aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph/mon_client.c
blob: b742b3b3e0f394f1bd549f4dee54438ec934b2e5 (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
#include "ceph_debug.h"

#include <linux/types.h>
#include <linux/random.h>
#include <linux/sched.h>

#include "mon_client.h"
#include "super.h"
#include "auth.h"
#include "decode.h"

/*
 * Interact with Ceph monitor cluster.  Handle requests for new map
 * versions, and periodically resend as needed.  Also implement
 * statfs() and umount().
 *
 * A small cluster of Ceph "monitors" are responsible for managing critical
 * cluster configuration and state information.  An odd number (e.g., 3, 5)
 * of cmon daemons use a modified version of the Paxos part-time parliament
 * algorithm to manage the MDS map (mds cluster membership), OSD map, and
 * list of clients who have mounted the file system.
 *
 * We maintain an open, active session with a monitor at all times in order to
 * receive timely MDSMap updates.  We periodically send a keepalive byte on the
 * TCP socket to ensure we detect a failure.  If the connection does break, we
 * randomly hunt for a new monitor.  Once the connection is reestablished, we
 * resend any outstanding requests.
 */

const static struct ceph_connection_operations mon_con_ops;

/*
 * Decode a monmap blob (e.g., during mount).
 */
struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
{
	struct ceph_monmap *m = NULL;
	int i, err = -EINVAL;
	struct ceph_fsid fsid;
	u32 epoch, num_mon;
	u16 version;
	u32 len;

	ceph_decode_32_safe(&p, end, len, bad);
	ceph_decode_need(&p, end, len, bad);

	dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));

	ceph_decode_16_safe(&p, end, version, bad);

	ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
	ceph_decode_copy(&p, &fsid, sizeof(fsid));
	epoch = ceph_decode_32(&p);

	num_mon = ceph_decode_32(&p);
	ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);

	if (num_mon >= CEPH_MAX_MON)
		goto bad;
	m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS);
	if (m == NULL)
		return ERR_PTR(-ENOMEM);
	m->fsid = fsid;
	m->epoch = epoch;
	m->num_mon = num_mon;
	ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0]));
	for (i = 0; i < num_mon; i++)
		ceph_decode_addr(&m->mon_inst[i].addr);

	dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
	     m->num_mon);
	for (i = 0; i < m->num_mon; i++)
		dout("monmap_decode  mon%d is %s\n", i,
		     pr_addr(&m->mon_inst[i].addr.in_addr));
	return m;

bad:
	dout("monmap_decode failed with %d\n", err);
	kfree(m);
	return ERR_PTR(err);
}

/*
 * return true if *addr is included in the monmap.
 */
int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
{
	int i;

	for (i = 0; i < m->num_mon; i++)
		if (ceph_entity_addr_equal(addr, &m->mon_inst[i].addr))
			return 1;
	return 0;
}

/*
 * Close monitor session, if any.
 */
static void __close_session(struct ceph_mon_client *monc)
{
	if (monc->con) {
		dout("__close_session closing mon%d\n", monc->cur_mon);
		ceph_con_revoke(monc->con, monc->m_auth);
		ceph_con_close(monc->con);
		monc->cur_mon = -1;
		ceph_auth_reset(monc->auth);
	}
}

/*
 * Open a session with a (new) monitor.
 */
static int __open_session(struct ceph_mon_client *monc)
{
	char r;
	int ret;

	if (monc->cur_mon < 0) {
		get_random_bytes(&r, 1);
		monc->cur_mon = r % monc->monmap->num_mon;
		dout("open_session num=%d r=%d -> mon%d\n",
		     monc->monmap->num_mon, r, monc->cur_mon);
		monc->sub_sent = 0;
		monc->sub_renew_after = jiffies;  /* i.e., expired */
		monc->want_next_osdmap = !!monc->want_next_osdmap;

		dout("open_session mon%d opening\n", monc->cur_mon);
		monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON;
		monc->con->peer_name.num = cpu_to_le64(monc->cur_mon);
		ceph_con_open(monc->con,
			      &monc->monmap->mon_inst[monc->cur_mon].addr);

