#include <linux/fs_struct.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/sched.h>

#include "super.h"
#include "mds_client.h"

/*
 * Directory operations: readdir, lookup, create, link, unlink,
 * rename, etc.
 */

/*
 * Ceph MDS operations are specified in terms of a base ino and
 * relative path.  Thus, the client can specify an operation on a
 * specific inode (e.g., a getattr due to fstat(2)), or as a path
 * relative to, say, the root directory.
 *
 * Normally, we limit ourselves to strict inode ops (no path component)
 * or dentry operations (a single path component relative to an ino).  The
 * exception to this is open_root_dentry(), which will open the mount
 * point by name.
 */

const struct inode_operations ceph_dir_iops;
const struct file_operations ceph_dir_fops;
const struct dentry_operations ceph_dentry_ops;

/*
 * Initialize ceph dentry state.
 */
int ceph_init_dentry(struct dentry *dentry)
{
	struct ceph_dentry_info *di;

	if (dentry->d_fsdata)
		return 0;

	di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
	if (!di)
		return -ENOMEM;          /* oh well */

	spin_lock(&dentry->d_lock);
	if (dentry->d_fsdata) {
		/* lost a race */
		kmem_cache_free(ceph_dentry_cachep, di);
		goto out_unlock;
	}

	if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
	    ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
		d_set_d_op(dentry, &ceph_dentry_ops);
	else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
		d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
	else
		d_set_d_op(dentry, &ceph_snap_dentry_ops);

	di->dentry = dentry;
	di->lease_session = NULL;
	dentry->d_time = jiffies;
	/* avoid reordering d_fsdata setup so that the check above is safe */
	smp_mb();
	dentry->d_fsdata = di;
	ceph_dentry_lru_add(dentry);
out_unlock:
	spin_unlock(&dentry->d_lock);
	return 0;
}

struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
{
	struct inode *inode = NULL;

	if (!dentry)
		return NULL;

	spin_lock(&dentry->d_lock);
	if (dentry->d_parent) {
		inode = dentry->d_parent->d_inode;
		ihold(inode);
	}
	spin_unlock(&dentry->d_lock);
	return inode;
}


/*
 * for readdir, we encode the directory frag and offset within that
 * frag into f_pos.
 */
static unsigned fpos_frag(loff_t p)
{
	return p >> 32;
}
static unsigned fpos_off(loff_t p)
{
	return p & 0xffffffff;
}

/*
 * When possible, we try to satisfy a readdir by peeking at the
 * dcache.  We make this work by carefully ordering dentries on
 * d_u.d_child when we initially get results back from the MDS, and
 * falling back to a "normal" sync readdir if any dentries in the dir
 * are dropped.
 *
 * D_COMPLETE tells indicates we have all dentries in the dir.  It is
 * defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
 * the MDS if/when the directory is modified).
 */
static int __dcache_readdir(struct file *filp,
			    void *dirent, filldir_t filldir)
{
	struct ceph_file_info *fi = filp->private_data;
	struct dentry *parent = filp->f_dentry;
	struct inode *dir = parent->d_inode;
	struct list_head *p;
	struct dentry *dentry, *last;
	struct ceph_dentry_info *di;
	int err = 0;

	/* claim ref on last dentry we returned */
	last = fi->dentry;
	fi->dentry = NULL;

	dout("__dcache_readdir %p at %llu (last %p)\n", dir, filp->f_pos,
	     last);

	spin_lock(&parent->d_lock);

	/* start at beginning? */
	if (filp->f_pos == 2 || last == NULL ||
	    filp->f_pos < ceph_dentry(last)->offset) {
		if (list_empty(&parent->d_subdirs))
			goto out_unlock;
		p = parent->d_subdirs.prev;
		dout(" initial p %p/%p\n", p->prev, p->next);
	} else {
		p = last->d_u.d_child.prev;
	}

more:
	dentry = list_entry(p, struct dentry, d_u.d_child);
	di = ceph_dentry(dentry);
	while (1) {
		dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
		     d_unhashed(dentry) ? "!hashed" : "hashed",
		     parent->d_subdirs.prev, parent->d_subdirs.next);
		if (p == &parent->d_subdirs) {
			fi->flags |= CEPH_F_ATEND;
			goto out_unlock;
		}
		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
		if (!d_unhashed(dentry) && dentry->d_inode &&
		    ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
		    ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
		    filp->f_pos <= di->offset)
			break;
		dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
		     dentry->d_name.len, dentry->d_name.name, di->offset,
		     filp->f_pos, d_unhashed(dentry) ? " unhashed" : "",
		     !dentry->d_inode ? " null" : "");
		spin_unlock(&dentry->d_lock);
		p = p->prev;
		dentry = list_entry(p, struct dentry, d_u.d_child);
		di = ceph_dentry(dentry);
	}

	dget_dlock(dentry);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&parent->d_lock);

	dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
	     dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
	filp->f_pos = di->offset;
	err = filldir(dirent, dentry->d_name.name,
		      dentry->d_name.len, di->offset,
		      ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
		      dentry->d_inode->i_mode >> 12);

	if (last) {
		if (err < 0) {
			/* remember our position */
			fi->dentry = last;
			fi->next_offset = di->offset;
		} else {
			dput(last);
		}
	}
	last = dentry;

	if (err < 0)
		goto out;

	filp->f_pos++;

