aboutsummaryrefslogtreecommitdiff
path: root/fs/nfs/pagelist.c
blob: 932c6cc27a7664a29c9bf8d5883990c510e59b02 (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
/*
 * linux/fs/nfs/pagelist.c
 *
 * A set of helper functions for managing NFS read and write requests.
 * The main purpose of these routines is to provide support for the
 * coalescing of several requests into a single RPC call.
 *
 * Copyright 2000, 2001 (c) Trond Myklebust <trond.myklebust@fys.uio.no>
 *
 */

#include <linux/slab.h>
#include <linux/file.h>
#include <linux/sched.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
#include <linux/nfs_page.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/export.h>

#include "internal.h"
#include "pnfs.h"

#define NFSDBG_FACILITY		NFSDBG_PAGECACHE

static struct kmem_cache *nfs_page_cachep;
static const struct rpc_call_ops nfs_pgio_common_ops;

static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
{
	p->npages = pagecount;
	if (pagecount <= ARRAY_SIZE(p->page_array))
		p->pagevec = p->page_array;
	else {
		p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
		if (!p->pagevec)
			p->npages = 0;
	}
	return p->pagevec != NULL;
}

void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
		       struct nfs_pgio_header *hdr,
		       void (*release)(struct nfs_pgio_header *hdr))
{
	hdr->req = nfs_list_entry(desc->pg_list.next);
	hdr->inode = desc->pg_inode;
	hdr->cred = hdr->req->wb_context->cred;
	hdr->io_start = req_offset(hdr->req);
	hdr->good_bytes = desc->pg_count;
	hdr->dreq = desc->pg_dreq;
	hdr->layout_private = desc->pg_layout_private;
	hdr->release = release;
	hdr->completion_ops = desc->pg_completion_ops;
	if (hdr->completion_ops->init_hdr)
		hdr->completion_ops->init_hdr(hdr);
}
EXPORT_SYMBOL_GPL(nfs_pgheader_init);

void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
{
	spin_lock(&hdr->lock);
	if (pos < hdr->io_start + hdr->good_bytes) {
		set_bit(NFS_IOHDR_ERROR, &hdr->flags);
		clear_bit(NFS_IOHDR_EOF, &hdr->flags);
		hdr->good_bytes = pos - hdr->io_start;
		hdr->error = error;
	}
	spin_unlock(&hdr->lock);
}

static inline struct nfs_page *
nfs_page_alloc(void)
{
	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
	if (p)
		INIT_LIST_HEAD(&p->wb_list);
	return p;
}

static inline void
nfs_page_free(struct nfs_page *p)
{
	kmem_cache_free(nfs_page_cachep, p);
}

static void
nfs_iocounter_inc(struct nfs_io_counter *c)
{
	atomic_inc(&c->io_count);
}

static void
nfs_iocounter_dec(struct nfs_io_counter *c)
{
	if (atomic_dec_and_test(&c->io_count)) {
		clear_bit(NFS_IO_INPROGRESS, &c->flags);
		smp_mb__after_atomic();
		wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
	}
}

static int
__nfs_iocounter_wait(struct nfs_io_counter *c)
{
	wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS);
	DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS);
	int ret = 0;

	do {
		prepare_to_wait(wq, &q.wait, TASK_KILLABLE);
		set_bit(NFS_IO_INPROGRESS, &c->flags);
		if (atomic_read(&c->io_count) == 0)
			break;
		ret = nfs_wait_bit_killable(&q.key);
	} while (atomic_read(&c->io_count) != 0);
	finish_wait(wq, &q.wait);
	return ret;
}

/**
 * nfs_iocounter_wait - wait for i/o to complete
 * @c: nfs_io_counter to use
 *
 * returns -ERESTARTSYS if interrupted by a fatal signal.
 * Otherwise returns 0 once the io_count hits 0.
 */
int
nfs_iocounter_wait(struct nfs_io_counter *c)
{
	if (atomic_read(&c->io_count) == 0)
		return 0;
	return __nfs_iocounter_wait(c);
}

