summaryrefslogtreecommitdiff
path: root/fs/ceph/file.c
blob: f68964076c0a758bf6a4f208e1226e7ab073ffa8 (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
#include <linux/ceph/ceph_debug.h>

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/aio.h>
#include <linux/falloc.h>

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

/*
 * Ceph file operations
 *
 * Implement basic open/close functionality, and implement
 * read/write.
 *
 * We implement three modes of file I/O:
 *  - buffered uses the generic_file_aio_{read,write} helpers
 *
 *  - synchronous is used when there is multi-client read/write
 *    sharing, avoids the page cache, and synchronously waits for an
 *    ack from the OSD.
 *
 *  - direct io takes the variant of the sync path that references
 *    user pages directly.
 *
 * fsync() flushes and waits on dirty pages, but just queues metadata
 * for writeback: since the MDS can recover size and mtime there is no
 * need to wait for MDS acknowledgement.
 */


/*
 * Prepare an open request.  Preallocate ceph_cap to avoid an
 * inopportune ENOMEM later.
 */
static struct ceph_mds_request *
prepare_open_request(struct super_block *sb, int flags, int create_mode)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int want_auth = USE_ANY_MDS;
	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;

	if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
		want_auth = USE_AUTH_MDS;

	req = ceph_mdsc_create_request(mdsc, op, want_auth);
	if (IS_ERR(req))
		goto out;
	req->r_fmode = ceph_flags_to_mode(flags);
	req->r_args.open.flags = cpu_to_le32(flags);
	req->r_args.open.mode = cpu_to_le32(create_mode);
out:
	return req;
}

/*
 * initialize private struct file data.
 * if we fail, clean up by dropping fmode reference on the ceph_inode
 */
static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
	struct ceph_file_info *cf;
	int ret = 0;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		/* First file open request creates the cookie, we want to keep
		 * this cookie around for the filetime of the inode as not to
		 * have to worry about fscache register / revoke / operation
		 * races.
		 *
		 * Also, if we know the operation is going to invalidate data
		 * (non readonly) just nuke the cache right away.
		 */
		ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
		if ((fmode & CEPH_FILE_MODE_WR))
			ceph_fscache_invalidate(inode);
	case S_IFDIR:
		dout("init_file %p %p 0%o (regular)\n", inode, file,
		     inode->i_mode);
		cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
		if (cf == NULL) {
			ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
			return -ENOMEM;
		}
		cf->fmode = fmode;
		cf->next_offset = 2;
		file->private_data = cf;
		BUG_ON(inode->i_fop->release != ceph_release);
		break;

	case S_IFLNK:
		dout("init_file %p %p 0%o (symlink)\n", inode, file,
		     inode->i_mode);
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		break;

	default:
		dout("init_file %p %p 0%o (special)\n", inode, file,
		     inode->i_mode);
		/*
		 * we need to drop the open ref now, since we don't
		 * have .release set to ceph_release.
		 */
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		BUG_ON(inode->i_fop->release == ceph_release);

		/* call the proper open fop */
		ret = inode->i_fop->open(inode, file);
	}
	return ret;
}

/*
 * If we already have the requisite capabilities, we can satisfy
 * the open request locally (no need to request new caps from the
 * MDS).  We do, however, need to inform the MDS (asynchronously)
 * if our wanted caps set expands.
 */
int ceph_open(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	struct ceph_file_info *cf = file->private_data;
	struct inode *parent_inode = NULL;
	int err;
	int flags, fmode, wanted;

	if (cf) {
		dout("open file %p is already opened\n", file);
		return 0;
	}

	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
	flags = file->f_flags & ~(O_CREAT|O_EXCL);
	if (S_ISDIR(inode->i_mode))
		flags = O_DIRECTORY;  /* mds likes to know */

	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
	     ceph_vinop(inode), file, flags, file->f_flags);
	fmode = ceph_flags_to_mode(flags);
	wanted = ceph_caps_for_mode(fmode);

