summaryrefslogtreecommitdiffstats
path: root/fs/nfs/blocklayout/blocklayout.c
blob: 61a858cd54fe3f215e6bfaf2f3ea694200afe183 (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
/*
 *  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/prefetch.h>
#include <linux/pagevec.h>

#include "../pnfs.h"
#include "../nfs4session.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 bool is_hole(struct pnfs_block_extent *be)
{
	switch (be->be_state) {
	case PNFS_BLOCK_NONE_DATA:
		return true;
	case PNFS_BLOCK_INVALID_DATA:
		return be->be_tag ? false : true;
	default:
		return false;
	}
}

/* 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);
	void *data;
};

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);
	}
	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);
	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_iter.bi_size,
			(unsigned long long)bio->bi_iter.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 pnfs_block_dev *dev =
		container_of(be->be_device, struct pnfs_block_dev, d_node);
	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_iter.bi_sector = isect - be->be_f_offset +
			be->be_v_offset;
		bio->bi_bdev = dev->d_bdev;
		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 void bl_end_io_read(struct bio *bio, int err)
{
	struct parallel_io *par = bio->bi_private;

	if (err) {
		struct nfs_pgio_header *header = par->data;

		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_pgio_header *hdr;
	dprintk("%s enter\n", __func__);
	task = container_of(work, struct rpc_task, u.tk_work);
	hdr = container_of(task, struct nfs_pgio_header, task);
	pnfs_ld_read_done(hdr);
}

static void
bl_end_par_io_read(void *data)
{
	struct nfs_pgio_header *hdr = data;

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

static enum pnfs_try_status
bl_read_pagelist(struct nfs_pgio_header *header)
{
	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
	struct bio *bio = NULL;
	struct pnfs_block_extent be;
	sector_t isect, extent_length = 0;
	struct parallel_io *par;
	loff_t f_offset = header->args.offset;
	size_t bytes_left = header->args.count;
	unsigned int pg_offset, pg_len;
	struct page **pages = header->args.pages;
	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
	const bool is_dio = (header->dreq != NULL);
	struct blk_plug plug;
	int i;

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

	par = alloc_parallel(header);
	if (!par)
		return PNFS_NOT_ATTEMPTED;
	par->pnfs_callback = bl_end_par_io_read;

	blk_start_plug(&plug);

	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
	/* Code assumes extents are page-aligned */
	for (i = pg_index; i < header->page_array.npages; i++) {
		if (extent_length <= 0) {
			/* We've used up the previous extent */
			bio = bl_submit_bio(READ, bio);

			/* Get the next one */
			if (!ext_tree_lookup(bl, isect, &be, false)) {
				header->pnfs_error = -EIO;
				goto out;
			}
			extent_length = be.be_length - (isect - be.be_f_offset);
		}

		pg_offset = f_offset & ~PAGE_CACHE_MASK;
		if (is_dio) {
			if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
				pg_len = PAGE_CACHE_SIZE - pg_offset;
			else
				pg_len = bytes_left;

			f_offset += pg_len;
			bytes_left -= pg_len;
			isect += (pg_offset >> SECTOR_SHIFT);
			extent_length -= (pg_offset >> SECTOR_SHIFT);
		} else {
			BUG_ON(pg_offset != 0);
			pg_len = PAGE_CACHE_SIZE;
		}

		if (is_hole(&be)) {
			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], pg_offset, pg_len);
		} else {
			bio = do_add_page_to_bio(bio,
						 header->page_array.npages - i,
						 READ,
						 isect, pages[i], &be,
						 bl_end_io_read, par,
						 pg_offset, pg_len);
			if (IS_ERR(bio)) {
				header->pnfs_error = PTR_ERR(bio);
				bio = NULL;
				goto out;
			}
		}
		isect += (pg_len >> SECTOR_SHIFT);
		extent_length -= (pg_len >> SECTOR_SHIFT);
	}
	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
		header->res.eof = 1;
		header->res.count = header->inode->i_size - header->args.offset;
	} else {
		header->res.count = (isect << SECTOR_SHIFT) - header->args.offset;
	}
out:
	bl_submit_bio(READ, bio);
	blk_finish_plug(&plug);
	put_parallel(par);
	return PNFS_ATTEMPTED;
}