/*
 * nfs_page_group_lock - lock the head of the page group
 * @req - request in group that is to be locked
 * @nonblock - if true don't block waiting for lock
 *
 * this lock must be held if modifying the page group list
 *
 * return 0 on success, < 0 on error: -EDELAY if nonblocking or the
 * result from wait_on_bit_lock
 *
 * NOTE: calling with nonblock=false should always have set the
 *       lock bit (see fs/buffer.c and other uses of wait_on_bit_lock
 *       with TASK_UNINTERRUPTIBLE), so there is no need to check the result.
 */
int
nfs_page_group_lock(struct nfs_page *req, bool nonblock)
{
	struct nfs_page *head = req->wb_head;

	WARN_ON_ONCE(head != head->wb_head);

	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
		return 0;

	if (!nonblock)
		return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
				TASK_UNINTERRUPTIBLE);

	return -EAGAIN;
}

/*
 * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it
 * @req - a request in the group
 *
 * This is a blocking call to wait for the group lock to be cleared.
 */
void
nfs_page_group_lock_wait(struct nfs_page *req)
{
	struct nfs_page *head = req->wb_head;

	WARN_ON_ONCE(head != head->wb_head);

	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
		TASK_UNINTERRUPTIBLE);
}

/*
 * nfs_page_group_unlock - unlock the head of the page group
 * @req - request in group that is to be unlocked
 */
void
nfs_page_group_unlock(struct nfs_page *req)
{
	struct nfs_page *head = req->wb_head;

	WARN_ON_ONCE(head != head->wb_head);

	smp_mb__before_atomic();
	clear_bit(PG_HEADLOCK, &head->wb_flags);
	smp_mb__after_atomic();
	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
}

/*
 * nfs_page_group_sync_on_bit_locked
 *
 * must be called with page group lock held
 */
static bool
nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit)
{
	struct nfs_page *head = req->wb_head;
	struct nfs_page *tmp;

	WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_flags));
	WARN_ON_ONCE(test_and_set_bit(bit, &req->wb_flags));

	tmp = req->wb_this_page;
	while (tmp != req) {
		if (!test_bit(bit, &tmp->wb_flags))
			return false;
		tmp = tmp->wb_this_page;
	}

	/* true! reset all bits */
	tmp = req;
	do {
		clear_bit(bit, &tmp->wb_flags);
		tmp = tmp->wb_this_page;
	} while (tmp != req);

	return true;
}

/*
 * nfs_page_group_sync_on_bit - set bit on current request, but only
 *   return true if the bit is set for all requests in page group
 * @req - request in page group
 * @bit - PG_* bit that is used to sync page group
 */
bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
{
	bool ret;

	nfs_page_group_lock(req, false);
	ret = nfs_page_group_sync_on_bit_locked(req, bit);
	nfs_page_group_unlock(req);

	return ret;
}

/*
 * nfs_page_group_init - Initialize the page group linkage for @req
 * @req - a new nfs request
 * @prev - the previous request in page group, or NULL if @req is the first
 *         or only request in the group (the head).
 */
static inline void
nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
{
	WARN_ON_ONCE(prev == req);

	if (!prev) {
		/* a head request */
		req->wb_head = req;
		req->wb_this_page = req;
	} else {
		/* a subrequest */
		WARN_ON_ONCE(prev->wb_this_page != prev->wb_head);
		WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags));
		req->wb_head = prev->wb_head;
		req->wb_this_page = prev->wb_this_page;
		prev->wb_this_page = req;

		/* All subrequests take a ref on the head request until
		 * nfs_page_group_destroy is called */
		kref_get(&req->wb_head->wb_kref);

		/* grab extra ref if head request has extra ref from
		 * the write/commit path to handle handoff between write
		 * and commit lists */
		if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
			set_bit(PG_INODE_REF, &req->wb_flags);
			kref_get(&req->wb_kref);
		}
	}
}

