en_netdev.c 62.3 KB
Newer Older
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
/*
 * Copyright (c) 2007 Mellanox Technologies. 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 <linux/etherdevice.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
#include <linux/delay.h>
38
#include <linux/slab.h>
39
40
#include <linux/hash.h>
#include <net/ip.h>
41
#include <net/busy_poll.h>
42
43
44
45
46
47
48
49
50

#include <linux/mlx4/driver.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/cmd.h>
#include <linux/mlx4/cq.h>

#include "mlx4_en.h"
#include "en_port.h"

51
int mlx4_en_setup_tc(struct net_device *dev, u8 up)
52
{
53
54
	struct mlx4_en_priv *priv = netdev_priv(dev);
	int i;
55
	unsigned int offset = 0;
56
57

	if (up && up != MLX4_EN_NUM_UP)
58
59
		return -EINVAL;

60
61
62
63
	netdev_set_num_tc(dev, up);

	/* Partition Tx queues evenly amongst UP's */
	for (i = 0; i < up; i++) {
64
65
		netdev_set_tc_queue(dev, i, priv->num_tx_rings_p_up, offset);
		offset += priv->num_tx_rings_p_up;
66
67
	}

68
69
70
	return 0;
}

71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
#ifdef CONFIG_NET_LL_RX_POLL
/* must be called with local_bh_disable()d */
static int mlx4_en_low_latency_recv(struct napi_struct *napi)
{
	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
	struct net_device *dev = cq->dev;
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_rx_ring *rx_ring = &priv->rx_ring[cq->ring];
	int done;

	if (!priv->port_up)
		return LL_FLUSH_FAILED;

	if (!mlx4_en_cq_lock_poll(cq))
		return LL_FLUSH_BUSY;

	done = mlx4_en_process_rx_cq(dev, cq, 4);
88
89
90
91
	if (likely(done))
		rx_ring->cleaned += done;
	else
		rx_ring->misses++;
92
93
94
95
96
97
98

	mlx4_en_cq_unlock_poll(cq);

	return done;
}
#endif	/* CONFIG_NET_LL_RX_POLL */

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
#ifdef CONFIG_RFS_ACCEL

struct mlx4_en_filter {
	struct list_head next;
	struct work_struct work;

	__be32 src_ip;
	__be32 dst_ip;
	__be16 src_port;
	__be16 dst_port;

	int rxq_index;
	struct mlx4_en_priv *priv;
	u32 flow_id;			/* RFS infrastructure id */
	int id;				/* mlx4_en driver id */
	u64 reg_id;			/* Flow steering API id */
	u8 activated;			/* Used to prevent expiry before filter
					 * is attached
					 */
	struct hlist_node filter_chain;
};

static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv);

static void mlx4_en_filter_work(struct work_struct *work)
{
	struct mlx4_en_filter *filter = container_of(work,
						     struct mlx4_en_filter,
						     work);
	struct mlx4_en_priv *priv = filter->priv;
	struct mlx4_spec_list spec_tcp = {
		.id = MLX4_NET_TRANS_RULE_ID_TCP,
		{
			.tcp_udp = {
				.dst_port = filter->dst_port,
				.dst_port_msk = (__force __be16)-1,
				.src_port = filter->src_port,
				.src_port_msk = (__force __be16)-1,
			},
		},
	};
	struct mlx4_spec_list spec_ip = {
		.id = MLX4_NET_TRANS_RULE_ID_IPV4,
		{
			.ipv4 = {
				.dst_ip = filter->dst_ip,
				.dst_ip_msk = (__force __be32)-1,
				.src_ip = filter->src_ip,
				.src_ip_msk = (__force __be32)-1,
			},
		},
	};
	struct mlx4_spec_list spec_eth = {
		.id = MLX4_NET_TRANS_RULE_ID_ETH,
	};
	struct mlx4_net_trans_rule rule = {
		.list = LIST_HEAD_INIT(rule.list),
		.queue_mode = MLX4_NET_TRANS_Q_LIFO,
		.exclusive = 1,
		.allow_loopback = 1,
159
		.promisc_mode = MLX4_FS_REGULAR,
160
161
162
163
164
165
166
167
168
169
170
		.port = priv->port,
		.priority = MLX4_DOMAIN_RFS,
	};
	int rc;
	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);

	list_add_tail(&spec_eth.list, &rule.list);
	list_add_tail(&spec_ip.list, &rule.list);
	list_add_tail(&spec_tcp.list, &rule.list);

	rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
171
	memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
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
	memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);

	filter->activated = 0;

	if (filter->reg_id) {
		rc = mlx4_flow_detach(priv->mdev->dev, filter->reg_id);
		if (rc && rc != -ENOENT)
			en_err(priv, "Error detaching flow. rc = %d\n", rc);
	}

	rc = mlx4_flow_attach(priv->mdev->dev, &rule, &filter->reg_id);
	if (rc)
		en_err(priv, "Error attaching flow. err = %d\n", rc);

	mlx4_en_filter_rfs_expire(priv);

	filter->activated = 1;
}

static inline struct hlist_head *
filter_hash_bucket(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
		   __be16 src_port, __be16 dst_port)
{
	unsigned long l;
	int bucket_idx;

	l = (__force unsigned long)src_port |
	    ((__force unsigned long)dst_port << 2);
	l ^= (__force unsigned long)(src_ip ^ dst_ip);

	bucket_idx = hash_long(l, MLX4_EN_FILTER_HASH_SHIFT);

	return &priv->filter_hash[bucket_idx];
}

static struct mlx4_en_filter *
mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
		     __be32 dst_ip, __be16 src_port, __be16 dst_port,
		     u32 flow_id)
{
	struct mlx4_en_filter *filter = NULL;

	filter = kzalloc(sizeof(struct mlx4_en_filter), GFP_ATOMIC);
	if (!filter)
		return NULL;

	filter->priv = priv;
	filter->rxq_index = rxq_index;
	INIT_WORK(&filter->work, mlx4_en_filter_work);

	filter->src_ip = src_ip;
	filter->dst_ip = dst_ip;
	filter->src_port = src_port;
	filter->dst_port = dst_port;

	filter->flow_id = flow_id;

