summaryrefslogtreecommitdiff
path: root/fs/nfs/pnfs.c
blob: d1ad7df3479eed8a0c4a2ed660701e4f09f4308e (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
/*
 *  pNFS functions to call and manage layout drivers.
 *
 *  Copyright (c) 2002 [year of first publication]
 *  The Regents of the University of Michigan
 *  All Rights Reserved
 *
 *  Dean Hildebrand <dhildebz@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 or warranty
 *  of any kind either express or implied, including without limitation
 *  the implied warranties of merchantability, fitness for a particular
 *  purpose, or noninfringement.  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 of 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/nfs_fs.h>
#include "internal.h"
#include "pnfs.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS

/* Locking:
 *
 * pnfs_spinlock:
 *      protects pnfs_modules_tbl.
 */
static DEFINE_SPINLOCK(pnfs_spinlock);

/*
 * pnfs_modules_tbl holds all pnfs modules
 */
static LIST_HEAD(pnfs_modules_tbl);

/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
find_pnfs_driver_locked(u32 id)
{
	struct pnfs_layoutdriver_type *local;

	list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
		if (local->id == id)
			goto out;
	local = NULL;
out:
	dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
	return local;
}

static struct pnfs_layoutdriver_type *
find_pnfs_driver(u32 id)
{
	struct pnfs_layoutdriver_type *local;

	spin_lock(&pnfs_spinlock);
	local = find_pnfs_driver_locked(id);
	spin_unlock(&pnfs_spinlock);
	return local;
}

void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
	if (nfss->pnfs_curr_ld) {
		nfss->pnfs_curr_ld->uninitialize_mountpoint(nfss);
		module_put(nfss->pnfs_curr_ld->owner);
	}
	nfss->pnfs_curr_ld = NULL;
}

/*
 * Try to set the server's pnfs module to the pnfs layout type specified by id.
 * Currently only one pNFS layout driver per filesystem is supported.
 *
 * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
 */
void
set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
{
	struct pnfs_layoutdriver_type *ld_type = NULL;

	if (id == 0)
		goto out_no_driver;
	if (!(server->nfs_client->cl_exchange_flags &
		 (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
		printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__,
		       id, server->nfs_client->cl_exchange_flags);
		goto out_no_driver;
	}
	ld_type = find_pnfs_driver(id);
	if (!ld_type) {
		request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id);
		ld_type = find_pnfs_driver(id);
		if (!ld_type) {
			dprintk("%s: No pNFS module found for %u.\n",
				__func__, id);
			goto out_no_driver;
		}
	}
	if (!try_module_get(ld_type->owner)) {
		dprintk("%s: Could not grab reference on module\n", __func__);
		goto out_no_driver;
	}
	server->pnfs_curr_ld = ld_type;
	if (ld_type->initialize_mountpoint(server)) {
		printk(KERN_ERR
		       "%s: Error initializing mount point for layout driver %u.\n",
		       __func__, id);
		module_put(ld_type->owner);
		goto out_no_driver;
	}
	dprintk("%s: pNFS module for %u set\n", __func__, id);
	return;

out_no_driver:
	dprintk("%s: Using NFSv4 I/O\n", __func__);
	server->pnfs_curr_ld = NULL;
}

int
pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
	int status = -EINVAL;
	struct pnfs_layoutdriver_type *tmp;

	if (ld_type->id == 0) {
		printk(KERN_ERR "%s id 0 is reserved\n", __func__);
		return status;
	}
	if (!ld_type->alloc_lseg || !ld_type->free_lseg) {
		printk(KERN_ERR "%s Layout driver must provide "
		       "alloc_lseg and free_lseg.\n", __func__);
		return status;
	}

	spin_lock(&pnfs_spinlock);
	tmp = find_pnfs_driver_locked(ld_type->id);
	if (!tmp) {
		list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
		status = 0;
		dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
			ld_type->name);
	} else {
		printk(KERN_ERR "%s Module with id %d already loaded!\n",
			__func__, ld_type->id);
	}
	spin_unlock(&pnfs_spinlock);

	return status;
}
EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);

void
pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
	dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
	spin_lock(&pnfs_spinlock);
	list_del(&ld_type->pnfs_tblid);
	spin_unlock(&pnfs_spinlock);
}
EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);

