Free Electrons

Embedded Linux Experts

  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
/*
 *  Device operations for the pnfs nfs4 file layout driver.
 *
 *  Copyright (c) 2002
 *  The Regents of the University of Michigan
 *  All Rights Reserved
 *
 *  Dean Hildebrand <dhildebz@umich.edu>
 *  Garth Goodson   <Garth.Goodson@netapp.com>
 *
 *  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 <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/sunrpc/addr.h>

#include "internal.h"
#include "nfs4session.h"
#include "nfs4filelayout.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS_LD

static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;

/*
 * Data server cache
 *
 * Data servers can be mapped to different device ids.
 * nfs4_pnfs_ds reference counting
 *   - set to 1 on allocation
 *   - incremented when a device id maps a data server already in the cache.
 *   - decremented when deviceid is removed from the cache.
 */
static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
static LIST_HEAD(nfs4_data_server_cache);

/* Debug routines */
void
print_ds(struct nfs4_pnfs_ds *ds)
{
	if (ds == NULL) {
		printk("%s NULL device\n", __func__);
		return;
	}
	printk("        ds %s\n"
		"        ref count %d\n"
		"        client %p\n"
		"        cl_exchange_flags %x\n",
		ds->ds_remotestr,
		atomic_read(&ds->ds_count), ds->ds_clp,
		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
}

static bool
same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
{
	struct sockaddr_in *a, *b;
	struct sockaddr_in6 *a6, *b6;

	if (addr1->sa_family != addr2->sa_family)
		return false;

	switch (addr1->sa_family) {
	case AF_INET:
		a = (struct sockaddr_in *)addr1;
		b = (struct sockaddr_in *)addr2;

		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
		    a->sin_port == b->sin_port)
			return true;
		break;

	case AF_INET6:
		a6 = (struct sockaddr_in6 *)addr1;
		b6 = (struct sockaddr_in6 *)addr2;

		/* LINKLOCAL addresses must have matching scope_id */
		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
		    IPV6_ADDR_SCOPE_LINKLOCAL &&
		    a6->sin6_scope_id != b6->sin6_scope_id)
			return false;

		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
		    a6->sin6_port == b6->sin6_port)
			return true;
		break;

	default:
		dprintk("%s: unhandled address family: %u\n",
			__func__, addr1->sa_family);
		return false;
	}

	return false;
}

static bool
_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
			       const struct list_head *dsaddrs2)
{
	struct nfs4_pnfs_ds_addr *da1, *da2;

	/* step through both lists, comparing as we go */
	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
	     da1 != NULL && da2 != NULL;
	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
				   (struct sockaddr *)&da2->da_addr))
			return false;
	}
	if (da1 == NULL && da2 == NULL)
		return true;

	return false;
}

/*
 * Lookup DS by addresses.  nfs4_ds_cache_lock is held
 */
static struct nfs4_pnfs_ds *
_data_server_lookup_locked(const struct list_head *dsaddrs)
{
	struct nfs4_pnfs_ds *ds;

	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
			return ds;
	return NULL;
}

/*
 * Create an rpc connection to the nfs4_pnfs_ds data server
 * Currently only supports IPv4 and IPv6 addresses
 */
static int
nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
{
	struct nfs_client *clp = ERR_PTR(-EIO);
	struct nfs4_pnfs_ds_addr *da;
	int status = 0;

	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);

	list_for_each_entry(da, &ds->ds_addrs, da_node) {
		dprintk("%s: DS %s: trying address %s\n",
			__func__, ds->ds_remotestr, da->da_remotestr);

		clp = nfs4_set_ds_client(mds_srv->nfs_client,
					(struct sockaddr *)&da->da_addr,
					da->da_addrlen, IPPROTO_TCP,
					dataserver_timeo, dataserver_retrans);
		if (!IS_ERR(clp))
			break;
	}

	if (IS_ERR(clp)) {
		status = PTR_ERR(clp);
		goto out;
	}

	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
	if (status)
		goto out_put;

	smp_wmb();
	ds->ds_clp = clp;
	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
	return status;
out_put:
	nfs_put_client(clp);
	goto out;
}