	/* snapped files are read-only */
	if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
		return -EROFS;

	/* trivially open snapdir */
	if (ceph_snap(inode) == CEPH_SNAPDIR) {
		spin_lock(&ci->i_ceph_lock);
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);
		return ceph_init_file(inode, file, fmode);
	}

	/*
	 * No need to block if we have caps on the auth MDS (for
	 * write) or any MDS (for read).  Update wanted set
	 * asynchronously.
	 */
	spin_lock(&ci->i_ceph_lock);
	if (__ceph_is_any_real_caps(ci) &&
	    (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
		int mds_wanted = __ceph_caps_mds_wanted(ci);
		int issued = __ceph_caps_issued(ci, NULL);

		dout("open %p fmode %d want %s issued %s using existing\n",
		     inode, fmode, ceph_cap_string(wanted),
		     ceph_cap_string(issued));
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);

		/* adjust wanted? */
		if ((issued & wanted) != wanted &&
		    (mds_wanted & wanted) != wanted &&
		    ceph_snap(inode) != CEPH_SNAPDIR)
			ceph_check_caps(ci, 0, NULL);

		return ceph_init_file(inode, file, fmode);
	} else if (ceph_snap(inode) != CEPH_NOSNAP &&
		   (ci->i_snap_caps & wanted) == wanted) {
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);
		return ceph_init_file(inode, file, fmode);
	}

	spin_unlock(&ci->i_ceph_lock);

	dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
	req = prepare_open_request(inode->i_sb, flags, 0);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}
	req->r_inode = inode;
	ihold(inode);

	req->r_num_caps = 1;
	if (flags & O_CREAT)
		parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
	iput(parent_inode);
	if (!err)
		err = ceph_init_file(inode, file, req->r_fmode);
	ceph_mdsc_put_request(req);
	dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
	return err;
}


/*
 * Do a lookup + open with a single request.  If we get a non-existent
 * file or symlink, return 1 so the VFS can retry.
 */
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
		     struct file *file, unsigned flags, umode_t mode,
		     int *opened)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	struct dentry *dn;
	int err;

	dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
	     dir, dentry, dentry->d_name.len, dentry->d_name.name,
	     d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);

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

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

	/* do the open */
	req = prepare_open_request(dir->i_sb, flags, mode);
	if (IS_ERR(req))
		return PTR_ERR(req);
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	if (flags & O_CREAT) {
		req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
	}
	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
	err = ceph_mdsc_do_request(mdsc,
				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
				   req);
	if (err)
		goto out_err;

	err = ceph_handle_snapdir(req, dentry, err);
	if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);

	if (d_unhashed(dentry)) {
		dn = ceph_finish_lookup(req, dentry, err);
		if (IS_ERR(dn))
			err = PTR_ERR(dn);
	} else {
		/* we were given a hashed negative dentry */
		dn = NULL;
	}
	if (err)
		goto out_err;
	if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
		/* make vfs retry on splice, ENOENT, or symlink */
		dout("atomic_open finish_no_open on dn %p\n", dn);
		err = finish_no_open(file, dn);
	} else {
		dout("atomic_open finish_open on dn %p\n", dn);
		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
			ceph_init_acl(dentry, dentry->d_inode, dir);
			*opened |= FILE_CREATED;
		}
		err = finish_open(file, dentry, ceph_open, opened);
	}
out_err:
	if (!req->r_err && req->r_target_inode)
		ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
	ceph_mdsc_put_request(req);
	dout("atomic_open result=%d\n", err);
	return err;
}

int ceph_release(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *cf = file->private_data;

	dout("release inode %p file %p\n", inode, file);
	ceph_put_fmode(ci, cf->fmode);
	if (cf->last_readdir)
		ceph_mdsc_put_request(cf->last_readdir);
	kfree(cf->last_name);
	kfree(cf->dir_info);
	dput(cf->dentry);
	kmem_cache_free(ceph_file_cachep, cf);