		/* initiatiate authentication handshake */
		ret = ceph_auth_build_hello(monc->auth,
					    monc->m_auth->front.iov_base,
					    monc->m_auth->front_max);
		monc->m_auth->front.iov_len = ret;
		monc->m_auth->hdr.front_len = cpu_to_le32(ret);
		ceph_msg_get(monc->m_auth);  /* keep our ref */
		ceph_con_send(monc->con, monc->m_auth);
	} else {
		dout("open_session mon%d already open\n", monc->cur_mon);
	}
	return 0;
}

static bool __sub_expired(struct ceph_mon_client *monc)
{
	return time_after_eq(jiffies, monc->sub_renew_after);
}

/*
 * Reschedule delayed work timer.
 */
static void __schedule_delayed(struct ceph_mon_client *monc)
{
	unsigned delay;

	if (monc->cur_mon < 0 || __sub_expired(monc))
		delay = 10 * HZ;
	else
		delay = 20 * HZ;
	dout("__schedule_delayed after %u\n", delay);
	schedule_delayed_work(&monc->delayed_work, delay);
}

/*
 * Send subscribe request for mdsmap and/or osdmap.
 */
static void __send_subscribe(struct ceph_mon_client *monc)
{
	dout("__send_subscribe sub_sent=%u exp=%u want_osd=%d\n",
	     (unsigned)monc->sub_sent, __sub_expired(monc),
	     monc->want_next_osdmap);
	if ((__sub_expired(monc) && !monc->sub_sent) ||
	    monc->want_next_osdmap == 1) {
		struct ceph_msg *msg;
		struct ceph_mon_subscribe_item *i;
		void *p, *end;

		msg = ceph_msg_new(CEPH_MSG_MON_SUBSCRIBE, 96, 0, 0, NULL);
		if (!msg)
			return;

		p = msg->front.iov_base;
		end = p + msg->front.iov_len;

		dout("__send_subscribe to 'mdsmap' %u+\n",
		     (unsigned)monc->have_mdsmap);
		if (monc->want_next_osdmap) {
			dout("__send_subscribe to 'osdmap' %u\n",
			     (unsigned)monc->have_osdmap);
			ceph_encode_32(&p, 3);
			ceph_encode_string(&p, end, "osdmap", 6);
			i = p;
			i->have = cpu_to_le64(monc->have_osdmap);
			i->onetime = 1;
			p += sizeof(*i);
			monc->want_next_osdmap = 2;  /* requested */
		} else {
			ceph_encode_32(&p, 2);
		}
		ceph_encode_string(&p, end, "mdsmap", 6);
		i = p;
		i->have = cpu_to_le64(monc->have_mdsmap);
		i->onetime = 0;
		p += sizeof(*i);
		ceph_encode_string(&p, end, "monmap", 6);
		i = p;
		i->have = 0;
		i->onetime = 0;
		p += sizeof(*i);

		msg->front.iov_len = p - msg->front.iov_base;
		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
		ceph_con_send(monc->con, msg);

		monc->sub_sent = jiffies | 1;  /* never 0 */
	}
}

static void handle_subscribe_ack(struct ceph_mon_client *monc,
				 struct ceph_msg *msg)
{
	unsigned seconds;
	struct ceph_mon_subscribe_ack *h = msg->front.iov_base;

	if (msg->front.iov_len < sizeof(*h))
		goto bad;
	seconds = le32_to_cpu(h->duration);

	mutex_lock(&monc->mutex);
	if (monc->hunting) {
		pr_info("mon%d %s session established\n",
			monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr));
		monc->hunting = false;
	}
	dout("handle_subscribe_ack after %d seconds\n", seconds);
	monc->sub_renew_after = monc->sub_sent + (seconds >> 1)*HZ - 1;
	monc->sub_sent = 0;
	mutex_unlock(&monc->mutex);
	return;
bad:
	pr_err("got corrupt subscribe-ack msg\n");
}