static void
destroy_ds(struct nfs4_pnfs_ds *ds)
{
	struct nfs4_pnfs_ds_addr *da;

	dprintk("--> %s\n", __func__);
	ifdebug(FACILITY)
		print_ds(ds);

	if (ds->ds_clp)
		nfs_put_client(ds->ds_clp);

	while (!list_empty(&ds->ds_addrs)) {
		da = list_first_entry(&ds->ds_addrs,
				      struct nfs4_pnfs_ds_addr,
				      da_node);
		list_del_init(&da->da_node);
		kfree(da->da_remotestr);
		kfree(da);
	}

	kfree(ds->ds_remotestr);
	kfree(ds);
}

void
nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
{
	struct nfs4_pnfs_ds *ds;
	int i;

	nfs4_print_deviceid(&dsaddr->id_node.deviceid);

	for (i = 0; i < dsaddr->ds_num; i++) {
		ds = dsaddr->ds_list[i];
		if (ds != NULL) {
			if (atomic_dec_and_lock(&ds->ds_count,
						&nfs4_ds_cache_lock)) {
				list_del_init(&ds->ds_node);
				spin_unlock(&nfs4_ds_cache_lock);
				destroy_ds(ds);
			}
		}
	}
	kfree(dsaddr->stripe_indices);
	kfree(dsaddr);
}

/*
 * Create a string with a human readable address and port to avoid
 * complicated setup around many dprinks.
 */
static char *
nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds_addr *da;
	char *remotestr;
	size_t len;
	char *p;

	len = 3;        /* '{', '}' and eol */
	list_for_each_entry(da, dsaddrs, da_node) {
		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
	}

	remotestr = kzalloc(len, gfp_flags);
	if (!remotestr)
		return NULL;

	p = remotestr;
	*(p++) = '{';
	len--;
	list_for_each_entry(da, dsaddrs, da_node) {
		size_t ll = strlen(da->da_remotestr);

		if (ll > len)
			goto out_err;

		memcpy(p, da->da_remotestr, ll);
		p += ll;
		len -= ll;

		if (len < 1)
			goto out_err;
		(*p++) = ',';
		len--;
	}
	if (len < 2)
		goto out_err;
	*(p++) = '}';
	*p = '\0';
	return remotestr;
out_err:
	kfree(remotestr);
	return NULL;
}

static struct nfs4_pnfs_ds *
nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
	char *remotestr;

	if (list_empty(dsaddrs)) {
		dprintk("%s: no addresses defined\n", __func__);
		goto out;
	}

	ds = kzalloc(sizeof(*ds), gfp_flags);
	if (!ds)
		goto out;

	/* this is only used for debugging, so it's ok if its NULL */
	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);

	spin_lock(&nfs4_ds_cache_lock);
	tmp_ds = _data_server_lookup_locked(dsaddrs);
	if (tmp_ds == NULL) {
		INIT_LIST_HEAD(&ds->ds_addrs);
		list_splice_init(dsaddrs, &ds->ds_addrs);
		ds->ds_remotestr = remotestr;
		atomic_set(&ds->ds_count, 1);
		INIT_LIST_HEAD(&ds->ds_node);
		ds->ds_clp = NULL;
		list_add(&ds->ds_node, &nfs4_data_server_cache);
		dprintk("%s add new data server %s\n", __func__,
			ds->ds_remotestr);
	} else {
		kfree(remotestr);
		kfree(ds);
		atomic_inc(&tmp_ds->ds_count);
		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
			__func__, tmp_ds->ds_remotestr,
			atomic_read(&tmp_ds->ds_count));
		ds = tmp_ds;
	}
	spin_unlock(&nfs4_ds_cache_lock);
out:
	return ds;
}

/*
 * Currently only supports ipv4, ipv6 and one multi-path address.
 */
static struct nfs4_pnfs_ds_addr *
decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds_addr *da = NULL;
	char *buf, *portstr;
	__be16 port;
	int nlen, rlen;
	int tmp[2];
	__be32 *p;
	char *netid, *match_netid;
	size_t len, match_netid_len;
	char *startsep = "";
	char *endsep = "";


