aboutsummaryrefslogtreecommitdiff
path: root/fs/nfs/blocklayout/blocklayout.c
blob: f3d16adc832c7d062c065c61945a36a86b533191 (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
/*
 *  linux/fs/nfs/blocklayout/blocklayout.c
 *
 *  Module for the NFSv4.1 pNFS block layout driver.
 *
 *  Copyright (c) 2006 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Andy Adamson <andros@citi.umich.edu>
 *  Fred Isaman <iisaman@umich.edu>
 *
 * permission is granted to use, copy, create derivative works and
 * redistribute this software and such derivative works for any purpose,
 * so long as the name of the university of michigan is not used in
 * any advertising or publicity pertaining to the use or distribution
 * of this software without specific, written prior authorization.  if
 * the above copyright notice or any other identification of the
 * university of michigan is included in any copy of any portion of
 * this software, then the disclaimer below must also be included.
 *
 * this software is provided as is, without representation from the
 * university of michigan as to its fitness for any purpose, and without
 * warranty by the university of michigan of any kind, either express
 * or implied, including without limitation the implied warranties of
 * merchantability and fitness for a particular purpose.  the regents
 * of the university of michigan shall not be liable for any damages,
 * including special, indirect, incidental, or consequential damages,
 * with respect to any claim arising out or in connection with the use
 * of the software, even if it has been or is hereafter advised of the
 * possibility of such damages.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/bio.h>		/* struct bio */
#include <linux/buffer_head.h>	/* various write calls */
#include <linux/prefetch.h>

#include "../pnfs.h"
#include "../internal.h"
#include "blocklayout.h"

#define NFSDBG_FACILITY	NFSDBG_PNFS_LD

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");

static void print_page(struct page *page)
{
	dprintk("PRINTPAGE page %p\n", page);
	dprintk("	PagePrivate %d\n", PagePrivate(page));
	dprintk("	PageUptodate %d\n", PageUptodate(page));
	dprintk("	PageError %d\n", PageError(page));
	dprintk("	PageDirty %d\n", PageDirty(page));
	dprintk("	PageReferenced %d\n", PageReferenced(page));
	dprintk("	PageLocked %d\n", PageLocked(page));
	dprintk("	PageWriteback %d\n", PageWriteback(page));
	dprintk("	PageMappedToDisk %d\n", PageMappedToDisk(page));
	dprintk("\n");
}

/* Given the be associated with isect, determine if page data needs to be
 * initialized.
 */
static int is_hole(struct pnfs_block_extent *be, sector_t isect)
{
	if (be->be_state == PNFS_BLOCK_NONE_DATA)
		return 1;
	else if (be->be_state != PNFS_BLOCK_INVALID_DATA)
		return 0;
	else
		return !bl_is_sector_init(be->be_inval, isect);
}

/* Given the be associated with isect, determine if page data can be
 * written to disk.
 */
static int is_writable(struct pnfs_block_extent *be, sector_t isect)
{
	return (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
		be->be_state == PNFS_BLOCK_INVALID_DATA);
}

/* The data we are handed might be spread across several bios.  We need
 * to track when the last one is finished.
 */
struct parallel_io {
	struct kref refcnt;
	void (*pnfs_callback) (void *data, int num_se);
	void *data;
	int bse_count;
};

static inline struct parallel_io *alloc_parallel(void *data)
{
	struct parallel_io *rv;

	rv  = kmalloc(sizeof(*rv), GFP_NOFS);
	if (rv) {
		rv->data = data;
		kref_init(&rv->refcnt);
		rv->bse_count = 0;
	}
	return rv;
}

static inline void get_parallel(struct parallel_io *p)
{
	kref_get(&p->refcnt);
}

static void destroy_parallel(struct kref *kref)
{
	struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);

	dprintk("%s enter\n", __func__);
	p->pnfs_callback(p->data, p->bse_count);
	kfree(p);
}

static inline void put_parallel(struct parallel_io *p)
{
	kref_put(&p->refcnt, destroy_parallel);
}

static struct bio *
bl_submit_bio(int rw, struct bio *bio)
{
	if (bio) {
		get_parallel(bio->bi_private);
		dprintk("%s submitting %s bio %u@%llu\n", __func__,
			rw == READ ? "read" : "write",
			bio->bi_size, (unsigned long long)bio->bi_sector);
		submit_bio(rw, bio);
	}
	return NULL;
}

static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
				     struct pnfs_block_extent *be,
				     void (*end_io)(struct bio *, int err),
				     struct parallel_io *par)
{
	struct bio *bio;

	npg = min(npg, BIO_MAX_PAGES);
	bio = bio_alloc(GFP_NOIO, npg);
	if (!bio && (current->flags & PF_MEMALLOC)) {
		while (!bio && (npg /= 2))
			bio = bio_alloc(GFP_NOIO, npg);
	}