/*
 * pNFS client layout cache
 */

static void
get_layout_hdr_locked(struct pnfs_layout_hdr *lo)
{
	assert_spin_locked(&lo->inode->i_lock);
	lo->refcount++;
}

static void
put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
{
	assert_spin_locked(&lo->inode->i_lock);
	BUG_ON(lo->refcount == 0);

	lo->refcount--;
	if (!lo->refcount) {
		dprintk("%s: freeing layout cache %p\n", __func__, lo);
		BUG_ON(!list_empty(&lo->layouts));
		NFS_I(lo->inode)->layout = NULL;
		kfree(lo);
	}
}

void
put_layout_hdr(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	put_layout_hdr_locked(NFS_I(inode)->layout);
	spin_unlock(&inode->i_lock);
}

static void
init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
{
	INIT_LIST_HEAD(&lseg->fi_list);
	kref_init(&lseg->kref);
	lseg->layout = lo;
}

/* Called without i_lock held, as the free_lseg call may sleep */
static void
destroy_lseg(struct kref *kref)
{
	struct pnfs_layout_segment *lseg =
		container_of(kref, struct pnfs_layout_segment, kref);
	struct inode *ino = lseg->layout->inode;

	dprintk("--> %s\n", __func__);
	NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
	/* Matched by get_layout_hdr_locked in pnfs_insert_layout */
	put_layout_hdr(ino);
}

static void
put_lseg(struct pnfs_layout_segment *lseg)
{
	if (!lseg)
		return;

	dprintk("%s: lseg %p ref %d\n", __func__, lseg,
		atomic_read(&lseg->kref.refcount));
	kref_put(&lseg->kref, destroy_lseg);
}

static void
pnfs_clear_lseg_list(struct pnfs_layout_hdr *lo, struct list_head *tmp_list)
{
	struct pnfs_layout_segment *lseg, *next;
	struct nfs_client *clp;

	dprintk("%s:Begin lo %p\n", __func__, lo);

	assert_spin_locked(&lo->inode->i_lock);
	list_for_each_entry_safe(lseg, next, &lo->segs, fi_list) {
		dprintk("%s: freeing lseg %p\n", __func__, lseg);
		list_move(&lseg->fi_list, tmp_list);
	}
	clp = NFS_SERVER(lo->inode)->nfs_client;
	spin_lock(&clp->cl_lock);
	/* List does not take a reference, so no need for put here */
	list_del_init(&lo->layouts);
	spin_unlock(&clp->cl_lock);
	write_seqlock(&lo->seqlock);
	clear_bit(NFS_LAYOUT_STATEID_SET, &lo->state);
	write_sequnlock(&lo->seqlock);

	dprintk("%s:Return\n", __func__);
}

static void
pnfs_free_lseg_list(struct list_head *tmp_list)
{
	struct pnfs_layout_segment *lseg;

	while (!list_empty(tmp_list)) {
		lseg = list_entry(tmp_list->next, struct pnfs_layout_segment,
				fi_list);
		dprintk("%s calling put_lseg on %p\n", __func__, lseg);
		list_del(&lseg->fi_list);
		put_lseg(lseg);
	}
}

void
pnfs_destroy_layout(struct nfs_inode *nfsi)
{
	struct pnfs_layout_hdr *lo;
	LIST_HEAD(tmp_list);

	spin_lock(&nfsi->vfs_inode.i_lock);
	lo = nfsi->layout;
	if (lo) {
		pnfs_clear_lseg_list(lo, &tmp_list);
		/* Matched by refcount set to 1 in alloc_init_layout_hdr */
		put_layout_hdr_locked(lo);
	}
	spin_unlock(&nfsi->vfs_inode.i_lock);
	pnfs_free_lseg_list(&tmp_list);
}