/*
 * Keep track of which maps we have
 */
int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got)
{
	mutex_lock(&monc->mutex);
	monc->have_mdsmap = got;
	mutex_unlock(&monc->mutex);
	return 0;
}

int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got)
{
	mutex_lock(&monc->mutex);
	monc->have_osdmap = got;
	monc->want_next_osdmap = 0;
	mutex_unlock(&monc->mutex);
	return 0;
}

/*
 * Register interest in the next osdmap
 */
void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
{
	dout("request_next_osdmap have %u\n", monc->have_osdmap);
	mutex_lock(&monc->mutex);
	if (!monc->want_next_osdmap)
		monc->want_next_osdmap = 1;
	if (monc->want_next_osdmap < 2)
		__send_subscribe(monc);
	mutex_unlock(&monc->mutex);
}

#if 0
/*
 * mount
 */
static void __request_mount(struct ceph_mon_client *monc)
{
	struct ceph_msg *msg;
	struct ceph_client_mount *h;

	dout("__request_mount\n");
	msg = ceph_msg_new(CEPH_MSG_CLIENT_MOUNT, sizeof(*h), 0, 0, NULL);
	if (IS_ERR(msg))
		return;
	h = msg->front.iov_base;
	h->monhdr.have_version = 0;
	h->monhdr.session_mon = cpu_to_le16(-1);
	h->monhdr.session_mon_tid = 0;
	ceph_con_send(monc->con, msg);
}
#endif

/*
 * 
 */
int ceph_monc_open_session(struct ceph_mon_client *monc)
{
	if (!monc->con) {
		monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL);
		if (!monc->con)
			return -ENOMEM;
		ceph_con_init(monc->client->msgr, monc->con);
		monc->con->private = monc;
		monc->con->ops = &mon_con_ops;
	}

	mutex_lock(&monc->mutex);
	__open_session(monc);
	__schedule_delayed(monc);
	mutex_unlock(&monc->mutex);
	return 0;
}

/*
 * The monitor responds with mount ack indicate mount success.  The
 * included client ticket allows the client to talk to MDSs and OSDs.
 */
static void ceph_monc_handle_map(struct ceph_mon_client *monc,
				 struct ceph_msg *msg)
{
	struct ceph_client *client = monc->client;
	struct ceph_monmap *monmap = NULL, *old = monc->monmap;
	void *p, *end;

	mutex_lock(&monc->mutex);

	dout("handle_monmap\n");
	p = msg->front.iov_base;
	end = p + msg->front.iov_len;

	monmap = ceph_monmap_decode(p, end);
	if (IS_ERR(monmap)) {
		pr_err("problem decoding monmap, %d\n",
		       (int)PTR_ERR(monmap));
		return;
	}

	if (ceph_check_fsid(monc->client, &monmap->fsid) < 0) {
		kfree(monmap);
		return;
	}

	client->monc.monmap = monmap;
	kfree(old);

	mutex_unlock(&monc->mutex);
	wake_up(&client->mount_wq);
}

/*
 * statfs
 */
static void handle_statfs_reply(struct ceph_mon_client *monc,
				struct ceph_msg *msg)
{
	struct ceph_mon_statfs_request *req;
	struct ceph_mon_statfs_reply *reply = msg->front.iov_base;
	u64 tid;

	if (msg->front.iov_len != sizeof(*reply))
		goto bad;
	tid = le64_to_cpu(reply->tid);
	dout("handle_statfs_reply %p tid %llu\n", msg, tid);

	mutex_lock(&monc->mutex);
	req = radix_tree_lookup(&monc->statfs_request_tree, tid);
	if (req) {
		*req->buf = reply->st;
		req->result = 0;
	}
	mutex_unlock(&monc->mutex);
	if (req)
		complete(&req->completion);
	return;