229
	filter->id = priv->last_filter_id++ % RPS_NO_FILTER;
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

	list_add_tail(&filter->next, &priv->filters);
	hlist_add_head(&filter->filter_chain,
		       filter_hash_bucket(priv, src_ip, dst_ip, src_port,
					  dst_port));

	return filter;
}

static void mlx4_en_filter_free(struct mlx4_en_filter *filter)
{
	struct mlx4_en_priv *priv = filter->priv;
	int rc;

	list_del(&filter->next);

	rc = mlx4_flow_detach(priv->mdev->dev, filter->reg_id);
	if (rc && rc != -ENOENT)
		en_err(priv, "Error detaching flow. rc = %d\n", rc);

	kfree(filter);
}

static inline struct mlx4_en_filter *
mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
		    __be16 src_port, __be16 dst_port)
{
	struct mlx4_en_filter *filter;
	struct mlx4_en_filter *ret = NULL;

260
	hlist_for_each_entry(filter,
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
			     filter_hash_bucket(priv, src_ip, dst_ip,
						src_port, dst_port),
			     filter_chain) {
		if (filter->src_ip == src_ip &&
		    filter->dst_ip == dst_ip &&
		    filter->src_port == src_port &&
		    filter->dst_port == dst_port) {
			ret = filter;
			break;
		}
	}

	return ret;
}

static int
mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
		   u16 rxq_index, u32 flow_id)
{
	struct mlx4_en_priv *priv = netdev_priv(net_dev);
	struct mlx4_en_filter *filter;
	const struct iphdr *ip;
	const __be16 *ports;
	__be32 src_ip;
	__be32 dst_ip;
	__be16 src_port;
	__be16 dst_port;
	int nhoff = skb_network_offset(skb);
	int ret = 0;

	if (skb->protocol != htons(ETH_P_IP))
		return -EPROTONOSUPPORT;

	ip = (const struct iphdr *)(skb->data + nhoff);
	if (ip_is_fragment(ip))
		return -EPROTONOSUPPORT;

	ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);

	src_ip = ip->saddr;
	dst_ip = ip->daddr;
	src_port = ports[0];
	dst_port = ports[1];

	if (ip->protocol != IPPROTO_TCP)
		return -EPROTONOSUPPORT;

	spin_lock_bh(&priv->filters_lock);
	filter = mlx4_en_filter_find(priv, src_ip, dst_ip, src_port, dst_port);
	if (filter) {
		if (filter->rxq_index == rxq_index)
			goto out;

		filter->rxq_index = rxq_index;
	} else {
		filter = mlx4_en_filter_alloc(priv, rxq_index,
					      src_ip, dst_ip,
					      src_port, dst_port, flow_id);
		if (!filter) {
			ret = -ENOMEM;
			goto err;
		}
	}

	queue_work(priv->mdev->workqueue, &filter->work);

out:
	ret = filter->id;
err:
	spin_unlock_bh(&priv->filters_lock);

	return ret;
}

void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv,
			     struct mlx4_en_rx_ring *rx_ring)
{
	struct mlx4_en_filter *filter, *tmp;
	LIST_HEAD(del_list);

	spin_lock_bh(&priv->filters_lock);
	list_for_each_entry_safe(filter, tmp, &priv->filters, next) {
		list_move(&filter->next, &del_list);
		hlist_del(&filter->filter_chain);
	}
	spin_unlock_bh(&priv->filters_lock);

	list_for_each_entry_safe(filter, tmp, &del_list, next) {
		cancel_work_sync(&filter->work);
		mlx4_en_filter_free(filter);
	}
}

static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv)
{
	struct mlx4_en_filter *filter = NULL, *tmp, *last_filter = NULL;
	LIST_HEAD(del_list);
	int i = 0;

	spin_lock_bh(&priv->filters_lock);
	list_for_each_entry_safe(filter, tmp, &priv->filters, next) {
		if (i > MLX4_EN_FILTER_EXPIRY_QUOTA)
			break;

		if (filter->activated &&
		    !work_pending(&filter->work) &&
		    rps_may_expire_flow(priv->dev,
					filter->rxq_index, filter->flow_id,
					filter->id)) {
			list_move(&filter->next, &del_list);
			hlist_del(&filter->filter_chain);
		} else
			last_filter = filter;

		i++;
	}

	if (last_filter && (&last_filter->next != priv->filters.next))
		list_move(&priv->filters, &last_filter->next);

	spin_unlock_bh(&priv->filters_lock);

	list_for_each_entry_safe(filter, tmp, &del_list, next)
		mlx4_en_filter_free(filter);
}
#endif

388
389
static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
				   __be16 proto, u16 vid)
390
391
392
393
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;
Eli Cohen's avatar
Eli Cohen committed
394
	int idx;
395

Jiri Pirko's avatar
Jiri Pirko committed
396
	en_dbg(HW, priv, "adding VLAN:%d\n", vid);
397

Jiri Pirko's avatar
Jiri Pirko committed
398
	set_bit(vid, priv->active_vlans);
399
400
401
402

	/* Add VID to port VLAN filter */
	mutex_lock(&mdev->state_lock);
	if (mdev->device_up && priv->port_up) {
Jiri Pirko's avatar
Jiri Pirko committed
403
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
404
		if (err)
405
			en_err(priv, "Failed configuring VLAN filter\n");
406
	}
Eli Cohen's avatar
Eli Cohen committed
407
	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
408
		en_dbg(HW, priv, "failed adding vlan %d\n", vid);
409
	mutex_unlock(&mdev->state_lock);
Eli Cohen's avatar
Eli Cohen committed
410