	/* r_netid */
	p = xdr_inline_decode(streamp, 4);
	if (unlikely(!p))
		goto out_err;
	nlen = be32_to_cpup(p++);

	p = xdr_inline_decode(streamp, nlen);
	if (unlikely(!p))
		goto out_err;

	netid = kmalloc(nlen+1, gfp_flags);
	if (unlikely(!netid))
		goto out_err;

	netid[nlen] = '\0';
	memcpy(netid, p, nlen);

	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
	p = xdr_inline_decode(streamp, 4);
	if (unlikely(!p))
		goto out_free_netid;
	rlen = be32_to_cpup(p);

	p = xdr_inline_decode(streamp, rlen);
	if (unlikely(!p))
		goto out_free_netid;

	/* port is ".ABC.DEF", 8 chars max */
	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
		dprintk("%s: Invalid address, length %d\n", __func__,
			rlen);
		goto out_free_netid;
	}
	buf = kmalloc(rlen + 1, gfp_flags);
	if (!buf) {
		dprintk("%s: Not enough memory\n", __func__);
		goto out_free_netid;
	}
	buf[rlen] = '\0';
	memcpy(buf, p, rlen);

	/* replace port '.' with '-' */
	portstr = strrchr(buf, '.');
	if (!portstr) {
		dprintk("%s: Failed finding expected dot in port\n",
			__func__);
		goto out_free_buf;
	}
	*portstr = '-';

	/* find '.' between address and port */
	portstr = strrchr(buf, '.');
	if (!portstr) {
		dprintk("%s: Failed finding expected dot between address and "
			"port\n", __func__);
		goto out_free_buf;
	}
	*portstr = '\0';

	da = kzalloc(sizeof(*da), gfp_flags);
	if (unlikely(!da))
		goto out_free_buf;

	INIT_LIST_HEAD(&da->da_node);

	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
		      sizeof(da->da_addr))) {
		dprintk("%s: error parsing address %s\n", __func__, buf);
		goto out_free_da;
	}

	portstr++;
	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
	port = htons((tmp[0] << 8) | (tmp[1]));

	switch (da->da_addr.ss_family) {
	case AF_INET:
		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
		da->da_addrlen = sizeof(struct sockaddr_in);
		match_netid = "tcp";
		match_netid_len = 3;
		break;

	case AF_INET6:
		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
		da->da_addrlen = sizeof(struct sockaddr_in6);
		match_netid = "tcp6";
		match_netid_len = 4;
		startsep = "[";
		endsep = "]";
		break;

	default:
		dprintk("%s: unsupported address family: %u\n",
			__func__, da->da_addr.ss_family);
		goto out_free_da;
	}

	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
			__func__, netid, match_netid);
		goto out_free_da;
	}

	/* save human readable address */
	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
	da->da_remotestr = kzalloc(len, gfp_flags);

	/* NULL is ok, only used for dprintk */
	if (da->da_remotestr)
		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
			 buf, endsep, ntohs(port));

	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
	kfree(buf);
	kfree(netid);
	return da;

out_free_da:
	kfree(da);
out_free_buf:
	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
	kfree(buf);
out_free_netid:
	kfree(netid);
out_err:
	return NULL;
}

/* Decode opaque device data and return the result */
static struct nfs4_file_layout_dsaddr*
decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
{
	int i;
	u32 cnt, num;
	u8 *indexp;
	__be32 *p;
	u8 *stripe_indices;
	u8 max_stripe_index;
	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
	struct xdr_stream stream;
	struct xdr_buf buf;
	struct page *scratch;
	struct list_head dsaddrs;
	struct nfs4_pnfs_ds_addr *da;

	/* set up xdr stream */
	scratch = alloc_page(gfp_flags);
	if (!scratch)
		goto out_err;

	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);

	/* Get the stripe count (number of stripe index) */
	p = xdr_inline_decode(&stream, 4);
	if (unlikely(!p))
		goto out_err_free_scratch;

	cnt = be32_to_cpup(p);
	dprintk("%s stripe count  %d\n", __func__, cnt);
	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
		printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
		       "supported maximum %d\n", __func__,
			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
		goto out_err_free_scratch;
	}

