summaryrefslogtreecommitdiffstats
path: root/net/smc/smc_core.c
blob: 87bb3e4771a818ae623262ab1c1b9ffca4f4f987 (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
/*
 *  Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 *  Basic Transport Functions exploiting Infiniband API
 *
 *  Copyright IBM Corp. 2016
 *
 *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 */

#include <linux/socket.h>
#include <linux/if_vlan.h>
#include <linux/random.h>
#include <linux/workqueue.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <rdma/ib_verbs.h>

#include "smc.h"
#include "smc_clc.h"
#include "smc_core.h"
#include "smc_ib.h"
#include "smc_wr.h"
#include "smc_llc.h"
#include "smc_cdc.h"
#include "smc_close.h"

#define SMC_LGR_NUM_INCR	256
#define SMC_LGR_FREE_DELAY	(600 * HZ)

static u32 smc_lgr_num;			/* unique link group number */

/* Register connection's alert token in our lookup structure.
 * To use rbtrees we have to implement our own insert core.
 * Requires @conns_lock
 * @smc		connection to register
 * Returns 0 on success, != otherwise.
 */
static void smc_lgr_add_alert_token(struct smc_connection *conn)
{
	struct rb_node **link, *parent = NULL;
	u32 token = conn->alert_token_local;

	link = &conn->lgr->conns_all.rb_node;
	while (*link) {
		struct smc_connection *cur = rb_entry(*link,
					struct smc_connection, alert_node);

		parent = *link;
		if (cur->alert_token_local > token)
			link = &parent->rb_left;
		else
			link = &parent->rb_right;
	}
	/* Put the new node there */
	rb_link_node(&conn->alert_node, parent, link);
	rb_insert_color(&conn->alert_node, &conn->lgr->conns_all);
}

/* Register connection in link group by assigning an alert token
 * registered in a search tree.
 * Requires @conns_lock
 * Note that '0' is a reserved value and not assigned.
 */
static void smc_lgr_register_conn(struct smc_connection *conn)
{
	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
	static atomic_t nexttoken = ATOMIC_INIT(0);

	/* find a new alert_token_local value not yet used by some connection
	 * in this link group
	 */
	sock_hold(&smc->sk); /* sock_put in smc_lgr_unregister_conn() */
	while (!conn->alert_token_local) {
		conn->alert_token_local = atomic_inc_return(&nexttoken);
		if (smc_lgr_find_conn(conn->alert_token_local, conn->lgr))
			conn->alert_token_local = 0;
	}
	smc_lgr_add_alert_token(conn);
	conn->lgr->conns_num++;
}

/* Unregister connection and reset the alert token of the given connection<
 */
static void __smc_lgr_unregister_conn(struct smc_connection *conn)
{
	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
	struct smc_link_group *lgr = conn->lgr;

	rb_erase(&conn->alert_node, &lgr->conns_all);
	lgr->conns_num--;
	conn->alert_token_local = 0;
	conn->lgr = NULL;
	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
}

/* Unregister connection and trigger lgr freeing if applicable
 */
static void smc_lgr_unregister_conn(struct smc_connection *conn)
{
	struct smc_link_group *lgr = conn->lgr;
	int reduced = 0;

	write_lock_bh(&lgr->conns_lock);
	if (conn->alert_token_local) {
		reduced = 1;
		__smc_lgr_unregister_conn(conn);
	}
	write_unlock_bh(&lgr->conns_lock);
	if (reduced && !lgr->conns_num)
		schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
}

static void smc_lgr_free_work(struct work_struct *work)
{
	struct smc_link_group *lgr = container_of(to_delayed_work(work),
						  struct smc_link_group,
						  free_work);
	bool conns;

	spin_lock_bh(&smc_lgr_list.lock);
	read_lock_bh(&lgr->conns_lock);
	conns = RB_EMPTY_ROOT(&lgr->conns_all);
	read_unlock_bh(&lgr->conns_lock);
	if (!conns) { /* number of lgr connections is no longer zero */
		spin_unlock_bh(&smc_lgr_list.lock);
		return;
	}
	list_del_init(&lgr->list); /* remove from smc_lgr_list */
	spin_unlock_bh(&smc_lgr_list.lock);
	smc_lgr_free(lgr);
}

