summaryrefslogtreecommitdiffstats
path: root/fs/nfs/direct.c
blob: 2c0e08f4cf712e439e0790e8be35607774a8f557 (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
/*
 * linux/fs/nfs/direct.c
 *
 * Copyright (C) 2003 by Chuck Lever <cel@netapp.com>
 *
 * High-performance uncached I/O for the Linux NFS client
 *
 * There are important applications whose performance or correctness
 * depends on uncached access to file data.  Database clusters
 * (multiple copies of the same instance running on separate hosts)
 * implement their own cache coherency protocol that subsumes file
 * system cache protocols.  Applications that process datasets
 * considerably larger than the client's memory do not always benefit
 * from a local cache.  A streaming video server, for instance, has no
 * need to cache the contents of a file.
 *
 * When an application requests uncached I/O, all read and write requests
 * are made directly to the server; data stored or fetched via these
 * requests is not cached in the Linux page cache.  The client does not
 * correct unaligned requests from applications.  All requested bytes are
 * held on permanent storage before a direct write system call returns to
 * an application.
 *
 * Solaris implements an uncached I/O facility called directio() that
 * is used for backups and sequential I/O to very large files.  Solaris
 * also supports uncaching whole NFS partitions with "-o forcedirectio,"
 * an undocumented mount option.
 *
 * Designed by Jeff Kimmel, Chuck Lever, and Trond Myklebust, with
 * help from Andrew Morton.
 *
 * 18 Dec 2001	Initial implementation for 2.4  --cel
 * 08 Jul 2002	Version for 2.4.19, with bug fixes --trondmy
 * 08 Jun 2003	Port to 2.5 APIs  --cel
 * 31 Mar 2004	Handle direct I/O without VFS support  --cel
 * 15 Sep 2004	Parallel async reads  --cel
 * 04 May 2005	support O_DIRECT with aio  --cel
 *
 */

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/kref.h>
#include <linux/slab.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/module.h>

#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/sunrpc/clnt.h>

#include <asm/uaccess.h>
#include <linux/atomic.h>

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

#define NFSDBG_FACILITY		NFSDBG_VFS

static struct kmem_cache *nfs_direct_cachep;

/*
 * This represents a set of asynchronous requests that we're waiting on
 */
struct nfs_direct_req {
	struct kref		kref;		/* release manager */

	/* I/O parameters */
	struct nfs_open_context	*ctx;		/* file open context info */
	struct nfs_lock_context *l_ctx;		/* Lock context info */
	struct kiocb *		iocb;		/* controlling i/o request */
	struct inode *		inode;		/* target file of i/o */

	/* completion state */
	atomic_t		io_count;	/* i/os we're waiting for */
	spinlock_t		lock;		/* protect completion state */
	ssize_t			count,		/* bytes actually processed */
				bytes_left,	/* bytes left to be sent */
				error;		/* any reported error */
	struct completion	completion;	/* wait for i/o completion */

	/* commit state */
	struct nfs_mds_commit_info mds_cinfo;	/* Storage for cinfo */
	struct pnfs_ds_commit_info ds_cinfo;	/* Storage for cinfo */
	struct work_struct	work;
	int			flags;
#define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
#define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
	struct nfs_writeverf	verf;		/* unstable write verifier */
};

static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops;
static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode);
static void nfs_direct_write_schedule_work(struct work_struct *work);

static inline void get_dreq(struct nfs_direct_req *dreq)
{
	atomic_inc(&dreq->io_count);
}

static inline int put_dreq(struct nfs_direct_req *dreq)
{
	return atomic_dec_and_test(&dreq->io_count);
}