	/* wake up anyone waiting for caps on this inode */
	wake_up_all(&ci->i_cap_wq);
	return 0;
}

/*
 * Read a range of bytes striped over one or more objects.  Iterate over
 * objects we stripe over.  (That's not atomic, but good enough for now.)
 *
 * If we get a short result from the OSD, check against i_size; we need to
 * only return a short read to the caller if we hit EOF.
 */
static int striped_read(struct inode *inode,
			u64 off, u64 len,
			struct page **pages, int num_pages,
			int *checkeof, bool o_direct,
			unsigned long buf_align)
{
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 pos, this_len, left;
	int io_align, page_align;
	int pages_left;
	int read;
	struct page **page_pos;
	int ret;
	bool hit_stripe, was_short;

	/*
	 * we may need to do multiple reads.  not atomic, unfortunately.
	 */
	pos = off;
	left = len;
	page_pos = pages;
	pages_left = num_pages;
	read = 0;
	io_align = off & ~PAGE_MASK;

more:
	if (o_direct)
		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
	else
		page_align = pos & ~PAGE_MASK;
	this_len = left;
	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
				  &ci->i_layout, pos, &this_len,
				  ci->i_truncate_seq,
				  ci->i_truncate_size,
				  page_pos, pages_left, page_align);
	if (ret == -ENOENT)
		ret = 0;
	hit_stripe = this_len < left;
	was_short = ret >= 0 && ret < this_len;
	dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");

	if (ret >= 0) {
		int didpages;
		if (was_short && (pos + ret < inode->i_size)) {
			u64 tmp = min(this_len - ret,
					inode->i_size - pos - ret);
			dout(" zero gap %llu to %llu\n",
				pos + ret, pos + ret + tmp);
			ceph_zero_page_vector_range(page_align + read + ret,
							tmp, pages);
			ret += tmp;
		}

		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
		pos += ret;
		read = pos - off;
		left -= ret;
		page_pos += didpages;
		pages_left -= didpages;

		/* hit stripe and need continue*/
		if (left && hit_stripe && pos < inode->i_size)
			goto more;
	}

	if (read > 0) {
		ret = read;
		/* did we bounce off eof? */
		if (pos + left > inode->i_size)
			*checkeof = 1;
	}

	dout("striped_read returns %d\n", ret);
	return ret;
}

/*
 * Completely synchronous read and write methods.  Direct from __user
 * buffer to osd, or directly to user pages (if O_DIRECT).
 *
 * If the read spans object boundary, just do multiple reads.
 */
static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
				int *checkeof)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct page **pages;
	u64 off = iocb->ki_pos;
	int num_pages, ret;
	size_t len = iov_iter_count(i);

	dout("sync_read on file %p %llu~%u %s\n", file, off,
	     (unsigned)len,
	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
	/*
	 * flush any page cache pages in this range.  this
	 * will make concurrent normal and sync io slow,
	 * but it will at least behave sensibly when they are
	 * in sequence.
	 */
	ret = filemap_write_and_wait_range(inode->i_mapping, off,
						off + len);
	if (ret < 0)
		return ret;

	if (file->f_flags & O_DIRECT) {
		while (iov_iter_count(i)) {
			size_t start;
			ssize_t n;

			n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start);
			if (n < 0)
				return n;

			num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;

			ret = striped_read(inode, off, n,
					   pages, num_pages, checkeof,
					   1, start);

			ceph_put_page_vector(pages, num_pages, true);

			if (ret <= 0)
				break;
			off += ret;
			iov_iter_advance(i, ret);
			if (ret < n)
				break;
		}
	} else {
		num_pages = calc_pages_for(off, len);
		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
		if (IS_ERR(pages))
			return PTR_ERR(pages);
		ret = striped_read(inode, off, len, pages,
					num_pages, checkeof, 0, 0);
		if (ret > 0) {
			int l, k = 0;
			size_t left = ret;