/* create a new SMC link group */
static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr,
			  struct smc_ib_device *smcibdev, u8 ibport,
			  char *peer_systemid, unsigned short vlan_id)
{
	struct smc_link_group *lgr;
	struct smc_link *lnk;
	u8 rndvec[3];
	int rc = 0;
	int i;

	lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
	if (!lgr) {
		rc = -ENOMEM;
		goto out;
	}
	lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
	lgr->sync_err = false;
	lgr->daddr = peer_in_addr;
	memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
	lgr->vlan_id = vlan_id;
	rwlock_init(&lgr->sndbufs_lock);
	rwlock_init(&lgr->rmbs_lock);
	for (i = 0; i < SMC_RMBE_SIZES; i++) {
		INIT_LIST_HEAD(&lgr->sndbufs[i]);
		INIT_LIST_HEAD(&lgr->rmbs[i]);
	}
	smc_lgr_num += SMC_LGR_NUM_INCR;
	memcpy(&lgr->id, (u8 *)&smc_lgr_num, SMC_LGR_ID_SIZE);
	INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
	lgr->conns_all = RB_ROOT;

	lnk = &lgr->lnk[SMC_SINGLE_LINK];
	/* initialize link */
	lnk->smcibdev = smcibdev;
	lnk->ibport = ibport;
	lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
	if (!smcibdev->initialized)
		smc_ib_setup_per_ibdev(smcibdev);
	get_random_bytes(rndvec, sizeof(rndvec));
	lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16);
	rc = smc_wr_alloc_link_mem(lnk);
	if (rc)
		goto free_lgr;
	rc = smc_ib_create_protection_domain(lnk);
	if (rc)
		goto free_link_mem;
	rc = smc_ib_create_queue_pair(lnk);
	if (rc)
		goto dealloc_pd;
	rc = smc_wr_create_link(lnk);
	if (rc)
		goto destroy_qp;
	init_completion(&lnk->llc_confirm);
	init_completion(&lnk->llc_confirm_resp);

	smc->conn.lgr = lgr;
	rwlock_init(&lgr->conns_lock);
	spin_lock_bh(&smc_lgr_list.lock);
	list_add(&lgr->list, &smc_lgr_list.list);
	spin_unlock_bh(&smc_lgr_list.lock);
	return 0;

destroy_qp:
	smc_ib_destroy_queue_pair(lnk);
dealloc_pd:
	smc_ib_dealloc_protection_domain(lnk);
free_link_mem:
	smc_wr_free_link_mem(lnk);
free_lgr:
	kfree(lgr);
out:
	return rc;
}

static void smc_sndbuf_unuse(struct smc_connection *conn)
{
	if (conn->sndbuf_desc) {
		conn->sndbuf_desc->used = 0;
		conn->sndbuf_size = 0;
	}
}

static void smc_rmb_unuse(struct smc_connection *conn)
{
	if (conn->rmb_desc) {
		conn->rmb_desc->reused = true;
		conn->rmb_desc->used = 0;
		conn->rmbe_size = 0;
	}
}

/* remove a finished connection from its link group */
void smc_conn_free(struct smc_connection *conn)
{
	struct smc_link_group *lgr = conn->lgr;

	if (!lgr)
		return;
	smc_cdc_tx_dismiss_slots(conn);
	smc_lgr_unregister_conn(conn);
	smc_rmb_unuse(conn);
	smc_sndbuf_unuse(conn);
}

static void smc_link_clear(struct smc_link *lnk)
{
	lnk->peer_qpn = 0;
	smc_ib_modify_qp_reset(lnk);
	smc_wr_free_link(lnk);
	smc_ib_destroy_queue_pair(lnk);
	smc_ib_dealloc_protection_domain(lnk);
	smc_wr_free_link_mem(lnk);
}