/**
 * nfs_direct_IO - NFS address space operation for direct I/O
 * @rw: direction (read or write)
 * @iocb: target I/O control block
 * @iov: array of vectors that define I/O buffer
 * @pos: offset in file to begin the operation
 * @nr_segs: size of iovec array
 *
 * The presence of this routine in the address space ops vector means
 * the NFS client supports direct I/O. However, for most direct IO, we
 * shunt off direct read and write requests before the VFS gets them,
 * so this method is only ever called for swap.
 */
ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
{
#ifndef CONFIG_NFS_SWAP
	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
			iocb->ki_filp, (long long) pos, nr_segs);

	return -EINVAL;
#else
	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);

	if (rw == READ || rw == KERNEL_READ)
		return nfs_file_direct_read(iocb, iov, nr_segs, pos,
				rw == READ ? true : false);
	return nfs_file_direct_write(iocb, iov, nr_segs, pos,
				rw == WRITE ? true : false);
#endif /* CONFIG_NFS_SWAP */
}

static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
{
	unsigned int i;
	for (i = 0; i < npages; i++)
		page_cache_release(pages[i]);
}

void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
			      struct nfs_direct_req *dreq)
{
	cinfo->lock = &dreq->lock;
	cinfo->mds = &dreq->mds_cinfo;
	cinfo->ds = &dreq->ds_cinfo;
	cinfo->dreq = dreq;
	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
}

static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
{
	struct nfs_direct_req *dreq;

	dreq = kmem_cache_zalloc(nfs_direct_cachep, GFP_KERNEL);
	if (!dreq)
		return NULL;

	kref_init(&dreq->kref);
	kref_get(&dreq->kref);
	init_completion(&dreq->completion);
	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
	spin_lock_init(&dreq->lock);

	return dreq;
}

static void nfs_direct_req_free(struct kref *kref)
{
	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);

	if (dreq->l_ctx != NULL)
		nfs_put_lock_context(dreq->l_ctx);
	if (dreq->ctx != NULL)
		put_nfs_open_context(dreq->ctx);
	kmem_cache_free(nfs_direct_cachep, dreq);
}

static void nfs_direct_req_release(struct nfs_direct_req *dreq)
{
	kref_put(&dreq->kref, nfs_direct_req_free);
}

ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
{
	return dreq->bytes_left;
}
EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);

/*
 * Collects and returns the final error value/byte-count.
 */
static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
{
	ssize_t result = -EIOCBQUEUED;

	/* Async requests don't wait here */
	if (dreq->iocb)
		goto out;

	result = wait_for_completion_killable(&dreq->completion);

	if (!result)
		result = dreq->error;
	if (!result)
		result = dreq->count;

out:
	return (ssize_t) result;
}

/*
 * Synchronous I/O uses a stack-allocated iocb.  Thus we can't trust
 * the iocb is still valid here if this is a synchronous request.
 */
static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
{
	struct inode *inode = dreq->inode;

	if (dreq->iocb && write) {
		loff_t pos = dreq->iocb->ki_pos + dreq->count;

		spin_lock(&inode->i_lock);
		if (i_size_read(inode) < pos)
			i_size_write(inode, pos);
		spin_unlock(&inode->i_lock);
	}

	if (write)
		nfs_zap_mapping(inode, inode->i_mapping);

	inode_dio_done(inode);

	if (dreq->iocb) {
		long res = (long) dreq->error;
		if (!res)
			res = (long) dreq->count;
		aio_complete(dreq->iocb, res, 0);
	}

	complete_all(&dreq->completion);

	nfs_direct_req_release(dreq);
}

static void nfs_direct_readpage_release(struct nfs_page *req)
{
	dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
		req->wb_context->dentry->d_inode->i_sb->s_id,
		(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
		req->wb_bytes,
		(long long)req_offset(req));
	nfs_release_request(req);
}

static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
{
	unsigned long bytes = 0;
	struct nfs_direct_req *dreq = hdr->dreq;

	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
		goto out_put;

	spin_lock(&dreq->lock);
	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
		dreq->error = hdr->error;
	else
		dreq->count += hdr->good_bytes;
	spin_unlock(&dreq->lock);

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

		if (!PageCompound(page) && bytes < hdr->good_bytes)
			set_page_dirty(page);
		bytes += req->wb_bytes;
		nfs_list_remove_request(req);
		nfs_direct_readpage_release(req);
	}
out_put:
	if (put_dreq(dreq))
		nfs_direct_complete(dreq, false);
	hdr->release(hdr);
}

static void nfs_read_sync_pgio_error(struct list_head *head)
{
	struct nfs_page *req;

