summaryrefslogtreecommitdiff
path: root/net/smc/smc_ib.c
blob: fc766b537ac7a9c2b36272c7f9b03e567b7bc6d0 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 *  IB infrastructure:
 *  Establish SMC-R as an Infiniband Client to be notified about added and
 *  removed IB devices of type RDMA.
 *  Determine device and port characteristics for these IB devices.
 *
 *  Copyright IBM Corp. 2016
 *
 *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 */

#include <linux/random.h>
#include <linux/workqueue.h>
#include <linux/scatterlist.h>
#include <linux/wait.h>
#include <linux/mutex.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>

#include "smc_pnet.h"
#include "smc_ib.h"
#include "smc_core.h"
#include "smc_wr.h"
#include "smc.h"

#define SMC_MAX_CQE 32766	/* max. # of completion queue elements */

#define SMC_QP_MIN_RNR_TIMER		5
#define SMC_QP_TIMEOUT			15 /* 4096 * 2 ** timeout usec */
#define SMC_QP_RETRY_CNT			7 /* 7: infinite */
#define SMC_QP_RNR_RETRY			7 /* 7: infinite */

struct smc_ib_devices smc_ib_devices = {	/* smc-registered ib devices */
	.mutex = __MUTEX_INITIALIZER(smc_ib_devices.mutex),
	.list = LIST_HEAD_INIT(smc_ib_devices.list),
};

u8 local_systemid[SMC_SYSTEMID_LEN];		/* unique system identifier */

static int smc_ib_modify_qp_init(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_INIT;
	qp_attr.pkey_index = 0;
	qp_attr.port_num = lnk->ibport;
	qp_attr.qp_access_flags = IB_ACCESS_LOCAL_WRITE
				| IB_ACCESS_REMOTE_WRITE;
	return ib_modify_qp(lnk->roce_qp, &qp_attr,
			    IB_QP_STATE | IB_QP_PKEY_INDEX |
			    IB_QP_ACCESS_FLAGS | IB_QP_PORT);
}

static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
{
	enum ib_qp_attr_mask qp_attr_mask =
		IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN |
		IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER;
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RTR;
	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
	       sizeof(lnk->peer_mac));
	qp_attr.dest_qp_num = lnk->peer_qpn;
	qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */
	qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming
					 * requests
					 */
	qp_attr.min_rnr_timer = SMC_QP_MIN_RNR_TIMER;

	return ib_modify_qp(lnk->roce_qp, &qp_attr, qp_attr_mask);
}

int smc_ib_modify_qp_rts(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RTS;
	qp_attr.timeout = SMC_QP_TIMEOUT;	/* local ack timeout */
	qp_attr.retry_cnt = SMC_QP_RETRY_CNT;	/* retry count */
	qp_attr.rnr_retry = SMC_QP_RNR_RETRY;	/* RNR retries, 7=infinite */
	qp_attr.sq_psn = lnk->psn_initial;	/* starting send packet seq # */
	qp_attr.max_rd_atomic = 1;	/* # of outstanding RDMA reads and
					 * atomic ops allowed
					 */
	return ib_modify_qp(lnk->roce_qp, &qp_attr,
			    IB_QP_STATE | IB_QP_TIMEOUT | IB_QP_RETRY_CNT |
			    IB_QP_SQ_PSN | IB_QP_RNR_RETRY |
			    IB_QP_MAX_QP_RD_ATOMIC);
}

int smc_ib_modify_qp_reset(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RESET;
	return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
}

int smc_ib_ready_link(struct smc_link *lnk)
{
	struct smc_link_group *lgr = smc_get_lgr(lnk);
	int rc = 0;

	rc = smc_ib_modify_qp_init(lnk);
	if (rc)
		goto out;

	rc = smc_ib_modify_qp_rtr(lnk);
	if (rc)
		goto out;
	smc_wr_remember_qp_attr(lnk);
	rc = ib_req_notify_cq(lnk->smcibdev->roce_cq_recv,
			      IB_CQ_SOLICITED_MASK);
	if (rc)
		goto out;
	rc = smc_wr_rx_post_init(lnk);
	if (rc)
		goto out;
	smc_wr_remember_qp_attr(lnk);

	if (lgr->role == SMC_SERV) {
		rc = smc_ib_modify_qp_rts(lnk);
		if (rc)
			goto out;
		smc_wr_remember_qp_attr(lnk);
	}
out:
	return rc;
}

static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
	const struct ib_gid_attr *attr;
	int rc;

	attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0);
	if (IS_ERR(attr))
		return -ENODEV;

	rc = rdma_read_gid_l2_fields(attr, NULL, smcibdev->mac[ibport - 1]);
	rdma_put_gid_attr(attr);
	return rc;
}