	if (bio) {
		bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
		bio->bi_bdev = be->be_mdev;
		bio->bi_end_io = end_io;
		bio->bi_private = par;
	}
	return bio;
}

static struct bio *do_add_page_to_bio(struct bio *bio, int npg, int rw,
				      sector_t isect, struct page *page,
				      struct pnfs_block_extent *be,
				      void (*end_io)(struct bio *, int err),
				      struct parallel_io *par,
				      unsigned int offset, int len)
{
	isect = isect + (offset >> SECTOR_SHIFT);
	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
		npg, rw, (unsigned long long)isect, offset, len);
retry:
	if (!bio) {
		bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
		if (!bio)
			return ERR_PTR(-ENOMEM);
	}
	if (bio_add_page(bio, page, len, offset) < len) {
		bio = bl_submit_bio(rw, bio);
		goto retry;
	}
	return bio;
}

static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
				      sector_t isect, struct page *page,
				      struct pnfs_block_extent *be,
				      void (*end_io)(struct bio *, int err),
				      struct parallel_io *par)
{
	return do_add_page_to_bio(bio, npg, rw, isect, page, be,
				  end_io, par, 0, PAGE_CACHE_SIZE);
}

/* This is basically copied from mpage_end_io_read */
static void bl_end_io_read(struct bio *bio, int err)
{
	struct parallel_io *par = bio->bi_private;
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;

	do {
		struct page *page = bvec->bv_page;

		if (--bvec >= bio->bi_io_vec)
			prefetchw(&bvec->bv_page->flags);
		if (uptodate)
			SetPageUptodate(page);
	} while (bvec >= bio->bi_io_vec);
	if (!uptodate) {
		struct nfs_read_data *rdata = par->data;
		struct nfs_pgio_header *header = rdata->header;

		if (!header->pnfs_error)
			header->pnfs_error = -EIO;
		pnfs_set_lo_fail(header->lseg);
	}
	bio_put(bio);
	put_parallel(par);
}

static void bl_read_cleanup(struct work_struct *work)
{
	struct rpc_task *task;
	struct nfs_read_data *rdata;
	dprintk("%s enter\n", __func__);
	task = container_of(work, struct rpc_task, u.tk_work);
	rdata = container_of(task, struct nfs_read_data, task);
	pnfs_ld_read_done(rdata);
}

static void
bl_end_par_io_read(void *data, int unused)
{
	struct nfs_read_data *rdata = data;

	rdata->task.tk_status = rdata->header->pnfs_error;
	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
	schedule_work(&rdata->task.u.tk_work);
}

static bool
bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
{
	if ((offset & blkmask) || (len & blkmask))
		return false;
	return true;
}

static enum pnfs_try_status
bl_read_pagelist(struct nfs_read_data *rdata)
{
	struct nfs_pgio_header *header = rdata->header;
	int i, hole;
	struct bio *bio = NULL;
	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
	sector_t isect, extent_length = 0;
	struct parallel_io *par;
	loff_t f_offset = rdata->args.offset;
	struct page **pages = rdata->args.pages;
	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;

	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);

	if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
		goto use_mds;

	par = alloc_parallel(rdata);
	if (!par)
		goto use_mds;
	par->pnfs_callback = bl_end_par_io_read;
	/* At this point, we can no longer jump to use_mds */

	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
	/* Code assumes extents are page-aligned */
	for (i = pg_index; i < rdata->pages.npages; i++) {
		if (!extent_length) {
			/* We've used up the previous extent */
			bl_put_extent(be);
			bl_put_extent(cow_read);
			bio = bl_submit_bio(READ, bio);
			/* Get the next one */
			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
					     isect, &cow_read);
			if (!be) {
				header->pnfs_error = -EIO;
				goto out;
			}
			extent_length = be->be_length -
				(isect - be->be_f_offset);
			if (cow_read) {
				sector_t cow_length = cow_read->be_length -
					(isect - cow_read->be_f_offset);
				extent_length = min(extent_length, cow_length);
			}
		}
		hole = is_hole(be, isect);
		if (hole && !cow_read) {
			bio = bl_submit_bio(READ, bio);
			/* Fill hole w/ zeroes w/o accessing device */
			dprintk("%s Zeroing page for hole\n", __func__);
			zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
			print_page(pages[i]);
			SetPageUptodate(pages[i]);
		} else {
			struct pnfs_block_extent *be_read;

			be_read = (hole && cow_read) ? cow_read : be;
			bio = bl_add_page_to_bio(bio, rdata->pages.npages - i,
						 READ,
						 isect, pages[i], be_read,
						 bl_end_io_read, par);
			if (IS_ERR(bio)) {
				header->pnfs_error = PTR_ERR(bio);
				bio = NULL;
				goto out;
			}
		}
		isect += PAGE_CACHE_SECTORS;
		extent_length -= PAGE_CACHE_SECTORS;
	}
	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
		rdata->res.eof = 1;
		rdata->res.count = header->inode->i_size - f_offset;
	} else {
		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
	}
out:
	bl_put_extent(be);
	bl_put_extent(cow_read);
	bl_submit_bio(READ, bio);
	put_parallel(par);
	return PNFS_ATTEMPTED;

