summaryrefslogtreecommitdiff
path: root/net/ceph/ceph_common.c
blob: a9d6c97b5b0d67e3a55a63b3aa0abd8401ce5b9c (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
// SPDX-License-Identifier: GPL-2.0-only

#include <linux/ceph/ceph_debug.h>
#include <linux/backing-dev.h>
#include <linux/ctype.h>
#include <linux/fs.h>
#include <linux/inet.h>
#include <linux/in6.h>
#include <linux/key.h>
#include <keys/ceph-type.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/nsproxy.h>
#include <linux/fs_parser.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/statfs.h>
#include <linux/string.h>
#include <linux/vmalloc.h>


#include <linux/ceph/ceph_features.h>
#include <linux/ceph/libceph.h>
#include <linux/ceph/debugfs.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/auth.h>
#include "crypto.h"


/*
 * Module compatibility interface.  For now it doesn't do anything,
 * but its existence signals a certain level of functionality.
 *
 * The data buffer is used to pass information both to and from
 * libceph.  The return value indicates whether libceph determines
 * it is compatible with the caller (from another kernel module),
 * given the provided data.
 *
 * The data pointer can be null.
 */
bool libceph_compatible(void *data)
{
	return true;
}
EXPORT_SYMBOL(libceph_compatible);

static int param_get_supported_features(char *buffer,
					const struct kernel_param *kp)
{
	return sprintf(buffer, "0x%llx", CEPH_FEATURES_SUPPORTED_DEFAULT);
}
static const struct kernel_param_ops param_ops_supported_features = {
	.get = param_get_supported_features,
};
module_param_cb(supported_features, &param_ops_supported_features, NULL,
		0444);

const char *ceph_msg_type_name(int type)
{
	switch (type) {
	case CEPH_MSG_SHUTDOWN: return "shutdown";
	case CEPH_MSG_PING: return "ping";
	case CEPH_MSG_AUTH: return "auth";
	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
	case CEPH_MSG_MON_MAP: return "mon_map";
	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
	case CEPH_MSG_STATFS: return "statfs";
	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
	case CEPH_MSG_MDS_MAP: return "mds_map";
	case CEPH_MSG_FS_MAP_USER: return "fs_map_user";
	case CEPH_MSG_CLIENT_SESSION: return "client_session";
	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
	case CEPH_MSG_CLIENT_QUOTA: return "client_quota";
	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
	case CEPH_MSG_POOLOP_REPLY: return "poolop_reply";
	case CEPH_MSG_POOLOP: return "poolop";
	case CEPH_MSG_MON_COMMAND: return "mon_command";
	case CEPH_MSG_MON_COMMAND_ACK: return "mon_command_ack";
	case CEPH_MSG_OSD_MAP: return "osd_map";
	case CEPH_MSG_OSD_OP: return "osd_op";
	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
	case CEPH_MSG_WATCH_NOTIFY: return "watch_notify";
	case CEPH_MSG_OSD_BACKOFF: return "osd_backoff";
	default: return "unknown";
	}
}
EXPORT_SYMBOL(ceph_msg_type_name);

/*
 * Initially learn our fsid, or verify an fsid matches.
 */
int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
{
	if (client->have_fsid) {
		if (ceph_fsid_compare(&client->fsid, fsid)) {
			pr_err("bad fsid, had %pU got %pU",
			       &client->fsid, fsid);
			return -1;
		}
	} else {
		memcpy(&client->fsid, fsid, sizeof(*fsid));
	}
	return 0;
}
EXPORT_SYMBOL(ceph_check_fsid);

static int strcmp_null(const char *s1, const char *s2)
{
	if (!s1 && !s2)
		return 0;
	if (s1 && !s2)
		return -1;
	if (!s1 && s2)
		return 1;
	return strcmp(s1, s2);
}

int ceph_compare_options(struct ceph_options *new_opt,
			 struct ceph_client *client)
{
	struct ceph_options *opt1 = new_opt;
	struct ceph_options *opt2 = client->options;
	int ofs = offsetof(struct ceph_options, mon_addr);
	int i;
	int ret;