/* Create an identifier unique for this instance of SMC-R.
 * The MAC-address of the first active registered IB device
 * plus a random 2-byte number is used to create this identifier.
 * This name is delivered to the peer during connection initialization.
 */
static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
						u8 ibport)
{
	memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
	       sizeof(smcibdev->mac[ibport - 1]));
}

bool smc_ib_is_valid_local_systemid(void)
{
	return !is_zero_ether_addr(&local_systemid[2]);
}

static void smc_ib_init_local_systemid(void)
{
	get_random_bytes(&local_systemid[0], 2);
}

bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
{
	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
}

/* determine the gid for an ib-device port and vlan id */
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
{
	const struct ib_gid_attr *attr;
	const struct net_device *ndev;
	int i;

	for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
		attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i);
		if (IS_ERR(attr))
			continue;

		rcu_read_lock();
		ndev = rdma_read_gid_attr_ndev_rcu(attr);
		if (!IS_ERR(ndev) &&
		    ((!vlan_id && !is_vlan_dev(ndev)) ||
		     (vlan_id && is_vlan_dev(ndev) &&
		      vlan_dev_vlan_id(ndev) == vlan_id)) &&
		    attr->gid_type == IB_GID_TYPE_ROCE) {
			rcu_read_unlock();
			if (gid)
				memcpy(gid, &attr->gid, SMC_GID_SIZE);
			if (sgid_index)
				*sgid_index = attr->index;
			rdma_put_gid_attr(attr);
			return 0;
		}
		rcu_read_unlock();
		rdma_put_gid_attr(attr);
	}
	return -ENODEV;
}

static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
{
	int rc;

	memset(&smcibdev->pattr[ibport - 1], 0,
	       sizeof(smcibdev->pattr[ibport - 1]));
	rc = ib_query_port(smcibdev->ibdev, ibport,
			   &smcibdev->pattr[ibport - 1]);
	if (rc)
		goto out;
	/* the SMC protocol requires specification of the RoCE MAC address */
	rc = smc_ib_fill_mac(smcibdev, ibport);
	if (rc)
		goto out;
	if (!smc_ib_is_valid_local_systemid() &&
	    smc_ib_port_active(smcibdev, ibport))
		/* create unique system identifier */
		smc_ib_define_local_systemid(smcibdev, ibport);
out:
	return rc;
}

/* process context wrapper for might_sleep smc_ib_remember_port_attr */
static void smc_ib_port_event_work(struct work_struct *work)
{
	struct smc_ib_device *smcibdev = container_of(
		work, struct smc_ib_device, port_event_work);
	u8 port_idx;

	for_each_set_bit(port_idx, &smcibdev->port_event_mask, SMC_MAX_PORTS) {
		smc_ib_remember_port_attr(smcibdev, port_idx + 1);
		clear_bit(port_idx, &smcibdev->port_event_mask);
		if (!smc_ib_port_active(smcibdev, port_idx + 1)) {
			set_bit(port_idx, smcibdev->ports_going_away);
			smcr_port_err(smcibdev, port_idx + 1);
		} else {
			clear_bit(port_idx, smcibdev->ports_going_away);
			smcr_port_add(smcibdev, port_idx + 1);
		}
	}
}