411
	return 0;
412
413
}

414
415
static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
				    __be16 proto, u16 vid)
416
417
418
419
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;
Eli Cohen's avatar
Eli Cohen committed
420
	int idx;
421

Jiri Pirko's avatar
Jiri Pirko committed
422
	en_dbg(HW, priv, "Killing VID:%d\n", vid);
423

Jiri Pirko's avatar
Jiri Pirko committed
424
	clear_bit(vid, priv->active_vlans);
425
426
427

	/* Remove VID from port VLAN filter */
	mutex_lock(&mdev->state_lock);
Eli Cohen's avatar
Eli Cohen committed
428
429
430
	if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx))
		mlx4_unregister_vlan(mdev->dev, priv->port, idx);
	else
431
		en_dbg(HW, priv, "could not find vid %d in cache\n", vid);
Eli Cohen's avatar
Eli Cohen committed
432

433
	if (mdev->device_up && priv->port_up) {
Jiri Pirko's avatar
Jiri Pirko committed
434
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
435
		if (err)
436
			en_err(priv, "Failed configuring VLAN filter\n");
437
438
	}
	mutex_unlock(&mdev->state_lock);
439
440

	return 0;
441
442
}

443
444
static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
{
445
446
	int i;
	for (i = ETH_ALEN - 1; i >= 0; --i) {
447
448
449
450
451
452
		dst_mac[i] = src_mac & 0xff;
		src_mac >>= 8;
	}
	memset(&dst_mac[ETH_ALEN], 0, 2);
}

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
static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
				unsigned char *mac, int *qpn, u64 *reg_id)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int err;

	switch (dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_B0: {
		struct mlx4_qp qp;
		u8 gid[16] = {0};

		qp.qpn = *qpn;
		memcpy(&gid[10], mac, ETH_ALEN);
		gid[5] = priv->port;

		err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
		break;
	}
	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
		struct mlx4_spec_list spec_eth = { {NULL} };
		__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);

		struct mlx4_net_trans_rule rule = {
			.queue_mode = MLX4_NET_TRANS_Q_FIFO,
			.exclusive = 0,
			.allow_loopback = 1,
480
			.promisc_mode = MLX4_FS_REGULAR,
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
			.priority = MLX4_DOMAIN_NIC,
		};

		rule.port = priv->port;
		rule.qpn = *qpn;
		INIT_LIST_HEAD(&rule.list);

		spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
		memcpy(spec_eth.eth.dst_mac, mac, ETH_ALEN);
		memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
		list_add_tail(&spec_eth.list, &rule.list);

		err = mlx4_flow_attach(dev, &rule, reg_id);
		break;
	}
	default:
		return -EINVAL;
	}
	if (err)
		en_warn(priv, "Failed Attaching Unicast\n");

	return err;
}

static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv,
				     unsigned char *mac, int qpn, u64 reg_id)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;

	switch (dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_B0: {
		struct mlx4_qp qp;
		u8 gid[16] = {0};

		qp.qpn = qpn;
		memcpy(&gid[10], mac, ETH_ALEN);
		gid[5] = priv->port;

		mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
		break;
	}
	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
		mlx4_flow_detach(dev, reg_id);
		break;
	}
	default:
		en_err(priv, "Invalid steering mode.\n");
	}
}

static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	struct mlx4_mac_entry *entry;
	int index = 0;
	int err = 0;
	u64 reg_id;
	int *qpn = &priv->base_qpn;
	u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);

	en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
	       priv->dev->dev_addr);
	index = mlx4_register_mac(dev, priv->port, mac);
	if (index < 0) {
		err = index;
		en_err(priv, "Failed adding MAC: %pM\n",
		       priv->dev->dev_addr);
		return err;
	}

	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
		int base_qpn = mlx4_get_base_qpn(dev, priv->port);
		*qpn = base_qpn + index;
		return 0;
	}

	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
	if (err) {
		en_err(priv, "Failed to reserve qp for mac registration\n");
		goto qp_err;
	}

	err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, &reg_id);
	if (err)
		goto steer_err;

	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
	if (!entry) {
		err = -ENOMEM;
		goto alloc_err;
	}
	memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac));
	entry->reg_id = reg_id;

578
579
	hlist_add_head_rcu(&entry->hlist,
			   &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]);
580

581
	return 0;
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598

alloc_err:
	mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);

steer_err:
	mlx4_qp_release_range(dev, *qpn, 1);

qp_err:
	mlx4_unregister_mac(dev, priv->port, mac);
	return err;
}

static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int qpn = priv->base_qpn;
599
	u64 mac;
600

601
602
603
604
605
606
	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
		mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
		en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
		       priv->dev->dev_addr);
		mlx4_unregister_mac(dev, priv->port, mac);
	} else {
607
		struct mlx4_mac_entry *entry;
608
		struct hlist_node *tmp;
609
		struct hlist_head *bucket;
610
		unsigned int i;
611

612
613
614
615
616
617
		for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
			bucket = &priv->mac_hash[i];
			hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
				mac = mlx4_en_mac_to_u64(entry->mac);
				en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
				       entry->mac);
618
619
620
				mlx4_en_uc_steer_release(priv, entry->mac,
							 qpn, entry->reg_id);

621
				mlx4_unregister_mac(dev, priv->port, mac);
622
623
624
				hlist_del_rcu(&entry->hlist);
				kfree_rcu(entry, rcu);
			}
625
		}
626
627
628
629
630

		en_dbg(DRV, priv, "Releasing qp: port %d, qpn %d\n",
		       priv->port, qpn);
		mlx4_qp_release_range(dev, qpn, 1);
		priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;
631
632
633
634
	}
}

static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
635
			       unsigned char *new_mac, unsigned char *prev_mac)
636
637
638
639
640
641
642
{
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_dev *dev = mdev->dev;
	int err = 0;
	u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac);

