summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/mlx4/mad.c
blob: c27141fef1ab2f6dca170bb07aecd11ecaa3d48b (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
/*
 * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <rdma/ib_mad.h>
#include <rdma/ib_smi.h>

#include <linux/mlx4/cmd.h>
#include <linux/gfp.h>
#include <rdma/ib_pma.h>

#include "mlx4_ib.h"

enum {
	MLX4_IB_VENDOR_CLASS1 = 0x9,
	MLX4_IB_VENDOR_CLASS2 = 0xa
};

int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey,
		 int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
		 void *in_mad, void *response_mad)
{
	struct mlx4_cmd_mailbox *inmailbox, *outmailbox;
	void *inbox;
	int err;
	u32 in_modifier = port;
	u8 op_modifier = 0;

	inmailbox = mlx4_alloc_cmd_mailbox(dev->dev);
	if (IS_ERR(inmailbox))
		return PTR_ERR(inmailbox);
	inbox = inmailbox->buf;

	outmailbox = mlx4_alloc_cmd_mailbox(dev->dev);
	if (IS_ERR(outmailbox)) {
		mlx4_free_cmd_mailbox(dev->dev, inmailbox);
		return PTR_ERR(outmailbox);
	}

	memcpy(inbox, in_mad, 256);

	/*
	 * Key check traps can't be generated unless we have in_wc to
	 * tell us where to send the trap.
	 */
	if (ignore_mkey || !in_wc)
		op_modifier |= 0x1;
	if (ignore_bkey || !in_wc)
		op_modifier |= 0x2;

	if (in_wc) {
		struct {
			__be32		my_qpn;
			u32		reserved1;
			__be32		rqpn;
			u8		sl;
			u8		g_path;
			u16		reserved2[2];
			__be16		pkey;
			u32		reserved3[11];
			u8		grh[40];
		} *ext_info;

		memset(inbox + 256, 0, 256);
		ext_info = inbox + 256;

		ext_info->my_qpn = cpu_to_be32(in_wc->qp->qp_num);
		ext_info->rqpn   = cpu_to_be32(in_wc->src_qp);
		ext_info->sl     = in_wc->sl << 4;
		ext_info->g_path = in_wc->dlid_path_bits |
			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
		ext_info->pkey   = cpu_to_be16(in_wc->pkey_index);

		if (in_grh)
			memcpy(ext_info->grh, in_grh, 40);

		op_modifier |= 0x4;

		in_modifier |= in_wc->slid << 16;
	}

	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma,
			   in_modifier, op_modifier,
			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
			   MLX4_CMD_NATIVE);

	if (!err)
		memcpy(response_mad, outmailbox->buf, 256);

	mlx4_free_cmd_mailbox(dev->dev, inmailbox);
	mlx4_free_cmd_mailbox(dev->dev, outmailbox);

	return err;
}

static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
{
	struct ib_ah *new_ah;
	struct ib_ah_attr ah_attr;

	if (!dev->send_agent[port_num - 1][0])
		return;

	memset(&ah_attr, 0, sizeof ah_attr);
	ah_attr.dlid     = lid;
	ah_attr.sl       = sl;
	ah_attr.port_num = port_num;

	new_ah = ib_create_ah(dev->send_agent[port_num - 1][0]->qp->pd,
			      &ah_attr);
	if (IS_ERR(new_ah))
		return;

	spin_lock(&dev->sm_lock);
	if (dev->sm_ah[port_num - 1])
		ib_destroy_ah(dev->sm_ah[port_num - 1]);
	dev->sm_ah[port_num - 1] = new_ah;
	spin_unlock(&dev->sm_lock);
}