	/* read stripe indices */
	stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags);
	if (!stripe_indices)
		goto out_err_free_scratch;

	p = xdr_inline_decode(&stream, cnt << 2);
	if (unlikely(!p))
		goto out_err_free_stripe_indices;

	indexp = &stripe_indices[0];
	max_stripe_index = 0;
	for (i = 0; i < cnt; i++) {
		*indexp = be32_to_cpup(p++);
		max_stripe_index = max(max_stripe_index, *indexp);
		indexp++;
	}

	/* Check the multipath list count */
	p = xdr_inline_decode(&stream, 4);
	if (unlikely(!p))
		goto out_err_free_stripe_indices;

	num = be32_to_cpup(p);
	dprintk("%s ds_num %u\n", __func__, num);
	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
		printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
			"supported maximum %d\n", __func__,
			num, NFS4_PNFS_MAX_MULTI_CNT);
		goto out_err_free_stripe_indices;
	}

	/* validate stripe indices are all < num */
	if (max_stripe_index >= num) {
		printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
			__func__, max_stripe_index, num);
		goto out_err_free_stripe_indices;
	}

	dsaddr = kzalloc(sizeof(*dsaddr) +
			(sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
			gfp_flags);
	if (!dsaddr)
		goto out_err_free_stripe_indices;

	dsaddr->stripe_count = cnt;
	dsaddr->stripe_indices = stripe_indices;
	stripe_indices = NULL;
	dsaddr->ds_num = num;
	nfs4_init_deviceid_node(&dsaddr->id_node,
				NFS_SERVER(ino)->pnfs_curr_ld,
				NFS_SERVER(ino)->nfs_client,
				&pdev->dev_id);

	INIT_LIST_HEAD(&dsaddrs);

	for (i = 0; i < dsaddr->ds_num; i++) {
		int j;
		u32 mp_count;

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

		mp_count = be32_to_cpup(p); /* multipath count */
		for (j = 0; j < mp_count; j++) {
			da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net,
					    &stream, gfp_flags);
			if (da)
				list_add_tail(&da->da_node, &dsaddrs);
		}
		if (list_empty(&dsaddrs)) {
			dprintk("%s: no suitable DS addresses found\n",
				__func__);
			goto out_err_free_deviceid;
		}

		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
		if (!dsaddr->ds_list[i])
			goto out_err_drain_dsaddrs;

		/* If DS was already in cache, free ds addrs */
		while (!list_empty(&dsaddrs)) {
			da = list_first_entry(&dsaddrs,
					      struct nfs4_pnfs_ds_addr,
					      da_node);
			list_del_init(&da->da_node);
			kfree(da->da_remotestr);
			kfree(da);
		}
	}

	__free_page(scratch);
	return dsaddr;

out_err_drain_dsaddrs:
	while (!list_empty(&dsaddrs)) {
		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
				      da_node);
		list_del_init(&da->da_node);
		kfree(da->da_remotestr);
		kfree(da);
	}
out_err_free_deviceid:
	nfs4_fl_free_deviceid(dsaddr);
	/* stripe_indicies was part of dsaddr */
	goto out_err_free_scratch;
out_err_free_stripe_indices:
	kfree(stripe_indices);
out_err_free_scratch:
	__free_page(scratch);
out_err:
	dprintk("%s ERROR: returning NULL\n", __func__);
	return NULL;
}