/*
 * Called by the state manger to remove all layouts established under an
 * expired lease.
 */
void
pnfs_destroy_all_layouts(struct nfs_client *clp)
{
	struct pnfs_layout_hdr *lo;
	LIST_HEAD(tmp_list);

	spin_lock(&clp->cl_lock);
	list_splice_init(&clp->cl_layouts, &tmp_list);
	spin_unlock(&clp->cl_lock);

	while (!list_empty(&tmp_list)) {
		lo = list_entry(tmp_list.next, struct pnfs_layout_hdr,
				layouts);
		dprintk("%s freeing layout for inode %lu\n", __func__,
			lo->inode->i_ino);
		pnfs_destroy_layout(NFS_I(lo->inode));
	}
}

/* update lo->stateid with new if is more recent
 *
 * lo->stateid could be the open stateid, in which case we just use what given.
 */
static void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
			const nfs4_stateid *new)
{
	nfs4_stateid *old = &lo->stateid;
	bool overwrite = false;

	write_seqlock(&lo->seqlock);
	if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state) ||
	    memcmp(old->stateid.other, new->stateid.other, sizeof(new->stateid.other)))
		overwrite = true;
	else {
		u32 oldseq, newseq;

		oldseq = be32_to_cpu(old->stateid.seqid);
		newseq = be32_to_cpu(new->stateid.seqid);
		if ((int)(newseq - oldseq) > 0)
			overwrite = true;
	}
	if (overwrite)
		memcpy(&old->stateid, &new->stateid, sizeof(new->stateid));
	write_sequnlock(&lo->seqlock);
}

static void
pnfs_layout_from_open_stateid(struct pnfs_layout_hdr *lo,
			      struct nfs4_state *state)
{
	int seq;

	dprintk("--> %s\n", __func__);
	write_seqlock(&lo->seqlock);
	do {
		seq = read_seqbegin(&state->seqlock);
		memcpy(lo->stateid.data, state->stateid.data,
		       sizeof(state->stateid.data));
	} while (read_seqretry(&state->seqlock, seq));
	set_bit(NFS_LAYOUT_STATEID_SET, &lo->state);
	write_sequnlock(&lo->seqlock);
	dprintk("<-- %s\n", __func__);
}

void
pnfs_get_layout_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
			struct nfs4_state *open_state)
{
	int seq;

	dprintk("--> %s\n", __func__);
	do {
		seq = read_seqbegin(&lo->seqlock);
		if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state)) {
			/* This will trigger retry of the read */
			pnfs_layout_from_open_stateid(lo, open_state);
		} else
			memcpy(dst->data, lo->stateid.data,
			       sizeof(lo->stateid.data));
	} while (read_seqretry(&lo->seqlock, seq));
	dprintk("<-- %s\n", __func__);
}

/*
* Get layout from server.
*    for now, assume that whole file layouts are requested.
*    arg->offset: 0
*    arg->length: all ones
*/
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
	   struct nfs_open_context *ctx,
	   u32 iomode)
{
	struct inode *ino = lo->inode;
	struct nfs_server *server = NFS_SERVER(ino);
	struct nfs4_layoutget *lgp;
	struct pnfs_layout_segment *lseg = NULL;

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

	BUG_ON(ctx == NULL);
	lgp = kzalloc(sizeof(*lgp), GFP_KERNEL);
	if (lgp == NULL) {
		put_layout_hdr(lo->inode);
		return NULL;
	}
	lgp->args.minlength = NFS4_MAX_UINT64;
	lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
	lgp->args.range.iomode = iomode;
	lgp->args.range.offset = 0;
	lgp->args.range.length = NFS4_MAX_UINT64;
	lgp->args.type = server->pnfs_curr_ld->id;
	lgp->args.inode = ino;
	lgp->args.ctx = get_nfs_open_context(ctx);
	lgp->lsegpp = &lseg;