	/*
	 * Don't bother comparing options if network namespaces don't
	 * match.
	 */
	if (!net_eq(current->nsproxy->net_ns, read_pnet(&client->msgr.net)))
		return -1;

	ret = memcmp(opt1, opt2, ofs);
	if (ret)
		return ret;

	ret = strcmp_null(opt1->name, opt2->name);
	if (ret)
		return ret;

	if (opt1->key && !opt2->key)
		return -1;
	if (!opt1->key && opt2->key)
		return 1;
	if (opt1->key && opt2->key) {
		if (opt1->key->type != opt2->key->type)
			return -1;
		if (opt1->key->created.tv_sec != opt2->key->created.tv_sec)
			return -1;
		if (opt1->key->created.tv_nsec != opt2->key->created.tv_nsec)
			return -1;
		if (opt1->key->len != opt2->key->len)
			return -1;
		if (opt1->key->key && !opt2->key->key)
			return -1;
		if (!opt1->key->key && opt2->key->key)
			return 1;
		if (opt1->key->key && opt2->key->key) {
			ret = memcmp(opt1->key->key, opt2->key->key, opt1->key->len);
			if (ret)
				return ret;
		}
	}

	/* any matching mon ip implies a match */
	for (i = 0; i < opt1->num_mon; i++) {
		if (ceph_monmap_contains(client->monc.monmap,
				 &opt1->mon_addr[i]))
			return 0;
	}
	return -1;
}
EXPORT_SYMBOL(ceph_compare_options);

/*
 * kvmalloc() doesn't fall back to the vmalloc allocator unless flags are
 * compatible with (a superset of) GFP_KERNEL.  This is because while the
 * actual pages are allocated with the specified flags, the page table pages
 * are always allocated with GFP_KERNEL.  map_vm_area() doesn't even take
 * flags because GFP_KERNEL is hard-coded in {p4d,pud,pmd,pte}_alloc().
 *
 * ceph_kvmalloc() may be called with GFP_KERNEL, GFP_NOFS or GFP_NOIO.
 */
void *ceph_kvmalloc(size_t size, gfp_t flags)
{
	void *p;

	if ((flags & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) {
		p = kvmalloc(size, flags);
	} else if ((flags & (__GFP_IO | __GFP_FS)) == __GFP_IO) {
		unsigned int nofs_flag = memalloc_nofs_save();
		p = kvmalloc(size, GFP_KERNEL);
		memalloc_nofs_restore(nofs_flag);
	} else {
		unsigned int noio_flag = memalloc_noio_save();
		p = kvmalloc(size, GFP_KERNEL);
		memalloc_noio_restore(noio_flag);
	}

	return p;
}

static int parse_fsid(const char *str, struct ceph_fsid *fsid)
{
	int i = 0;
	char tmp[3];
	int err = -EINVAL;
	int d;

	dout("parse_fsid '%s'\n", str);
	tmp[2] = 0;
	while (*str && i < 16) {
		if (ispunct(*str)) {
			str++;
			continue;
		}
		if (!isxdigit(str[0]) || !isxdigit(str[1]))
			break;
		tmp[0] = str[0];
		tmp[1] = str[1];
		if (sscanf(tmp, "%x", &d) < 1)
			break;
		fsid->fsid[i] = d & 0xff;
		i++;
		str += 2;
	}

	if (i == 16)
		err = 0;
	dout("parse_fsid ret %d got fsid %pU\n", err, fsid);
	return err;
}