static void smc_lgr_free_sndbufs(struct smc_link_group *lgr)
{
	struct smc_buf_desc *sndbuf_desc, *bf_desc;
	int i;

	for (i = 0; i < SMC_RMBE_SIZES; i++) {
		list_for_each_entry_safe(sndbuf_desc, bf_desc, &lgr->sndbufs[i],
					 list) {
			list_del(&sndbuf_desc->list);
			smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
					 smc_uncompress_bufsize(i),
					 sndbuf_desc, DMA_TO_DEVICE);
			kfree(sndbuf_desc->cpu_addr);
			kfree(sndbuf_desc);
		}
	}
}

static void smc_lgr_free_rmbs(struct smc_link_group *lgr)
{
	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
	struct smc_buf_desc *rmb_desc, *bf_desc;
	int i;

	for (i = 0; i < SMC_RMBE_SIZES; i++) {
		list_for_each_entry_safe(rmb_desc, bf_desc, &lgr->rmbs[i],
					 list) {
			list_del(&rmb_desc->list);
			smc_ib_put_memory_region(
					rmb_desc->mr_rx[SMC_SINGLE_LINK]);
			smc_ib_buf_unmap_sg(lnk->smcibdev, rmb_desc,
					    DMA_FROM_DEVICE);
			kfree(rmb_desc->cpu_addr);
			kfree(rmb_desc);
		}
	}
}

/* remove a link group */
void smc_lgr_free(struct smc_link_group *lgr)
{
	smc_lgr_free_rmbs(lgr);
	smc_lgr_free_sndbufs(lgr);
	smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
	kfree(lgr);
}

/* terminate linkgroup abnormally */
void smc_lgr_terminate(struct smc_link_group *lgr)
{
	struct smc_connection *conn;
	struct smc_sock *smc;
	struct rb_node *node;

	spin_lock_bh(&smc_lgr_list.lock);
	if (list_empty(&lgr->list)) {
		/* termination already triggered */
		spin_unlock_bh(&smc_lgr_list.lock);
		return;
	}
	/* do not use this link group for new connections */
	list_del_init(&lgr->list);
	spin_unlock_bh(&smc_lgr_list.lock);

	write_lock_bh(&lgr->conns_lock);
	node = rb_first(&lgr->conns_all);
	while (node) {
		conn = rb_entry(node, struct smc_connection, alert_node);
		smc = container_of(conn, struct smc_sock, conn);
		sock_hold(&smc->sk);
		__smc_lgr_unregister_conn(conn);
		schedule_work(&conn->close_work);
		sock_put(&smc->sk);
		node = rb_first(&lgr->conns_all);
	}
	write_unlock_bh(&lgr->conns_lock);
}

/* Determine vlan of internal TCP socket.
 * @vlan_id: address to store the determined vlan id into
 */
static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
{
	struct dst_entry *dst = sk_dst_get(clcsock->sk);
	int rc = 0;

	*vlan_id = 0;
	if (!dst) {
		rc = -ENOTCONN;
		goto out;
	}
	if (!dst->dev) {
		rc = -ENODEV;
		goto out_rel;
	}

	if (is_vlan_dev(dst->dev))
		*vlan_id = vlan_dev_vlan_id(dst->dev);

out_rel:
	dst_release(dst);
out:
	return rc;
}

/* determine the link gid matching the vlan id of the link group */
static int smc_link_determine_gid(struct smc_link_group *lgr)
{
	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
	struct ib_gid_attr gattr;
	union ib_gid gid;
	int i;

	if (!lgr->vlan_id) {
		lnk->gid = lnk->smcibdev->gid[lnk->ibport - 1];
		return 0;
	}

	for (i = 0; i < lnk->smcibdev->pattr[lnk->ibport - 1].gid_tbl_len;
	     i++) {
		if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
				 &gattr))
			continue;
		if (gattr.ndev &&
		    (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) {
			lnk->gid = gid;
			return 0;
		}
	}
	return -ENODEV;
}