	/* Synchronously retrieve layout information from server and
	 * store in lseg.
	 */
	nfs4_proc_layoutget(lgp);
	if (!lseg) {
		/* remember that LAYOUTGET failed and suspend trying */
		set_bit(lo_fail_bit(iomode), &lo->state);
	}
	return lseg;
}

/*
 * Compare two layout segments for sorting into layout cache.
 * We want to preferentially return RW over RO layouts, so ensure those
 * are seen first.
 */
static s64
cmp_layout(u32 iomode1, u32 iomode2)
{
	/* read > read/write */
	return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ);
}

static void
pnfs_insert_layout(struct pnfs_layout_hdr *lo,
		   struct pnfs_layout_segment *lseg)
{
	struct pnfs_layout_segment *lp;
	int found = 0;

	dprintk("%s:Begin\n", __func__);

	assert_spin_locked(&lo->inode->i_lock);
	if (list_empty(&lo->segs)) {
		struct nfs_client *clp = NFS_SERVER(lo->inode)->nfs_client;

		spin_lock(&clp->cl_lock);
		BUG_ON(!list_empty(&lo->layouts));
		list_add_tail(&lo->layouts, &clp->cl_layouts);
		spin_unlock(&clp->cl_lock);
	}
	list_for_each_entry(lp, &lo->segs, fi_list) {
		if (cmp_layout(lp->range.iomode, lseg->range.iomode) > 0)
			continue;
		list_add_tail(&lseg->fi_list, &lp->fi_list);
		dprintk("%s: inserted lseg %p "
			"iomode %d offset %llu length %llu before "
			"lp %p iomode %d offset %llu length %llu\n",
			__func__, lseg, lseg->range.iomode,
			lseg->range.offset, lseg->range.length,
			lp, lp->range.iomode, lp->range.offset,
			lp->range.length);
		found = 1;
		break;
	}
	if (!found) {
		list_add_tail(&lseg->fi_list, &lo->segs);
		dprintk("%s: inserted lseg %p "
			"iomode %d offset %llu length %llu at tail\n",
			__func__, lseg, lseg->range.iomode,
			lseg->range.offset, lseg->range.length);
	}
	get_layout_hdr_locked(lo);

	dprintk("%s:Return\n", __func__);
}

static struct pnfs_layout_hdr *
alloc_init_layout_hdr(struct inode *ino)
{
	struct pnfs_layout_hdr *lo;

	lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL);
	if (!lo)
		return NULL;
	lo->refcount = 1;
	INIT_LIST_HEAD(&lo->layouts);
	INIT_LIST_HEAD(&lo->segs);
	seqlock_init(&lo->seqlock);
	lo->inode = ino;
	return lo;
}

static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino)
{
	struct nfs_inode *nfsi = NFS_I(ino);
	struct pnfs_layout_hdr *new = NULL;

	dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);

	assert_spin_locked(&ino->i_lock);
	if (nfsi->layout)
		return nfsi->layout;

	spin_unlock(&ino->i_lock);
	new = alloc_init_layout_hdr(ino);
	spin_lock(&ino->i_lock);

	if (likely(nfsi->layout == NULL))	/* Won the race? */
		nfsi->layout = new;
	else
		kfree(new);
	return nfsi->layout;
}

/*
 * iomode matching rules:
 * iomode	lseg	match
 * -----	-----	-----
 * ANY		READ	true
 * ANY		RW	true
 * RW		READ	false
 * RW		RW	true
 * READ		READ	true
 * READ		RW	true
 */
static int
is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode)
{
	return (iomode != IOMODE_RW || lseg->range.iomode == IOMODE_RW);
}