			while (left) {
				int copy = min_t(size_t, PAGE_SIZE, left);
				l = copy_page_to_iter(pages[k++], 0, copy, i);
				off += l;
				left -= l;
				if (l < copy)
					break;
			}
		}
		ceph_release_page_vector(pages, num_pages);
	}

	if (off > iocb->ki_pos) {
		ret = off - iocb->ki_pos;
		iocb->ki_pos = off;
	}

	dout("sync_read result %d\n", ret);
	return ret;
}

/*
 * Write commit request unsafe callback, called to tell us when a
 * request is unsafe (that is, in flight--has been handed to the
 * messenger to send to its target osd).  It is called again when
 * we've received a response message indicating the request is
 * "safe" (its CEPH_OSD_FLAG_ONDISK flag is set), or when a request
 * is completed early (and unsuccessfully) due to a timeout or
 * interrupt.
 *
 * This is used if we requested both an ACK and ONDISK commit reply
 * from the OSD.
 */
static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
{
	struct ceph_inode_info *ci = ceph_inode(req->r_inode);

	dout("%s %p tid %llu %ssafe\n", __func__, req, req->r_tid,
		unsafe ? "un" : "");
	if (unsafe) {
		ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
		spin_lock(&ci->i_unsafe_lock);
		list_add_tail(&req->r_unsafe_item,
			      &ci->i_unsafe_writes);
		spin_unlock(&ci->i_unsafe_lock);
	} else {
		spin_lock(&ci->i_unsafe_lock);
		list_del_init(&req->r_unsafe_item);
		spin_unlock(&ci->i_unsafe_lock);
		ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
	}
}


/*
 * Synchronous write, straight from __user pointer or user pages.
 *
 * If write spans object boundary, just do multiple writes.  (For a
 * correct atomic write, we should e.g. take write locks on all
 * objects, rollback on failure, etc.)
 */
static ssize_t
ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
		       unsigned long nr_segs, size_t count)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_snap_context *snapc;
	struct ceph_vino vino;
	struct ceph_osd_request *req;
	struct page **pages;
	int num_pages;
	int written = 0;
	int flags;
	int check_caps = 0;
	int ret;
	struct timespec mtime = CURRENT_TIME;
	loff_t pos = iocb->ki_pos;
	struct iov_iter i;

	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
		return -EROFS;

	dout("sync_direct_write on file %p %lld~%u\n", file, pos,
	     (unsigned)count);

	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count);
	if (ret < 0)
		return ret;

	ret = invalidate_inode_pages2_range(inode->i_mapping,
					    pos >> PAGE_CACHE_SHIFT,
					    (pos + count) >> PAGE_CACHE_SHIFT);
	if (ret < 0)
		dout("invalidate_inode_pages2_range returned %d\n", ret);

	flags = CEPH_OSD_FLAG_ORDERSNAP |
		CEPH_OSD_FLAG_ONDISK |
		CEPH_OSD_FLAG_WRITE;

	iov_iter_init(&i, WRITE, iov, nr_segs, count);

	while (iov_iter_count(&i) > 0) {
		u64 len = iov_iter_single_seg_count(&i);
		size_t start;
		ssize_t n;

		snapc = ci->i_snap_realm->cached_context;
		vino = ceph_vino(inode);
		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					    vino, pos, &len,
					    2,/*include a 'startsync' command*/
					    CEPH_OSD_OP_WRITE, flags, snapc,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
					    false);
		if (IS_ERR(req)) {
			ret = PTR_ERR(req);
			break;
		}

		n = iov_iter_get_pages_alloc(&i, &pages, len, &start);
		if (unlikely(n < 0)) {
			ret = n;
			ceph_osdc_put_request(req);
			break;
		}

		num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
		/*
		 * throw out any page cache pages in this range. this
		 * may block.
		 */
		truncate_inode_pages_range(inode->i_mapping, pos,
				   (pos+n) | (PAGE_CACHE_SIZE-1));
		osd_req_op_extent_osd_data_pages(req, 0, pages, n, start,
						false, false);