/*
 * nfs_page_group_destroy - sync the destruction of page groups
 * @req - request that no longer needs the page group
 *
 * releases the page group reference from each member once all
 * members have called this function.
 */
static void
nfs_page_group_destroy(struct kref *kref)
{
	struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
	struct nfs_page *tmp, *next;

	/* subrequests must release the ref on the head request */
	if (req->wb_head != req)
		nfs_release_request(req->wb_head);

	if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN))
		return;

	tmp = req;
	do {
		next = tmp->wb_this_page;
		/* unlink and free */
		tmp->wb_this_page = tmp;
		tmp->wb_head = tmp;
		nfs_free_request(tmp);
		tmp = next;
	} while (tmp != req);
}

/**
 * nfs_create_request - Create an NFS read/write request.
 * @ctx: open context to use
 * @page: page to write
 * @last: last nfs request created for this page group or NULL if head
 * @offset: starting offset within the page for the write
 * @count: number of bytes to read/write
 *
 * The page must be locked by the caller. This makes sure we never
 * create two different requests for the same page.
 * User should ensure it is safe to sleep in this function.
 */
struct nfs_page *
nfs_create_request(struct nfs_open_context *ctx, struct page *page,
		   struct nfs_page *last, unsigned int offset,
		   unsigned int count)
{
	struct nfs_page		*req;
	struct nfs_lock_context *l_ctx;

	if (test_bit(NFS_CONTEXT_BAD, &ctx->flags))
		return ERR_PTR(-EBADF);
	/* try to allocate the request struct */
	req = nfs_page_alloc();
	if (req == NULL)
		return ERR_PTR(-ENOMEM);

	/* get lock context early so we can deal with alloc failures */
	l_ctx = nfs_get_lock_context(ctx);
	if (IS_ERR(l_ctx)) {
		nfs_page_free(req);
		return ERR_CAST(l_ctx);
	}
	req->wb_lock_context = l_ctx;
	nfs_iocounter_inc(&l_ctx->io_count);

	/* Initialize the request struct. Initially, we assume a
	 * long write-back delay. This will be adjusted in
	 * update_nfs_request below if the region is not locked. */
	req->wb_page    = page;
	req->wb_index	= page_file_index(page);
	page_cache_get(page);
	req->wb_offset  = offset;
	req->wb_pgbase	= offset;
	req->wb_bytes   = count;
	req->wb_context = get_nfs_open_context(ctx);
	kref_init(&req->wb_kref);
	nfs_page_group_init(req, last);
	return req;
}

/**
 * nfs_unlock_request - Unlock request and wake up sleepers.
 * @req:
 */
void nfs_unlock_request(struct nfs_page *req)
{
	if (!NFS_WBACK_BUSY(req)) {
		printk(KERN_ERR "NFS: Invalid unlock attempted\n");
		BUG();
	}
	smp_mb__before_atomic();
	clear_bit(PG_BUSY, &req->wb_flags);
	smp_mb__after_atomic();
	wake_up_bit(&req->wb_flags, PG_BUSY);
}

/**
 * nfs_unlock_and_release_request - Unlock request and release the nfs_page
 * @req:
 */
void nfs_unlock_and_release_request(struct nfs_page *req)
{
	nfs_unlock_request(req);
	nfs_release_request(req);
}

/*
 * nfs_clear_request - Free up all resources allocated to the request
 * @req:
 *
 * Release page and open context resources associated with a read/write
 * request after it has completed.
 */
static void nfs_clear_request(struct nfs_page *req)
{
	struct page *page = req->wb_page;
	struct nfs_open_context *ctx = req->wb_context;
	struct nfs_lock_context *l_ctx = req->wb_lock_context;

	if (page != NULL) {
		page_cache_release(page);
		req->wb_page = NULL;
	}
	if (l_ctx != NULL) {
		nfs_iocounter_dec(&l_ctx->io_count);
		nfs_put_lock_context(l_ctx);
		req->wb_lock_context = NULL;
	}
	if (ctx != NULL) {
		put_nfs_open_context(ctx);
		req->wb_context = NULL;
	}
}