	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_release_request(req);
	}
}

static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr)
{
	get_dreq(hdr->dreq);
}

static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
	.error_cleanup = nfs_read_sync_pgio_error,
	.init_hdr = nfs_direct_pgio_init,
	.completion = nfs_direct_read_completion,
};

/*
 * For each rsize'd chunk of the user's buffer, dispatch an NFS READ
 * operation.  If nfs_readdata_alloc() or get_user_pages() fails,
 * bail and stop sending more reads.  Read length accounting is
 * handled automatically by nfs_direct_read_result().  Otherwise, if
 * no requests have been sent, just return an error.
 */
static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
						const struct iovec *iov,
						loff_t pos, bool uio)
{
	struct nfs_direct_req *dreq = desc->pg_dreq;
	struct nfs_open_context *ctx = dreq->ctx;
	struct inode *inode = ctx->dentry->d_inode;
	unsigned long user_addr = (unsigned long)iov->iov_base;
	size_t count = iov->iov_len;
	size_t rsize = NFS_SERVER(inode)->rsize;
	unsigned int pgbase;
	int result;
	ssize_t started = 0;
	struct page **pagevec = NULL;
	unsigned int npages;

	do {
		size_t bytes;
		int i;

		pgbase = user_addr & ~PAGE_MASK;
		bytes = min(max_t(size_t, rsize, PAGE_SIZE), count);

		result = -ENOMEM;
		npages = nfs_page_array_len(pgbase, bytes);
		if (!pagevec)
			pagevec = kmalloc(npages * sizeof(struct page *),
					  GFP_KERNEL);
		if (!pagevec)
			break;
		if (uio) {
			down_read(&current->mm->mmap_sem);
			result = get_user_pages(current, current->mm, user_addr,
					npages, 1, 0, pagevec, NULL);
			up_read(&current->mm->mmap_sem);
			if (result < 0)
				break;
		} else {
			WARN_ON(npages != 1);
			result = get_kernel_page(user_addr, 1, pagevec);
			if (WARN_ON(result != 1))
				break;
		}

		if ((unsigned)result < npages) {
			bytes = result * PAGE_SIZE;
			if (bytes <= pgbase) {
				nfs_direct_release_pages(pagevec, result);
				break;
			}
			bytes -= pgbase;
			npages = result;
		}

		for (i = 0; i < npages; i++) {
			struct nfs_page *req;
			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
			/* XXX do we need to do the eof zeroing found in async_filler? */
			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
						 pgbase, req_len);
			if (IS_ERR(req)) {
				result = PTR_ERR(req);
				break;
			}
			req->wb_index = pos >> PAGE_SHIFT;
			req->wb_offset = pos & ~PAGE_MASK;
			if (!nfs_pageio_add_request(desc, req)) {
				result = desc->pg_error;
				nfs_release_request(req);
				break;
			}
			pgbase = 0;
			bytes -= req_len;
			started += req_len;
			user_addr += req_len;
			pos += req_len;
			count -= req_len;
			dreq->bytes_left -= req_len;
		}
		/* The nfs_page now hold references to these pages */
		nfs_direct_release_pages(pagevec, npages);
	} while (count != 0 && result >= 0);

	kfree(pagevec);

	if (started)
		return started;
	return result < 0 ? (ssize_t) result : -EFAULT;
}

static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
					      const struct iovec *iov,
					      unsigned long nr_segs,
					      loff_t pos, bool uio)
{
	struct nfs_pageio_descriptor desc;
	struct inode *inode = dreq->inode;
	ssize_t result = -EINVAL;
	size_t requested_bytes = 0;
	unsigned long seg;

	nfs_pageio_init_read(&desc, dreq->inode, false,
			     &nfs_direct_read_completion_ops);
	get_dreq(dreq);
	desc.pg_dreq = dreq;
	atomic_inc(&inode->i_dio_count);

	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *vec = &iov[seg];
		result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
		if (result < 0)
			break;
		requested_bytes += result;
		if ((size_t)result < vec->iov_len)
			break;
		pos += vec->iov_len;
	}

	nfs_pageio_complete(&desc);