	/* make sure a dentry wasn't dropped while we didn't have parent lock */
	if (!ceph_dir_test_complete(dir)) {
		dout(" lost D_COMPLETE on %p; falling back to mds\n", dir);
		err = -EAGAIN;
		goto out;
	}

	spin_lock(&parent->d_lock);
	p = p->prev;	/* advance to next dentry */
	goto more;

out_unlock:
	spin_unlock(&parent->d_lock);
out:
	if (last)
		dput(last);
	return err;
}

/*
 * make note of the last dentry we read, so we can
 * continue at the same lexicographical point,
 * regardless of what dir changes take place on the
 * server.
 */
static int note_last_dentry(struct ceph_file_info *fi, const char *name,
			    int len)
{
	kfree(fi->last_name);
	fi->last_name = kmalloc(len+1, GFP_NOFS);
	if (!fi->last_name)
		return -ENOMEM;
	memcpy(fi->last_name, name, len);
	fi->last_name[len] = 0;
	dout("note_last_dentry '%s'\n", fi->last_name);
	return 0;
}

static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
	struct ceph_file_info *fi = filp->private_data;
	struct inode *inode = filp->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	unsigned frag = fpos_frag(filp->f_pos);
	int off = fpos_off(filp->f_pos);
	int err;
	u32 ftype;
	struct ceph_mds_reply_info_parsed *rinfo;
	const int max_entries = fsc->mount_options->max_readdir;
	const int max_bytes = fsc->mount_options->max_readdir_bytes;

	dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off);
	if (fi->flags & CEPH_F_ATEND)
		return 0;

	/* always start with . and .. */
	if (filp->f_pos == 0) {
		/* note dir version at start of readdir so we can tell
		 * if any dentries get dropped */
		fi->dir_release_count = ci->i_release_count;

		dout("readdir off 0 -> '.'\n");
		if (filldir(dirent, ".", 1, ceph_make_fpos(0, 0),
			    ceph_translate_ino(inode->i_sb, inode->i_ino),
			    inode->i_mode >> 12) < 0)
			return 0;
		filp->f_pos = 1;
		off = 1;
	}
	if (filp->f_pos == 1) {
		ino_t ino = parent_ino(filp->f_dentry);
		dout("readdir off 1 -> '..'\n");
		if (filldir(dirent, "..", 2, ceph_make_fpos(0, 1),
			    ceph_translate_ino(inode->i_sb, ino),
			    inode->i_mode >> 12) < 0)
			return 0;
		filp->f_pos = 2;
		off = 2;
	}

	/* can we use the dcache? */
	spin_lock(&ci->i_ceph_lock);
	if ((filp->f_pos == 2 || fi->dentry) &&
	    !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
	    ceph_snap(inode) != CEPH_SNAPDIR &&
	    ceph_dir_test_complete(inode) &&
	    __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
		spin_unlock(&ci->i_ceph_lock);
		err = __dcache_readdir(filp, dirent, filldir);
		if (err != -EAGAIN)
			return err;
	} else {
		spin_unlock(&ci->i_ceph_lock);
	}
	if (fi->dentry) {
		err = note_last_dentry(fi, fi->dentry->d_name.name,
				       fi->dentry->d_name.len);
		if (err)
			return err;
		dput(fi->dentry);
		fi->dentry = NULL;
	}

	/* proceed with a normal readdir */

more:
	/* do we have the correct frag content buffered? */
	if (fi->frag != frag || fi->last_readdir == NULL) {
		struct ceph_mds_request *req;
		int op = ceph_snap(inode) == CEPH_SNAPDIR ?
			CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;

		/* discard old result, if any */
		if (fi->last_readdir) {
			ceph_mdsc_put_request(fi->last_readdir);
			fi->last_readdir = NULL;
		}

		/* requery frag tree, as the frag topology may have changed */
		frag = ceph_choose_frag(ceph_inode(inode), frag, NULL, NULL);

		dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
		     ceph_vinop(inode), frag, fi->last_name);
		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
		if (IS_ERR(req))
			return PTR_ERR(req);
		req->r_inode = inode;
		ihold(inode);
		req->r_dentry = dget(filp->f_dentry);
		/* hints to request -> mds selection code */
		req->r_direct_mode = USE_AUTH_MDS;
		req->r_direct_hash = ceph_frag_value(frag);
		req->r_direct_is_hash = true;
		req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
		req->r_readdir_offset = fi->next_offset;
		req->r_args.readdir.frag = cpu_to_le32(frag);
		req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
		req->r_args.readdir.max_bytes = cpu_to_le32(max_bytes);
		req->r_num_caps = max_entries + 1;
		err = ceph_mdsc_do_request(mdsc, NULL, req);
		if (err < 0) {
			ceph_mdsc_put_request(req);
			return err;
		}
		dout("readdir got and parsed readdir result=%d"
		     " on frag %x, end=%d, complete=%d\n", err, frag,
		     (int)req->r_reply_info.dir_end,
		     (int)req->r_reply_info.dir_complete);

		if (!req->r_did_prepopulate) {
			dout("readdir !did_prepopulate");
			fi->dir_release_count--;    /* preclude D_COMPLETE */
		}