 use_mds:
	dprintk("Giving up and using normal NFS\n");
	return PNFS_NOT_ATTEMPTED;
}

static void mark_extents_written(struct pnfs_block_layout *bl,
				 __u64 offset, __u32 count)
{
	sector_t isect, end;
	struct pnfs_block_extent *be;
	struct pnfs_block_short_extent *se;

	dprintk("%s(%llu, %u)\n", __func__, offset, count);
	if (count == 0)
		return;
	isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT;
	end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK);
	end >>= SECTOR_SHIFT;
	while (isect < end) {
		sector_t len;
		be = bl_find_get_extent(bl, isect, NULL);
		BUG_ON(!be); /* FIXME */
		len = min(end, be->be_f_offset + be->be_length) - isect;
		if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
			se = bl_pop_one_short_extent(be->be_inval);
			BUG_ON(!se);
			bl_mark_for_commit(be, isect, len, se);
		}
		isect += len;
		bl_put_extent(be);
	}
}

static void bl_end_io_write_zero(struct bio *bio, int err)
{
	struct parallel_io *par = bio->bi_private;
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;

	do {
		struct page *page = bvec->bv_page;

		if (--bvec >= bio->bi_io_vec)
			prefetchw(&bvec->bv_page->flags);
		/* This is the zeroing page we added */
		end_page_writeback(page);
		page_cache_release(page);
	} while (bvec >= bio->bi_io_vec);

	if (unlikely(!uptodate)) {
		struct nfs_write_data *data = par->data;
		struct nfs_pgio_header *header = data->header;

		if (!header->pnfs_error)
			header->pnfs_error = -EIO;
		pnfs_set_lo_fail(header->lseg);
	}
	bio_put(bio);
	put_parallel(par);
}

static void bl_end_io_write(struct bio *bio, int err)
{
	struct parallel_io *par = bio->bi_private;
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct nfs_write_data *data = par->data;
	struct nfs_pgio_header *header = data->header;

	if (!uptodate) {
		if (!header->pnfs_error)
			header->pnfs_error = -EIO;
		pnfs_set_lo_fail(header->lseg);
	}
	bio_put(bio);
	put_parallel(par);
}

/* Function scheduled for call during bl_end_par_io_write,
 * it marks sectors as written and extends the commitlist.
 */
static void bl_write_cleanup(struct work_struct *work)
{
	struct rpc_task *task;
	struct nfs_write_data *wdata;
	dprintk("%s enter\n", __func__);
	task = container_of(work, struct rpc_task, u.tk_work);
	wdata = container_of(task, struct nfs_write_data, task);
	if (likely(!wdata->header->pnfs_error)) {
		/* Marks for LAYOUTCOMMIT */
		mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
				     wdata->args.offset, wdata->args.count);
	}
	pnfs_ld_write_done(wdata);
}

/* Called when last of bios associated with a bl_write_pagelist call finishes */
static void bl_end_par_io_write(void *data, int num_se)
{
	struct nfs_write_data *wdata = data;

	if (unlikely(wdata->header->pnfs_error)) {
		bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
					num_se);
	}

	wdata->task.tk_status = wdata->header->pnfs_error;
	wdata->verf.committed = NFS_FILE_SYNC;
	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
	schedule_work(&wdata->task.u.tk_work);
}

/* FIXME STUB - mark intersection of layout and page as bad, so is not
 * used again.
 */
static void mark_bad_read(void)
{
	return;
}

/*
 * map_block:  map a requested I/0 block (isect) into an offset in the LVM
 * block_device
 */
static void
map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
{
	dprintk("%s enter be=%p\n", __func__, be);

	set_buffer_mapped(bh);
	bh->b_bdev = be->be_mdev;
	bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >>
	    (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT);

	dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n",
		__func__, (unsigned long long)isect, (long)bh->b_blocknr,
		bh->b_size);
	return;
}

static void
bl_read_single_end_io(struct bio *bio, int error)
{
	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
	struct page *page = bvec->bv_page;