	/*
	 * If no bytes were started, return the error, and let the
	 * generic layer handle the completion.
	 */
	if (requested_bytes == 0) {
		inode_dio_done(inode);
		nfs_direct_req_release(dreq);
		return result < 0 ? result : -EIO;
	}

	if (put_dreq(dreq))
		nfs_direct_complete(dreq, false);
	return 0;
}

/**
 * nfs_file_direct_read - file direct read operation for NFS files
 * @iocb: target I/O control block
 * @iov: vector of user buffers into which to read data
 * @nr_segs: size of iov vector
 * @pos: byte offset in file where reading starts
 *
 * We use this function for direct reads instead of calling
 * generic_file_aio_read() in order to avoid gfar's check to see if
 * the request starts before the end of the file.  For that check
 * to work, we must generate a GETATTR before each direct read, and
 * even then there is a window between the GETATTR and the subsequent
 * READ where the file size could change.  Our preference is simply
 * to do all reads the application wants, and the server will take
 * care of managing the end of file boundary.
 *
 * This function also eliminates unnecessarily updating the file's
 * atime locally, as the NFS server sets the file's atime, and this
 * client must read the updated atime from the server back into its
 * cache.
 */
ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos, bool uio)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	struct nfs_direct_req *dreq;
	struct nfs_lock_context *l_ctx;
	ssize_t result = -EINVAL;
	size_t count;

	count = iov_length(iov, nr_segs);
	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);

	dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
		file, count, (long long) pos);

	result = 0;
	if (!count)
		goto out;

	mutex_lock(&inode->i_mutex);
	result = nfs_sync_mapping(mapping);
	if (result)
		goto out_unlock;

	task_io_account_read(count);

	result = -ENOMEM;
	dreq = nfs_direct_req_alloc();
	if (dreq == NULL)
		goto out_unlock;

	dreq->inode = inode;
	dreq->bytes_left = iov_length(iov, nr_segs);
	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
	l_ctx = nfs_get_lock_context(dreq->ctx);
	if (IS_ERR(l_ctx)) {
		result = PTR_ERR(l_ctx);
		goto out_release;
	}
	dreq->l_ctx = l_ctx;
	if (!is_sync_kiocb(iocb))
		dreq->iocb = iocb;

	NFS_I(inode)->read_io += iov_length(iov, nr_segs);
	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);

	mutex_unlock(&inode->i_mutex);

	if (!result) {
		result = nfs_direct_wait(dreq);
		if (result > 0)
			iocb->ki_pos = pos + result;
	}

	nfs_direct_req_release(dreq);
	return result;

out_release:
	nfs_direct_req_release(dreq);
out_unlock:
	mutex_unlock(&inode->i_mutex);
out:
	return result;
}

#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
{
	struct nfs_pageio_descriptor desc;
	struct nfs_page *req, *tmp;
	LIST_HEAD(reqs);
	struct nfs_commit_info cinfo;
	LIST_HEAD(failed);

	nfs_init_cinfo_from_dreq(&cinfo, dreq);
	pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
	spin_lock(cinfo.lock);
	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
	spin_unlock(cinfo.lock);

	dreq->count = 0;
	get_dreq(dreq);

	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
			      &nfs_direct_write_completion_ops);
	desc.pg_dreq = dreq;

	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
		if (!nfs_pageio_add_request(&desc, req)) {
			nfs_list_remove_request(req);
			nfs_list_add_request(req, &failed);
			spin_lock(cinfo.lock);
			dreq->flags = 0;
			dreq->error = -EIO;
			spin_unlock(cinfo.lock);
		}
		nfs_release_request(req);
	}
	nfs_pageio_complete(&desc);

	while (!list_empty(&failed)) {
		req = nfs_list_entry(failed.next);
		nfs_list_remove_request(req);
		nfs_unlock_and_release_request(req);
	}

	if (put_dreq(dreq))
		nfs_direct_write_complete(dreq, dreq->inode);
}

static void nfs_direct_commit_complete(struct nfs_commit_data *data)
{
	struct nfs_direct_req *dreq = data->dreq;
	struct nfs_commit_info cinfo;
	struct nfs_page *req;
	int status = data->task.tk_status;