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_pgio_header *header = par->data;

	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 = container_of(work, struct rpc_task, u.tk_work);
	struct nfs_pgio_header *hdr =
			container_of(task, struct nfs_pgio_header, task);

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

	if (likely(!hdr->pnfs_error)) {
		struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg);
		u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK;
		u64 end = (hdr->args.offset + hdr->args.count +
			PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK;

		ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
					(end - start) >> SECTOR_SHIFT);
	}

	pnfs_ld_write_done(hdr);
}

/* Called when last of bios associated with a bl_write_pagelist call finishes */
static void bl_end_par_io_write(void *data)
{
	struct nfs_pgio_header *hdr = data;

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

static enum pnfs_try_status
bl_write_pagelist(struct nfs_pgio_header *header, int sync)
{
	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
	struct bio *bio = NULL;
	struct pnfs_block_extent be;
	sector_t isect, extent_length = 0;
	struct parallel_io *par = NULL;
	loff_t offset = header->args.offset;
	size_t count = header->args.count;
	struct page **pages = header->args.pages;
	int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
	struct blk_plug plug;
	int i;

	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);

	/* At this point, header->page_aray 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(header);
	if (!par)
		return PNFS_NOT_ATTEMPTED;
	par->pnfs_callback = bl_end_par_io_write;

	blk_start_plug(&plug);

	/* we always write out the whole page */
	offset = offset & (loff_t)PAGE_CACHE_MASK;
	isect = offset >> SECTOR_SHIFT;

	for (i = pg_index; i < header->page_array.npages; i++) {
		if (extent_length <= 0) {
			/* We've used up the previous extent */
			bio = bl_submit_bio(WRITE, bio);
			/* Get the next one */
			if (!ext_tree_lookup(bl, isect, &be, true)) {
				header->pnfs_error = -EINVAL;
				goto out;
			}

			extent_length = be.be_length - (isect - be.be_f_offset);
		}

		bio = do_add_page_to_bio(bio, header->page_array.npages - i,
					 WRITE, isect, pages[i], &be,
					 bl_end_io_write, par,
					 0, PAGE_CACHE_SIZE);
		if (IS_ERR(bio)) {
			header->pnfs_error = PTR_ERR(bio);
			bio = NULL;
			goto out;
		}
		offset += PAGE_CACHE_SIZE;
		count -= PAGE_CACHE_SIZE;
		isect += PAGE_CACHE_SECTORS;
		extent_length -= PAGE_CACHE_SECTORS;
	}

	header->res.count = header->args.count;
out:
	bl_submit_bio(WRITE, bio);
	blk_finish_plug(&plug);
	put_parallel(par);
	return PNFS_ATTEMPTED;
}

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

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

	err = ext_tree_remove(bl, true, 0, LLONG_MAX);
	WARN_ON(err);

	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;

	bl->bl_ext_rw = RB_ROOT;
	bl->bl_ext_ro = RB_ROOT;
	spin_lock_init(&bl->bl_ext_lock);

	return &bl->bl_layout;
}

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

/* Tracks info needed to ensure extents in layout obey constraints of spec */
struct layout_verification {
	u32 mode;	/* R or RW */
	u64 start;	/* Expected start of next non-COW extent */
	u64 inval;	/* Start of INVAL coverage */
	u64 cowread;	/* End of COW read coverage */
};

/* Verify the extent meets the layout requirements of the pnfs-block draft,
 * section 2.3.1.
 */
static int verify_extent(struct pnfs_block_extent *be,
			 struct layout_verification *lv)
{
	if (lv->mode == IOMODE_READ) {
		if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
		    be->be_state == PNFS_BLOCK_INVALID_DATA)
			return -EIO;
		if (be->be_f_offset != lv->start)
			return -EIO;
		lv->start += be->be_length;
		return 0;
	}
	/* lv->mode == IOMODE_RW */
	if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
		if (be->be_f_offset != lv->start)
			return -EIO;
		if (lv->cowread > lv->start)
			return -EIO;
		lv->start += be->be_length;
		lv->inval = lv->start;
		return 0;
	} else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
		if (be->be_f_offset != lv->start)
			return -EIO;
		lv->start += be->be_length;
		return 0;
	} else if (be->be_state == PNFS_BLOCK_READ_DATA) {
		if (be->be_f_offset > lv->start)
			return -EIO;
		if (be->be_f_offset < lv->inval)
			return -EIO;
		if (be->be_f_offset < lv->cowread)
			return -EIO;
		/* It looks like you might want to min this with lv->start,
		 * but you really don't.
		 */
		lv->inval = lv->inval + be->be_length;
		lv->cowread = be->be_f_offset + be->be_length;
		return 0;
	} else
		return -EIO;
}

static int decode_sector_number(__be32 **rp, sector_t *sp)
{
	uint64_t s;