	/* Only one page in bvec */
	unlock_page(page);
}

static int
bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
		    unsigned int offset, unsigned int len)
{
	struct bio *bio;
	struct page *shadow_page;
	sector_t isect;
	char *kaddr, *kshadow_addr;
	int ret = 0;

	dprintk("%s: offset %u len %u\n", __func__, offset, len);

	shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
	if (shadow_page == NULL)
		return -ENOMEM;

	bio = bio_alloc(GFP_NOIO, 1);
	if (bio == NULL)
		return -ENOMEM;

	isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
		(offset / SECTOR_SIZE);

	bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
	bio->bi_bdev = be->be_mdev;
	bio->bi_end_io = bl_read_single_end_io;

	lock_page(shadow_page);
	if (bio_add_page(bio, shadow_page,
			 SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) {
		unlock_page(shadow_page);
		bio_put(bio);
		return -EIO;
	}

	submit_bio(READ, bio);
	wait_on_page_locked(shadow_page);
	if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) {
		ret = -EIO;
	} else {
		kaddr = kmap_atomic(page);
		kshadow_addr = kmap_atomic(shadow_page);
		memcpy(kaddr + offset, kshadow_addr + offset, len);
		kunmap_atomic(kshadow_addr);
		kunmap_atomic(kaddr);
	}
	__free_page(shadow_page);
	bio_put(bio);

	return ret;
}

static int
bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be,
			  unsigned int dirty_offset, unsigned int dirty_len,
			  bool full_page)
{
	int ret = 0;
	unsigned int start, end;

	if (full_page) {
		start = 0;
		end = PAGE_CACHE_SIZE;
	} else {
		start = round_down(dirty_offset, SECTOR_SIZE);
		end = round_up(dirty_offset + dirty_len, SECTOR_SIZE);
	}

	dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len);
	if (!be) {
		zero_user_segments(page, start, dirty_offset,
				   dirty_offset + dirty_len, end);
		if (start == 0 && end == PAGE_CACHE_SIZE &&
		    trylock_page(page)) {
			SetPageUptodate(page);
			unlock_page(page);
		}
		return ret;
	}

	if (start != dirty_offset)
		ret = bl_do_readpage_sync(page, be, start, dirty_offset - start);

	if (!ret && (dirty_offset + dirty_len < end))
		ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len,
					  end - dirty_offset - dirty_len);

	return ret;
}

/* Given an unmapped page, zero it or read in page for COW, page is locked
 * by caller.
 */
static int
init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
{
	struct buffer_head *bh = NULL;
	int ret = 0;
	sector_t isect;

	dprintk("%s enter, %p\n", __func__, page);
	BUG_ON(PageUptodate(page));
	if (!cow_read) {
		zero_user_segment(page, 0, PAGE_SIZE);
		SetPageUptodate(page);
		goto cleanup;
	}

	bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0);
	if (!bh) {
		ret = -ENOMEM;
		goto cleanup;
	}

	isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT;
	map_block(bh, isect, cow_read);
	if (!bh_uptodate_or_lock(bh))
		ret = bh_submit_read(bh);
	if (ret)
		goto cleanup;
	SetPageUptodate(page);

cleanup:
	if (bh)
		free_buffer_head(bh);
	if (ret) {
		/* Need to mark layout with bad read...should now
		 * just use nfs4 for reads and writes.
		 */
		mark_bad_read();
	}
	return ret;
}

/* Find or create a zeroing page marked being writeback.
 * Return ERR_PTR on error, NULL to indicate skip this page and page itself
 * to indicate write out.
 */
static struct page *
bl_find_get_zeroing_page(struct inode *inode, pgoff_t index,
			struct pnfs_block_extent *cow_read)
{
	struct page *page;
	int locked = 0;
	page = find_get_page(inode->i_mapping, index);
	if (page)
		goto check_page;

	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
	if (unlikely(!page)) {
		dprintk("%s oom\n", __func__);
		return ERR_PTR(-ENOMEM);
	}
	locked = 1;

check_page:
	/* PageDirty: Other will write this out
	 * PageWriteback: Other is writing this out
	 * PageUptodate: It was read before
	 */
	if (PageDirty(page) || PageWriteback(page)) {
		print_page(page);
		if (locked)
			unlock_page(page);
		page_cache_release(page);
		return NULL;
	}

	if (!locked) {
		lock_page(page);
		locked = 1;
		goto check_page;
	}
	if (!PageUptodate(page)) {
		/* New page, readin or zero it */
		init_page_for_write(page, cow_read);
	}
	set_page_writeback(page);
	unlock_page(page);

	return page;
}

static enum pnfs_try_status
bl_write_pagelist(struct nfs_write_data *wdata, int sync)
{
	struct nfs_pgio_header *header = wdata->header;
	int i, ret, npg_zero, pg_index, last = 0;
	struct bio *bio = NULL;
	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
	sector_t isect, last_isect = 0, extent_length = 0;
	struct parallel_io *par = NULL;
	loff_t offset = wdata->args.offset;
	size_t count = wdata->args.count;
	unsigned int pg_offset, pg_len, saved_len;
	struct page **pages = wdata->args.pages;
	struct page *page;
	pgoff_t index;
	u64 temp;
	int npg_per_block =
	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;

	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
	/* Check for alignment first */
	if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
		goto out_mds;