/**
 * nfs_release_request - Release the count on an NFS read/write request
 * @req: request to release
 *
 * Note: Should never be called with the spinlock held!
 */
void nfs_free_request(struct nfs_page *req)
{
	WARN_ON_ONCE(req->wb_this_page != req);

	/* extra debug: make sure no sync bits are still set */
	WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags));
	WARN_ON_ONCE(test_bit(PG_UNLOCKPAGE, &req->wb_flags));
	WARN_ON_ONCE(test_bit(PG_UPTODATE, &req->wb_flags));
	WARN_ON_ONCE(test_bit(PG_WB_END, &req->wb_flags));
	WARN_ON_ONCE(test_bit(PG_REMOVE, &req->wb_flags));

	/* Release struct file and open context */
	nfs_clear_request(req);
	nfs_page_free(req);
}

void nfs_release_request(struct nfs_page *req)
{
	kref_put(&req->wb_kref, nfs_page_group_destroy);
}

/**
 * nfs_wait_on_request - Wait for a request to complete.
 * @req: request to wait upon.
 *
 * Interruptible by fatal signals only.
 * The user is responsible for holding a count on the request.
 */
int
nfs_wait_on_request(struct nfs_page *req)
{
	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
			      TASK_UNINTERRUPTIBLE);
}

/*
 * nfs_generic_pg_test - determine if requests can be coalesced
 * @desc: pointer to descriptor
 * @prev: previous request in desc, or NULL
 * @req: this request
 *
 * Returns zero if @req can be coalesced into @desc, otherwise it returns
 * the size of the request.
 */
size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
			   struct nfs_page *prev, struct nfs_page *req)
{
	if (desc->pg_count > desc->pg_bsize) {
		/* should never happen */
		WARN_ON_ONCE(1);
		return 0;
	}

	return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
}
EXPORT_SYMBOL_GPL(nfs_generic_pg_test);

struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops)
{
	struct nfs_pgio_header *hdr = ops->rw_alloc_header();

	if (hdr) {
		INIT_LIST_HEAD(&hdr->pages);
		spin_lock_init(&hdr->lock);
		hdr->rw_ops = ops;
	}
	return hdr;
}
EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc);

/*
 * nfs_pgio_header_free - Free a read or write header
 * @hdr: The header to free
 */
void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
{
	hdr->rw_ops->rw_free_header(hdr);
}
EXPORT_SYMBOL_GPL(nfs_pgio_header_free);

/**
 * nfs_pgio_data_destroy - make @hdr suitable for reuse
 *
 * Frees memory and releases refs from nfs_generic_pgio, so that it may
 * be called again.
 *
 * @hdr: A header that has had nfs_generic_pgio called
 */
void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
{
	put_nfs_open_context(hdr->args.context);
	if (hdr->page_array.pagevec != hdr->page_array.page_array)
		kfree(hdr->page_array.pagevec);
}
EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy);

/**
 * nfs_pgio_rpcsetup - Set up arguments for a pageio call
 * @hdr: The pageio hdr
 * @count: Number of bytes to read
 * @offset: Initial offset
 * @how: How to commit data (writes only)
 * @cinfo: Commit information for the call (writes only)
 */
static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
			      unsigned int count, unsigned int offset,
			      int how, struct nfs_commit_info *cinfo)
{
	struct nfs_page *req = hdr->req;

	/* Set up the RPC argument and reply structs
	 * NB: take care not to mess about with hdr->commit et al. */

	hdr->args.fh     = NFS_FH(hdr->inode);
	hdr->args.offset = req_offset(req) + offset;
	/* pnfs_set_layoutcommit needs this */
	hdr->mds_offset = hdr->args.offset;
	hdr->args.pgbase = req->wb_pgbase + offset;
	hdr->args.pages  = hdr->page_array.pagevec;
	hdr->args.count  = count;
	hdr->args.context = get_nfs_open_context(req->wb_context);
	hdr->args.lock_context = req->wb_lock_context;
	hdr->args.stable  = NFS_UNSTABLE;
	switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
	case 0:
		break;
	case FLUSH_COND_STABLE:
		if (nfs_reqs_to_commit(cinfo))
			break;
	default:
		hdr->args.stable = NFS_FILE_SYNC;
	}

	hdr->res.fattr   = &hdr->fattr;
	hdr->res.count   = count;
	hdr->res.eof     = 0;
	hdr->res.verf    = &hdr->verf;
	nfs_fattr_init(&hdr->fattr);
}