	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
643
644
645
		struct hlist_head *bucket;
		unsigned int mac_hash;
		struct mlx4_mac_entry *entry;
646
		struct hlist_node *tmp;
647
648
649
		u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac);

		bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
650
		hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
			if (ether_addr_equal_64bits(entry->mac, prev_mac)) {
				mlx4_en_uc_steer_release(priv, entry->mac,
							 qpn, entry->reg_id);
				mlx4_unregister_mac(dev, priv->port,
						    prev_mac_u64);
				hlist_del_rcu(&entry->hlist);
				synchronize_rcu();
				memcpy(entry->mac, new_mac, ETH_ALEN);
				entry->reg_id = 0;
				mac_hash = new_mac[MLX4_EN_MAC_HASH_IDX];
				hlist_add_head_rcu(&entry->hlist,
						   &priv->mac_hash[mac_hash]);
				mlx4_register_mac(dev, priv->port, new_mac_u64);
				err = mlx4_en_uc_steer_add(priv, new_mac,
							   &qpn,
							   &entry->reg_id);
				return err;
			}
		}
		return -EINVAL;
671
672
673
674
675
	}

	return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
}

676
u64 mlx4_en_mac_to_u64(u8 *addr)
677
678
679
680
681
682
683
684
685
686
687
{
	u64 mac = 0;
	int i;

	for (i = 0; i < ETH_ALEN; i++) {
		mac <<= 8;
		mac |= addr[i];
	}
	return mac;
}

688
static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
689
690
691
692
693
{
	int err = 0;

	if (priv->port_up) {
		/* Remove old MAC and insert the new one */
694
		err = mlx4_en_replace_mac(priv, priv->base_qpn,
695
					  priv->dev->dev_addr, priv->prev_mac);
696
		if (err)
697
			en_err(priv, "Failed changing HW MAC address\n");
698
699
		memcpy(priv->prev_mac, priv->dev->dev_addr,
		       sizeof(priv->prev_mac));
700
	} else
701
		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
702

703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
	return err;
}

static int mlx4_en_set_mac(struct net_device *dev, void *addr)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct sockaddr *saddr = addr;
	int err;

	if (!is_valid_ether_addr(saddr->sa_data))
		return -EADDRNOTAVAIL;

	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);

	mutex_lock(&mdev->state_lock);
	err = mlx4_en_do_set_mac(priv);
720
	mutex_unlock(&mdev->state_lock);
721
722

	return err;
723
724
725
726
727
}

static void mlx4_en_clear_list(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
728
	struct mlx4_en_mc_list *tmp, *mc_to_del;
729

730
731
732
733
	list_for_each_entry_safe(mc_to_del, tmp, &priv->mc_list, list) {
		list_del(&mc_to_del->list);
		kfree(mc_to_del);
	}
734
735
736
737
738
}

static void mlx4_en_cache_mclist(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
739
	struct netdev_hw_addr *ha;
740
	struct mlx4_en_mc_list *tmp;
741

742
	mlx4_en_clear_list(dev);
743
744
745
746
747
748
749
750
751
	netdev_for_each_mc_addr(ha, dev) {
		tmp = kzalloc(sizeof(struct mlx4_en_mc_list), GFP_ATOMIC);
		if (!tmp) {
			mlx4_en_clear_list(dev);
			return;
		}
		memcpy(tmp->addr, ha->addr, ETH_ALEN);
		list_add_tail(&tmp->list, &priv->mc_list);
	}
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
static void update_mclist_flags(struct mlx4_en_priv *priv,
				struct list_head *dst,
				struct list_head *src)
{
	struct mlx4_en_mc_list *dst_tmp, *src_tmp, *new_mc;
	bool found;

	/* Find all the entries that should be removed from dst,
	 * These are the entries that are not found in src
	 */
	list_for_each_entry(dst_tmp, dst, list) {
		found = false;
		list_for_each_entry(src_tmp, src, list) {
			if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
				found = true;
				break;
			}
		}
		if (!found)
			dst_tmp->action = MCLIST_REM;
	}

	/* Add entries that exist in src but not in dst
	 * mark them as need to add
	 */
	list_for_each_entry(src_tmp, src, list) {
		found = false;
		list_for_each_entry(dst_tmp, dst, list) {
			if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
				dst_tmp->action = MCLIST_NONE;
				found = true;
				break;
			}
		}
		if (!found) {
789
790
			new_mc = kmemdup(src_tmp,
					 sizeof(struct mlx4_en_mc_list),
791
					 GFP_KERNEL);
792
			if (!new_mc)
793
				return;
794

795
796
797
798
799
			new_mc->action = MCLIST_ADD;
			list_add_tail(&new_mc->list, dst);
		}
	}
}
800

801
static void mlx4_en_set_rx_mode(struct net_device *dev)
802
803
804
805
806
807
{
	struct mlx4_en_priv *priv = netdev_priv(dev);

	if (!priv->port_up)
		return;

808
	queue_work(priv->mdev->workqueue, &priv->rx_mode_task);
809
810
}

811
812
static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv,
				     struct mlx4_en_dev *mdev)
813
{
814
	int err = 0;
815

816
	if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
817
		if (netif_msg_rx_status(priv))
818
819
			en_warn(priv, "Entering promiscuous mode\n");
		priv->flags |= MLX4_EN_FLAG_PROMISC;
820

821
		/* Enable promiscouos mode */
822
		switch (mdev->dev->caps.steering_mode) {
823
		case MLX4_STEERING_MODE_DEVICE_MANAGED:
824
825
826
			err = mlx4_flow_steer_promisc_add(mdev->dev,
							  priv->port,
							  priv->base_qpn,
827
							  MLX4_FS_ALL_DEFAULT);
828
			if (err)
829
830
				en_err(priv, "Failed enabling promiscuous mode\n");
			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
831
832
			break;

833
		case MLX4_STEERING_MODE_B0:
834
835
836
			err = mlx4_unicast_promisc_add(mdev->dev,
						       priv->base_qpn,
						       priv->port);
837
			if (err)
838
839
840
841
842
843
844
845
846
				en_err(priv, "Failed enabling unicast promiscuous mode\n");