	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
	 * We want to write each, and if there is an error set pnfs_error
	 * to have it redone using nfs.
	 */
	par = alloc_parallel(wdata);
	if (!par)
		goto out_mds;
	par->pnfs_callback = bl_end_par_io_write;
	/* At this point, have to be more careful with error handling */

	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
	be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
	if (!be || !is_writable(be, isect)) {
		dprintk("%s no matching extents!\n", __func__);
		goto out_mds;
	}

	/* First page inside INVALID extent */
	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
		if (likely(!bl_push_one_short_extent(be->be_inval)))
			par->bse_count++;
		else
			goto out_mds;
		temp = offset >> PAGE_CACHE_SHIFT;
		npg_zero = do_div(temp, npg_per_block);
		isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) &
				     (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
		extent_length = be->be_length - (isect - be->be_f_offset);

fill_invalid_ext:
		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
		for (;npg_zero > 0; npg_zero--) {
			if (bl_is_sector_init(be->be_inval, isect)) {
				dprintk("isect %llu already init\n",
					(unsigned long long)isect);
				goto next_page;
			}
			/* page ref released in bl_end_io_write_zero */
			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
			dprintk("%s zero %dth page: index %lu isect %llu\n",
				__func__, npg_zero, index,
				(unsigned long long)isect);
			page = bl_find_get_zeroing_page(header->inode, index,
							cow_read);
			if (unlikely(IS_ERR(page))) {
				header->pnfs_error = PTR_ERR(page);
				goto out;
			} else if (page == NULL)
				goto next_page;

			ret = bl_mark_sectors_init(be->be_inval, isect,
						       PAGE_CACHE_SECTORS);
			if (unlikely(ret)) {
				dprintk("%s bl_mark_sectors_init fail %d\n",
					__func__, ret);
				end_page_writeback(page);
				page_cache_release(page);
				header->pnfs_error = ret;
				goto out;
			}
			if (likely(!bl_push_one_short_extent(be->be_inval)))
				par->bse_count++;
			else {
				end_page_writeback(page);
				page_cache_release(page);
				header->pnfs_error = -ENOMEM;
				goto out;
			}
			/* FIXME: This should be done in bi_end_io */
			mark_extents_written(BLK_LSEG2EXT(header->lseg),
					     page->index << PAGE_CACHE_SHIFT,
					     PAGE_CACHE_SIZE);

			bio = bl_add_page_to_bio(bio, npg_zero, WRITE,
						 isect, page, be,
						 bl_end_io_write_zero, par);
			if (IS_ERR(bio)) {
				header->pnfs_error = PTR_ERR(bio);
				bio = NULL;
				goto out;
			}
next_page:
			isect += PAGE_CACHE_SECTORS;
			extent_length -= PAGE_CACHE_SECTORS;
		}
		if (last)
			goto write_done;
	}
	bio = bl_submit_bio(WRITE, bio);

	/* Middle pages */
	pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
	for (i = pg_index; i < wdata->pages.npages; i++) {
		if (!extent_length) {
			/* We've used up the previous extent */
			bl_put_extent(be);
			bl_put_extent(cow_read);
			bio = bl_submit_bio(WRITE, bio);
			/* Get the next one */
			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
					     isect, &cow_read);
			if (!be || !is_writable(be, isect)) {
				header->pnfs_error = -EINVAL;
				goto out;
			}
			if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
				if (likely(!bl_push_one_short_extent(
								be->be_inval)))
					par->bse_count++;
				else {
					header->pnfs_error = -ENOMEM;
					goto out;
				}
			}
			extent_length = be->be_length -
			    (isect - be->be_f_offset);
		}

		dprintk("%s offset %lld count %Zu\n", __func__, offset, count);
		pg_offset = offset & ~PAGE_CACHE_MASK;
		if (pg_offset + count > PAGE_CACHE_SIZE)
			pg_len = PAGE_CACHE_SIZE - pg_offset;
		else
			pg_len = count;

		saved_len = pg_len;
		if (be->be_state == PNFS_BLOCK_INVALID_DATA &&
		    !bl_is_sector_init(be->be_inval, isect)) {
			ret = bl_read_partial_page_sync(pages[i], cow_read,
							pg_offset, pg_len, true);
			if (ret) {
				dprintk("%s bl_read_partial_page_sync fail %d\n",
					__func__, ret);
				header->pnfs_error = ret;
				goto out;
			}

			ret = bl_mark_sectors_init(be->be_inval, isect,
						       PAGE_CACHE_SECTORS);
			if (unlikely(ret)) {
				dprintk("%s bl_mark_sectors_init fail %d\n",
					__func__, ret);
				header->pnfs_error = ret;
				goto out;
			}