	nfs_init_cinfo_from_dreq(&cinfo, dreq);
	if (status < 0) {
		dprintk("NFS: %5u commit failed with error %d.\n",
			data->task.tk_pid, status);
		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
	} else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) {
		dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
	}

	dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
	while (!list_empty(&data->pages)) {
		req = nfs_list_entry(data->pages.next);
		nfs_list_remove_request(req);
		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
			/* Note the rewrite will go through mds */
			nfs_mark_request_commit(req, NULL, &cinfo);
		} else
			nfs_release_request(req);
		nfs_unlock_and_release_request(req);
	}

	if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
		nfs_direct_write_complete(dreq, data->inode);
}

static void nfs_direct_error_cleanup(struct nfs_inode *nfsi)
{
	/* There is no lock to clear */
}

static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = {
	.completion = nfs_direct_commit_complete,
	.error_cleanup = nfs_direct_error_cleanup,
};

static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
{
	int res;
	struct nfs_commit_info cinfo;
	LIST_HEAD(mds_list);

	nfs_init_cinfo_from_dreq(&cinfo, dreq);
	nfs_scan_commit(dreq->inode, &mds_list, &cinfo);
	res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo);
	if (res < 0) /* res == -ENOMEM */
		nfs_direct_write_reschedule(dreq);
}

static void nfs_direct_write_schedule_work(struct work_struct *work)
{
	struct nfs_direct_req *dreq = container_of(work, struct nfs_direct_req, work);
	int flags = dreq->flags;

	dreq->flags = 0;
	switch (flags) {
		case NFS_ODIRECT_DO_COMMIT:
			nfs_direct_commit_schedule(dreq);
			break;
		case NFS_ODIRECT_RESCHED_WRITES:
			nfs_direct_write_reschedule(dreq);
			break;
		default:
			nfs_direct_complete(dreq, true);
	}
}

static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
{
	schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */
}

#else
static void nfs_direct_write_schedule_work(struct work_struct *work)
{
}

static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
{
	nfs_direct_complete(dreq, true);
}
#endif

/*
 * NB: Return the value of the first error return code.  Subsequent
 *     errors after the first one are ignored.
 */
/*
 * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
 * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
 * bail and stop sending more writes.  Write length accounting is
 * handled automatically by nfs_direct_write_result().  Otherwise, if
 * no requests have been sent, just return an error.
 */
static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
						 const struct iovec *iov,
						 loff_t pos, bool uio)
{
	struct nfs_direct_req *dreq = desc->pg_dreq;
	struct nfs_open_context *ctx = dreq->ctx;
	struct inode *inode = ctx->dentry->d_inode;
	unsigned long user_addr = (unsigned long)iov->iov_base;
	size_t count = iov->iov_len;
	size_t wsize = NFS_SERVER(inode)->wsize;
	unsigned int pgbase;
	int result;
	ssize_t started = 0;
	struct page **pagevec = NULL;
	unsigned int npages;

	do {
		size_t bytes;
		int i;

		pgbase = user_addr & ~PAGE_MASK;
		bytes = min(max_t(size_t, wsize, PAGE_SIZE), count);

		result = -ENOMEM;
		npages = nfs_page_array_len(pgbase, bytes);
		if (!pagevec)
			pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL);
		if (!pagevec)
			break;

		if (uio) {
			down_read(&current->mm->mmap_sem);
			result = get_user_pages(current, current->mm, user_addr,
						npages, 0, 0, pagevec, NULL);
			up_read(&current->mm->mmap_sem);
			if (result < 0)
				break;
		} else {
			WARN_ON(npages != 1);
			result = get_kernel_page(user_addr, 0, pagevec);
			if (WARN_ON(result != 1))
				break;
		}

		if ((unsigned)result < npages) {
			bytes = result * PAGE_SIZE;
			if (bytes <= pgbase) {
				nfs_direct_release_pages(pagevec, result);
				break;
			}
			bytes -= pgbase;
			npages = result;
		}

		for (i = 0; i < npages; i++) {
			struct nfs_page *req;
			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);