		/* BUG_ON(vino.snap != CEPH_NOSNAP); */
		ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);

		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
		if (!ret)
			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);

		ceph_put_page_vector(pages, num_pages, false);

		ceph_osdc_put_request(req);
		if (ret)
			break;
		pos += n;
		written += n;
		iov_iter_advance(&i, n);

		if (pos > i_size_read(inode)) {
			check_caps = ceph_inode_set_size(inode, pos);
			if (check_caps)
				ceph_check_caps(ceph_inode(inode),
						CHECK_CAPS_AUTHONLY,
						NULL);
		}
	}

	if (ret != -EOLDSNAPC && written > 0) {
		iocb->ki_pos = pos;
		ret = written;
	}
	return ret;
}


/*
 * Synchronous write, straight from __user pointer or user pages.
 *
 * If write spans object boundary, just do multiple writes.  (For a
 * correct atomic write, we should e.g. take write locks on all
 * objects, rollback on failure, etc.)
 */
static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
			       unsigned long nr_segs, size_t count)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_snap_context *snapc;
	struct ceph_vino vino;
	struct ceph_osd_request *req;
	struct page **pages;
	u64 len;
	int num_pages;
	int written = 0;
	int flags;
	int check_caps = 0;
	int ret;
	struct timespec mtime = CURRENT_TIME;
	loff_t pos = iocb->ki_pos;
	struct iov_iter i;

	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
		return -EROFS;

	dout("sync_write on file %p %lld~%u\n", file, pos, (unsigned)count);

	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count);
	if (ret < 0)
		return ret;

	ret = invalidate_inode_pages2_range(inode->i_mapping,
					    pos >> PAGE_CACHE_SHIFT,
					    (pos + count) >> PAGE_CACHE_SHIFT);
	if (ret < 0)
		dout("invalidate_inode_pages2_range returned %d\n", ret);

	flags = CEPH_OSD_FLAG_ORDERSNAP |
		CEPH_OSD_FLAG_ONDISK |
		CEPH_OSD_FLAG_WRITE |
		CEPH_OSD_FLAG_ACK;

	iov_iter_init(&i, WRITE, iov, nr_segs, count);

	while ((len = iov_iter_count(&i)) > 0) {
		size_t left;
		int n;

		snapc = ci->i_snap_realm->cached_context;
		vino = ceph_vino(inode);
		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					    vino, pos, &len, 1,
					    CEPH_OSD_OP_WRITE, flags, snapc,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
					    false);
		if (IS_ERR(req)) {
			ret = PTR_ERR(req);
			break;
		}

		/*
		 * write from beginning of first page,
		 * regardless of io alignment
		 */
		num_pages = (len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
		if (IS_ERR(pages)) {
			ret = PTR_ERR(pages);
			goto out;
		}

		left = len;
		for (n = 0; n < num_pages; n++) {
			size_t plen = min_t(size_t, left, PAGE_SIZE);
			ret = copy_page_from_iter(pages[n], 0, plen, &i);
			if (ret != plen) {
				ret = -EFAULT;
				break;
			}
			left -= ret;
		}

		if (ret < 0) {
			ceph_release_page_vector(pages, num_pages);
			goto out;
		}

		/* get a second commit callback */
		req->r_unsafe_callback = ceph_sync_write_unsafe;
		req->r_inode = inode;

		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
						false, true);

		/* BUG_ON(vino.snap != CEPH_NOSNAP); */
		ceph_osdc_build_request(req, pos, snapc, vino.snap, &mtime);

		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
		if (!ret)
			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);

out:
		ceph_osdc_put_request(req);
		if (ret == 0) {
			pos += len;
			written += len;

			if (pos > i_size_read(inode)) {
				check_caps = ceph_inode_set_size(inode, pos);
				if (check_caps)
					ceph_check_caps(ceph_inode(inode),
							CHECK_CAPS_AUTHONLY,
							NULL);
			}
		} else
			break;
	}

	if (ret != -EOLDSNAPC && written > 0) {
		ret = written;
		iocb->ki_pos = pos;
	}
	return ret;
}