/* can be called in IRQ context */
static void smc_ib_global_event_handler(struct ib_event_handler *handler,
					struct ib_event *ibevent)
{
	struct smc_ib_device *smcibdev;
	bool schedule = false;
	u8 port_idx;

	smcibdev = container_of(handler, struct smc_ib_device, event_handler);

	switch (ibevent->event) {
	case IB_EVENT_DEVICE_FATAL:
		/* terminate all ports on device */
		for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) {
			set_bit(port_idx, &smcibdev->port_event_mask);
			if (!test_and_set_bit(port_idx,
					      smcibdev->ports_going_away))
				schedule = true;
		}
		if (schedule)
			schedule_work(&smcibdev->port_event_work);
		break;
	case IB_EVENT_PORT_ACTIVE:
		port_idx = ibevent->element.port_num - 1;
		if (port_idx >= SMC_MAX_PORTS)
			break;
		set_bit(port_idx, &smcibdev->port_event_mask);
		if (test_and_clear_bit(port_idx, smcibdev->ports_going_away))
			schedule_work(&smcibdev->port_event_work);
		break;
	case IB_EVENT_PORT_ERR:
		port_idx = ibevent->element.port_num - 1;
		if (port_idx >= SMC_MAX_PORTS)
			break;
		set_bit(port_idx, &smcibdev->port_event_mask);
		if (!test_and_set_bit(port_idx, smcibdev->ports_going_away))
			schedule_work(&smcibdev->port_event_work);
		break;
	case IB_EVENT_GID_CHANGE:
		port_idx = ibevent->element.port_num - 1;
		if (port_idx >= SMC_MAX_PORTS)
			break;
		set_bit(port_idx, &smcibdev->port_event_mask);
		schedule_work(&smcibdev->port_event_work);
		break;
	default:
		break;
	}
}

void smc_ib_dealloc_protection_domain(struct smc_link *lnk)
{
	if (lnk->roce_pd)
		ib_dealloc_pd(lnk->roce_pd);
	lnk->roce_pd = NULL;
}

int smc_ib_create_protection_domain(struct smc_link *lnk)
{
	int rc;

	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
	rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
	if (IS_ERR(lnk->roce_pd))
		lnk->roce_pd = NULL;
	return rc;
}

static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
	struct smc_link *lnk = (struct smc_link *)priv;
	struct smc_ib_device *smcibdev = lnk->smcibdev;
	u8 port_idx;

	switch (ibevent->event) {
	case IB_EVENT_QP_FATAL:
	case IB_EVENT_QP_ACCESS_ERR:
		port_idx = ibevent->element.qp->port - 1;
		if (port_idx >= SMC_MAX_PORTS)
			break;
		set_bit(port_idx, &smcibdev->port_event_mask);
		if (!test_and_set_bit(port_idx, smcibdev->ports_going_away))
			schedule_work(&smcibdev->port_event_work);
		break;
	default:
		break;
	}
}

void smc_ib_destroy_queue_pair(struct smc_link *lnk)
{
	if (lnk->roce_qp)
		ib_destroy_qp(lnk->roce_qp);
	lnk->roce_qp = NULL;
}

/* create a queue pair within the protection domain for a link */
int smc_ib_create_queue_pair(struct smc_link *lnk)
{
	struct ib_qp_init_attr qp_attr = {
		.event_handler = smc_ib_qp_event_handler,
		.qp_context = lnk,
		.send_cq = lnk->smcibdev->roce_cq_send,
		.recv_cq = lnk->smcibdev->roce_cq_recv,
		.srq = NULL,
		.cap = {
				/* include unsolicited rdma_writes as well,
				 * there are max. 2 RDMA_WRITE per 1 WR_SEND
				 */
			.max_send_wr = SMC_WR_BUF_CNT * 3,
			.max_recv_wr = SMC_WR_BUF_CNT * 3,
			.max_send_sge = SMC_IB_MAX_SEND_SGE,
			.max_recv_sge = 1,
		},
		.sq_sig_type = IB_SIGNAL_REQ_WR,
		.qp_type = IB_QPT_RC,
	};
	int rc;

	lnk->roce_qp = ib_create_qp(lnk->roce_pd, &qp_attr);
	rc = PTR_ERR_OR_ZERO(lnk->roce_qp);
	if (IS_ERR(lnk->roce_qp))
		lnk->roce_qp = NULL;
	else
		smc_wr_remember_qp_attr(lnk);
	return rc;
}

void smc_ib_put_memory_region(struct ib_mr *mr)
{
	ib_dereg_mr(mr);
}

static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot, u8 link_idx)
{
	unsigned int offset = 0;
	int sg_num;