/*
 * Snoop SM MADs for port info, GUID info, and  P_Key table sets, so we can
 * synthesize LID change, Client-Rereg, GID change, and P_Key change events.
 */
static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
		      u16 prev_lid)
{
	struct ib_port_info *pinfo;
	u16 lid;

	struct mlx4_ib_dev *dev = to_mdev(ibdev);
	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
	     mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
	    mad->mad_hdr.method == IB_MGMT_METHOD_SET)
		switch (mad->mad_hdr.attr_id) {
		case IB_SMP_ATTR_PORT_INFO:
			pinfo = (struct ib_port_info *) ((struct ib_smp *) mad)->data;
			lid = be16_to_cpu(pinfo->lid);

			update_sm_ah(dev, port_num,
				     be16_to_cpu(pinfo->sm_lid),
				     pinfo->neighbormtu_mastersmsl & 0xf);

			if (pinfo->clientrereg_resv_subnetto & 0x80)
				mlx4_ib_dispatch_event(dev, port_num,
						       IB_EVENT_CLIENT_REREGISTER);

			if (prev_lid != lid)
				mlx4_ib_dispatch_event(dev, port_num,
						       IB_EVENT_LID_CHANGE);
			break;

		case IB_SMP_ATTR_PKEY_TABLE:
			mlx4_ib_dispatch_event(dev, port_num,
					       IB_EVENT_PKEY_CHANGE);
			break;

		case IB_SMP_ATTR_GUID_INFO:
			/* paravirtualized master's guid is guid 0 -- does not change */
			if (!mlx4_is_master(dev->dev))
				mlx4_ib_dispatch_event(dev, port_num,
						       IB_EVENT_GID_CHANGE);
			break;
		default:
			break;
		}
}

static void node_desc_override(struct ib_device *dev,
			       struct ib_mad *mad)
{
	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
	     mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
	    mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP &&
	    mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {
		spin_lock(&to_mdev(dev)->sm_lock);
		memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64);
		spin_unlock(&to_mdev(dev)->sm_lock);
	}
}

static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *mad)
{
	int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
	struct ib_mad_send_buf *send_buf;
	struct ib_mad_agent *agent = dev->send_agent[port_num - 1][qpn];
	int ret;

	if (agent) {
		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
					      IB_MGMT_MAD_DATA, GFP_ATOMIC);
		if (IS_ERR(send_buf))
			return;
		/*
		 * We rely here on the fact that MLX QPs don't use the
		 * address handle after the send is posted (this is
		 * wrong following the IB spec strictly, but we know
		 * it's OK for our devices).
		 */
		spin_lock(&dev->sm_lock);
		memcpy(send_buf->mad, mad, sizeof *mad);
		if ((send_buf->ah = dev->sm_ah[port_num - 1]))
			ret = ib_post_send_mad(send_buf, NULL);
		else
			ret = -EINVAL;
		spin_unlock(&dev->sm_lock);

		if (ret)
			ib_free_send_mad(send_buf);
	}
}

static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
			struct ib_wc *in_wc, struct ib_grh *in_grh,
			struct ib_mad *in_mad, struct ib_mad *out_mad)
{
	u16 slid, prev_lid = 0;
	int err;
	struct ib_port_attr pattr;

	if (in_wc && in_wc->qp->qp_num) {
		pr_debug("received MAD: slid:%d sqpn:%d "
			"dlid_bits:%d dqpn:%d wc_flags:0x%x, cls %x, mtd %x, atr %x\n",
			in_wc->slid, in_wc->src_qp,
			in_wc->dlid_path_bits,
			in_wc->qp->qp_num,
			in_wc->wc_flags,
			in_mad->mad_hdr.mgmt_class, in_mad->mad_hdr.method,
			be16_to_cpu(in_mad->mad_hdr.attr_id));
		if (in_wc->wc_flags & IB_WC_GRH) {
			pr_debug("sgid_hi:0x%016llx sgid_lo:0x%016llx\n",
				 be64_to_cpu(in_grh->sgid.global.subnet_prefix),
				 be64_to_cpu(in_grh->sgid.global.interface_id));
			pr_debug("dgid_hi:0x%016llx dgid_lo:0x%016llx\n",
				 be64_to_cpu(in_grh->dgid.global.subnet_prefix),
				 be64_to_cpu(in_grh->dgid.global.interface_id));
		}
	}