/*
 * Decode the opaque device specified in 'dev' and add it to the cache of
 * available devices.
 */
static struct nfs4_file_layout_dsaddr *
decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
{
	struct nfs4_deviceid_node *d;
	struct nfs4_file_layout_dsaddr *n, *new;

	new = decode_device(inode, dev, gfp_flags);
	if (!new) {
		printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
			__func__);
		return NULL;
	}

	d = nfs4_insert_deviceid_node(&new->id_node);
	n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
	if (n != new) {
		nfs4_fl_free_deviceid(new);
		return n;
	}

	return new;
}

/*
 * Retrieve the information for dev_id, add it to the list
 * of available devices, and return it.
 */
struct nfs4_file_layout_dsaddr *
filelayout_get_device_info(struct inode *inode,
		struct nfs4_deviceid *dev_id,
		struct rpc_cred *cred,
		gfp_t gfp_flags)
{
	struct pnfs_device *pdev = NULL;
	u32 max_resp_sz;
	int max_pages;
	struct page **pages = NULL;
	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
	int rc, i;
	struct nfs_server *server = NFS_SERVER(inode);

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

	pdev = kzalloc(sizeof(struct pnfs_device), gfp_flags);
	if (pdev == NULL)
		return NULL;

	pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags);
	if (pages == NULL) {
		kfree(pdev);
		return NULL;
	}
	for (i = 0; i < max_pages; i++) {
		pages[i] = alloc_page(gfp_flags);
		if (!pages[i])
			goto out_free;
	}

	memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
	pdev->pages = pages;
	pdev->pgbase = 0;
	pdev->pglen = max_resp_sz;
	pdev->mincount = 0;
	pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;

	rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
	dprintk("%s getdevice info returns %d\n", __func__, rc);
	if (rc)
		goto out_free;

	/*
	 * Found new device, need to decode it and then add it to the
	 * list of known devices for this mountpoint.
	 */
	dsaddr = decode_and_add_device(inode, pdev, gfp_flags);
out_free:
	for (i = 0; i < max_pages; i++)
		__free_page(pages[i]);
	kfree(pages);
	kfree(pdev);
	dprintk("<-- %s dsaddr %p\n", __func__, dsaddr);
	return dsaddr;
}

void
nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
{
	nfs4_put_deviceid_node(&dsaddr->id_node);
}

/*
 * Want res = (offset - layout->pattern_offset)/ layout->stripe_unit
 * Then: ((res + fsi) % dsaddr->stripe_count)
 */
u32
nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset)
{
	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
	u64 tmp;

	tmp = offset - flseg->pattern_offset;
	do_div(tmp, flseg->stripe_unit);
	tmp += flseg->first_stripe_index;
	return do_div(tmp, flseg->dsaddr->stripe_count);
}

u32
nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j)
{
	return FILELAYOUT_LSEG(lseg)->dsaddr->stripe_indices[j];
}

struct nfs_fh *
nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
{
	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
	u32 i;

	if (flseg->stripe_type == STRIPE_SPARSE) {
		if (flseg->num_fh == 1)
			i = 0;
		else if (flseg->num_fh == 0)
			/* Use the MDS OPEN fh set in nfs_read_rpcsetup */
			return NULL;
		else
			i = nfs4_fl_calc_ds_index(lseg, j);
	} else
		i = j;
	return flseg->fh_array[i];
}

static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
{
	might_sleep();
	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
			nfs_wait_bit_killable, TASK_KILLABLE);
}

static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
	smp_mb__before_clear_bit();
	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
	smp_mb__after_clear_bit();
	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
}


struct nfs4_pnfs_ds *
nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
{
	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
	struct nfs4_pnfs_ds *ret = ds;

	if (ds == NULL) {
		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
			__func__, ds_idx);
		filelayout_mark_devid_invalid(devid);
		goto out;
	}
	smp_rmb();
	if (ds->ds_clp)
		goto out_test_devid;

	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
		int err;

		err = nfs4_ds_connect(s, ds);
		if (err)
			nfs4_mark_deviceid_unavailable(devid);
		nfs4_clear_ds_conn_bit(ds);
	} else {
		/* Either ds is connected, or ds is NULL */
		nfs4_wait_ds_connect(ds);
	}
out_test_devid:
	if (filelayout_test_devid_unavailable(devid))
		ret = NULL;
out:
	return ret;
}

module_param(dataserver_retrans, uint, 0644);
MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
			"retries a request before it attempts further "
			" recovery  action.");
module_param(dataserver_timeo, uint, 0644);
MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
			"NFSv4.1  client  waits for a response from a "
			" data server before it retries an NFS request.");