/**
 * nfs_pgio_prepare - Prepare pageio hdr to go over the wire
 * @task: The current task
 * @calldata: pageio header to prepare
 */
static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
{
	struct nfs_pgio_header *hdr = calldata;
	int err;
	err = NFS_PROTO(hdr->inode)->pgio_rpc_prepare(task, hdr);
	if (err)
		rpc_exit(task, err);
}

int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
		      const struct rpc_call_ops *call_ops, int how, int flags)
{
	struct rpc_task *task;
	struct rpc_message msg = {
		.rpc_argp = &hdr->args,
		.rpc_resp = &hdr->res,
		.rpc_cred = hdr->cred,
	};
	struct rpc_task_setup task_setup_data = {
		.rpc_client = clnt,
		.task = &hdr->task,
		.rpc_message = &msg,
		.callback_ops = call_ops,
		.callback_data = hdr,
		.workqueue = nfsiod_workqueue,
		.flags = RPC_TASK_ASYNC | flags,
	};
	int ret = 0;

	hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how);

	dprintk("NFS: %5u initiated pgio call "
		"(req %s/%llu, %u bytes @ offset %llu)\n",
		hdr->task.tk_pid,
		hdr->inode->i_sb->s_id,
		(unsigned long long)NFS_FILEID(hdr->inode),
		hdr->args.count,
		(unsigned long long)hdr->args.offset);

	task = rpc_run_task(&task_setup_data);
	if (IS_ERR(task)) {
		ret = PTR_ERR(task);
		goto out;
	}
	if (how & FLUSH_SYNC) {
		ret = rpc_wait_for_completion_task(task);
		if (ret == 0)
			ret = task->tk_status;
	}
	rpc_put_task(task);
out:
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_initiate_pgio);

/**
 * nfs_pgio_error - Clean up from a pageio error
 * @desc: IO descriptor
 * @hdr: pageio header
 */
static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
			  struct nfs_pgio_header *hdr)
{
	set_bit(NFS_IOHDR_REDO, &hdr->flags);
	nfs_pgio_data_destroy(hdr);
	hdr->completion_ops->completion(hdr);
	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
	return -ENOMEM;
}

/**
 * nfs_pgio_release - Release pageio data
 * @calldata: The pageio header to release
 */
static void nfs_pgio_release(void *calldata)
{
	struct nfs_pgio_header *hdr = calldata;
	if (hdr->rw_ops->rw_release)
		hdr->rw_ops->rw_release(hdr);
	nfs_pgio_data_destroy(hdr);
	hdr->completion_ops->completion(hdr);
}

/**
 * nfs_pageio_init - initialise a page io descriptor
 * @desc: pointer to descriptor
 * @inode: pointer to inode
 * @doio: pointer to io function
 * @bsize: io block size
 * @io_flags: extra parameters for the io function
 */
void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
		     struct inode *inode,
		     const struct nfs_pageio_ops *pg_ops,
		     const struct nfs_pgio_completion_ops *compl_ops,
		     const struct nfs_rw_ops *rw_ops,
		     size_t bsize,
		     int io_flags)
{
	INIT_LIST_HEAD(&desc->pg_list);
	desc->pg_bytes_written = 0;
	desc->pg_count = 0;
	desc->pg_bsize = bsize;
	desc->pg_base = 0;
	desc->pg_moreio = 0;
	desc->pg_recoalesce = 0;
	desc->pg_inode = inode;
	desc->pg_ops = pg_ops;
	desc->pg_completion_ops = compl_ops;
	desc->pg_rw_ops = rw_ops;
	desc->pg_ioflags = io_flags;
	desc->pg_error = 0;
	desc->pg_lseg = NULL;
	desc->pg_dreq = NULL;
	desc->pg_layout_private = NULL;
}
EXPORT_SYMBOL_GPL(nfs_pageio_init);