/*
 * Wrap generic_file_aio_read with checks for cap bits on the inode.
 * Atomically grab references, so that those bits are not released
 * back to the MDS mid-read.
 *
 * Hmm, the sync read case isn't actually async... should it be?
 */
static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *filp = iocb->ki_filp;
	struct ceph_file_info *fi = filp->private_data;
	size_t len = iocb->ki_nbytes;
	struct inode *inode = file_inode(filp);
	struct ceph_inode_info *ci = ceph_inode(inode);
	ssize_t ret;
	int want, got = 0;
	int checkeof = 0, read = 0;

again:
	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
	     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);

	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_CACHE;
	ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, &got, -1);
	if (ret < 0)
		return ret;

	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
	    (iocb->ki_filp->f_flags & O_DIRECT) ||
	    (fi->flags & CEPH_F_SYNC)) {

		dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
		     ceph_cap_string(got));

		/* hmm, this isn't really async... */
		ret = ceph_sync_read(iocb, to, &checkeof);
	} else {
		dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
		     ceph_cap_string(got));

		ret = generic_file_read_iter(iocb, to);
	}
	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
	ceph_put_cap_refs(ci, got);

	if (checkeof && ret >= 0) {
		int statret = ceph_do_getattr(inode,
					      CEPH_STAT_CAP_SIZE);

		/* hit EOF or hole? */
		if (statret == 0 && iocb->ki_pos < inode->i_size &&
			ret < len) {
			dout("sync_read hit hole, ppos %lld < size %lld"
			     ", reading more\n", iocb->ki_pos,
			     inode->i_size);

			iov_iter_advance(to, ret);
			read += ret;
			len -= ret;
			checkeof = 0;
			goto again;
		}
	}

	if (ret >= 0)
		ret += read;

	return ret;
}

/*
 * Take cap references to avoid releasing caps to MDS mid-write.
 *
 * If we are synchronous, and write with an old snap context, the OSD
 * may return EOLDSNAPC.  In that case, retry the write.. _after_
 * dropping our cap refs and allowing the pending snap to logically
 * complete _before_ this write occurs.
 *
 * If we are near ENOSPC, write synchronously.
 */
static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
		       unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_client *osdc =
		&ceph_sb_to_client(inode->i_sb)->client->osdc;
	ssize_t count, written = 0;
	int err, want, got;

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

	mutex_lock(&inode->i_mutex);

	count = iov_length(iov, nr_segs);

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = file->f_mapping->backing_dev_info;

	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
	if (err)
		goto out;

	if (count == 0)
		goto out;

	err = file_remove_suid(file);
	if (err)
		goto out;

	err = file_update_time(file);
	if (err)
		goto out;

retry_snap:
	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
		err = -ENOSPC;
		goto out;
	}

	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
	     inode, ceph_vinop(inode), pos, count, inode->i_size);
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;
	got = 0;
	err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos + count);
	if (err < 0)
		goto out;

	dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));

	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
	    (file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
		mutex_unlock(&inode->i_mutex);
		if (file->f_flags & O_DIRECT)
			written = ceph_sync_direct_write(iocb, iov,
							 nr_segs, count);
		else
			written = ceph_sync_write(iocb, iov, nr_segs, count);
		if (written == -EOLDSNAPC) {
			dout("aio_write %p %llx.%llx %llu~%u"
				"got EOLDSNAPC, retrying\n",
				inode, ceph_vinop(inode),
				pos, (unsigned)iov->iov_len);
			mutex_lock(&inode->i_mutex);
			goto retry_snap;
		}
	} else {
		loff_t old_size = inode->i_size;
		struct iov_iter from;
		/*
		 * No need to acquire the i_truncate_mutex. Because
		 * the MDS revokes Fwb caps before sending truncate
		 * message to us. We can't get Fwb cap while there
		 * are pending vmtruncate. So write and vmtruncate
		 * can not run at the same time
		 */
		iov_iter_init(&from, WRITE, iov, nr_segs, count);
		written = generic_perform_write(file, &from, pos);
		if (likely(written >= 0))
			iocb->ki_pos = pos + written;
		if (inode->i_size > old_size)
			ceph_fscache_update_objectsize(inode);
		mutex_unlock(&inode->i_mutex);
	}