/*
 * lookup range in layout
 */
static struct pnfs_layout_segment *
pnfs_has_layout(struct pnfs_layout_hdr *lo, u32 iomode)
{
	struct pnfs_layout_segment *lseg, *ret = NULL;

	dprintk("%s:Begin\n", __func__);

	assert_spin_locked(&lo->inode->i_lock);
	list_for_each_entry(lseg, &lo->segs, fi_list) {
		if (is_matching_lseg(lseg, iomode)) {
			ret = lseg;
			break;
		}
		if (cmp_layout(iomode, lseg->range.iomode) > 0)
			break;
	}

	dprintk("%s:Return lseg %p ref %d\n",
		__func__, ret, ret ? atomic_read(&ret->kref.refcount) : 0);
	return ret;
}

/*
 * Layout segment is retreived from the server if not cached.
 * The appropriate layout segment is referenced and returned to the caller.
 */
struct pnfs_layout_segment *
pnfs_update_layout(struct inode *ino,
		   struct nfs_open_context *ctx,
		   enum pnfs_iomode iomode)
{
	struct nfs_inode *nfsi = NFS_I(ino);
	struct pnfs_layout_hdr *lo;
	struct pnfs_layout_segment *lseg = NULL;

	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
		return NULL;
	spin_lock(&ino->i_lock);
	lo = pnfs_find_alloc_layout(ino);
	if (lo == NULL) {
		dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
		goto out_unlock;
	}

	/* Check to see if the layout for the given range already exists */
	lseg = pnfs_has_layout(lo, iomode);
	if (lseg) {
		dprintk("%s: Using cached lseg %p for iomode %d)\n",
			__func__, lseg, iomode);
		goto out_unlock;
	}

	/* if LAYOUTGET already failed once we don't try again */
	if (test_bit(lo_fail_bit(iomode), &nfsi->layout->state))
		goto out_unlock;

	get_layout_hdr_locked(lo); /* Matched in nfs4_layoutget_release */
	spin_unlock(&ino->i_lock);

	lseg = send_layoutget(lo, ctx, iomode);
out:
	dprintk("%s end, state 0x%lx lseg %p\n", __func__,
		nfsi->layout->state, lseg);
	return lseg;
out_unlock:
	spin_unlock(&ino->i_lock);
	goto out;
}

int
pnfs_layout_process(struct nfs4_layoutget *lgp)
{
	struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout;
	struct nfs4_layoutget_res *res = &lgp->res;
	struct pnfs_layout_segment *lseg;
	struct inode *ino = lo->inode;
	int status = 0;

	/* Inject layout blob into I/O device driver */
	lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res);
	if (!lseg || IS_ERR(lseg)) {
		if (!lseg)
			status = -ENOMEM;
		else
			status = PTR_ERR(lseg);
		dprintk("%s: Could not allocate layout: error %d\n",
		       __func__, status);
		goto out;
	}

	spin_lock(&ino->i_lock);
	init_lseg(lo, lseg);
	lseg->range = res->range;
	*lgp->lsegpp = lseg;
	pnfs_insert_layout(lo, lseg);

	/* Done processing layoutget. Set the layout stateid */
	pnfs_set_layout_stateid(lo, &res->stateid);
	spin_unlock(&ino->i_lock);
out:
	return status;
}

/*
 * Device ID cache. Currently supports one layout type per struct nfs_client.
 * Add layout type to the lookup key to expand to support multiple types.
 */
int
pnfs_alloc_init_deviceid_cache(struct nfs_client *clp,
			 void (*free_callback)(struct pnfs_deviceid_node *))
{
	struct pnfs_deviceid_cache *c;

	c = kzalloc(sizeof(struct pnfs_deviceid_cache), GFP_KERNEL);
	if (!c)
		return -ENOMEM;
	spin_lock(&clp->cl_lock);
	if (clp->cl_devid_cache != NULL) {
		atomic_inc(&clp->cl_devid_cache->dc_ref);
		dprintk("%s [kref [%d]]\n", __func__,
			atomic_read(&clp->cl_devid_cache->dc_ref));
		kfree(c);
	} else {
		/* kzalloc initializes hlists */
		spin_lock_init(&c->dc_lock);
		atomic_set(&c->dc_ref, 1);
		c->dc_free_callback = free_callback;
		clp->cl_devid_cache = c;
		dprintk("%s [new]\n", __func__);
	}
	spin_unlock(&clp->cl_lock);
	return 0;
}
EXPORT_SYMBOL_GPL(pnfs_alloc_init_deviceid_cache);