/*
 * ceph options
 */
enum {
	Opt_osdtimeout,
	Opt_osdkeepalivetimeout,
	Opt_mount_timeout,
	Opt_osd_idle_ttl,
	Opt_osd_request_timeout,
	/* int args above */
	Opt_fsid,
	Opt_name,
	Opt_secret,
	Opt_key,
	Opt_ip,
	/* string args above */
	Opt_share,
	Opt_crc,
	Opt_cephx_require_signatures,
	Opt_cephx_sign_messages,
	Opt_tcp_nodelay,
	Opt_abort_on_full,
};

static const struct fs_parameter_spec ceph_param_specs[] = {
	fsparam_flag	("abort_on_full",		Opt_abort_on_full),
	fsparam_flag_no ("cephx_require_signatures",	Opt_cephx_require_signatures),
	fsparam_flag_no ("cephx_sign_messages",		Opt_cephx_sign_messages),
	fsparam_flag_no ("crc",				Opt_crc),
	fsparam_string	("fsid",			Opt_fsid),
	fsparam_string	("ip",				Opt_ip),
	fsparam_string	("key",				Opt_key),
	fsparam_u32	("mount_timeout",		Opt_mount_timeout),
	fsparam_string	("name",			Opt_name),
	fsparam_u32	("osd_idle_ttl",		Opt_osd_idle_ttl),
	fsparam_u32	("osd_request_timeout",		Opt_osd_request_timeout),
	fsparam_u32	("osdkeepalive",		Opt_osdkeepalivetimeout),
	__fsparam	(fs_param_is_s32, "osdtimeout", Opt_osdtimeout,
			 fs_param_deprecated),
	fsparam_string	("secret",			Opt_secret),
	fsparam_flag_no ("share",			Opt_share),
	fsparam_flag_no ("tcp_nodelay",			Opt_tcp_nodelay),
	{}
};

static const struct fs_parameter_description ceph_parameters = {
        .name           = "libceph",
        .specs          = ceph_param_specs,
};

struct ceph_options *ceph_alloc_options(void)
{
	struct ceph_options *opt;

	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
	if (!opt)
		return NULL;

	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
				GFP_KERNEL);
	if (!opt->mon_addr) {
		kfree(opt);
		return NULL;
	}

	opt->flags = CEPH_OPT_DEFAULT;
	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
	return opt;
}
EXPORT_SYMBOL(ceph_alloc_options);

void ceph_destroy_options(struct ceph_options *opt)
{
	dout("destroy_options %p\n", opt);
	if (!opt)
		return;

	kfree(opt->name);
	if (opt->key) {
		ceph_crypto_key_destroy(opt->key);
		kfree(opt->key);
	}
	kfree(opt->mon_addr);
	kfree(opt);
}
EXPORT_SYMBOL(ceph_destroy_options);

/* get secret from key store */
static int get_secret(struct ceph_crypto_key *dst, const char *name,
		      struct fs_context *fc)
{
	struct key *ukey;
	int key_err;
	int err = 0;
	struct ceph_crypto_key *ckey;

	ukey = request_key(&key_type_ceph, name, NULL);
	if (IS_ERR(ukey)) {
		/* request_key errors don't map nicely to mount(2)
		   errors; don't even try, but still printk */
		key_err = PTR_ERR(ukey);
		switch (key_err) {
		case -ENOKEY:
			errorf(fc, "libceph: Failed due to key not found: %s",
			       name);
			break;
		case -EKEYEXPIRED:
			errorf(fc, "libceph: Failed due to expired key: %s",
			       name);
			break;
		case -EKEYREVOKED:
			errorf(fc, "libceph: Failed due to revoked key: %s",
			       name);
			break;
		default:
			errorf(fc, "libceph: Failed due to key error %d: %s",
			       key_err, name);
		}
		err = -EPERM;
		goto out;
	}

	ckey = ukey->payload.data[0];
	err = ceph_crypto_key_clone(dst, ckey);
	if (err)
		goto out_key;
	/* pass through, err is 0 */

out_key:
	key_put(ukey);
out:
	return err;
}

int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt,
		       struct fs_context *fc)
{
	int ret;