	if (written >= 0) {
		int dirty;
		spin_lock(&ci->i_ceph_lock);
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
		spin_unlock(&ci->i_ceph_lock);
		if (dirty)
			__mark_inode_dirty(inode, dirty);
	}

	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
	     ceph_cap_string(got));
	ceph_put_cap_refs(ci, got);

	if (written >= 0 &&
	    ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) ||
	     ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
		err = vfs_fsync_range(file, pos, pos + written - 1, 1);
		if (err < 0)
			written = err;
	}

	goto out_unlocked;

out:
	mutex_unlock(&inode->i_mutex);
out_unlocked:
	current->backing_dev_info = NULL;
	return written ? written : err;
}

/*
 * llseek.  be sure to verify file size on SEEK_END.
 */
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	int ret;

	mutex_lock(&inode->i_mutex);

	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
		if (ret < 0) {
			offset = ret;
			goto out;
		}
	}

	switch (whence) {
	case SEEK_END:
		offset += inode->i_size;
		break;
	case SEEK_CUR:
		/*
		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
		 * position-querying operation.  Avoid rewriting the "same"
		 * f_pos value back to the file because a concurrent read(),
		 * write() or lseek() might have altered it
		 */
		if (offset == 0) {
			offset = file->f_pos;
			goto out;
		}
		offset += file->f_pos;
		break;
	case SEEK_DATA:
		if (offset >= inode->i_size) {
			ret = -ENXIO;
			goto out;
		}
		break;
	case SEEK_HOLE:
		if (offset >= inode->i_size) {
			ret = -ENXIO;
			goto out;
		}
		offset = inode->i_size;
		break;
	}

	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);

out:
	mutex_unlock(&inode->i_mutex);
	return offset;
}

static inline void ceph_zero_partial_page(
	struct inode *inode, loff_t offset, unsigned size)
{
	struct page *page;
	pgoff_t index = offset >> PAGE_CACHE_SHIFT;

	page = find_lock_page(inode->i_mapping, index);
	if (page) {
		wait_on_page_writeback(page);
		zero_user(page, offset & (PAGE_CACHE_SIZE - 1), size);
		unlock_page(page);
		page_cache_release(page);
	}
}

static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
				      loff_t length)
{
	loff_t nearly = round_up(offset, PAGE_CACHE_SIZE);
	if (offset < nearly) {
		loff_t size = nearly - offset;
		if (length < size)
			size = length;
		ceph_zero_partial_page(inode, offset, size);
		offset += size;
		length -= size;
	}
	if (length >= PAGE_CACHE_SIZE) {
		loff_t size = round_down(length, PAGE_CACHE_SIZE);
		truncate_pagecache_range(inode, offset, offset + size - 1);
		offset += size;
		length -= size;
	}
	if (length)
		ceph_zero_partial_page(inode, offset, length);
}

static int ceph_zero_partial_object(struct inode *inode,
				    loff_t offset, loff_t *length)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_osd_request *req;
	int ret = 0;
	loff_t zero = 0;
	int op;

	if (!length) {
		op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE;
		length = &zero;
	} else {
		op = CEPH_OSD_OP_ZERO;
	}

	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					ceph_vino(inode),
					offset, length,
					1, op,
					CEPH_OSD_FLAG_WRITE |
					CEPH_OSD_FLAG_ONDISK,
					NULL, 0, 0, false);
	if (IS_ERR(req)) {
		ret = PTR_ERR(req);
		goto out;
	}

	ceph_osdc_build_request(req, offset, NULL, ceph_vino(inode).snap,
				&inode->i_mtime);