/*
 * Called from pnfs_layoutdriver_type->free_lseg
 * last layout segment reference frees deviceid
 */
void
pnfs_put_deviceid(struct pnfs_deviceid_cache *c,
		  struct pnfs_deviceid_node *devid)
{
	struct nfs4_deviceid *id = &devid->de_id;
	struct pnfs_deviceid_node *d;
	struct hlist_node *n;
	long h = nfs4_deviceid_hash(id);

	dprintk("%s [%d]\n", __func__, atomic_read(&devid->de_ref));
	if (!atomic_dec_and_lock(&devid->de_ref, &c->dc_lock))
		return;

	hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[h], de_node)
		if (!memcmp(&d->de_id, id, sizeof(*id))) {
			hlist_del_rcu(&d->de_node);
			spin_unlock(&c->dc_lock);
			synchronize_rcu();
			c->dc_free_callback(devid);
			return;
		}
	spin_unlock(&c->dc_lock);
	/* Why wasn't it found in  the list? */
	BUG();
}
EXPORT_SYMBOL_GPL(pnfs_put_deviceid);

/* Find and reference a deviceid */
struct pnfs_deviceid_node *
pnfs_find_get_deviceid(struct pnfs_deviceid_cache *c, struct nfs4_deviceid *id)
{
	struct pnfs_deviceid_node *d;
	struct hlist_node *n;
	long hash = nfs4_deviceid_hash(id);

	dprintk("--> %s hash %ld\n", __func__, hash);
	rcu_read_lock();
	hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[hash], de_node) {
		if (!memcmp(&d->de_id, id, sizeof(*id))) {
			if (!atomic_inc_not_zero(&d->de_ref)) {
				goto fail;
			} else {
				rcu_read_unlock();
				return d;
			}
		}
	}
fail:
	rcu_read_unlock();
	return NULL;
}
EXPORT_SYMBOL_GPL(pnfs_find_get_deviceid);

/*
 * Add a deviceid to the cache.
 * GETDEVICEINFOs for same deviceid can race. If deviceid is found, discard new
 */
struct pnfs_deviceid_node *
pnfs_add_deviceid(struct pnfs_deviceid_cache *c, struct pnfs_deviceid_node *new)
{
	struct pnfs_deviceid_node *d;
	long hash = nfs4_deviceid_hash(&new->de_id);

	dprintk("--> %s hash %ld\n", __func__, hash);
	spin_lock(&c->dc_lock);
	d = pnfs_find_get_deviceid(c, &new->de_id);
	if (d) {
		spin_unlock(&c->dc_lock);
		dprintk("%s [discard]\n", __func__);
		c->dc_free_callback(new);
		return d;
	}
	INIT_HLIST_NODE(&new->de_node);
	atomic_set(&new->de_ref, 1);
	hlist_add_head_rcu(&new->de_node, &c->dc_deviceids[hash]);
	spin_unlock(&c->dc_lock);
	dprintk("%s [new]\n", __func__);
	return new;
}
EXPORT_SYMBOL_GPL(pnfs_add_deviceid);

void
pnfs_put_deviceid_cache(struct nfs_client *clp)
{
	struct pnfs_deviceid_cache *local = clp->cl_devid_cache;

	dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache);
	if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) {
		int i;
		/* Verify cache is empty */
		for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i++)
			BUG_ON(!hlist_empty(&local->dc_deviceids[i]));
		clp->cl_devid_cache = NULL;
		spin_unlock(&clp->cl_lock);
		kfree(local);
	}
}
EXPORT_SYMBOL_GPL(pnfs_put_deviceid_cache);