bad:
	pr_err("corrupt statfs reply, no tid\n");
}

/*
 * (re)send a statfs request
 */
static int send_statfs(struct ceph_mon_client *monc,
		       struct ceph_mon_statfs_request *req)
{
	struct ceph_msg *msg;
	struct ceph_mon_statfs *h;

	dout("send_statfs tid %llu\n", req->tid);
	msg = ceph_msg_new(CEPH_MSG_STATFS, sizeof(*h), 0, 0, NULL);
	if (IS_ERR(msg))
		return PTR_ERR(msg);
	req->request = msg;
	h = msg->front.iov_base;
	h->monhdr.have_version = 0;
	h->monhdr.session_mon = cpu_to_le16(-1);
	h->monhdr.session_mon_tid = 0;
	h->fsid = monc->monmap->fsid;
	h->tid = cpu_to_le64(req->tid);
	ceph_con_send(monc->con, msg);
	return 0;
}

/*
 * Do a synchronous statfs().
 */
int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf)
{
	struct ceph_mon_statfs_request req;
	int err;

	req.buf = buf;
	init_completion(&req.completion);

	/* allocate memory for reply */
	err = ceph_msgpool_resv(&monc->msgpool_statfs_reply, 1);
	if (err)
		return err;

	/* register request */
	mutex_lock(&monc->mutex);
	req.tid = ++monc->last_tid;
	req.last_attempt = jiffies;
	req.delay = BASE_DELAY_INTERVAL;
	if (radix_tree_insert(&monc->statfs_request_tree, req.tid, &req) < 0) {
		mutex_unlock(&monc->mutex);
		pr_err("ENOMEM in do_statfs\n");
		return -ENOMEM;
	}
	monc->num_statfs_requests++;
	mutex_unlock(&monc->mutex);

	/* send request and wait */
	err = send_statfs(monc, &req);
	if (!err)
		err = wait_for_completion_interruptible(&req.completion);

	mutex_lock(&monc->mutex);
	radix_tree_delete(&monc->statfs_request_tree, req.tid);
	monc->num_statfs_requests--;
	ceph_msgpool_resv(&monc->msgpool_statfs_reply, -1);
	mutex_unlock(&monc->mutex);

	if (!err)
		err = req.result;
	return err;
}

/*
 * Resend pending statfs requests.
 */
static void __resend_statfs(struct ceph_mon_client *monc)
{
	u64 next_tid = 0;
	int got;
	int did = 0;
	struct ceph_mon_statfs_request *req;

	while (1) {
		got = radix_tree_gang_lookup(&monc->statfs_request_tree,
					     (void **)&req,
					     next_tid, 1);
		if (got == 0)
			break;
		did++;
		next_tid = req->tid + 1;

		send_statfs(monc, req);
	}
}

/*
 * Delayed work.  If we haven't mounted yet, retry.  Otherwise,
 * renew/retry subscription as needed (in case it is timing out, or we
 * got an ENOMEM).  And keep the monitor connection alive.
 */
static void delayed_work(struct work_struct *work)
{
	struct ceph_mon_client *monc =
		container_of(work, struct ceph_mon_client, delayed_work.work);

	dout("monc delayed_work\n");
	mutex_lock(&monc->mutex);
	if (monc->hunting) {
		__close_session(monc);
		__open_session(monc);  /* continue hunting */
	} else {
		ceph_con_keepalive(monc->con);
		if (monc->auth->ops->is_authenticated(monc->auth))
			__send_subscribe(monc);
	}
	__schedule_delayed(monc);
	mutex_unlock(&monc->mutex);
}

/*
 * On startup, we build a temporary monmap populated with the IPs
 * provided by mount(2).
 */
static int build_initial_monmap(struct ceph_mon_client *monc)
{
	struct ceph_mount_args *args = monc->client->mount_args;
	struct ceph_entity_addr *mon_addr = args->mon_addr;
	int num_mon = args->num_mon;
	int i;