			/* Add the default qp number as multicast
			 * promisc
			 */
			if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
				err = mlx4_multicast_promisc_add(mdev->dev,
								 priv->base_qpn,
								 priv->port);
847
				if (err)
848
849
					en_err(priv, "Failed enabling multicast promiscuous mode\n");
				priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
850
851
			}
			break;
852

853
854
855
		case MLX4_STEERING_MODE_A0:
			err = mlx4_SET_PORT_qpn_calc(mdev->dev,
						     priv->port,
856
857
						     priv->base_qpn,
						     1);
858
			if (err)
859
				en_err(priv, "Failed enabling promiscuous mode\n");
860
			break;
861
862
		}

863
864
865
866
867
868
869
		/* Disable port multicast filter (unconditionally) */
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
			en_err(priv, "Failed disabling multicast filter\n");

		/* Disable port VLAN filter */
Jiri Pirko's avatar
Jiri Pirko committed
870
		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
871
		if (err)
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
			en_err(priv, "Failed disabling VLAN filter\n");
	}
}

static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv,
				       struct mlx4_en_dev *mdev)
{
	int err = 0;

	if (netif_msg_rx_status(priv))
		en_warn(priv, "Leaving promiscuous mode\n");
	priv->flags &= ~MLX4_EN_FLAG_PROMISC;

	/* Disable promiscouos mode */
	switch (mdev->dev->caps.steering_mode) {
	case MLX4_STEERING_MODE_DEVICE_MANAGED:
		err = mlx4_flow_steer_promisc_remove(mdev->dev,
						     priv->port,
890
						     MLX4_FS_ALL_DEFAULT);
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
		if (err)
			en_err(priv, "Failed disabling promiscuous mode\n");
		priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		break;

	case MLX4_STEERING_MODE_B0:
		err = mlx4_unicast_promisc_remove(mdev->dev,
						  priv->base_qpn,
						  priv->port);
		if (err)
			en_err(priv, "Failed disabling unicast promiscuous mode\n");
		/* Disable Multicast promisc */
		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
			err = mlx4_multicast_promisc_remove(mdev->dev,
							    priv->base_qpn,
							    priv->port);
			if (err)
				en_err(priv, "Failed disabling multicast promiscuous mode\n");
			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		}
		break;

	case MLX4_STEERING_MODE_A0:
		err = mlx4_SET_PORT_qpn_calc(mdev->dev,
					     priv->port,
					     priv->base_qpn, 0);
		if (err)
			en_err(priv, "Failed disabling promiscuous mode\n");
		break;
920
921
	}

922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
	/* Enable port VLAN filter */
	err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
	if (err)
		en_err(priv, "Failed enabling VLAN filter\n");
}

static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
				 struct net_device *dev,
				 struct mlx4_en_dev *mdev)
{
	struct mlx4_en_mc_list *mclist, *tmp;
	u64 mcast_addr = 0;
	u8 mc_list[16] = {0};
	int err = 0;

937
938
939
940
941
	/* Enable/disable the multicast filter according to IFF_ALLMULTI */
	if (dev->flags & IFF_ALLMULTI) {
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
942
			en_err(priv, "Failed disabling multicast filter\n");
943
944
945

		/* Add the default qp number as multicast promisc */
		if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
946
			switch (mdev->dev->caps.steering_mode) {
947
948
949
950
			case MLX4_STEERING_MODE_DEVICE_MANAGED:
				err = mlx4_flow_steer_promisc_add(mdev->dev,
								  priv->port,
								  priv->base_qpn,
951
								  MLX4_FS_MC_DEFAULT);
952
953
				break;

954
955
956
957
958
959
960
961
962
			case MLX4_STEERING_MODE_B0:
				err = mlx4_multicast_promisc_add(mdev->dev,
								 priv->base_qpn,
								 priv->port);
				break;

			case MLX4_STEERING_MODE_A0:
				break;
			}
963
964
965
966
			if (err)
				en_err(priv, "Failed entering multicast promisc mode\n");
			priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
		}
967
	} else {
968
969
		/* Disable Multicast promisc */
		if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
970
			switch (mdev->dev->caps.steering_mode) {
971
972
973
			case MLX4_STEERING_MODE_DEVICE_MANAGED:
				err = mlx4_flow_steer_promisc_remove(mdev->dev,
								     priv->port,
974
								     MLX4_FS_MC_DEFAULT);
975
976
				break;

977
978
979
980
981
982
983
984
985
			case MLX4_STEERING_MODE_B0:
				err = mlx4_multicast_promisc_remove(mdev->dev,
								    priv->base_qpn,
								    priv->port);
				break;

			case MLX4_STEERING_MODE_A0:
				break;
			}
986
			if (err)
Lucas De Marchi's avatar
Lucas De Marchi committed
987
				en_err(priv, "Failed disabling multicast promiscuous mode\n");
988
989
			priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
		}
990

991
992
993
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_DISABLE);
		if (err)
994
			en_err(priv, "Failed disabling multicast filter\n");
995
996
997
998
999
1000
1001

		/* Flush mcast filter and init it with broadcast address */
		mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, ETH_BCAST,
				    1, MLX4_MCAST_CONFIG);

		/* Update multicast list - we cache all addresses so they won't
		 * change while HW is updated holding the command semaphor */
1002
		netif_addr_lock_bh(dev);
1003
		mlx4_en_cache_mclist(dev);
1004
		netif_addr_unlock_bh(dev);
1005
1006
		list_for_each_entry(mclist, &priv->mc_list, list) {
			mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
1007
1008
1009
1010
1011
1012
			mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
					    mcast_addr, 0, MLX4_MCAST_CONFIG);
		}
		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
					  0, MLX4_MCAST_ENABLE);
		if (err)
1013
			en_err(priv, "Failed enabling multicast filter\n");
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023

		update_mclist_flags(priv, &priv->curr_list, &priv->mc_list);
		list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
			if (mclist->action == MCLIST_REM) {
				/* detach this address and delete from list */
				memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
				mc_list[5] = priv->port;
				err = mlx4_multicast_detach(mdev->dev,
							    &priv->rss_map.indir_qp,
							    mc_list,
1024
1025
							    MLX4_PROT_ETH,
							    mclist->reg_id);
1026
1027
1028
1029
1030
1031
				if (err)
					en_err(priv, "Fail to detach multicast address\n");