/* create a new SMC connection (and a new link group if necessary) */
int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr,
		    struct smc_ib_device *smcibdev, u8 ibport,
		    struct smc_clc_msg_local *lcl, int srv_first_contact)
{
	struct smc_connection *conn = &smc->conn;
	struct smc_link_group *lgr;
	unsigned short vlan_id;
	enum smc_lgr_role role;
	int local_contact = SMC_FIRST_CONTACT;
	int rc = 0;

	role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
	rc = smc_vlan_by_tcpsk(smc->clcsock, &vlan_id);
	if (rc)
		return rc;

	if ((role == SMC_CLNT) && srv_first_contact)
		/* create new link group as well */
		goto create;

	/* determine if an existing link group can be reused */
	spin_lock_bh(&smc_lgr_list.lock);
	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
		write_lock_bh(&lgr->conns_lock);
		if (!memcmp(lgr->peer_systemid, lcl->id_for_peer,
			    SMC_SYSTEMID_LEN) &&
		    !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
			    SMC_GID_SIZE) &&
		    !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
			    sizeof(lcl->mac)) &&
		    !lgr->sync_err &&
		    (lgr->role == role) &&
		    (lgr->vlan_id == vlan_id) &&
		    ((role == SMC_CLNT) ||
		     (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) {
			/* link group found */
			local_contact = SMC_REUSE_CONTACT;
			conn->lgr = lgr;
			smc_lgr_register_conn(conn); /* add smc conn to lgr */
			write_unlock_bh(&lgr->conns_lock);
			break;
		}
		write_unlock_bh(&lgr->conns_lock);
	}
	spin_unlock_bh(&smc_lgr_list.lock);

	if (role == SMC_CLNT && !srv_first_contact &&
	    (local_contact == SMC_FIRST_CONTACT)) {
		/* Server reuses a link group, but Client wants to start
		 * a new one
		 * send out_of_sync decline, reason synchr. error
		 */
		return -ENOLINK;
	}

create:
	if (local_contact == SMC_FIRST_CONTACT) {
		rc = smc_lgr_create(smc, peer_in_addr, smcibdev, ibport,
				    lcl->id_for_peer, vlan_id);
		if (rc)
			goto out;
		smc_lgr_register_conn(conn); /* add smc conn to lgr */
		rc = smc_link_determine_gid(conn->lgr);
	}
	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
	conn->local_tx_ctrl.len = sizeof(struct smc_cdc_msg);
#ifndef KERNEL_HAS_ATOMIC64
	spin_lock_init(&conn->acurs_lock);
#endif

out:
	return rc ? rc : local_contact;
}

/* try to reuse a sndbuf description slot of the sndbufs list for a certain
 * buf_size; if not available, return NULL
 */
static inline
struct smc_buf_desc *smc_sndbuf_get_slot(struct smc_link_group *lgr,
					 int compressed_bufsize)
{
	struct smc_buf_desc *sndbuf_slot;

	read_lock_bh(&lgr->sndbufs_lock);
	list_for_each_entry(sndbuf_slot, &lgr->sndbufs[compressed_bufsize],
			    list) {
		if (cmpxchg(&sndbuf_slot->used, 0, 1) == 0) {
			read_unlock_bh(&lgr->sndbufs_lock);
			return sndbuf_slot;
		}
	}
	read_unlock_bh(&lgr->sndbufs_lock);
	return NULL;
}

/* try to reuse an rmb description slot of the rmbs list for a certain
 * rmbe_size; if not available, return NULL
 */
static inline
struct smc_buf_desc *smc_rmb_get_slot(struct smc_link_group *lgr,
				      int compressed_bufsize)
{
	struct smc_buf_desc *rmb_slot;

	read_lock_bh(&lgr->rmbs_lock);
	list_for_each_entry(rmb_slot, &lgr->rmbs[compressed_bufsize],
			    list) {
		if (cmpxchg(&rmb_slot->used, 0, 1) == 0) {
			read_unlock_bh(&lgr->rmbs_lock);
			return rmb_slot;
		}
	}
	read_unlock_bh(&lgr->rmbs_lock);
	return NULL;
}