	/* ip1[:port1][,ip2[:port2]...] */
	ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON,
			     &opt->num_mon);
	if (ret) {
		errorf(fc, "libceph: Failed to parse monitor IPs: %d", ret);
		return ret;
	}

	return 0;
}
EXPORT_SYMBOL(ceph_parse_mon_ips);

int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
		     struct fs_context *fc)
{
	struct fs_parse_result result;
	int token, err;

	token = fs_parse(fc, &ceph_parameters, param, &result);
	dout("%s fs_parse '%s' token %d\n", __func__, param->key, token);
	if (token < 0)
		return token;

	switch (token) {
	case Opt_ip:
		err = ceph_parse_ips(param->string,
				     param->string + param->size,
				     &opt->my_addr,
				     1, NULL);
		if (err) {
			errorf(fc, "libceph: Failed to parse ip: %d", err);
			return err;
		}
		opt->flags |= CEPH_OPT_MYIP;
		break;

	case Opt_fsid:
		err = parse_fsid(param->string, &opt->fsid);
		if (err) {
			errorf(fc, "libceph: Failed to parse fsid: %d", err);
			return err;
		}
		opt->flags |= CEPH_OPT_FSID;
		break;
	case Opt_name:
		kfree(opt->name);
		opt->name = param->string;
		param->string = NULL;
		break;
	case Opt_secret:
		ceph_crypto_key_destroy(opt->key);
		kfree(opt->key);

		opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL);
		if (!opt->key)
			return -ENOMEM;
		err = ceph_crypto_key_unarmor(opt->key, param->string);
		if (err) {
			errorf(fc, "libceph: Failed to parse secret: %d", err);
			return err;
		}
		break;
	case Opt_key:
		ceph_crypto_key_destroy(opt->key);
		kfree(opt->key);

		opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL);
		if (!opt->key)
			return -ENOMEM;
		return get_secret(opt->key, param->string, fc);

	case Opt_osdtimeout:
		warnf(fc, "libceph: Ignoring osdtimeout");
		break;
	case Opt_osdkeepalivetimeout:
		/* 0 isn't well defined right now, reject it */
		if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000)
			goto out_of_range;
		opt->osd_keepalive_timeout =
		    msecs_to_jiffies(result.uint_32 * 1000);
		break;
	case Opt_osd_idle_ttl:
		/* 0 isn't well defined right now, reject it */
		if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000)
			goto out_of_range;
		opt->osd_idle_ttl = msecs_to_jiffies(result.uint_32 * 1000);
		break;
	case Opt_mount_timeout:
		/* 0 is "wait forever" (i.e. infinite timeout) */
		if (result.uint_32 > INT_MAX / 1000)
			goto out_of_range;
		opt->mount_timeout = msecs_to_jiffies(result.uint_32 * 1000);
		break;
	case Opt_osd_request_timeout:
		/* 0 is "wait forever" (i.e. infinite timeout) */
		if (result.uint_32 > INT_MAX / 1000)
			goto out_of_range;
		opt->osd_request_timeout =
		    msecs_to_jiffies(result.uint_32 * 1000);
		break;

	case Opt_share:
		if (!result.negated)
			opt->flags &= ~CEPH_OPT_NOSHARE;
		else
			opt->flags |= CEPH_OPT_NOSHARE;
		break;
	case Opt_crc:
		if (!result.negated)
			opt->flags &= ~CEPH_OPT_NOCRC;
		else
			opt->flags |= CEPH_OPT_NOCRC;
		break;
	case Opt_cephx_require_signatures:
		if (!result.negated)
			opt->flags &= ~CEPH_OPT_NOMSGAUTH;
		else
			opt->flags |= CEPH_OPT_NOMSGAUTH;
		break;
	case Opt_cephx_sign_messages:
		if (!result.negated)
			opt->flags &= ~CEPH_OPT_NOMSGSIGN;
		else
			opt->flags |= CEPH_OPT_NOMSGSIGN;
		break;
	case Opt_tcp_nodelay:
		if (!result.negated)
			opt->flags |= CEPH_OPT_TCP_NODELAY;
		else
			opt->flags &= ~CEPH_OPT_TCP_NODELAY;
		break;

	case Opt_abort_on_full:
		opt->flags |= CEPH_OPT_ABORT_ON_FULL;
		break;

	default:
		BUG();
	}

	return 0;