		/* note next offset and last dentry name */
		fi->offset = fi->next_offset;
		fi->last_readdir = req;

		if (req->r_reply_info.dir_end) {
			kfree(fi->last_name);
			fi->last_name = NULL;
			if (ceph_frag_is_rightmost(frag))
				fi->next_offset = 2;
			else
				fi->next_offset = 0;
		} else {
			rinfo = &req->r_reply_info;
			err = note_last_dentry(fi,
				       rinfo->dir_dname[rinfo->dir_nr-1],
				       rinfo->dir_dname_len[rinfo->dir_nr-1]);
			if (err)
				return err;
			fi->next_offset += rinfo->dir_nr;
		}
	}

	rinfo = &fi->last_readdir->r_reply_info;
	dout("readdir frag %x num %d off %d chunkoff %d\n", frag,
	     rinfo->dir_nr, off, fi->offset);
	while (off >= fi->offset && off - fi->offset < rinfo->dir_nr) {
		u64 pos = ceph_make_fpos(frag, off);
		struct ceph_mds_reply_inode *in =
			rinfo->dir_in[off - fi->offset].in;
		struct ceph_vino vino;
		ino_t ino;

		dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n",
		     off, off - fi->offset, rinfo->dir_nr, pos,
		     rinfo->dir_dname_len[off - fi->offset],
		     rinfo->dir_dname[off - fi->offset], in);
		BUG_ON(!in);
		ftype = le32_to_cpu(in->mode) >> 12;
		vino.ino = le64_to_cpu(in->ino);
		vino.snap = le64_to_cpu(in->snapid);
		ino = ceph_vino_to_ino(vino);
		if (filldir(dirent,
			    rinfo->dir_dname[off - fi->offset],
			    rinfo->dir_dname_len[off - fi->offset],
			    pos,
			    ceph_translate_ino(inode->i_sb, ino), ftype) < 0) {
			dout("filldir stopping us...\n");
			return 0;
		}
		off++;
		filp->f_pos = pos + 1;
	}

	if (fi->last_name) {
		ceph_mdsc_put_request(fi->last_readdir);
		fi->last_readdir = NULL;
		goto more;
	}

	/* more frags? */
	if (!ceph_frag_is_rightmost(frag)) {
		frag = ceph_frag_next(frag);
		off = 0;
		filp->f_pos = ceph_make_fpos(frag, off);
		dout("readdir next frag is %x\n", frag);
		goto more;
	}
	fi->flags |= CEPH_F_ATEND;

	/*
	 * if dir_release_count still matches the dir, no dentries
	 * were released during the whole readdir, and we should have
	 * the complete dir contents in our cache.
	 */
	spin_lock(&ci->i_ceph_lock);
	if (ci->i_release_count == fi->dir_release_count) {
		ceph_dir_set_complete(inode);
		ci->i_max_offset = filp->f_pos;
	}
	spin_unlock(&ci->i_ceph_lock);

	dout("readdir %p filp %p done.\n", inode, filp);
	return 0;
}

static void reset_readdir(struct ceph_file_info *fi)
{
	if (fi->last_readdir) {
		ceph_mdsc_put_request(fi->last_readdir);
		fi->last_readdir = NULL;
	}
	kfree(fi->last_name);
	fi->last_name = NULL;
	fi->next_offset = 2;  /* compensate for . and .. */
	if (fi->dentry) {
		dput(fi->dentry);
		fi->dentry = NULL;
	}
	fi->flags &= ~CEPH_F_ATEND;
}

static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
{
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file->f_mapping->host;
	loff_t old_offset = offset;
	loff_t retval;

	mutex_lock(&inode->i_mutex);
	retval = -EINVAL;
	switch (origin) {
	case SEEK_END:
		offset += inode->i_size + 2;   /* FIXME */
		break;
	case SEEK_CUR:
		offset += file->f_pos;
	case SEEK_SET:
		break;
	default:
		goto out;
	}

	if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
		if (offset != file->f_pos) {
			file->f_pos = offset;
			file->f_version = 0;
			fi->flags &= ~CEPH_F_ATEND;
		}
		retval = offset;

		/*
		 * discard buffered readdir content on seekdir(0), or
		 * seek to new frag, or seek prior to current chunk.
		 */
		if (offset == 0 ||
		    fpos_frag(offset) != fpos_frag(old_offset) ||
		    fpos_off(offset) < fi->offset) {
			dout("dir_llseek dropping %p content\n", file);
			reset_readdir(fi);
		}