/* one of the conditions for announcing a receiver's current window size is
 * that it "results in a minimum increase in the window size of 10% of the
 * receive buffer space" [RFC7609]
 */
static inline int smc_rmb_wnd_update_limit(int rmbe_size)
{
	return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
}

/* create the tx buffer for an SMC socket */
int smc_sndbuf_create(struct smc_sock *smc)
{
	struct smc_connection *conn = &smc->conn;
	struct smc_link_group *lgr = conn->lgr;
	struct smc_buf_desc *sndbuf_desc;
	int bufsize, bufsize_short;
	int rc;

	/* use socket send buffer size (w/o overhead) as start value */
	for (bufsize_short = smc_compress_bufsize(smc->sk.sk_sndbuf / 2);
	     bufsize_short >= 0; bufsize_short--) {
		bufsize = smc_uncompress_bufsize(bufsize_short);
		/* check for reusable sndbuf_slot in the link group */
		sndbuf_desc = smc_sndbuf_get_slot(lgr, bufsize_short);
		if (sndbuf_desc) {
			memset(sndbuf_desc->cpu_addr, 0, bufsize);
			break; /* found reusable slot */
		}
		/* try to alloc a new send buffer */
		sndbuf_desc = kzalloc(sizeof(*sndbuf_desc), GFP_KERNEL);
		if (!sndbuf_desc)
			break; /* give up with -ENOMEM */
		sndbuf_desc->cpu_addr = kzalloc(bufsize,
						GFP_KERNEL | __GFP_NOWARN |
						__GFP_NOMEMALLOC |
						__GFP_NORETRY);
		if (!sndbuf_desc->cpu_addr) {
			kfree(sndbuf_desc);
			sndbuf_desc = NULL;
			/* if send buffer allocation has failed,
			 * try a smaller one
			 */
			continue;
		}
		rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
				    bufsize, sndbuf_desc, DMA_TO_DEVICE);
		if (rc) {
			kfree(sndbuf_desc->cpu_addr);
			kfree(sndbuf_desc);
			sndbuf_desc = NULL;
			continue; /* if mapping failed, try smaller one */
		}
		sndbuf_desc->used = 1;
		write_lock_bh(&lgr->sndbufs_lock);
		list_add(&sndbuf_desc->list, &lgr->sndbufs[bufsize_short]);
		write_unlock_bh(&lgr->sndbufs_lock);
		break;
	}
	if (sndbuf_desc && sndbuf_desc->cpu_addr) {
		conn->sndbuf_desc = sndbuf_desc;
		conn->sndbuf_size = bufsize;
		smc->sk.sk_sndbuf = bufsize * 2;
		atomic_set(&conn->sndbuf_space, bufsize);
		return 0;
	} else {
		return -ENOMEM;
	}
}

/* create the RMB for an SMC socket (even though the SMC protocol
 * allows more than one RMB-element per RMB, the Linux implementation
 * uses just one RMB-element per RMB, i.e. uses an extra RMB for every
 * connection in a link group
 */
int smc_rmb_create(struct smc_sock *smc)
{
	struct smc_connection *conn = &smc->conn;
	struct smc_link_group *lgr = conn->lgr;
	struct smc_buf_desc *rmb_desc;
	int bufsize, bufsize_short;
	int rc;

	/* use socket recv buffer size (w/o overhead) as start value */
	for (bufsize_short = smc_compress_bufsize(smc->sk.sk_rcvbuf / 2);
	     bufsize_short >= 0; bufsize_short--) {
		bufsize = smc_uncompress_bufsize(bufsize_short);
		if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC)
			continue;