			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
						 pgbase, req_len);
			if (IS_ERR(req)) {
				result = PTR_ERR(req);
				break;
			}
			nfs_lock_request(req);
			req->wb_index = pos >> PAGE_SHIFT;
			req->wb_offset = pos & ~PAGE_MASK;
			if (!nfs_pageio_add_request(desc, req)) {
				result = desc->pg_error;
				nfs_unlock_and_release_request(req);
				break;
			}
			pgbase = 0;
			bytes -= req_len;
			started += req_len;
			user_addr += req_len;
			pos += req_len;
			count -= req_len;
			dreq->bytes_left -= req_len;
		}
		/* The nfs_page now hold references to these pages */
		nfs_direct_release_pages(pagevec, npages);
	} while (count != 0 && result >= 0);

	kfree(pagevec);

	if (started)
		return started;
	return result < 0 ? (ssize_t) result : -EFAULT;
}

static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
{
	struct nfs_direct_req *dreq = hdr->dreq;
	struct nfs_commit_info cinfo;
	int bit = -1;
	struct nfs_page *req = nfs_list_entry(hdr->pages.next);

	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
		goto out_put;

	nfs_init_cinfo_from_dreq(&cinfo, dreq);

	spin_lock(&dreq->lock);

	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
		dreq->flags = 0;
		dreq->error = hdr->error;
	}
	if (dreq->error != 0)
		bit = NFS_IOHDR_ERROR;
	else {
		dreq->count += hdr->good_bytes;
		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) {
			dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
			bit = NFS_IOHDR_NEED_RESCHED;
		} else if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
				bit = NFS_IOHDR_NEED_RESCHED;
			else if (dreq->flags == 0) {
				memcpy(&dreq->verf, &hdr->verf,
				       sizeof(dreq->verf));
				bit = NFS_IOHDR_NEED_COMMIT;
				dreq->flags = NFS_ODIRECT_DO_COMMIT;
			} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
				if (memcmp(&dreq->verf, &hdr->verf, sizeof(dreq->verf))) {
					dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
					bit = NFS_IOHDR_NEED_RESCHED;
				} else
					bit = NFS_IOHDR_NEED_COMMIT;
			}
		}
	}
	spin_unlock(&dreq->lock);

	while (!list_empty(&hdr->pages)) {
		bool do_destroy = true;

		req = nfs_list_entry(hdr->pages.next);
		nfs_list_remove_request(req);
		switch (bit) {
		case NFS_IOHDR_NEED_RESCHED:
		case NFS_IOHDR_NEED_COMMIT:
			kref_get(&req->wb_kref);
			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
			do_destroy = false;
		}
		nfs_unlock_and_release_request(req);
	}

out_put:
	if (put_dreq(dreq))
		nfs_direct_write_complete(dreq, hdr->inode);
	hdr->release(hdr);
}

static void nfs_write_sync_pgio_error(struct list_head *head)
{
	struct nfs_page *req;

	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_unlock_and_release_request(req);
	}
}

static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
	.error_cleanup = nfs_write_sync_pgio_error,
	.init_hdr = nfs_direct_pgio_init,
	.completion = nfs_direct_write_completion,
};

static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
					       const struct iovec *iov,
					       unsigned long nr_segs,
					       loff_t pos, bool uio)
{
	struct nfs_pageio_descriptor desc;
	struct inode *inode = dreq->inode;
	ssize_t result = 0;
	size_t requested_bytes = 0;
	unsigned long seg;

	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
			      &nfs_direct_write_completion_ops);
	desc.pg_dreq = dreq;
	get_dreq(dreq);
	atomic_inc(&inode->i_dio_count);

	NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *vec = &iov[seg];
		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
		if (result < 0)
			break;
		requested_bytes += result;
		if ((size_t)result < vec->iov_len)
			break;
		pos += vec->iov_len;
	}
	nfs_pageio_complete(&desc);