	*rp = xdr_decode_hyper(*rp, &s);
	if (s & 0x1ff) {
		printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
		return -1;
	}
	*sp = s >> SECTOR_SHIFT;
	return 0;
}

/* XDR decode pnfs_block_layout4 structure */
static int
nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
			   struct nfs4_layoutget_res *lgr, gfp_t gfp_flags)
{
	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
	int i, status = -EIO;
	uint32_t count;
	struct pnfs_block_extent *be = NULL, *save;
	struct xdr_stream stream;
	struct xdr_buf buf;
	struct page *scratch;
	__be32 *p;
	struct layout_verification lv = {
		.mode = lgr->range.iomode,
		.start = lgr->range.offset >> SECTOR_SHIFT,
		.inval = lgr->range.offset >> SECTOR_SHIFT,
		.cowread = lgr->range.offset >> SECTOR_SHIFT,
	};
	LIST_HEAD(extents);

	dprintk("---> %s\n", __func__);

	scratch = alloc_page(gfp_flags);
	if (!scratch)
		return -ENOMEM;

	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);

	p = xdr_inline_decode(&stream, 4);
	if (unlikely(!p))
		goto out_err;

	count = be32_to_cpup(p++);

	dprintk("%s enter, number of extents %i\n", __func__, count);
	p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count);
	if (unlikely(!p))
		goto out_err;

	/* Decode individual extents, putting them in temporary
	 * staging area until whole layout is decoded to make error
	 * recovery easier.
	 */
	for (i = 0; i < count; i++) {
		struct nfs4_deviceid id;

		be = kzalloc(sizeof(struct pnfs_block_extent), GFP_NOFS);
		if (!be) {
			status = -ENOMEM;
			goto out_err;
		}
		memcpy(&id, p, NFS4_DEVICEID4_SIZE);
		p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);

		be->be_device =
			nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
						lo->plh_lc_cred, gfp_flags);
		if (!be->be_device)
			goto out_err;

		/* The next three values are read in as bytes,
		 * but stored as 512-byte sector lengths
		 */
		if (decode_sector_number(&p, &be->be_f_offset) < 0)
			goto out_err;
		if (decode_sector_number(&p, &be->be_length) < 0)
			goto out_err;
		if (decode_sector_number(&p, &be->be_v_offset) < 0)
			goto out_err;
		be->be_state = be32_to_cpup(p++);
		if (verify_extent(be, &lv)) {
			dprintk("%s verify failed\n", __func__);
			goto out_err;
		}
		list_add_tail(&be->be_list, &extents);
	}
	if (lgr->range.offset + lgr->range.length !=
			lv.start << SECTOR_SHIFT) {
		dprintk("%s Final length mismatch\n", __func__);
		be = NULL;
		goto out_err;
	}
	if (lv.start < lv.cowread) {
		dprintk("%s Final uncovered COW extent\n", __func__);
		be = NULL;
		goto out_err;
	}
	/* Extents decoded properly, now try to merge them in to
	 * existing layout extents.
	 */
	list_for_each_entry_safe(be, save, &extents, be_list) {
		list_del(&be->be_list);

		status = ext_tree_insert(bl, be);
		if (status)
			goto out_free_list;
	}
	status = 0;
 out:
	__free_page(scratch);
	dprintk("%s returns %i\n", __func__, status);
	return status;

 out_err:
	nfs4_put_deviceid_node(be->be_device);
	kfree(be);
 out_free_list:
	while (!list_empty(&extents)) {
		be = list_first_entry(&extents, struct pnfs_block_extent,
				      be_list);
		list_del(&be->be_list);
		nfs4_put_deviceid_node(be->be_device);
		kfree(be);
	}
	goto out;
}