		/* bump dir_release_count if we did a forward seek */
		if (offset > old_offset)
			fi->dir_release_count--;
	}
out:
	mutex_unlock(&inode->i_mutex);
	return retval;
}

/*
 * Handle lookups for the hidden .snap directory.
 */
int ceph_handle_snapdir(struct ceph_mds_request *req,
			struct dentry *dentry, int err)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
	struct inode *parent = dentry->d_parent->d_inode; /* we hold i_mutex */

	/* .snap dir? */
	if (err == -ENOENT &&
	    ceph_snap(parent) == CEPH_NOSNAP &&
	    strcmp(dentry->d_name.name,
		   fsc->mount_options->snapdir_name) == 0) {
		struct inode *inode = ceph_get_snapdir(parent);
		dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
		     dentry, dentry->d_name.len, dentry->d_name.name, inode);
		BUG_ON(!d_unhashed(dentry));
		d_add(dentry, inode);
		err = 0;
	}
	return err;
}

/*
 * Figure out final result of a lookup/open request.
 *
 * Mainly, make sure we return the final req->r_dentry (if it already
 * existed) in place of the original VFS-provided dentry when they
 * differ.
 *
 * Gracefully handle the case where the MDS replies with -ENOENT and
 * no trace (which it may do, at its discretion, e.g., if it doesn't
 * care to issue a lease on the negative dentry).
 */
struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
				  struct dentry *dentry, int err)
{
	if (err == -ENOENT) {
		/* no trace? */
		err = 0;
		if (!req->r_reply_info.head->is_dentry) {
			dout("ENOENT and no trace, dentry %p inode %p\n",
			     dentry, dentry->d_inode);
			if (dentry->d_inode) {
				d_drop(dentry);
				err = -ENOENT;
			} else {
				d_add(dentry, NULL);
			}
		}
	}
	if (err)
		dentry = ERR_PTR(err);
	else if (dentry != req->r_dentry)
		dentry = dget(req->r_dentry);   /* we got spliced */
	else
		dentry = NULL;
	return dentry;
}

static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
{
	return ceph_ino(inode) == CEPH_INO_ROOT &&
		strncmp(dentry->d_name.name, ".ceph", 5) == 0;
}

/*
 * Look up a single dir entry.  If there is a lookup intent, inform
 * the MDS so that it gets our 'caps wanted' value in a single op.
 */
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
				  struct nameidata *nd)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int op;
	int err;

	dout("lookup %p dentry %p '%.*s'\n",
	     dir, dentry, dentry->d_name.len, dentry->d_name.name);

	if (dentry->d_name.len > NAME_MAX)
		return ERR_PTR(-ENAMETOOLONG);

	err = ceph_init_dentry(dentry);
	if (err < 0)
		return ERR_PTR(err);

	/* open (but not create!) intent? */
	if (nd &&
	    (nd->flags & LOOKUP_OPEN) &&
	    !(nd->intent.open.flags & O_CREAT)) {
		int mode = nd->intent.open.create_mode & ~current->fs->umask;
		return ceph_lookup_open(dir, dentry, nd, mode, 1);
	}

	/* can we conclude ENOENT locally? */
	if (dentry->d_inode == NULL) {
		struct ceph_inode_info *ci = ceph_inode(dir);
		struct ceph_dentry_info *di = ceph_dentry(dentry);

		spin_lock(&ci->i_ceph_lock);
		dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
		if (strncmp(dentry->d_name.name,
			    fsc->mount_options->snapdir_name,
			    dentry->d_name.len) &&
		    !is_root_ceph_dentry(dir, dentry) &&
		    ceph_dir_test_complete(dir) &&
		    (__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
			spin_unlock(&ci->i_ceph_lock);
			dout(" dir %p complete, -ENOENT\n", dir);
			d_add(dentry, NULL);
			di->lease_shared_gen = ci->i_shared_gen;
			return NULL;
		}
		spin_unlock(&ci->i_ceph_lock);
	}

	op = ceph_snap(dir) == CEPH_SNAPDIR ?
		CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
	req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
	if (IS_ERR(req))
		return ERR_CAST(req);
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	/* we only need inode linkage */
	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
	req->r_locked_dir = dir;
	err = ceph_mdsc_do_request(mdsc, NULL, req);
	err = ceph_handle_snapdir(req, dentry, err);
	dentry = ceph_finish_lookup(req, dentry, err);
	ceph_mdsc_put_request(req);  /* will dput(dentry) */
	dout("lookup result=%p\n", dentry);
	return dentry;
}