out_of_range:
	return invalf(fc, "libceph: %s out of range", param->key);
}
EXPORT_SYMBOL(ceph_parse_param);

int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
			      bool show_all)
{
	struct ceph_options *opt = client->options;
	size_t pos = m->count;

	if (opt->name) {
		seq_puts(m, "name=");
		seq_escape(m, opt->name, ", \t\n\\");
		seq_putc(m, ',');
	}
	if (opt->key)
		seq_puts(m, "secret=<hidden>,");

	if (opt->flags & CEPH_OPT_FSID)
		seq_printf(m, "fsid=%pU,", &opt->fsid);
	if (opt->flags & CEPH_OPT_NOSHARE)
		seq_puts(m, "noshare,");
	if (opt->flags & CEPH_OPT_NOCRC)
		seq_puts(m, "nocrc,");
	if (opt->flags & CEPH_OPT_NOMSGAUTH)
		seq_puts(m, "nocephx_require_signatures,");
	if (opt->flags & CEPH_OPT_NOMSGSIGN)
		seq_puts(m, "nocephx_sign_messages,");
	if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0)
		seq_puts(m, "notcp_nodelay,");
	if (show_all && (opt->flags & CEPH_OPT_ABORT_ON_FULL))
		seq_puts(m, "abort_on_full,");

	if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
		seq_printf(m, "mount_timeout=%d,",
			   jiffies_to_msecs(opt->mount_timeout) / 1000);
	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
		seq_printf(m, "osd_idle_ttl=%d,",
			   jiffies_to_msecs(opt->osd_idle_ttl) / 1000);
	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
		seq_printf(m, "osdkeepalivetimeout=%d,",
		    jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
	if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
		seq_printf(m, "osd_request_timeout=%d,",
			   jiffies_to_msecs(opt->osd_request_timeout) / 1000);

	/* drop redundant comma */
	if (m->count != pos)
		m->count--;

	return 0;
}
EXPORT_SYMBOL(ceph_print_client_options);

struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client)
{
	return &client->msgr.inst.addr;
}
EXPORT_SYMBOL(ceph_client_addr);

u64 ceph_client_gid(struct ceph_client *client)
{
	return client->monc.auth->global_id;
}
EXPORT_SYMBOL(ceph_client_gid);

/*
 * create a fresh client instance
 */
struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
{
	struct ceph_client *client;
	struct ceph_entity_addr *myaddr = NULL;
	int err;

	err = wait_for_random_bytes();
	if (err < 0)
		return ERR_PTR(err);

	client = kzalloc(sizeof(*client), GFP_KERNEL);
	if (client == NULL)
		return ERR_PTR(-ENOMEM);

	client->private = private;
	client->options = opt;

	mutex_init(&client->mount_mutex);
	init_waitqueue_head(&client->auth_wq);
	client->auth_err = 0;

	client->extra_mon_dispatch = NULL;
	client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT;
	client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT;

	if (!ceph_test_opt(client, NOMSGAUTH))
		client->required_features |= CEPH_FEATURE_MSG_AUTH;

	/* msgr */
	if (ceph_test_opt(client, MYIP))
		myaddr = &client->options->my_addr;

	ceph_messenger_init(&client->msgr, myaddr);

	/* subsystems */
	err = ceph_monc_init(&client->monc, client);
	if (err < 0)
		goto fail;
	err = ceph_osdc_init(&client->osdc, client);
	if (err < 0)
		goto fail_monc;

	return client;

fail_monc:
	ceph_monc_stop(&client->monc);
fail:
	ceph_messenger_fini(&client->msgr);
	kfree(client);
	return ERR_PTR(err);
}
EXPORT_SYMBOL(ceph_create_client);

void ceph_destroy_client(struct ceph_client *client)
{
	dout("destroy_client %p\n", client);

	atomic_set(&client->msgr.stopping, 1);