/* 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_return_range(struct pnfs_layout_hdr *lo,
		struct pnfs_layout_range *range)
{
	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
	sector_t offset = range->offset >> SECTOR_SHIFT, end;
	int err;

	if (range->offset % 8) {
		dprintk("%s: offset %lld not block size aligned\n",
			__func__, range->offset);
		return;
	}

	if (range->length != NFS4_MAX_UINT64) {
		if (range->length % 8) {
			dprintk("%s: length %lld not block size aligned\n",
				__func__, range->length);
			return;
		}

		end = offset + (range->length >> SECTOR_SHIFT);
	} else {
		end = round_down(NFS4_MAX_UINT64, PAGE_SIZE);
	}

	err = ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
}

static int
bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
{
	return ext_tree_prepare_commit(arg);
}

static void
bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
{
	ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
}

static int
bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
{
	dprintk("%s enter\n", __func__);

	if (server->pnfs_blksize == 0) {
		dprintk("%s Server did not return blksize\n", __func__);
		return -EINVAL;
	}
	if (server->pnfs_blksize > PAGE_SIZE) {
		printk(KERN_ERR "%s: pNFS blksize %d not supported.\n",
			__func__, server->pnfs_blksize);
		return -EINVAL;
	}

	return 0;
}

static bool
is_aligned_req(struct nfs_pageio_descriptor *pgio,
		struct nfs_page *req, unsigned int alignment)
{
	/*
	 * Always accept buffered writes, higher layers take care of the
	 * right alignment.
	 */
	if (pgio->pg_dreq == NULL)
		return true;

	if (!IS_ALIGNED(req->wb_offset, alignment))
		return false;

	if (IS_ALIGNED(req->wb_bytes, alignment))
		return true;

	if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
		/*
		 * If the write goes up to the inode size, just write
		 * the full page.  Data past the inode size is
		 * guaranteed to be zeroed by the higher level client
		 * code, and this behaviour is mandated by RFC 5663
		 * section 2.3.2.
		 */
		return true;
	}

	return false;
}

static void
bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
	if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
		nfs_pageio_reset_read_mds(pgio);
		return;
	}

	pnfs_generic_pg_init_read(pgio, req);
}

/*
 * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
 * of bytes (maximum @req->wb_bytes) that can be coalesced.
 */
static size_t
bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
		struct nfs_page *req)
{
	if (!is_aligned_req(pgio, req, SECTOR_SIZE))
		return 0;
	return pnfs_generic_pg_test(pgio, prev, req);
}

/*
 * Return the number of contiguous bytes for a given inode
 * starting at page frame idx.
 */
static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
{
	struct address_space *mapping = inode->i_mapping;
	pgoff_t end;

	/* Optimize common case that writes from 0 to end of file */
	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
	if (end != NFS_I(inode)->npages) {
		rcu_read_lock();
		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
		rcu_read_unlock();
	}

	if (!end)
		return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT);
	else
		return (end - idx) << PAGE_CACHE_SHIFT;
}

static void
bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
	u64 wb_size;

	if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
		nfs_pageio_reset_write_mds(pgio);
		return;
	}

	if (pgio->pg_dreq == NULL)
		wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
					      req->wb_index);
	else
		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);

	pnfs_generic_pg_init_write(pgio, req, wb_size);
}

/*
 * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
 * of bytes (maximum @req->wb_bytes) that can be coalesced.
 */
static size_t
bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
		 struct nfs_page *req)
{
	if (!is_aligned_req(pgio, req, PAGE_SIZE))
		return 0;
	return pnfs_generic_pg_test(pgio, prev, req);
}

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

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

static struct pnfs_layoutdriver_type blocklayout_type = {
	.id				= LAYOUT_BLOCK_VOLUME,
	.name				= "LAYOUT_BLOCK_VOLUME",
	.owner				= THIS_MODULE,
	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
					  PNFS_READ_WHOLE_PAGE,
	.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,
	.return_range			= bl_return_range,
	.prepare_layoutcommit		= bl_prepare_layoutcommit,
	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
	.set_layoutdriver		= bl_set_layoutdriver,
	.alloc_deviceid_node		= bl_alloc_deviceid_node,
	.free_deviceid_node		= bl_free_deviceid_node,
	.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);