				/* remove from list */
				list_del(&mclist->list);
				kfree(mclist);
1032
			} else if (mclist->action == MCLIST_ADD) {
1033
1034
				/* attach the address */
				memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
1035
				/* needed for B0 steering support */
1036
1037
1038
				mc_list[5] = priv->port;
				err = mlx4_multicast_attach(mdev->dev,
							    &priv->rss_map.indir_qp,
1039
1040
1041
1042
							    mc_list,
							    priv->port, 0,
							    MLX4_PROT_ETH,
							    &mclist->reg_id);
1043
1044
1045
1046
1047
				if (err)
					en_err(priv, "Fail to attach multicast address\n");

			}
		}
1048
	}
1049
1050
}

1051
1052
1053
1054
1055
1056
static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
				 struct net_device *dev,
				 struct mlx4_en_dev *mdev)
{
	struct netdev_hw_addr *ha;
	struct mlx4_mac_entry *entry;
1057
	struct hlist_node *tmp;
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
	bool found;
	u64 mac;
	int err = 0;
	struct hlist_head *bucket;
	unsigned int i;
	int removed = 0;
	u32 prev_flags;

	/* Note that we do not need to protect our mac_hash traversal with rcu,
	 * since all modification code is protected by mdev->state_lock
	 */

	/* find what to remove */
	for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
		bucket = &priv->mac_hash[i];
1073
		hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
			found = false;
			netdev_for_each_uc_addr(ha, dev) {
				if (ether_addr_equal_64bits(entry->mac,
							    ha->addr)) {
					found = true;
					break;
				}
			}

			/* MAC address of the port is not in uc list */
			if (ether_addr_equal_64bits(entry->mac, dev->dev_addr))
				found = true;

			if (!found) {
				mac = mlx4_en_mac_to_u64(entry->mac);
				mlx4_en_uc_steer_release(priv, entry->mac,
							 priv->base_qpn,
							 entry->reg_id);
				mlx4_unregister_mac(mdev->dev, priv->port, mac);

				hlist_del_rcu(&entry->hlist);
				kfree_rcu(entry, rcu);
				en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n",
				       entry->mac, priv->port);
				++removed;
			}
		}
	}

	/* if we didn't remove anything, there is no use in trying to add
	 * again once we are in a forced promisc mode state
	 */
	if ((priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) && 0 == removed)
		return;

	prev_flags = priv->flags;
	priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;

	/* find what to add */
	netdev_for_each_uc_addr(ha, dev) {
		found = false;
		bucket = &priv->mac_hash[ha->addr[MLX4_EN_MAC_HASH_IDX]];
1116
		hlist_for_each_entry(entry, bucket, hlist) {
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
			if (ether_addr_equal_64bits(entry->mac, ha->addr)) {
				found = true;
				break;
			}
		}

		if (!found) {
			entry = kmalloc(sizeof(*entry), GFP_KERNEL);
			if (!entry) {
				en_err(priv, "Failed adding MAC %pM on port:%d (out of memory)\n",
				       ha->addr, priv->port);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			}
			mac = mlx4_en_mac_to_u64(ha->addr);
			memcpy(entry->mac, ha->addr, ETH_ALEN);
			err = mlx4_register_mac(mdev->dev, priv->port, mac);
			if (err < 0) {
				en_err(priv, "Failed registering MAC %pM on port %d: %d\n",
				       ha->addr, priv->port, err);
				kfree(entry);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			}
			err = mlx4_en_uc_steer_add(priv, ha->addr,
						   &priv->base_qpn,
						   &entry->reg_id);
			if (err) {
				en_err(priv, "Failed adding MAC %pM on port %d: %d\n",
				       ha->addr, priv->port, err);
				mlx4_unregister_mac(mdev->dev, priv->port, mac);
				kfree(entry);
				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
				break;
			} else {
				unsigned int mac_hash;
				en_dbg(DRV, priv, "Added MAC %pM on port:%d\n",
				       ha->addr, priv->port);
				mac_hash = ha->addr[MLX4_EN_MAC_HASH_IDX];
				bucket = &priv->mac_hash[mac_hash];
				hlist_add_head_rcu(&entry->hlist, bucket);
			}
		}
	}

	if (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) {
		en_warn(priv, "Forcing promiscuous mode on port:%d\n",
			priv->port);
	} else if (prev_flags & MLX4_EN_FLAG_FORCE_PROMISC) {
		en_warn(priv, "Stop forcing promiscuous mode on port:%d\n",
			priv->port);
	}
}

1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
static void mlx4_en_do_set_rx_mode(struct work_struct *work)
{
	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
						 rx_mode_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct net_device *dev = priv->dev;

	mutex_lock(&mdev->state_lock);
	if (!mdev->device_up) {
		en_dbg(HW, priv, "Card is not up, ignoring rx mode change.\n");
		goto out;
	}
	if (!priv->port_up) {
		en_dbg(HW, priv, "Port is down, ignoring rx mode change.\n");
		goto out;
	}

	if (!netif_carrier_ok(dev)) {
		if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
			if (priv->port_state.link_state) {
				priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
				netif_carrier_on(dev);
				en_dbg(LINK, priv, "Link Up\n");
			}
		}
	}

1198
1199
1200
	if (dev->priv_flags & IFF_UNICAST_FLT)
		mlx4_en_do_uc_filter(priv, dev, mdev);