/**
 * nfs_pgio_result - Basic pageio error handling
 * @task: The task that ran
 * @calldata: Pageio header to check
 */
static void nfs_pgio_result(struct rpc_task *task, void *calldata)
{
	struct nfs_pgio_header *hdr = calldata;
	struct inode *inode = hdr->inode;

	dprintk("NFS: %s: %5u, (status %d)\n", __func__,
		task->tk_pid, task->tk_status);

	if (hdr->rw_ops->rw_done(task, hdr, inode) != 0)
		return;
	if (task->tk_status < 0)
		nfs_set_pgio_error(hdr, task->tk_status, hdr->args.offset);
	else
		hdr->rw_ops->rw_result(task, hdr);
}

/*
 * Create an RPC task for the given read or write request and kick it.
 * The page must have been locked by the caller.
 *
 * It may happen that the page we're passed is not marked dirty.
 * This is the case if nfs_updatepage detects a conflicting request
 * that has been written but not committed.
 */
int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
		     struct nfs_pgio_header *hdr)
{
	struct nfs_page		*req;
	struct page		**pages,
				*last_page;
	struct list_head *head = &desc->pg_list;
	struct nfs_commit_info cinfo;
	unsigned int pagecount, pageused;

	pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count);
	if (!nfs_pgarray_set(&hdr->page_array, pagecount))
		return nfs_pgio_error(desc, hdr);

	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
	pages = hdr->page_array.pagevec;
	last_page = NULL;
	pageused = 0;
	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_list_add_request(req, &hdr->pages);

		if (WARN_ON_ONCE(pageused >= pagecount))
			return nfs_pgio_error(desc, hdr);

		if (!last_page || last_page != req->wb_page) {
			*pages++ = last_page = req->wb_page;
			pageused++;
		}
	}
	if (WARN_ON_ONCE(pageused != pagecount))
		return nfs_pgio_error(desc, hdr);

	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
		desc->pg_ioflags &= ~FLUSH_COND_STABLE;

	/* Set up the argument struct */
	nfs_pgio_rpcsetup(hdr, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
	desc->pg_rpc_callops = &nfs_pgio_common_ops;
	return 0;
}
EXPORT_SYMBOL_GPL(nfs_generic_pgio);

static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
{
	struct nfs_pgio_header *hdr;
	int ret;

	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
	if (!hdr) {
		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
		return -ENOMEM;
	}
	nfs_pgheader_init(desc, hdr, nfs_pgio_header_free);
	ret = nfs_generic_pgio(desc, hdr);
	if (ret == 0)
		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
					hdr, desc->pg_rpc_callops,
					desc->pg_ioflags, 0);
	return ret;
}

static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
		const struct nfs_open_context *ctx2)
{
	return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state;
}

static bool nfs_match_lock_context(const struct nfs_lock_context *l1,
		const struct nfs_lock_context *l2)
{
	return l1->lockowner.l_owner == l2->lockowner.l_owner
		&& l1->lockowner.l_pid == l2->lockowner.l_pid;
}

/**
 * nfs_can_coalesce_requests - test two requests for compatibility
 * @prev: pointer to nfs_page
 * @req: pointer to nfs_page
 *
 * The nfs_page structures 'prev' and 'req' are compared to ensure that the
 * page data area they describe is contiguous, and that their RPC
 * credentials, NFSv4 open state, and lockowners are the same.
 *
 * Return 'true' if this is the case, else return 'false'.
 */
static bool nfs_can_coalesce_requests(struct nfs_page *prev,
				      struct nfs_page *req,
				      struct nfs_pageio_descriptor *pgio)
{
	size_t size;