/*
 * If we do a create but get no trace back from the MDS, follow up with
 * a lookup (the VFS expects us to link up the provided dentry).
 */
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
	struct dentry *result = ceph_lookup(dir, dentry, NULL);

	if (result && !IS_ERR(result)) {
		/*
		 * We created the item, then did a lookup, and found
		 * it was already linked to another inode we already
		 * had in our cache (and thus got spliced).  Link our
		 * dentry to that inode, but don't hash it, just in
		 * case the VFS wants to dereference it.
		 */
		BUG_ON(!result->d_inode);
		d_instantiate(dentry, result->d_inode);
		return 0;
	}
	return PTR_ERR(result);
}

static int ceph_mknod(struct inode *dir, struct dentry *dentry,
		      int mode, dev_t rdev)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int err;

	if (ceph_snap(dir) != CEPH_NOSNAP)
		return -EROFS;

	dout("mknod in dir %p dentry %p mode 0%o rdev %d\n",
	     dir, dentry, mode, rdev);
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
	if (IS_ERR(req)) {
		d_drop(dentry);
		return PTR_ERR(req);
	}
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	req->r_locked_dir = dir;
	req->r_args.mknod.mode = cpu_to_le32(mode);
	req->r_args.mknod.rdev = cpu_to_le32(rdev);
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	err = ceph_mdsc_do_request(mdsc, dir, req);
	if (!err && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);
	ceph_mdsc_put_request(req);
	if (err)
		d_drop(dentry);
	return err;
}

static int ceph_create(struct inode *dir, struct dentry *dentry, int mode,
		       struct nameidata *nd)
{
	dout("create in dir %p dentry %p name '%.*s'\n",
	     dir, dentry, dentry->d_name.len, dentry->d_name.name);

	if (ceph_snap(dir) != CEPH_NOSNAP)
		return -EROFS;

	if (nd) {
		BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
		dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
		/* hrm, what should i do here if we get aliased? */
		if (IS_ERR(dentry))
			return PTR_ERR(dentry);
		return 0;
	}

	/* fall back to mknod */
	return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
}

static int ceph_symlink(struct inode *dir, struct dentry *dentry,
			    const char *dest)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int err;

	if (ceph_snap(dir) != CEPH_NOSNAP)
		return -EROFS;

	dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
	if (IS_ERR(req)) {
		d_drop(dentry);
		return PTR_ERR(req);
	}
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	req->r_path2 = kstrdup(dest, GFP_NOFS);
	req->r_locked_dir = dir;
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	err = ceph_mdsc_do_request(mdsc, dir, req);
	if (!err && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);
	ceph_mdsc_put_request(req);
	if (err)
		d_drop(dentry);
	return err;
}

static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int err = -EROFS;
	int op;

	if (ceph_snap(dir) == CEPH_SNAPDIR) {
		/* mkdir .snap/foo is a MKSNAP */
		op = CEPH_MDS_OP_MKSNAP;
		dout("mksnap dir %p snap '%.*s' dn %p\n", dir,
		     dentry->d_name.len, dentry->d_name.name, dentry);
	} else if (ceph_snap(dir) == CEPH_NOSNAP) {
		dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode);
		op = CEPH_MDS_OP_MKDIR;
	} else {
		goto out;
	}
	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}

	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	req->r_locked_dir = dir;
	req->r_args.mkdir.mode = cpu_to_le32(mode);
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	err = ceph_mdsc_do_request(mdsc, dir, req);
	if (!err && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);
	ceph_mdsc_put_request(req);
out:
	if (err < 0)
		d_drop(dentry);
	return err;
}

static int ceph_link(struct dentry *old_dentry, struct inode *dir,
		     struct dentry *dentry)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int err;

	if (ceph_snap(dir) != CEPH_NOSNAP)
		return -EROFS;

	dout("link in dir %p old_dentry %p dentry %p\n", dir,
	     old_dentry, dentry);
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LINK, USE_AUTH_MDS);
	if (IS_ERR(req)) {
		d_drop(dentry);
		return PTR_ERR(req);
	}
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	req->r_old_dentry = dget(old_dentry); /* or inode? hrm. */
	req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
	req->r_locked_dir = dir;
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	err = ceph_mdsc_do_request(mdsc, dir, req);
	if (err) {
		d_drop(dentry);
	} else if (!req->r_reply_info.head->is_dentry) {
		ihold(old_dentry->d_inode);
		d_instantiate(dentry, old_dentry->d_inode);
	}
	ceph_mdsc_put_request(req);
	return err;
}

/*
 * For a soon-to-be unlinked file, drop the AUTH_RDCACHE caps.  If it
 * looks like the link count will hit 0, drop any other caps (other
 * than PIN) we don't specifically want (due to the file still being
 * open).
 */
static int drop_caps_for_unlink(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL;

	spin_lock(&ci->i_ceph_lock);
	if (inode->i_nlink == 1) {
		drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN);
		ci->i_ceph_flags |= CEPH_I_NODELAY;
	}
	spin_unlock(&ci->i_ceph_lock);
	return drop;
}