	/* build initial monmap */
	monc->monmap = kzalloc(sizeof(*monc->monmap) +
			       num_mon*sizeof(monc->monmap->mon_inst[0]),
			       GFP_KERNEL);
	if (!monc->monmap)
		return -ENOMEM;
	for (i = 0; i < num_mon; i++) {
		monc->monmap->mon_inst[i].addr = mon_addr[i];
		monc->monmap->mon_inst[i].addr.erank = 0;
		monc->monmap->mon_inst[i].addr.nonce = 0;
		monc->monmap->mon_inst[i].name.type =
			CEPH_ENTITY_TYPE_MON;
		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
	}
	monc->monmap->num_mon = num_mon;
	monc->have_fsid = false;

	/* release addr memory */
	kfree(args->mon_addr);
	args->mon_addr = NULL;
	args->num_mon = 0;
	return 0;
}

int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
{
	int err = 0;

	dout("init\n");
	memset(monc, 0, sizeof(*monc));
	monc->client = cl;
	monc->monmap = NULL;
	mutex_init(&monc->mutex);

	err = build_initial_monmap(monc);
	if (err)
		goto out;

	monc->con = NULL;

	/* authentication */
	monc->auth = ceph_auth_init(cl->mount_args->name,
				    cl->mount_args->secret);
	if (IS_ERR(monc->auth))
		return PTR_ERR(monc->auth);
	monc->auth->want_keys =
		CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON |
		CEPH_ENTITY_TYPE_OSD | CEPH_ENTITY_TYPE_MDS;

	/* msg pools */
	err = ceph_msgpool_init(&monc->msgpool_subscribe_ack,
			       sizeof(struct ceph_mon_subscribe_ack), 1, false);
	if (err < 0)
		goto out_monmap;
	err = ceph_msgpool_init(&monc->msgpool_statfs_reply,
				sizeof(struct ceph_mon_statfs_reply), 0, false);
	if (err < 0)
		goto out_pool1;
	err = ceph_msgpool_init(&monc->msgpool_auth_reply, 4096, 1, false);
	if (err < 0)
		goto out_pool2;

	monc->m_auth = ceph_msg_new(CEPH_MSG_AUTH, 4096, 0, 0, NULL);
	if (IS_ERR(monc->m_auth)) {
		err = PTR_ERR(monc->m_auth);
		monc->m_auth = NULL;
		goto out_pool3;
	}

	monc->cur_mon = -1;
	monc->hunting = true;
	monc->sub_renew_after = jiffies;
	monc->sub_sent = 0;

	INIT_DELAYED_WORK(&monc->delayed_work, delayed_work);
	INIT_RADIX_TREE(&monc->statfs_request_tree, GFP_NOFS);
	monc->num_statfs_requests = 0;
	monc->last_tid = 0;

	monc->have_mdsmap = 0;
	monc->have_osdmap = 0;
	monc->want_next_osdmap = 1;
	return 0;

out_pool3:
	ceph_msgpool_destroy(&monc->msgpool_auth_reply);
out_pool2:
	ceph_msgpool_destroy(&monc->msgpool_subscribe_ack);
out_pool1:
	ceph_msgpool_destroy(&monc->msgpool_statfs_reply);
out_monmap:
	kfree(monc->monmap);
out:
	return err;
}

void ceph_monc_stop(struct ceph_mon_client *monc)
{
	dout("stop\n");
	cancel_delayed_work_sync(&monc->delayed_work);

	mutex_lock(&monc->mutex);
	__close_session(monc);
	if (monc->con) {
		monc->con->private = NULL;
		monc->con->ops->put(monc->con);
		monc->con = NULL;
	}
	mutex_unlock(&monc->mutex);

	ceph_auth_destroy(monc->auth);

	ceph_msg_put(monc->m_auth);
	ceph_msgpool_destroy(&monc->msgpool_subscribe_ack);
	ceph_msgpool_destroy(&monc->msgpool_statfs_reply);
	ceph_msgpool_destroy(&monc->msgpool_auth_reply);