	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);

	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
		forward_trap(to_mdev(ibdev), port_num, in_mad);
		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
	}

	if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
	    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
		if (in_mad->mad_hdr.method   != IB_MGMT_METHOD_GET &&
		    in_mad->mad_hdr.method   != IB_MGMT_METHOD_SET &&
		    in_mad->mad_hdr.method   != IB_MGMT_METHOD_TRAP_REPRESS)
			return IB_MAD_RESULT_SUCCESS;

		/*
		 * Don't process SMInfo queries -- the SMA can't handle them.
		 */
		if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO)
			return IB_MAD_RESULT_SUCCESS;
	} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
		   in_mad->mad_hdr.mgmt_class == MLX4_IB_VENDOR_CLASS1   ||
		   in_mad->mad_hdr.mgmt_class == MLX4_IB_VENDOR_CLASS2   ||
		   in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_CONG_MGMT) {
		if (in_mad->mad_hdr.method  != IB_MGMT_METHOD_GET &&
		    in_mad->mad_hdr.method  != IB_MGMT_METHOD_SET)
			return IB_MAD_RESULT_SUCCESS;
	} else
		return IB_MAD_RESULT_SUCCESS;

	if ((in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
	     in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
	    !ib_query_port(ibdev, port_num, &pattr))
		prev_lid = pattr.lid;

	err = mlx4_MAD_IFC(to_mdev(ibdev),
			   mad_flags & IB_MAD_IGNORE_MKEY,
			   mad_flags & IB_MAD_IGNORE_BKEY,
			   port_num, in_wc, in_grh, in_mad, out_mad);
	if (err)
		return IB_MAD_RESULT_FAILURE;

	if (!out_mad->mad_hdr.status) {
		if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV))
			smp_snoop(ibdev, port_num, in_mad, prev_lid);
		node_desc_override(ibdev, out_mad);
	}

	/* set return bit in status of directed route responses */
	if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
		out_mad->mad_hdr.status |= cpu_to_be16(1 << 15);

	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS)
		/* no response for trap repress */
		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;

	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}

static void edit_counter(struct mlx4_counter *cnt,
					struct ib_pma_portcounters *pma_cnt)
{
	pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2));
	pma_cnt->port_rcv_data  = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2));
	pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames));
	pma_cnt->port_rcv_packets  = cpu_to_be32(be64_to_cpu(cnt->rx_frames));
}

static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
			struct ib_wc *in_wc, struct ib_grh *in_grh,
			struct ib_mad *in_mad, struct ib_mad *out_mad)
{
	struct mlx4_cmd_mailbox *mailbox;
	struct mlx4_ib_dev *dev = to_mdev(ibdev);
	int err;
	u32 inmod = dev->counters[port_num - 1] & 0xffff;
	u8 mode;

	if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
		return -EINVAL;

	mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
	if (IS_ERR(mailbox))
		return IB_MAD_RESULT_FAILURE;

	err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0,
			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
			   MLX4_CMD_WRAPPED);
	if (err)
		err = IB_MAD_RESULT_FAILURE;
	else {
		memset(out_mad->data, 0, sizeof out_mad->data);
		mode = ((struct mlx4_counter *)mailbox->buf)->counter_mode;
		switch (mode & 0xf) {
		case 0:
			edit_counter(mailbox->buf,
						(void *)(out_mad->data + 40));
			err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
			break;
		default:
			err = IB_MAD_RESULT_FAILURE;
		}
	}

	mlx4_free_cmd_mailbox(dev->dev, mailbox);

	return err;
}

int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
			struct ib_wc *in_wc, struct ib_grh *in_grh,
			struct ib_mad *in_mad, struct ib_mad *out_mad)
{
	switch (rdma_port_get_link_layer(ibdev, port_num)) {
	case IB_LINK_LAYER_INFINIBAND:
		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
				      in_grh, in_mad, out_mad);
	case IB_LINK_LAYER_ETHERNET:
		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
					  in_grh, in_mad, out_mad);
	default:
		return -EINVAL;
	}
}