/*
 * rmdir and unlink are differ only by the metadata op code
 */
static int ceph_unlink(struct inode *dir, struct dentry *dentry)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct inode *inode = dentry->d_inode;
	struct ceph_mds_request *req;
	int err = -EROFS;
	int op;

	if (ceph_snap(dir) == CEPH_SNAPDIR) {
		/* rmdir .snap/foo is RMSNAP */
		dout("rmsnap dir %p '%.*s' dn %p\n", dir, dentry->d_name.len,
		     dentry->d_name.name, dentry);
		op = CEPH_MDS_OP_RMSNAP;
	} else if (ceph_snap(dir) == CEPH_NOSNAP) {
		dout("unlink/rmdir dir %p dn %p inode %p\n",
		     dir, dentry, inode);
		op = ((dentry->d_inode->i_mode & S_IFMT) == S_IFDIR) ?
			CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK;
	} else
		goto out;
	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	req->r_locked_dir = dir;
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	req->r_inode_drop = drop_caps_for_unlink(inode);
	err = ceph_mdsc_do_request(mdsc, dir, req);
	if (!err && !req->r_reply_info.head->is_dentry)
		d_delete(dentry);
	ceph_mdsc_put_request(req);
out:
	return err;
}

static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
		       struct inode *new_dir, struct dentry *new_dentry)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int err;

	if (ceph_snap(old_dir) != ceph_snap(new_dir))
		return -EXDEV;
	if (ceph_snap(old_dir) != CEPH_NOSNAP ||
	    ceph_snap(new_dir) != CEPH_NOSNAP)
		return -EROFS;
	dout("rename dir %p dentry %p to dir %p dentry %p\n",
	     old_dir, old_dentry, new_dir, new_dentry);
	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RENAME, USE_AUTH_MDS);
	if (IS_ERR(req))
		return PTR_ERR(req);
	req->r_dentry = dget(new_dentry);
	req->r_num_caps = 2;
	req->r_old_dentry = dget(old_dentry);
	req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
	req->r_locked_dir = new_dir;
	req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_old_dentry_unless = CEPH_CAP_FILE_EXCL;
	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	/* release LINK_RDCACHE on source inode (mds will lock it) */
	req->r_old_inode_drop = CEPH_CAP_LINK_SHARED;
	if (new_dentry->d_inode)
		req->r_inode_drop = drop_caps_for_unlink(new_dentry->d_inode);
	err = ceph_mdsc_do_request(mdsc, old_dir, req);
	if (!err && !req->r_reply_info.head->is_dentry) {
		/*
		 * Normally d_move() is done by fill_trace (called by
		 * do_request, above).  If there is no trace, we need
		 * to do it here.
		 */

		/* d_move screws up d_subdirs order */
		ceph_dir_clear_complete(new_dir);

		d_move(old_dentry, new_dentry);

		/* ensure target dentry is invalidated, despite
		   rehashing bug in vfs_rename_dir */
		ceph_invalidate_dentry_lease(new_dentry);
	}
	ceph_mdsc_put_request(req);
	return err;
}

/*
 * Ensure a dentry lease will no longer revalidate.
 */
void ceph_invalidate_dentry_lease(struct dentry *dentry)
{
	spin_lock(&dentry->d_lock);
	dentry->d_time = jiffies;
	ceph_dentry(dentry)->lease_shared_gen = 0;
	spin_unlock(&dentry->d_lock);
}

/*
 * Check if dentry lease is valid.  If not, delete the lease.  Try to
 * renew if the least is more than half up.
 */
static int dentry_lease_is_valid(struct dentry *dentry)
{
	struct ceph_dentry_info *di;
	struct ceph_mds_session *s;
	int valid = 0;
	u32 gen;
	unsigned long ttl;
	struct ceph_mds_session *session = NULL;
	struct inode *dir = NULL;
	u32 seq = 0;

	spin_lock(&dentry->d_lock);
	di = ceph_dentry(dentry);
	if (di && di->lease_session) {
		s = di->lease_session;
		spin_lock(&s->s_cap_lock);
		gen = s->s_cap_gen;
		ttl = s->s_cap_ttl;
		spin_unlock(&s->s_cap_lock);

		if (di->lease_gen == gen &&
		    time_before(jiffies, dentry->d_time) &&
		    time_before(jiffies, ttl)) {
			valid = 1;
			if (di->lease_renew_after &&
			    time_after(jiffies, di->lease_renew_after)) {
				/* we should renew */
				dir = dentry->d_parent->d_inode;
				session = ceph_get_mds_session(s);
				seq = di->lease_seq;
				di->lease_renew_after = 0;
				di->lease_renew_from = jiffies;
			}
		}
	}
	spin_unlock(&dentry->d_lock);

	if (session) {
		ceph_mdsc_lease_send_msg(session, dir, dentry,
					 CEPH_MDS_LEASE_RENEW, seq);
		ceph_put_mds_session(session);
	}
	dout("dentry_lease_is_valid - dentry %p = %d\n", dentry, valid);
	return valid;
}

/*
 * Check if directory-wide content lease/cap is valid.
 */
static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
{
	struct ceph_inode_info *ci = ceph_inode(dir);
	struct ceph_dentry_info *di = ceph_dentry(dentry);
	int valid = 0;

	spin_lock(&ci->i_ceph_lock);
	if (ci->i_shared_gen == di->lease_shared_gen)
		valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
	spin_unlock(&ci->i_ceph_lock);
	dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n",
	     dir, (unsigned)ci->i_shared_gen, dentry,
	     (unsigned)di->lease_shared_gen, valid);
	return valid;
}