	/* map the largest prefix of a dma mapped SG list */
	sg_num = ib_map_mr_sg(buf_slot->mr_rx[link_idx],
			      buf_slot->sgt[link_idx].sgl,
			      buf_slot->sgt[link_idx].orig_nents,
			      &offset, PAGE_SIZE);

	return sg_num;
}

/* Allocate a memory region and map the dma mapped SG list of buf_slot */
int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
			     struct smc_buf_desc *buf_slot, u8 link_idx)
{
	if (buf_slot->mr_rx[link_idx])
		return 0; /* already done */

	buf_slot->mr_rx[link_idx] =
		ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order);
	if (IS_ERR(buf_slot->mr_rx[link_idx])) {
		int rc;

		rc = PTR_ERR(buf_slot->mr_rx[link_idx]);
		buf_slot->mr_rx[link_idx] = NULL;
		return rc;
	}

	if (smc_ib_map_mr_sg(buf_slot, link_idx) != 1)
		return -EINVAL;

	return 0;
}

/* synchronize buffer usage for cpu access */
void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
			    struct smc_buf_desc *buf_slot,
			    enum dma_data_direction data_direction)
{
	struct scatterlist *sg;
	unsigned int i;

	/* for now there is just one DMA address */
	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
		    buf_slot->sgt[lnk->link_idx].nents, i) {
		if (!sg_dma_len(sg))
			break;
		ib_dma_sync_single_for_cpu(lnk->smcibdev->ibdev,
					   sg_dma_address(sg),
					   sg_dma_len(sg),
					   data_direction);
	}
}

/* synchronize buffer usage for device access */
void smc_ib_sync_sg_for_device(struct smc_link *lnk,
			       struct smc_buf_desc *buf_slot,
			       enum dma_data_direction data_direction)
{
	struct scatterlist *sg;
	unsigned int i;

	/* for now there is just one DMA address */
	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
		    buf_slot->sgt[lnk->link_idx].nents, i) {
		if (!sg_dma_len(sg))
			break;
		ib_dma_sync_single_for_device(lnk->smcibdev->ibdev,
					      sg_dma_address(sg),
					      sg_dma_len(sg),
					      data_direction);
	}
}

/* Map a new TX or RX buffer SG-table to DMA */
int smc_ib_buf_map_sg(struct smc_link *lnk,
		      struct smc_buf_desc *buf_slot,
		      enum dma_data_direction data_direction)
{
	int mapped_nents;

	mapped_nents = ib_dma_map_sg(lnk->smcibdev->ibdev,
				     buf_slot->sgt[lnk->link_idx].sgl,
				     buf_slot->sgt[lnk->link_idx].orig_nents,
				     data_direction);
	if (!mapped_nents)
		return -ENOMEM;

	return mapped_nents;
}

void smc_ib_buf_unmap_sg(struct smc_link *lnk,
			 struct smc_buf_desc *buf_slot,
			 enum dma_data_direction data_direction)
{
	if (!buf_slot->sgt[lnk->link_idx].sgl->dma_address)
		return; /* already unmapped */

	ib_dma_unmap_sg(lnk->smcibdev->ibdev,
			buf_slot->sgt[lnk->link_idx].sgl,
			buf_slot->sgt[lnk->link_idx].orig_nents,
			data_direction);
	buf_slot->sgt[lnk->link_idx].sgl->dma_address = 0;
}

long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
{
	struct ib_cq_init_attr cqattr =	{
		.cqe = SMC_MAX_CQE, .comp_vector = 0 };
	int cqe_size_order, smc_order;
	long rc;