			/* Expand to full page write */
			pg_offset = 0;
			pg_len = PAGE_CACHE_SIZE;
		} else if  ((pg_offset & (SECTOR_SIZE - 1)) ||
			    (pg_len & (SECTOR_SIZE - 1))){
			/* ahh, nasty case. We have to do sync full sector
			 * read-modify-write cycles.
			 */
			unsigned int saved_offset = pg_offset;
			ret = bl_read_partial_page_sync(pages[i], be, pg_offset,
							pg_len, false);
			pg_offset = round_down(pg_offset, SECTOR_SIZE);
			pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE)
				 - pg_offset;
		}


		bio = do_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
					 isect, pages[i], be,
					 bl_end_io_write, par,
					 pg_offset, pg_len);
		if (IS_ERR(bio)) {
			header->pnfs_error = PTR_ERR(bio);
			bio = NULL;
			goto out;
		}
		offset += saved_len;
		count -= saved_len;
		isect += PAGE_CACHE_SECTORS;
		last_isect = isect;
		extent_length -= PAGE_CACHE_SECTORS;
	}

	/* Last page inside INVALID extent */
	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
		bio = bl_submit_bio(WRITE, bio);
		temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT;
		npg_zero = npg_per_block - do_div(temp, npg_per_block);
		if (npg_zero < npg_per_block) {
			last = 1;
			goto fill_invalid_ext;
		}
	}

write_done:
	wdata->res.count = wdata->args.count;
out:
	bl_put_extent(be);
	bl_put_extent(cow_read);
	bl_submit_bio(WRITE, bio);
	put_parallel(par);
	return PNFS_ATTEMPTED;
out_mds:
	bl_put_extent(be);
	bl_put_extent(cow_read);
	kfree(par);
	return PNFS_NOT_ATTEMPTED;
}

/* FIXME - range ignored */
static void
release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range)
{
	int i;
	struct pnfs_block_extent *be;

	spin_lock(&bl->bl_ext_lock);
	for (i = 0; i < EXTENT_LISTS; i++) {
		while (!list_empty(&bl->bl_extents[i])) {
			be = list_first_entry(&bl->bl_extents[i],
					      struct pnfs_block_extent,
					      be_node);
			list_del(&be->be_node);
			bl_put_extent(be);
		}
	}
	spin_unlock(&bl->bl_ext_lock);
}

static void
release_inval_marks(struct pnfs_inval_markings *marks)
{
	struct pnfs_inval_tracking *pos, *temp;
	struct pnfs_block_short_extent *se, *stemp;

	list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) {
		list_del(&pos->it_link);
		kfree(pos);
	}

	list_for_each_entry_safe(se, stemp, &marks->im_extents, bse_node) {
		list_del(&se->bse_node);
		kfree(se);
	}
	return;
}

static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);

	dprintk("%s enter\n", __func__);
	release_extents(bl, NULL);
	release_inval_marks(&bl->bl_inval);
	kfree(bl);
}

static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
						   gfp_t gfp_flags)
{
	struct pnfs_block_layout *bl;

	dprintk("%s enter\n", __func__);
	bl = kzalloc(sizeof(*bl), gfp_flags);
	if (!bl)
		return NULL;
	spin_lock_init(&bl->bl_ext_lock);
	INIT_LIST_HEAD(&bl->bl_extents[0]);
	INIT_LIST_HEAD(&bl->bl_extents[1]);
	INIT_LIST_HEAD(&bl->bl_commit);
	INIT_LIST_HEAD(&bl->bl_committing);
	bl->bl_count = 0;
	bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT;
	BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize);
	return &bl->bl_layout;
}

static void bl_free_lseg(struct pnfs_layout_segment *lseg)
{
	dprintk("%s enter\n", __func__);
	kfree(lseg);
}

/* We pretty much ignore lseg, and store all data layout wide, so we
 * can correctly merge.
 */
static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo,
						 struct nfs4_layoutget_res *lgr,
						 gfp_t gfp_flags)
{
	struct pnfs_layout_segment *lseg;
	int status;

	dprintk("%s enter\n", __func__);
	lseg = kzalloc(sizeof(*lseg), gfp_flags);
	if (!lseg)
		return ERR_PTR(-ENOMEM);
	status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags);
	if (status) {
		/* We don't want to call the full-blown bl_free_lseg,
		 * since on error extents were not touched.
		 */
		kfree(lseg);
		return ERR_PTR(status);
	}
	return lseg;
}

static void
bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
		       const struct nfs4_layoutcommit_args *arg)
{
	dprintk("%s enter\n", __func__);
	encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
}

static void
bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
{
	struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;

	dprintk("%s enter\n", __func__);
	clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
}

static void free_blk_mountid(struct block_mount_id *mid)
{
	if (mid) {
		struct pnfs_block_dev *dev, *tmp;

		/* No need to take bm_lock as we are last user freeing bm_devlist */
		list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) {
			list_del(&dev->bm_node);
			bl_free_block_dev(dev);
		}
		kfree(mid);
	}
}