static void send_handler(struct ib_mad_agent *agent,
			 struct ib_mad_send_wc *mad_send_wc)
{
	ib_free_send_mad(mad_send_wc->send_buf);
}

int mlx4_ib_mad_init(struct mlx4_ib_dev *dev)
{
	struct ib_mad_agent *agent;
	int p, q;
	int ret;
	enum rdma_link_layer ll;

	for (p = 0; p < dev->num_ports; ++p) {
		ll = rdma_port_get_link_layer(&dev->ib_dev, p + 1);
		for (q = 0; q <= 1; ++q) {
			if (ll == IB_LINK_LAYER_INFINIBAND) {
				agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
							      q ? IB_QPT_GSI : IB_QPT_SMI,
							      NULL, 0, send_handler,
							      NULL, NULL);
				if (IS_ERR(agent)) {
					ret = PTR_ERR(agent);
					goto err;
				}
				dev->send_agent[p][q] = agent;
			} else
				dev->send_agent[p][q] = NULL;
		}
	}

	return 0;

err:
	for (p = 0; p < dev->num_ports; ++p)
		for (q = 0; q <= 1; ++q)
			if (dev->send_agent[p][q])
				ib_unregister_mad_agent(dev->send_agent[p][q]);

	return ret;
}

void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
{
	struct ib_mad_agent *agent;
	int p, q;

	for (p = 0; p < dev->num_ports; ++p) {
		for (q = 0; q <= 1; ++q) {
			agent = dev->send_agent[p][q];
			if (agent) {
				dev->send_agent[p][q] = NULL;
				ib_unregister_mad_agent(agent);
			}
		}

		if (dev->sm_ah[p])
			ib_destroy_ah(dev->sm_ah[p]);
	}
}

void handle_port_mgmt_change_event(struct work_struct *work)
{
	struct ib_event_work *ew = container_of(work, struct ib_event_work, work);
	struct mlx4_ib_dev *dev = ew->ib_dev;
	struct mlx4_eqe *eqe = &(ew->ib_eqe);
	u8 port = eqe->event.port_mgmt_change.port;
	u32 changed_attr;

	switch (eqe->subtype) {
	case MLX4_DEV_PMC_SUBTYPE_PORT_INFO:
		changed_attr = be32_to_cpu(eqe->event.port_mgmt_change.params.port_info.changed_attr);

		/* Update the SM ah - This should be done before handling
		   the other changed attributes so that MADs can be sent to the SM */
		if (changed_attr & MSTR_SM_CHANGE_MASK) {
			u16 lid = be16_to_cpu(eqe->event.port_mgmt_change.params.port_info.mstr_sm_lid);
			u8 sl = eqe->event.port_mgmt_change.params.port_info.mstr_sm_sl & 0xf;
			update_sm_ah(dev, port, lid, sl);
		}

		/* Check if it is a lid change event */
		if (changed_attr & MLX4_EQ_PORT_INFO_LID_CHANGE_MASK)
			mlx4_ib_dispatch_event(dev, port, IB_EVENT_LID_CHANGE);

		/* Generate GUID changed event */
		if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK)
			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);

		if (changed_attr & MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK)
			mlx4_ib_dispatch_event(dev, port,
					       IB_EVENT_CLIENT_REREGISTER);
		break;

	case MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE:
		mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE);
		break;
	case MLX4_DEV_PMC_SUBTYPE_GUID_INFO:
		/* paravirtualized master's guid is guid 0 -- does not change */
		if (!mlx4_is_master(dev->dev))
			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
		break;
	default:
		pr_warn("Unsupported subtype 0x%x for "
			"Port Management Change event\n", eqe->subtype);
	}

	kfree(ew);
}

void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num,
			    enum ib_event_type type)
{
	struct ib_event event;

	event.device		= &dev->ib_dev;
	event.element.port_num	= port_num;
	event.event		= type;

	ib_dispatch_event(&event);
}