	mutex_lock(&smcibdev->mutex);
	rc = 0;
	if (smcibdev->initialized)
		goto out;
	/* the calculated number of cq entries fits to mlx5 cq allocation */
	cqe_size_order = cache_line_size() == 128 ? 7 : 6;
	smc_order = MAX_ORDER - cqe_size_order - 1;
	if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE)
		cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2;
	smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev,
					      smc_wr_tx_cq_handler, NULL,
					      smcibdev, &cqattr);
	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send);
	if (IS_ERR(smcibdev->roce_cq_send)) {
		smcibdev->roce_cq_send = NULL;
		goto out;
	}
	smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev,
					      smc_wr_rx_cq_handler, NULL,
					      smcibdev, &cqattr);
	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_recv);
	if (IS_ERR(smcibdev->roce_cq_recv)) {
		smcibdev->roce_cq_recv = NULL;
		goto err;
	}
	smc_wr_add_dev(smcibdev);
	smcibdev->initialized = 1;
	goto out;

err:
	ib_destroy_cq(smcibdev->roce_cq_send);
out:
	mutex_unlock(&smcibdev->mutex);
	return rc;
}

static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev)
{
	mutex_lock(&smcibdev->mutex);
	if (!smcibdev->initialized)
		goto out;
	smcibdev->initialized = 0;
	ib_destroy_cq(smcibdev->roce_cq_recv);
	ib_destroy_cq(smcibdev->roce_cq_send);
	smc_wr_remove_dev(smcibdev);
out:
	mutex_unlock(&smcibdev->mutex);
}

static struct ib_client smc_ib_client;

/* callback function for ib_register_client() */
static int smc_ib_add_dev(struct ib_device *ibdev)
{
	struct smc_ib_device *smcibdev;
	u8 port_cnt;
	int i;

	if (ibdev->node_type != RDMA_NODE_IB_CA)
		return -EOPNOTSUPP;

	smcibdev = kzalloc(sizeof(*smcibdev), GFP_KERNEL);
	if (!smcibdev)
		return -ENOMEM;

	smcibdev->ibdev = ibdev;
	INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work);
	atomic_set(&smcibdev->lnk_cnt, 0);
	init_waitqueue_head(&smcibdev->lnks_deleted);
	mutex_init(&smcibdev->mutex);
	mutex_lock(&smc_ib_devices.mutex);
	list_add_tail(&smcibdev->list, &smc_ib_devices.list);
	mutex_unlock(&smc_ib_devices.mutex);
	ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
			      smc_ib_global_event_handler);
	ib_register_event_handler(&smcibdev->event_handler);

	/* trigger reading of the port attributes */
	port_cnt = smcibdev->ibdev->phys_port_cnt;
	pr_warn_ratelimited("smc: adding ib device %s with port count %d\n",
			    smcibdev->ibdev->name, port_cnt);
	for (i = 0;
	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
	     i++) {
		set_bit(i, &smcibdev->port_event_mask);
		/* determine pnetids of the port */
		if (smc_pnetid_by_dev_port(ibdev->dev.parent, i,
					   smcibdev->pnetid[i]))
			smc_pnetid_by_table_ib(smcibdev, i + 1);
		pr_warn_ratelimited("smc:    ib device %s port %d has pnetid "
				    "%.16s%s\n",
				    smcibdev->ibdev->name, i + 1,
				    smcibdev->pnetid[i],
				    smcibdev->pnetid_by_user[i] ?
				     " (user defined)" :
				     "");
	}
	schedule_work(&smcibdev->port_event_work);
	return 0;
}

/* callback function for ib_unregister_client() */
static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
{
	struct smc_ib_device *smcibdev = client_data;

	mutex_lock(&smc_ib_devices.mutex);
	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
	mutex_unlock(&smc_ib_devices.mutex);
	pr_warn_ratelimited("smc: removing ib device %s\n",
			    smcibdev->ibdev->name);
	smc_smcr_terminate_all(smcibdev);
	smc_ib_cleanup_per_ibdev(smcibdev);
	ib_unregister_event_handler(&smcibdev->event_handler);
	cancel_work_sync(&smcibdev->port_event_work);
	kfree(smcibdev);
}

static struct ib_client smc_ib_client = {
	.name	= "smc_ib",
	.add	= smc_ib_add_dev,
	.remove = smc_ib_remove_dev,
};

int __init smc_ib_register_client(void)
{
	smc_ib_init_local_systemid();
	return ib_register_client(&smc_ib_client);
}

void smc_ib_unregister_client(void)
{
	ib_unregister_client(&smc_ib_client);
}