	/* unmount */
	ceph_osdc_stop(&client->osdc);
	ceph_monc_stop(&client->monc);
	ceph_messenger_fini(&client->msgr);

	ceph_debugfs_client_cleanup(client);

	ceph_destroy_options(client->options);

	kfree(client);
	dout("destroy_client %p done\n", client);
}
EXPORT_SYMBOL(ceph_destroy_client);

void ceph_reset_client_addr(struct ceph_client *client)
{
	ceph_messenger_reset_nonce(&client->msgr);
	ceph_monc_reopen_session(&client->monc);
	ceph_osdc_reopen_osds(&client->osdc);
}
EXPORT_SYMBOL(ceph_reset_client_addr);

/*
 * true if we have the mon map (and have thus joined the cluster)
 */
static bool have_mon_and_osd_map(struct ceph_client *client)
{
	return client->monc.monmap && client->monc.monmap->epoch &&
	       client->osdc.osdmap && client->osdc.osdmap->epoch;
}

/*
 * mount: join the ceph cluster, and open root directory.
 */
int __ceph_open_session(struct ceph_client *client, unsigned long started)
{
	unsigned long timeout = client->options->mount_timeout;
	long err;

	/* open session, and wait for mon and osd maps */
	err = ceph_monc_open_session(&client->monc);
	if (err < 0)
		return err;

	while (!have_mon_and_osd_map(client)) {
		if (timeout && time_after_eq(jiffies, started + timeout))
			return -ETIMEDOUT;

		/* wait */
		dout("mount waiting for mon_map\n");
		err = wait_event_interruptible_timeout(client->auth_wq,
			have_mon_and_osd_map(client) || (client->auth_err < 0),
			ceph_timeout_jiffies(timeout));
		if (err < 0)
			return err;
		if (client->auth_err < 0)
			return client->auth_err;
	}

	pr_info("client%llu fsid %pU\n", ceph_client_gid(client),
		&client->fsid);
	ceph_debugfs_client_init(client);

	return 0;
}
EXPORT_SYMBOL(__ceph_open_session);

int ceph_open_session(struct ceph_client *client)
{
	int ret;
	unsigned long started = jiffies;  /* note the start time */

	dout("open_session start\n");
	mutex_lock(&client->mount_mutex);

	ret = __ceph_open_session(client, started);

	mutex_unlock(&client->mount_mutex);
	return ret;
}
EXPORT_SYMBOL(ceph_open_session);

int ceph_wait_for_latest_osdmap(struct ceph_client *client,
				unsigned long timeout)
{
	u64 newest_epoch;
	int ret;

	ret = ceph_monc_get_version(&client->monc, "osdmap", &newest_epoch);
	if (ret)
		return ret;

	if (client->osdc.osdmap->epoch >= newest_epoch)
		return 0;

	ceph_osdc_maybe_request_map(&client->osdc);
	return ceph_monc_wait_osdmap(&client->monc, newest_epoch, timeout);
}
EXPORT_SYMBOL(ceph_wait_for_latest_osdmap);

static int __init init_ceph_lib(void)
{
	int ret = 0;

	ceph_debugfs_init();

	ret = ceph_crypto_init();
	if (ret < 0)
		goto out_debugfs;

	ret = ceph_msgr_init();
	if (ret < 0)
		goto out_crypto;

	ret = ceph_osdc_setup();
	if (ret < 0)
		goto out_msgr;

	pr_info("loaded (mon/osd proto %d/%d)\n",
		CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL);

	return 0;

out_msgr:
	ceph_msgr_exit();
out_crypto:
	ceph_crypto_shutdown();
out_debugfs:
	ceph_debugfs_cleanup();
	return ret;
}

static void __exit exit_ceph_lib(void)
{
	dout("exit_ceph_lib\n");
	WARN_ON(!ceph_strings_empty());

	ceph_osdc_cleanup();
	ceph_msgr_exit();
	ceph_crypto_shutdown();
	ceph_debugfs_cleanup();
}

module_init(init_ceph_lib);
module_exit(exit_ceph_lib);

MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
MODULE_DESCRIPTION("Ceph core library");
MODULE_LICENSE("GPL");