1201
	/* Promsicuous mode: disable all filters */
1202
1203
	if ((dev->flags & IFF_PROMISC) ||
	    (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC)) {
1204
1205
1206
1207
1208
1209
1210
1211
1212
		mlx4_en_set_promisc_mode(priv, mdev);
		goto out;
	}

	/* Not in promiscuous mode */
	if (priv->flags & MLX4_EN_FLAG_PROMISC)
		mlx4_en_clear_promisc_mode(priv, mdev);

	mlx4_en_do_multicast(priv, dev, mdev);
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
out:
	mutex_unlock(&mdev->state_lock);
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void mlx4_en_netpoll(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_cq *cq;
	unsigned long flags;
	int i;

	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = &priv->rx_cq[i];
		spin_lock_irqsave(&cq->lock, flags);
		napi_synchronize(&cq->napi);
		mlx4_en_process_rx_cq(dev, cq, 0);
		spin_unlock_irqrestore(&cq->lock, flags);
	}
}
#endif

static void mlx4_en_tx_timeout(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
1239
	int i;
1240
1241

	if (netif_msg_timer(priv))
1242
		en_warn(priv, "Tx timeout called on port:%d\n", priv->port);
1243

1244
1245
1246
1247
1248
1249
1250
1251
	for (i = 0; i < priv->tx_ring_num; i++) {
		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
			continue;
		en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
			i, priv->tx_ring[i].qpn, priv->tx_ring[i].cqn,
			priv->tx_ring[i].cons, priv->tx_ring[i].prod);
	}

1252
	priv->port_stats.tx_timeout++;
1253
	en_dbg(DRV, priv, "Scheduling watchdog\n");
1254
	queue_work(mdev->workqueue, &priv->watchdog_task);
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
}


static struct net_device_stats *mlx4_en_get_stats(struct net_device *dev)
{
	struct mlx4_en_priv *priv = netdev_priv(dev);

	spin_lock_bh(&priv->stats_lock);
	memcpy(&priv->ret_stats, &priv->stats, sizeof(priv->stats));
	spin_unlock_bh(&priv->stats_lock);

	return &priv->ret_stats;
}

static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
{
	struct mlx4_en_cq *cq;
	int i;

	/* If we haven't received a specific coalescing setting
1275
	 * (module param), we set the moderation parameters as follows:
1276
	 * - moder_cnt is set to the number of mtu sized packets to
1277
	 *   satisfy our coalescing target.
1278
1279
	 * - moder_time is set to a fixed value.
	 */
1280
	priv->rx_frames = MLX4_EN_RX_COAL_TARGET;
1281
	priv->rx_usecs = MLX4_EN_RX_COAL_TIME;
1282
1283
	priv->tx_frames = MLX4_EN_TX_COAL_PKTS;
	priv->tx_usecs = MLX4_EN_TX_COAL_TIME;
1284
1285
	en_dbg(INTR, priv, "Default coalesing params for mtu:%d - rx_frames:%d rx_usecs:%d\n",
	       priv->dev->mtu, priv->rx_frames, priv->rx_usecs);
1286
1287
1288
1289
1290
1291

	/* Setup cq moderation params */
	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = &priv->rx_cq[i];
		cq->moder_cnt = priv->rx_frames;
		cq->moder_time = priv->rx_usecs;
1292
1293
1294
		priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
		priv->last_moder_packets[i] = 0;
		priv->last_moder_bytes[i] = 0;
1295
1296
1297
1298
	}

	for (i = 0; i < priv->tx_ring_num; i++) {
		cq = &priv->tx_cq[i];
1299
1300
		cq->moder_cnt = priv->tx_frames;
		cq->moder_time = priv->tx_usecs;
1301
1302
1303
1304
1305
1306
1307
1308
	}

	/* Reset auto-moderation params */
	priv->pkt_rate_low = MLX4_EN_RX_RATE_LOW;
	priv->rx_usecs_low = MLX4_EN_RX_COAL_TIME_LOW;
	priv->pkt_rate_high = MLX4_EN_RX_RATE_HIGH;
	priv->rx_usecs_high = MLX4_EN_RX_COAL_TIME_HIGH;
	priv->sample_interval = MLX4_EN_SAMPLE_INTERVAL;
1309
	priv->adaptive_rx_coal = 1;
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
	priv->last_moder_jiffies = 0;
	priv->last_moder_tx_packets = 0;
}

static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
{
	unsigned long period = (unsigned long) (jiffies - priv->last_moder_jiffies);
	struct mlx4_en_cq *cq;
	unsigned long packets;
	unsigned long rate;
	unsigned long avg_pkt_size;
	unsigned long rx_packets;
	unsigned long rx_bytes;
	unsigned long rx_pkt_diff;
	int moder_time;
1325
	int ring, err;
1326
1327
1328
1329

	if (!priv->adaptive_rx_coal || period < priv->sample_interval * HZ)
		return;

1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
	for (ring = 0; ring < priv->rx_ring_num; ring++) {
		spin_lock_bh(&priv->stats_lock);
		rx_packets = priv->rx_ring[ring].packets;
		rx_bytes = priv->rx_ring[ring].bytes;
		spin_unlock_bh(&priv->stats_lock);

		rx_pkt_diff = ((unsigned long) (rx_packets -
				priv->last_moder_packets[ring]));
		packets = rx_pkt_diff;
		rate = packets * HZ / period;
		avg_pkt_size = packets ? ((unsigned long) (rx_bytes -
				priv->last_moder_bytes[ring])) / packets : 0;

		/* Apply auto-moderation only when packet rate
		 * exceeds a rate that it matters */
		if (rate > (MLX4_EN_RX_RATE_THRESH / priv->rx_ring_num) &&
		    avg_pkt_size > MLX4_EN_AVG_PKT_SMALL) {
1347
1348
1349
1350
1351
1352
1353
1354
1355
			if (rate < priv->pkt_rate_low)
				moder_time = priv->rx_usecs_low;
			else if (rate > priv->pkt_rate_high)
				moder_time = priv->rx_usecs_high;
			else
				moder_time = (rate - priv->pkt_rate_low) *
					(priv->rx_usecs_high - priv->rx_usecs_low) /
					(priv->pkt_rate_high - priv->pkt_rate_low) +
					priv->rx_usecs_low;
1356
1357
		} else {
			moder_time = priv->rx_usecs_low;
1358
1359
		}