/* This is mostly copied from the filelayout's get_device_info function.
 * It seems much of this should be at the generic pnfs level.
 */
static struct pnfs_block_dev *
nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
			struct nfs4_deviceid *d_id)
{
	struct pnfs_device *dev;
	struct pnfs_block_dev *rv;
	u32 max_resp_sz;
	int max_pages;
	struct page **pages = NULL;
	int i, rc;

	/*
	 * Use the session max response size as the basis for setting
	 * GETDEVICEINFO's maxcount
	 */
	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
	max_pages = nfs_page_array_len(0, max_resp_sz);
	dprintk("%s max_resp_sz %u max_pages %d\n",
		__func__, max_resp_sz, max_pages);

	dev = kmalloc(sizeof(*dev), GFP_NOFS);
	if (!dev) {
		dprintk("%s kmalloc failed\n", __func__);
		return ERR_PTR(-ENOMEM);
	}

	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
	if (pages == NULL) {
		kfree(dev);
		return ERR_PTR(-ENOMEM);
	}
	for (i = 0; i < max_pages; i++) {
		pages[i] = alloc_page(GFP_NOFS);
		if (!pages[i]) {
			rv = ERR_PTR(-ENOMEM);
			goto out_free;
		}
	}

	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
	dev->layout_type = LAYOUT_BLOCK_VOLUME;
	dev->pages = pages;
	dev->pgbase = 0;
	dev->pglen = PAGE_SIZE * max_pages;
	dev->mincount = 0;

	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
	rc = nfs4_proc_getdeviceinfo(server, dev);
	dprintk("%s getdevice info returns %d\n", __func__, rc);
	if (rc) {
		rv = ERR_PTR(rc);
		goto out_free;
	}

	rv = nfs4_blk_decode_device(server, dev);
 out_free:
	for (i = 0; i < max_pages; i++)
		__free_page(pages[i]);
	kfree(pages);
	kfree(dev);
	return rv;
}

static int
bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
{
	struct block_mount_id *b_mt_id = NULL;
	struct pnfs_devicelist *dlist = NULL;
	struct pnfs_block_dev *bdev;
	LIST_HEAD(block_disklist);
	int status, i;

	dprintk("%s enter\n", __func__);

	if (server->pnfs_blksize == 0) {
		dprintk("%s Server did not return blksize\n", __func__);
		return -EINVAL;
	}
	b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS);
	if (!b_mt_id) {
		status = -ENOMEM;
		goto out_error;
	}
	/* Initialize nfs4 block layout mount id */
	spin_lock_init(&b_mt_id->bm_lock);
	INIT_LIST_HEAD(&b_mt_id->bm_devlist);

	dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS);
	if (!dlist) {
		status = -ENOMEM;
		goto out_error;
	}
	dlist->eof = 0;
	while (!dlist->eof) {
		status = nfs4_proc_getdevicelist(server, fh, dlist);
		if (status)
			goto out_error;
		dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n",
			__func__, dlist->num_devs, dlist->eof);
		for (i = 0; i < dlist->num_devs; i++) {
			bdev = nfs4_blk_get_deviceinfo(server, fh,
						       &dlist->dev_id[i]);
			if (IS_ERR(bdev)) {
				status = PTR_ERR(bdev);
				goto out_error;
			}
			spin_lock(&b_mt_id->bm_lock);
			list_add(&bdev->bm_node, &b_mt_id->bm_devlist);
			spin_unlock(&b_mt_id->bm_lock);
		}
	}
	dprintk("%s SUCCESS\n", __func__);
	server->pnfs_ld_data = b_mt_id;

 out_return:
	kfree(dlist);
	return status;

 out_error:
	free_blk_mountid(b_mt_id);
	goto out_return;
}

static int
bl_clear_layoutdriver(struct nfs_server *server)
{
	struct block_mount_id *b_mt_id = server->pnfs_ld_data;

	dprintk("%s enter\n", __func__);
	free_blk_mountid(b_mt_id);
	dprintk("%s RETURNS\n", __func__);
	return 0;
}

static void
bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
		nfs_pageio_reset_read_mds(pgio);
	else
		pnfs_generic_pg_init_read(pgio, req);
}

static void
bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
		nfs_pageio_reset_write_mds(pgio);
	else
		pnfs_generic_pg_init_write(pgio, req);
}

static const struct nfs_pageio_ops bl_pg_read_ops = {
	.pg_init = bl_pg_init_read,
	.pg_test = pnfs_generic_pg_test,
	.pg_doio = pnfs_generic_pg_readpages,
};

static const struct nfs_pageio_ops bl_pg_write_ops = {
	.pg_init = bl_pg_init_write,
	.pg_test = pnfs_generic_pg_test,
	.pg_doio = pnfs_generic_pg_writepages,
};