	if (prev) {
		if (!nfs_match_open_context(req->wb_context, prev->wb_context))
			return false;
		if (req->wb_context->dentry->d_inode->i_flock != NULL &&
		    !nfs_match_lock_context(req->wb_lock_context,
					    prev->wb_lock_context))
			return false;
		if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
			return false;
		if (req->wb_page == prev->wb_page) {
			if (req->wb_pgbase != prev->wb_pgbase + prev->wb_bytes)
				return false;
		} else {
			if (req->wb_pgbase != 0 ||
			    prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
				return false;
		}
	}
	size = pgio->pg_ops->pg_test(pgio, prev, req);
	WARN_ON_ONCE(size > req->wb_bytes);
	if (size && size < req->wb_bytes)
		req->wb_bytes = size;
	return size > 0;
}

/**
 * nfs_pageio_do_add_request - Attempt to coalesce a request into a page list.
 * @desc: destination io descriptor
 * @req: request
 *
 * Returns true if the request 'req' was successfully coalesced into the
 * existing list of pages 'desc'.
 */
static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
				     struct nfs_page *req)
{
	struct nfs_page *prev = NULL;
	if (desc->pg_count != 0) {
		prev = nfs_list_entry(desc->pg_list.prev);
	} else {
		if (desc->pg_ops->pg_init)
			desc->pg_ops->pg_init(desc, req);
		desc->pg_base = req->wb_pgbase;
	}
	if (!nfs_can_coalesce_requests(prev, req, desc))
		return 0;
	nfs_list_remove_request(req);
	nfs_list_add_request(req, &desc->pg_list);
	desc->pg_count += req->wb_bytes;
	return 1;
}

/*
 * Helper for nfs_pageio_add_request and nfs_pageio_complete
 */
static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
{
	if (!list_empty(&desc->pg_list)) {
		int error = desc->pg_ops->pg_doio(desc);
		if (error < 0)
			desc->pg_error = error;
		else
			desc->pg_bytes_written += desc->pg_count;
	}
	if (list_empty(&desc->pg_list)) {
		desc->pg_count = 0;
		desc->pg_base = 0;
	}
}

/**
 * nfs_pageio_add_request - Attempt to coalesce a request into a page list.
 * @desc: destination io descriptor
 * @req: request
 *
 * This may split a request into subrequests which are all part of the
 * same page group.
 *
 * Returns true if the request 'req' was successfully coalesced into the
 * existing list of pages 'desc'.
 */
static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
			   struct nfs_page *req)
{
	struct nfs_page *subreq;
	unsigned int bytes_left = 0;
	unsigned int offset, pgbase;

	nfs_page_group_lock(req, false);

	subreq = req;
	bytes_left = subreq->wb_bytes;
	offset = subreq->wb_offset;
	pgbase = subreq->wb_pgbase;

	do {
		if (!nfs_pageio_do_add_request(desc, subreq)) {
			/* make sure pg_test call(s) did nothing */
			WARN_ON_ONCE(subreq->wb_bytes != bytes_left);
			WARN_ON_ONCE(subreq->wb_offset != offset);
			WARN_ON_ONCE(subreq->wb_pgbase != pgbase);

			nfs_page_group_unlock(req);
			desc->pg_moreio = 1;
			nfs_pageio_doio(desc);
			if (desc->pg_error < 0)
				return 0;
			if (desc->pg_recoalesce)
				return 0;
			/* retry add_request for this subreq */
			nfs_page_group_lock(req, false);
			continue;
		}

		/* check for buggy pg_test call(s) */
		WARN_ON_ONCE(subreq->wb_bytes + subreq->wb_pgbase > PAGE_SIZE);
		WARN_ON_ONCE(subreq->wb_bytes > bytes_left);
		WARN_ON_ONCE(subreq->wb_bytes == 0);

		bytes_left -= subreq->wb_bytes;
		offset += subreq->wb_bytes;
		pgbase += subreq->wb_bytes;

		if (bytes_left) {
			subreq = nfs_create_request(req->wb_context,
					req->wb_page,
					subreq, pgbase, bytes_left);
			if (IS_ERR(subreq))
				goto err_ptr;
			nfs_lock_request(subreq);
			subreq->wb_offset  = offset;
			subreq->wb_index = req->wb_index;
		}
	} while (bytes_left > 0);