		/* check for reusable rmb_slot in the link group */
		rmb_desc = smc_rmb_get_slot(lgr, bufsize_short);
		if (rmb_desc) {
			memset(rmb_desc->cpu_addr, 0, bufsize);
			break; /* found reusable slot */
		}

		/* try to alloc a new RMB */
		rmb_desc = kzalloc(sizeof(*rmb_desc), GFP_KERNEL);
		if (!rmb_desc)
			break; /* give up with -ENOMEM */
		rmb_desc->cpu_addr =
			(void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN |
						 __GFP_NOMEMALLOC |
						 __GFP_NORETRY | __GFP_ZERO,
						 get_order(bufsize));
		if (!rmb_desc->cpu_addr) {
			kfree(rmb_desc);
			rmb_desc = NULL;
			continue;
		}
		rmb_desc->order = get_order(bufsize);

		rc = sg_alloc_table(&rmb_desc->sgt[SMC_SINGLE_LINK], 1,
				    GFP_KERNEL);
		if (rc) {
			free_pages((unsigned long)rmb_desc->cpu_addr,
				   rmb_desc->order);
			kfree(rmb_desc);
			rmb_desc = NULL;
			continue;
		}
		sg_set_buf(rmb_desc->sgt[SMC_SINGLE_LINK].sgl,
			   rmb_desc->cpu_addr, bufsize);

		rc = smc_ib_buf_map_sg(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
				       rmb_desc, DMA_FROM_DEVICE);
		if (rc != 1)  {
			sg_free_table(&rmb_desc->sgt[SMC_SINGLE_LINK]);
			free_pages((unsigned long)rmb_desc->cpu_addr,
				   rmb_desc->order);
			kfree(rmb_desc);
			rmb_desc = NULL;
			continue; /* if mapping failed, try smaller one */
		}
		rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd,
					      IB_ACCESS_REMOTE_WRITE |
					      IB_ACCESS_LOCAL_WRITE,
					      rmb_desc);
		if (rc) {
			smc_ib_buf_unmap_sg(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
					    rmb_desc, DMA_FROM_DEVICE);
			sg_free_table(&rmb_desc->sgt[SMC_SINGLE_LINK]);
			free_pages((unsigned long)rmb_desc->cpu_addr,
				   rmb_desc->order);
			kfree(rmb_desc);
			rmb_desc = NULL;
			continue;
		}

		rmb_desc->used = 1;
		write_lock_bh(&lgr->rmbs_lock);
		list_add(&rmb_desc->list, &lgr->rmbs[bufsize_short]);
		write_unlock_bh(&lgr->rmbs_lock);
		break;
	}
	if (rmb_desc && rmb_desc->cpu_addr) {
		conn->rmb_desc = rmb_desc;
		conn->rmbe_size = bufsize;
		conn->rmbe_size_short = bufsize_short;
		smc->sk.sk_rcvbuf = bufsize * 2;
		atomic_set(&conn->bytes_to_rcv, 0);
		conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
		return 0;
	} else {
		return -ENOMEM;
	}
}

static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr)
{
	int i;

	for_each_clear_bit(i, lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX) {
		if (!test_and_set_bit(i, lgr->rtokens_used_mask))
			return i;
	}
	return -ENOSPC;
}

/* save rkey and dma_addr received from peer during clc handshake */
int smc_rmb_rtoken_handling(struct smc_connection *conn,
			    struct smc_clc_msg_accept_confirm *clc)
{
	u64 dma_addr = be64_to_cpu(clc->rmb_dma_addr);
	struct smc_link_group *lgr = conn->lgr;
	u32 rkey = ntohl(clc->rmb_rkey);
	int i;

	for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
		if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) &&
		    (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) &&
		    test_bit(i, lgr->rtokens_used_mask)) {
			conn->rtoken_idx = i;
			return 0;
		}
	}
	conn->rtoken_idx = smc_rmb_reserve_rtoken_idx(lgr);
	if (conn->rtoken_idx < 0)
		return conn->rtoken_idx;
	lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey = rkey;
	lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr = dma_addr;
	return 0;
}