	/*
	 * If no bytes were started, return the error, and let the
	 * generic layer handle the completion.
	 */
	if (requested_bytes == 0) {
		inode_dio_done(inode);
		nfs_direct_req_release(dreq);
		return result < 0 ? result : -EIO;
	}

	if (put_dreq(dreq))
		nfs_direct_write_complete(dreq, dreq->inode);
	return 0;
}

/**
 * nfs_file_direct_write - file direct write operation for NFS files
 * @iocb: target I/O control block
 * @iov: vector of user buffers from which to write data
 * @nr_segs: size of iov vector
 * @pos: byte offset in file where writing starts
 *
 * We use this function for direct writes instead of calling
 * generic_file_aio_write() in order to avoid taking the inode
 * semaphore and updating the i_size.  The NFS server will set
 * the new i_size and this client must read the updated size
 * back into its cache.  We let the server do generic write
 * parameter checking and report problems.
 *
 * We eliminate local atime updates, see direct read above.
 *
 * We avoid unnecessary page cache invalidations for normal cached
 * readers of this file.
 *
 * Note that O_APPEND is not supported for NFS direct writes, as there
 * is no atomic O_APPEND write facility in the NFS protocol.
 */
ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos, bool uio)
{
	ssize_t result = -EINVAL;
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	struct nfs_direct_req *dreq;
	struct nfs_lock_context *l_ctx;
	loff_t end;
	size_t count;

	count = iov_length(iov, nr_segs);
	end = (pos + count - 1) >> PAGE_CACHE_SHIFT;

	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);

	dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
		file, count, (long long) pos);

	result = generic_write_checks(file, &pos, &count, 0);
	if (result)
		goto out;

	result = -EINVAL;
	if ((ssize_t) count < 0)
		goto out;
	result = 0;
	if (!count)
		goto out;

	mutex_lock(&inode->i_mutex);

	result = nfs_sync_mapping(mapping);
	if (result)
		goto out_unlock;

	if (mapping->nrpages) {
		result = invalidate_inode_pages2_range(mapping,
					pos >> PAGE_CACHE_SHIFT, end);
		if (result)
			goto out_unlock;
	}

	task_io_account_write(count);

	result = -ENOMEM;
	dreq = nfs_direct_req_alloc();
	if (!dreq)
		goto out_unlock;

	dreq->inode = inode;
	dreq->bytes_left = count;
	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
	l_ctx = nfs_get_lock_context(dreq->ctx);
	if (IS_ERR(l_ctx)) {
		result = PTR_ERR(l_ctx);
		goto out_release;
	}
	dreq->l_ctx = l_ctx;
	if (!is_sync_kiocb(iocb))
		dreq->iocb = iocb;

	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);

	if (mapping->nrpages) {
		invalidate_inode_pages2_range(mapping,
					      pos >> PAGE_CACHE_SHIFT, end);
	}

	mutex_unlock(&inode->i_mutex);

	if (!result) {
		result = nfs_direct_wait(dreq);
		if (result > 0) {
			struct inode *inode = mapping->host;

			iocb->ki_pos = pos + result;
			spin_lock(&inode->i_lock);
			if (i_size_read(inode) < iocb->ki_pos)
				i_size_write(inode, iocb->ki_pos);
			spin_unlock(&inode->i_lock);
		}
	}
	nfs_direct_req_release(dreq);
	return result;

out_release:
	nfs_direct_req_release(dreq);
out_unlock:
	mutex_unlock(&inode->i_mutex);
out:
	return result;
}

/**
 * nfs_init_directcache - create a slab cache for nfs_direct_req structures
 *
 */
int __init nfs_init_directcache(void)
{
	nfs_direct_cachep = kmem_cache_create("nfs_direct_cache",
						sizeof(struct nfs_direct_req),
						0, (SLAB_RECLAIM_ACCOUNT|
							SLAB_MEM_SPREAD),
						NULL);
	if (nfs_direct_cachep == NULL)
		return -ENOMEM;

	return 0;
}

/**
 * nfs_destroy_directcache - destroy the slab cache for nfs_direct_req structures
 *
 */
void nfs_destroy_directcache(void)
{
	kmem_cache_destroy(nfs_direct_cachep);
}