/*
 * Check if cached dentry can be trusted.
 */
static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	int valid = 0;
	struct inode *dir;

	if (nd && nd->flags & LOOKUP_RCU)
		return -ECHILD;

	dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
	     dentry->d_name.len, dentry->d_name.name, dentry->d_inode,
	     ceph_dentry(dentry)->offset);

	dir = ceph_get_dentry_parent_inode(dentry);

	/* always trust cached snapped dentries, snapdir dentry */
	if (ceph_snap(dir) != CEPH_NOSNAP) {
		dout("d_revalidate %p '%.*s' inode %p is SNAPPED\n", dentry,
		     dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
		valid = 1;
	} else if (dentry->d_inode &&
		   ceph_snap(dentry->d_inode) == CEPH_SNAPDIR) {
		valid = 1;
	} else if (dentry_lease_is_valid(dentry) ||
		   dir_lease_is_valid(dir, dentry)) {
		valid = 1;
	}

	dout("d_revalidate %p %s\n", dentry, valid ? "valid" : "invalid");
	if (valid)
		ceph_dentry_lru_touch(dentry);
	else
		d_drop(dentry);
	iput(dir);
	return valid;
}

/*
 * Release our ceph_dentry_info.
 */
static void ceph_d_release(struct dentry *dentry)
{
	struct ceph_dentry_info *di = ceph_dentry(dentry);

	dout("d_release %p\n", dentry);
	if (di) {
		ceph_dentry_lru_del(dentry);
		if (di->lease_session)
			ceph_put_mds_session(di->lease_session);
		kmem_cache_free(ceph_dentry_cachep, di);
		dentry->d_fsdata = NULL;
	}
}

static int ceph_snapdir_d_revalidate(struct dentry *dentry,
					  struct nameidata *nd)
{
	/*
	 * Eventually, we'll want to revalidate snapped metadata
	 * too... probably...
	 */
	return 1;
}

/*
 * Set/clear/test dir complete flag on the dir's dentry.
 */
void ceph_dir_set_complete(struct inode *inode)
{
	/* not yet implemented */
}

void ceph_dir_clear_complete(struct inode *inode)
{
	/* not yet implemented */
}

bool ceph_dir_test_complete(struct inode *inode)
{
	/* not yet implemented */
	return false;
}

/*
 * When the VFS prunes a dentry from the cache, we need to clear the
 * complete flag on the parent directory.
 *
 * Called under dentry->d_lock.
 */
static void ceph_d_prune(struct dentry *dentry)
{
	struct ceph_dentry_info *di;

	dout("ceph_d_prune %p\n", dentry);

	/* do we have a valid parent? */
	if (!dentry->d_parent || IS_ROOT(dentry))
		return;

	/* if we are not hashed, we don't affect D_COMPLETE */
	if (d_unhashed(dentry))
		return;

	/*
	 * we hold d_lock, so d_parent is stable, and d_fsdata is never
	 * cleared until d_release
	 */
	di = ceph_dentry(dentry->d_parent);
	clear_bit(CEPH_D_COMPLETE, &di->flags);
}

/*
 * read() on a dir.  This weird interface hack only works if mounted
 * with '-o dirstat'.
 */
static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
			     loff_t *ppos)
{
	struct ceph_file_info *cf = file->private_data;
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	int left;
	const int bufsize = 1024;

	if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
		return -EISDIR;

	if (!cf->dir_info) {
		cf->dir_info = kmalloc(bufsize, GFP_NOFS);
		if (!cf->dir_info)
			return -ENOMEM;
		cf->dir_info_len =
			snprintf(cf->dir_info, bufsize,
				"entries:   %20lld\n"
				" files:    %20lld\n"
				" subdirs:  %20lld\n"
				"rentries:  %20lld\n"
				" rfiles:   %20lld\n"
				" rsubdirs: %20lld\n"
				"rbytes:    %20lld\n"
				"rctime:    %10ld.%09ld\n",
				ci->i_files + ci->i_subdirs,
				ci->i_files,
				ci->i_subdirs,
				ci->i_rfiles + ci->i_rsubdirs,
				ci->i_rfiles,
				ci->i_rsubdirs,
				ci->i_rbytes,
				(long)ci->i_rctime.tv_sec,
				(long)ci->i_rctime.tv_nsec);
	}

	if (*ppos >= cf->dir_info_len)
		return 0;
	size = min_t(unsigned, size, cf->dir_info_len-*ppos);
	left = copy_to_user(buf, cf->dir_info + *ppos, size);
	if (left == size)
		return -EFAULT;
	*ppos += (size - left);
	return size - left;
}