1360
1361
1362
		if (moder_time != priv->last_moder_time[ring]) {
			priv->last_moder_time[ring] = moder_time;
			cq = &priv->rx_cq[ring];
1363
			cq->moder_time = moder_time;
1364
			cq->moder_cnt = priv->rx_frames;
1365
			err = mlx4_en_set_cq_moder(priv, cq);
1366
			if (err)
1367
1368
				en_err(priv, "Failed modifying moderation for cq:%d\n",
				       ring);
1369
		}
1370
1371
		priv->last_moder_packets[ring] = rx_packets;
		priv->last_moder_bytes[ring] = rx_bytes;
1372
1373
1374
1375
1376
1377
1378
	}

	priv->last_moder_jiffies = jiffies;
}

static void mlx4_en_do_get_stats(struct work_struct *work)
{
1379
	struct delayed_work *delay = to_delayed_work(work);
1380
1381
1382
1383
1384
1385
1386
	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
						 stats_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	int err;

	mutex_lock(&mdev->state_lock);
	if (mdev->device_up) {
1387
1388
1389
1390
		if (priv->port_up) {
			err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0);
			if (err)
				en_dbg(HW, priv, "Could not update stats\n");
1391

1392
			mlx4_en_auto_moderation(priv);
1393
		}
1394
1395
1396

		queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
	}
1397
	if (mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port]) {
1398
		mlx4_en_do_set_mac(priv);
1399
1400
		mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port] = 0;
	}
1401
1402
1403
	mutex_unlock(&mdev->state_lock);
}

Amir Vadai's avatar
Amir Vadai committed
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
/* mlx4_en_service_task - Run service task for tasks that needed to be done
 * periodically
 */
static void mlx4_en_service_task(struct work_struct *work)
{
	struct delayed_work *delay = to_delayed_work(work);
	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
						 service_task);
	struct mlx4_en_dev *mdev = priv->mdev;

	mutex_lock(&mdev->state_lock);
	if (mdev->device_up) {
1416
1417
		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
			mlx4_en_ptp_overflow_check(mdev);
Amir Vadai's avatar
Amir Vadai committed
1418
1419
1420
1421
1422
1423
1424

		queue_delayed_work(mdev->workqueue, &priv->service_task,
				   SERVICE_TASK_DELAY);
	}
	mutex_unlock(&mdev->state_lock);
}

1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
static void mlx4_en_linkstate(struct work_struct *work)
{
	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
						 linkstate_task);
	struct mlx4_en_dev *mdev = priv->mdev;
	int linkstate = priv->link_state;

	mutex_lock(&mdev->state_lock);
	/* If observable port state changed set carrier state and
	 * report to system log */
	if (priv->last_link_state != linkstate) {
		if (linkstate == MLX4_DEV_EVENT_PORT_DOWN) {
1437
			en_info(priv, "Link Down\n");
1438
1439
			netif_carrier_off(priv->dev);
		} else {
1440
			en_info(priv, "Link Up\n");
1441
1442
1443
1444
1445
1446
1447
1448
			netif_carrier_on(priv->dev);
		}
	}
	priv->last_link_state = linkstate;
	mutex_unlock(&mdev->state_lock);
}


1449
int mlx4_en_start_port(struct net_device *dev)
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
{
	struct mlx4_en_priv *priv = netdev_priv(dev);
	struct mlx4_en_dev *mdev = priv->mdev;
	struct mlx4_en_cq *cq;
	struct mlx4_en_tx_ring *tx_ring;
	int rx_index = 0;
	int tx_index = 0;
	int err = 0;
	int i;
	int j;
1460
	u8 mc_list[16] = {0};
1461
1462

	if (priv->port_up) {
1463
		en_dbg(DRV, priv, "start port called while port already up\n");
1464
1465
1466
		return 0;
	}

1467
1468
	INIT_LIST_HEAD(&priv->mc_list);
	INIT_LIST_HEAD(&priv->curr_list);
1469
1470
1471
	INIT_LIST_HEAD(&priv->ethtool_list);
	memset(&priv->ethtool_rules[0], 0,
	       sizeof(struct ethtool_flow_id) * MAX_NUM_OF_FS_RULES);
1472

1473
1474
1475
	/* Calculate Rx buf size */
	dev->mtu = min(dev->mtu, priv->max_mtu);
	mlx4_en_calc_rx_buf(dev);
1476
	en_dbg(DRV, priv, "Rx buf size:%d\n", priv->rx_skb_size);
1477

1478
	/* Configure rx cq's and rings */
1479
1480
	err = mlx4_en_activate_rx_rings(priv);
	if (err) {
1481
		en_err(priv, "Failed to activate RX rings\n");
1482
1483
		return err;
	}
1484
1485
1486
	for (i = 0; i < priv->rx_ring_num; i++) {
		cq = &priv->rx_cq[i];

1487
1488
		mlx4_en_cq_init_lock(cq);

1489
		err = mlx4_en_activate_cq(priv, cq, i);
1490
		if (err) {
1491
			en_err(priv, "Failed activating Rx CQ\n");
1492
			goto cq_err;
1493
1494
1495
1496
1497
		}
		for (j = 0; j < cq->size; j++)
			cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK;
		err = mlx4_en_set_cq_moder(priv, cq);
		if (err) {
1498
			en_err(priv, "Failed setting cq moderation parameters");
1499
1500
1501
1502
			mlx4_en_deactivate_cq(priv, cq);
			goto cq_err;
		}
		mlx4_en_arm_cq(priv, cq);