	nfs_page_group_unlock(req);
	return 1;
err_ptr:
	desc->pg_error = PTR_ERR(subreq);
	nfs_page_group_unlock(req);
	return 0;
}

static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
{
	LIST_HEAD(head);

	do {
		list_splice_init(&desc->pg_list, &head);
		desc->pg_bytes_written -= desc->pg_count;
		desc->pg_count = 0;
		desc->pg_base = 0;
		desc->pg_recoalesce = 0;
		desc->pg_moreio = 0;

		while (!list_empty(&head)) {
			struct nfs_page *req;

			req = list_first_entry(&head, struct nfs_page, wb_list);
			nfs_list_remove_request(req);
			if (__nfs_pageio_add_request(desc, req))
				continue;
			if (desc->pg_error < 0)
				return 0;
			break;
		}
	} while (desc->pg_recoalesce);
	return 1;
}

int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
		struct nfs_page *req)
{
	int ret;

	do {
		ret = __nfs_pageio_add_request(desc, req);
		if (ret)
			break;
		if (desc->pg_error < 0)
			break;
		ret = nfs_do_recoalesce(desc);
	} while (ret);
	return ret;
}

/*
 * nfs_pageio_resend - Transfer requests to new descriptor and resend
 * @hdr - the pgio header to move request from
 * @desc - the pageio descriptor to add requests to
 *
 * Try to move each request (nfs_page) from @hdr to @desc then attempt
 * to send them.
 *
 * Returns 0 on success and < 0 on error.
 */
int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
		      struct nfs_pgio_header *hdr)
{
	LIST_HEAD(failed);

	desc->pg_dreq = hdr->dreq;
	while (!list_empty(&hdr->pages)) {
		struct nfs_page *req = nfs_list_entry(hdr->pages.next);

		nfs_list_remove_request(req);
		if (!nfs_pageio_add_request(desc, req))
			nfs_list_add_request(req, &failed);
	}
	nfs_pageio_complete(desc);
	if (!list_empty(&failed)) {
		list_move(&failed, &hdr->pages);
		return -EIO;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(nfs_pageio_resend);

/**
 * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
 * @desc: pointer to io descriptor
 */
void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
{
	for (;;) {
		nfs_pageio_doio(desc);
		if (!desc->pg_recoalesce)
			break;
		if (!nfs_do_recoalesce(desc))
			break;
	}
}

/**
 * nfs_pageio_cond_complete - Conditional I/O completion
 * @desc: pointer to io descriptor
 * @index: page index
 *
 * It is important to ensure that processes don't try to take locks
 * on non-contiguous ranges of pages as that might deadlock. This
 * function should be called before attempting to wait on a locked
 * nfs_page. It will complete the I/O if the page index 'index'
 * is not contiguous with the existing list of pages in 'desc'.
 */
void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
{
	if (!list_empty(&desc->pg_list)) {
		struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev);
		if (index != prev->wb_index + 1)
			nfs_pageio_complete(desc);
	}
}

int __init nfs_init_nfspagecache(void)
{
	nfs_page_cachep = kmem_cache_create("nfs_page",
					    sizeof(struct nfs_page),
					    0, SLAB_HWCACHE_ALIGN,
					    NULL);
	if (nfs_page_cachep == NULL)
		return -ENOMEM;

	return 0;
}

void nfs_destroy_nfspagecache(void)
{
	kmem_cache_destroy(nfs_page_cachep);
}

static const struct rpc_call_ops nfs_pgio_common_ops = {
	.rpc_call_prepare = nfs_pgio_prepare,
	.rpc_call_done = nfs_pgio_result,
	.rpc_release = nfs_pgio_release,
};

const struct nfs_pageio_ops nfs_pgio_rw_ops = {
	.pg_test = nfs_generic_pg_test,
	.pg_doio = nfs_generic_pg_pgios,
};