	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
	if (!ret) {
		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
		if (ret == -ENOENT)
			ret = 0;
	}
	ceph_osdc_put_request(req);

out:
	return ret;
}

static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length)
{
	int ret = 0;
	struct ceph_inode_info *ci = ceph_inode(inode);
	s32 stripe_unit = ceph_file_layout_su(ci->i_layout);
	s32 stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
	s32 object_size = ceph_file_layout_object_size(ci->i_layout);
	u64 object_set_size = object_size * stripe_count;
	u64 nearly, t;

	/* round offset up to next period boundary */
	nearly = offset + object_set_size - 1;
	t = nearly;
	nearly -= do_div(t, object_set_size);

	while (length && offset < nearly) {
		loff_t size = length;
		ret = ceph_zero_partial_object(inode, offset, &size);
		if (ret < 0)
			return ret;
		offset += size;
		length -= size;
	}
	while (length >= object_set_size) {
		int i;
		loff_t pos = offset;
		for (i = 0; i < stripe_count; ++i) {
			ret = ceph_zero_partial_object(inode, pos, NULL);
			if (ret < 0)
				return ret;
			pos += stripe_unit;
		}
		offset += object_set_size;
		length -= object_set_size;
	}
	while (length) {
		loff_t size = length;
		ret = ceph_zero_partial_object(inode, offset, &size);
		if (ret < 0)
			return ret;
		offset += size;
		length -= size;
	}
	return ret;
}

static long ceph_fallocate(struct file *file, int mode,
				loff_t offset, loff_t length)
{
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_client *osdc =
		&ceph_inode_to_client(inode)->client->osdc;
	int want, got = 0;
	int dirty;
	int ret = 0;
	loff_t endoff = 0;
	loff_t size;

	if (!S_ISREG(inode->i_mode))
		return -EOPNOTSUPP;

	mutex_lock(&inode->i_mutex);

	if (ceph_snap(inode) != CEPH_NOSNAP) {
		ret = -EROFS;
		goto unlock;
	}

	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) &&
		!(mode & FALLOC_FL_PUNCH_HOLE)) {
		ret = -ENOSPC;
		goto unlock;
	}

	size = i_size_read(inode);
	if (!(mode & FALLOC_FL_KEEP_SIZE))
		endoff = offset + length;

	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;

	ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
	if (ret < 0)
		goto unlock;

	if (mode & FALLOC_FL_PUNCH_HOLE) {
		if (offset < size)
			ceph_zero_pagecache_range(inode, offset, length);
		ret = ceph_zero_objects(inode, offset, length);
	} else if (endoff > size) {
		truncate_pagecache_range(inode, size, -1);
		if (ceph_inode_set_size(inode, endoff))
			ceph_check_caps(ceph_inode(inode),
				CHECK_CAPS_AUTHONLY, NULL);
	}

	if (!ret) {
		spin_lock(&ci->i_ceph_lock);
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
		spin_unlock(&ci->i_ceph_lock);
		if (dirty)
			__mark_inode_dirty(inode, dirty);
	}

	ceph_put_cap_refs(ci, got);
unlock:
	mutex_unlock(&inode->i_mutex);
	return ret;
}

const struct file_operations ceph_file_fops = {
	.open = ceph_open,
	.release = ceph_release,
	.llseek = ceph_llseek,
	.read = new_sync_read,
	.write = do_sync_write,
	.read_iter = ceph_read_iter,
	.aio_write = ceph_aio_write,
	.mmap = ceph_mmap,
	.fsync = ceph_fsync,
	.lock = ceph_lock,
	.flock = ceph_flock,
	.splice_read = generic_file_splice_read,
	.splice_write = generic_file_splice_write,
	.unlocked_ioctl = ceph_ioctl,
	.compat_ioctl	= ceph_ioctl,
	.fallocate	= ceph_fallocate,
};