	kfree(monc->monmap);
}


static void handle_auth_reply(struct ceph_mon_client *monc,
			      struct ceph_msg *msg)
{
	int ret;

	mutex_lock(&monc->mutex);
	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
				     msg->front.iov_len,
				     monc->m_auth->front.iov_base,
				     monc->m_auth->front_max);
	if (ret < 0) {
		monc->client->mount_err = ret;
		wake_up(&monc->client->mount_wq);
	} else if (ret > 0) {
		monc->m_auth->front.iov_len = ret;
		monc->m_auth->hdr.front_len = cpu_to_le32(ret);
		ceph_msg_get(monc->m_auth);  /* keep our ref */
		ceph_con_send(monc->con, monc->m_auth);
	} else if (monc->auth->ops->is_authenticated(monc->auth)) {
		dout("authenticated, starting session\n");

		monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
		monc->client->msgr->inst.name.num = monc->auth->global_id;

		__send_subscribe(monc);
		__resend_statfs(monc);
	}
	mutex_unlock(&monc->mutex);
}

/*
 * handle incoming message
 */
static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
	struct ceph_mon_client *monc = con->private;
	int type = le16_to_cpu(msg->hdr.type);

	if (!monc)
		return;

	switch (type) {
	case CEPH_MSG_AUTH_REPLY:
		handle_auth_reply(monc, msg);
		break;

	case CEPH_MSG_MON_SUBSCRIBE_ACK:
		handle_subscribe_ack(monc, msg);
		break;

	case CEPH_MSG_STATFS_REPLY:
		handle_statfs_reply(monc, msg);
		break;

	case CEPH_MSG_MON_MAP:
		ceph_monc_handle_map(monc, msg);
		break;

	case CEPH_MSG_MDS_MAP:
		ceph_mdsc_handle_map(&monc->client->mdsc, msg);
		break;

	case CEPH_MSG_OSD_MAP:
		ceph_osdc_handle_map(&monc->client->osdc, msg);
		break;

	default:
		pr_err("received unknown message type %d %s\n", type,
		       ceph_msg_type_name(type));
	}
	ceph_msg_put(msg);
}

/*
 * Allocate memory for incoming message
 */
static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
				      struct ceph_msg_header *hdr)
{
	struct ceph_mon_client *monc = con->private;
	int type = le16_to_cpu(hdr->type);
	int front = le32_to_cpu(hdr->front_len);

	switch (type) {
	case CEPH_MSG_MON_SUBSCRIBE_ACK:
		return ceph_msgpool_get(&monc->msgpool_subscribe_ack, front);
	case CEPH_MSG_STATFS_REPLY:
		return ceph_msgpool_get(&monc->msgpool_statfs_reply, front);
	case CEPH_MSG_AUTH_REPLY:
		return ceph_msgpool_get(&monc->msgpool_auth_reply, front);
	}
	return ceph_alloc_msg(con, hdr);
}

/*
 * If the monitor connection resets, pick a new monitor and resubmit
 * any pending requests.
 */
static void mon_fault(struct ceph_connection *con)
{
	struct ceph_mon_client *monc = con->private;

	if (!monc)
		return;

	dout("mon_fault\n");
	mutex_lock(&monc->mutex);
	if (!con->private)
		goto out;

	if (monc->con && !monc->hunting)
		pr_info("mon%d %s session lost, "
			"hunting for new mon\n", monc->cur_mon,
			pr_addr(&monc->con->peer_addr.in_addr));

	__close_session(monc);
	if (!monc->hunting) {
		/* start hunting */
		monc->hunting = true;
		__open_session(monc);
	} else {
		/* already hunting, let's wait a bit */
		__schedule_delayed(monc);
	}
out:
	mutex_unlock(&monc->mutex);
}

const static struct ceph_connection_operations mon_con_ops = {
	.get = ceph_con_get,
	.put = ceph_con_put,
	.dispatch = dispatch,
	.fault = mon_fault,
	.alloc_msg = mon_alloc_msg,
	.alloc_middle = ceph_alloc_middle,
};