/*
 * an fsync() on a dir will wait for any uncommitted directory
 * operations to commit.
 */
static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
			  int datasync)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct list_head *head = &ci->i_unsafe_dirops;
	struct ceph_mds_request *req;
	u64 last_tid;
	int ret = 0;

	dout("dir_fsync %p\n", inode);
	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (ret)
		return ret;
	mutex_lock(&inode->i_mutex);

	spin_lock(&ci->i_unsafe_lock);
	if (list_empty(head))
		goto out;

	req = list_entry(head->prev,
			 struct ceph_mds_request, r_unsafe_dir_item);
	last_tid = req->r_tid;

	do {
		ceph_mdsc_get_request(req);
		spin_unlock(&ci->i_unsafe_lock);
		dout("dir_fsync %p wait on tid %llu (until %llu)\n",
		     inode, req->r_tid, last_tid);
		if (req->r_timeout) {
			ret = wait_for_completion_timeout(
				&req->r_safe_completion, req->r_timeout);
			if (ret > 0)
				ret = 0;
			else if (ret == 0)
				ret = -EIO;  /* timed out */
		} else {
			wait_for_completion(&req->r_safe_completion);
		}
		spin_lock(&ci->i_unsafe_lock);
		ceph_mdsc_put_request(req);

		if (ret || list_empty(head))
			break;
		req = list_entry(head->next,
				 struct ceph_mds_request, r_unsafe_dir_item);
	} while (req->r_tid < last_tid);
out:
	spin_unlock(&ci->i_unsafe_lock);
	mutex_unlock(&inode->i_mutex);

	return ret;
}

/*
 * We maintain a private dentry LRU.
 *
 * FIXME: this needs to be changed to a per-mds lru to be useful.
 */
void ceph_dentry_lru_add(struct dentry *dn)
{
	struct ceph_dentry_info *di = ceph_dentry(dn);
	struct ceph_mds_client *mdsc;

	dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
	     dn->d_name.len, dn->d_name.name);
	if (di) {
		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
		spin_lock(&mdsc->dentry_lru_lock);
		list_add_tail(&di->lru, &mdsc->dentry_lru);
		mdsc->num_dentry++;
		spin_unlock(&mdsc->dentry_lru_lock);
	}
}

void ceph_dentry_lru_touch(struct dentry *dn)
{
	struct ceph_dentry_info *di = ceph_dentry(dn);
	struct ceph_mds_client *mdsc;

	dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
	     dn->d_name.len, dn->d_name.name, di->offset);
	if (di) {
		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
		spin_lock(&mdsc->dentry_lru_lock);
		list_move_tail(&di->lru, &mdsc->dentry_lru);
		spin_unlock(&mdsc->dentry_lru_lock);
	}
}

void ceph_dentry_lru_del(struct dentry *dn)
{
	struct ceph_dentry_info *di = ceph_dentry(dn);
	struct ceph_mds_client *mdsc;

	dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
	     dn->d_name.len, dn->d_name.name);
	if (di) {
		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
		spin_lock(&mdsc->dentry_lru_lock);
		list_del_init(&di->lru);
		mdsc->num_dentry--;
		spin_unlock(&mdsc->dentry_lru_lock);
	}
}

/*
 * Return name hash for a given dentry.  This is dependent on
 * the parent directory's hash function.
 */
unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
{
	struct ceph_inode_info *dci = ceph_inode(dir);

	switch (dci->i_dir_layout.dl_dir_hash) {
	case 0:	/* for backward compat */
	case CEPH_STR_HASH_LINUX:
		return dn->d_name.hash;

	default:
		return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
				     dn->d_name.name, dn->d_name.len);
	}
}

const struct file_operations ceph_dir_fops = {
	.read = ceph_read_dir,
	.readdir = ceph_readdir,
	.llseek = ceph_dir_llseek,
	.open = ceph_open,
	.release = ceph_release,
	.unlocked_ioctl = ceph_ioctl,
	.fsync = ceph_dir_fsync,
};

const struct inode_operations ceph_dir_iops = {
	.lookup = ceph_lookup,
	.permission = ceph_permission,
	.getattr = ceph_getattr,
	.setattr = ceph_setattr,
	.setxattr = ceph_setxattr,
	.getxattr = ceph_getxattr,
	.listxattr = ceph_listxattr,
	.removexattr = ceph_removexattr,
	.mknod = ceph_mknod,
	.symlink = ceph_symlink,
	.mkdir = ceph_mkdir,
	.link = ceph_link,
	.unlink = ceph_unlink,
	.rmdir = ceph_unlink,
	.rename = ceph_rename,
	.create = ceph_create,
};

const struct dentry_operations ceph_dentry_ops = {
	.d_revalidate = ceph_d_revalidate,
	.d_release = ceph_d_release,
	.d_prune = ceph_d_prune,
};

const struct dentry_operations ceph_snapdir_dentry_ops = {
	.d_revalidate = ceph_snapdir_d_revalidate,
	.d_release = ceph_d_release,
};

const struct dentry_operations ceph_snap_dentry_ops = {
	.d_release = ceph_d_release,
	.d_prune = ceph_d_prune,
};
OpenPOWER on IntegriCloud