static struct pnfs_layoutdriver_type blocklayout_type = {
	.id				= LAYOUT_BLOCK_VOLUME,
	.name				= "LAYOUT_BLOCK_VOLUME",
	.read_pagelist			= bl_read_pagelist,
	.write_pagelist			= bl_write_pagelist,
	.alloc_layout_hdr		= bl_alloc_layout_hdr,
	.free_layout_hdr		= bl_free_layout_hdr,
	.alloc_lseg			= bl_alloc_lseg,
	.free_lseg			= bl_free_lseg,
	.encode_layoutcommit		= bl_encode_layoutcommit,
	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
	.set_layoutdriver		= bl_set_layoutdriver,
	.clear_layoutdriver		= bl_clear_layoutdriver,
	.pg_read_ops			= &bl_pg_read_ops,
	.pg_write_ops			= &bl_pg_write_ops,
};

static const struct rpc_pipe_ops bl_upcall_ops = {
	.upcall		= rpc_pipe_generic_upcall,
	.downcall	= bl_pipe_downcall,
	.destroy_msg	= bl_pipe_destroy_msg,
};

static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
					    struct rpc_pipe *pipe)
{
	struct dentry *dir, *dentry;

	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
	if (dir == NULL)
		return ERR_PTR(-ENOENT);
	dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
	dput(dir);
	return dentry;
}

static void nfs4blocklayout_unregister_sb(struct super_block *sb,
					  struct rpc_pipe *pipe)
{
	if (pipe->dentry)
		rpc_unlink(pipe->dentry);
}

static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
			   void *ptr)
{
	struct super_block *sb = ptr;
	struct net *net = sb->s_fs_info;
	struct nfs_net *nn = net_generic(net, nfs_net_id);
	struct dentry *dentry;
	int ret = 0;

	if (!try_module_get(THIS_MODULE))
		return 0;

	if (nn->bl_device_pipe == NULL) {
		module_put(THIS_MODULE);
		return 0;
	}

	switch (event) {
	case RPC_PIPEFS_MOUNT:
		dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
		if (IS_ERR(dentry)) {
			ret = PTR_ERR(dentry);
			break;
		}
		nn->bl_device_pipe->dentry = dentry;
		break;
	case RPC_PIPEFS_UMOUNT:
		if (nn->bl_device_pipe->dentry)
			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
		break;
	default:
		ret = -ENOTSUPP;
		break;
	}
	module_put(THIS_MODULE);
	return ret;
}

static struct notifier_block nfs4blocklayout_block = {
	.notifier_call = rpc_pipefs_event,
};

static struct dentry *nfs4blocklayout_register_net(struct net *net,
						   struct rpc_pipe *pipe)
{
	struct super_block *pipefs_sb;
	struct dentry *dentry;

	pipefs_sb = rpc_get_sb_net(net);
	if (!pipefs_sb)
		return NULL;
	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
	rpc_put_sb_net(net);
	return dentry;
}

static void nfs4blocklayout_unregister_net(struct net *net,
					   struct rpc_pipe *pipe)
{
	struct super_block *pipefs_sb;

	pipefs_sb = rpc_get_sb_net(net);
	if (pipefs_sb) {
		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
		rpc_put_sb_net(net);
	}
}

static int nfs4blocklayout_net_init(struct net *net)
{
	struct nfs_net *nn = net_generic(net, nfs_net_id);
	struct dentry *dentry;

	init_waitqueue_head(&nn->bl_wq);
	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
	if (IS_ERR(nn->bl_device_pipe))
		return PTR_ERR(nn->bl_device_pipe);
	dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
	if (IS_ERR(dentry)) {
		rpc_destroy_pipe_data(nn->bl_device_pipe);
		return PTR_ERR(dentry);
	}
	nn->bl_device_pipe->dentry = dentry;
	return 0;
}

static void nfs4blocklayout_net_exit(struct net *net)
{
	struct nfs_net *nn = net_generic(net, nfs_net_id);

	nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
	rpc_destroy_pipe_data(nn->bl_device_pipe);
	nn->bl_device_pipe = NULL;
}

static struct pernet_operations nfs4blocklayout_net_ops = {
	.init = nfs4blocklayout_net_init,
	.exit = nfs4blocklayout_net_exit,
};

static int __init nfs4blocklayout_init(void)
{
	int ret;

	dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);

	ret = pnfs_register_layoutdriver(&blocklayout_type);
	if (ret)
		goto out;

	ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
	if (ret)
		goto out_remove;
	ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
	if (ret)
		goto out_notifier;
out:
	return ret;

out_notifier:
	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
out_remove:
	pnfs_unregister_layoutdriver(&blocklayout_type);
	return ret;
}

static void __exit nfs4blocklayout_exit(void)
{
	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
	       __func__);

	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
	pnfs_unregister_layoutdriver(&blocklayout_type);
}

MODULE_ALIAS("nfs-layouttype4-3");

module_init(nfs4blocklayout_init);
module_exit(nfs4blocklayout_exit);