summaryrefslogtreecommitdiffstats
path: root/drivers/net/ifb.c
blob: 8870bd2a2e8a2439c4a0618506375db6b9b4f653 (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
/* drivers/net/ifb.c:

	The purpose of this driver is to provide a device that allows
	for sharing of resources:

	1) qdiscs/policies that are per device as opposed to system wide.
	ifb allows for a device which can be redirected to thus providing
	an impression of sharing.

	2) Allows for queueing incoming traffic for shaping instead of
	dropping.

	The original concept is based on what is known as the IMQ
	driver initially written by Martin Devera, later rewritten
	by Patrick McHardy and then maintained by Andre Correa.

	You need the tc action  mirror or redirect to feed this device
       	packets.

	This program is free software; you can redistribute it and/or
	modify it under the terms of the GNU General Public License
	as published by the Free Software Foundation; either version
	2 of the License, or (at your option) any later version.

  	Authors:	Jamal Hadi Salim (2005)

*/


#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/moduleparam.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>

#define TX_Q_LIMIT    32
struct ifb_q_private {
	struct net_device	*dev;
	struct tasklet_struct   ifb_tasklet;
	int			tasklet_pending;
	int			txqnum;
	struct sk_buff_head     rq;
	u64			rx_packets;
	u64			rx_bytes;
	struct u64_stats_sync	rsync;

	struct u64_stats_sync	tsync;
	u64			tx_packets;
	u64			tx_bytes;
	struct sk_buff_head     tq;
} ____cacheline_aligned_in_smp;

struct ifb_dev_private {
	struct ifb_q_private *tx_private;
};

static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev);
static int ifb_open(struct net_device *dev);
static int ifb_close(struct net_device *dev);

static void ifb_ri_tasklet(unsigned long _txp)
{
	struct ifb_q_private *txp = (struct ifb_q_private *)_txp;
	struct netdev_queue *txq;
	struct sk_buff *skb;

	txq = netdev_get_tx_queue(txp->dev, txp->txqnum);
	skb = skb_peek(&txp->tq);
	if (!skb) {
		if (!__netif_tx_trylock(txq))
			goto resched;
		skb_queue_splice_tail_init(&txp->rq, &txp->tq);
		__netif_tx_unlock(txq);
	}

	while ((skb = __skb_dequeue(&txp->tq)) != NULL) {
		skb->tc_redirected = 0;
		skb->tc_skip_classify = 1;

		u64_stats_update_begin(&txp->tsync);
		txp->tx_packets++;
		txp->tx_bytes += skb->len;
		u64_stats_update_end(&txp->tsync);

		rcu_read_lock();
		skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif);
		if (!skb->dev) {
			rcu_read_unlock();
			dev_kfree_skb(skb);
			txp->dev->stats.tx_dropped++;
			if (skb_queue_len(&txp->tq) != 0)
				goto resched;
			break;
		}
		rcu_read_unlock();
		skb->skb_iif = txp->dev->ifindex;

		if (!skb->tc_from_ingress) {
			dev_queue_xmit(skb);
		} else {
			skb_pull(skb, skb->mac_len);
			netif_receive_skb(skb);
		}
	}

	if (__netif_tx_trylock(txq)) {
		skb = skb_peek(&txp->rq);
		if (!skb) {
			txp->tasklet_pending = 0;
			if (netif_tx_queue_stopped(txq))
				netif_tx_wake_queue(txq);
		} else {
			__netif_tx_unlock(txq);
			goto resched;
		}
		__netif_tx_unlock(txq);
	} else {
resched:
		txp->tasklet_pending = 1;
		tasklet_schedule(&txp->ifb_tasklet);
	}

}

static void ifb_stats64(struct net_device *dev,
			struct rtnl_link_stats64 *stats)
{
	struct ifb_dev_private *dp = netdev_priv(dev);
	struct ifb_q_private *txp = dp->tx_private;
	unsigned int start;
	u64 packets, bytes;
	int i;

	for (i = 0; i < dev->num_tx_queues; i++,txp++) {
		do {
			start = u64_stats_fetch_begin_irq(&txp->rsync);
			packets = txp->rx_packets;
			bytes = txp->rx_bytes;
		} while (u64_stats_fetch_retry_irq(&txp->rsync, start));
		stats->rx_packets += packets;
		stats->rx_bytes += bytes;

		do {
			start = u64_stats_fetch_begin_irq(&txp->tsync);
			packets = txp->tx_packets;
			bytes = txp->tx_bytes;
		} while (u64_stats_fetch_retry_irq(&txp->tsync, start));
		stats->tx_packets += packets;
		stats->tx_bytes += bytes;
	}
	stats->rx_dropped = dev->stats.rx_dropped;
	stats->tx_dropped = dev->stats.tx_dropped;
}

static int ifb_dev_init(struct net_device *dev)
{
	struct ifb_dev_private *dp = netdev_priv(dev);
	struct ifb_q_private *txp;
	int i;

	txp = kcalloc(dev->num_tx_queues, sizeof(*txp), GFP_KERNEL);
	if (!txp)
		return -ENOMEM;
	dp->tx_private = txp;
	for (i = 0; i < dev->num_tx_queues; i++,txp++) {
		txp->txqnum = i;
		txp->dev = dev;
		__skb_queue_head_init(&txp->rq);
		__skb_queue_head_init(&txp->tq);
		u64_stats_init(&txp->rsync);
		u64_stats_init(&txp->tsync);
		tasklet_init(&txp->ifb_tasklet, ifb_ri_tasklet,
			     (unsigned long)txp);
		netif_tx_start_queue(netdev_get_tx_queue(dev, i));
	}
	return 0;
}

static const struct net_device_ops ifb_netdev_ops = {
	.ndo_open	= ifb_open,
	.ndo_stop	= ifb_close,
	.ndo_get_stats64 = ifb_stats64,
	.ndo_start_xmit	= ifb_xmit,
	.ndo_validate_addr = eth_validate_addr,
	.ndo_init	= ifb_dev_init,
};

#define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG  | NETIF_F_FRAGLIST	| \
		      NETIF_F_TSO_ECN | NETIF_F_TSO | NETIF_F_TSO6	| \
		      NETIF_F_GSO_ENCAP_ALL 				| \
		      NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX		| \
		      NETIF_F_HW_VLAN_STAG_TX)

static void ifb_dev_free(struct net_device *dev)
{
	struct ifb_dev_private *dp = netdev_priv(dev);
	struct ifb_q_private *txp = dp->tx_private;
	int i;

	for (i = 0; i < dev->num_tx_queues; i++,txp++) {
		tasklet_kill(&txp->ifb_tasklet);
		__skb_queue_purge(&txp->rq);
		__skb_queue_purge(&txp->tq);
	}
	kfree(dp->tx_private);
}

static void ifb_setup(struct net_device *dev)
{
	/* Initialize the device structure. */
	dev->netdev_ops = &ifb_netdev_ops;

	/* Fill in device structure with ethernet-generic values. */
	ether_setup(dev);
	dev->tx_queue_len = TX_Q_LIMIT;

	dev->features |= IFB_FEATURES;
	dev->hw_features |= dev->features;
	dev->hw_enc_features |= dev->features;
	dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX |
					       NETIF_F_HW_VLAN_STAG_TX);

	dev->flags |= IFF_NOARP;
	dev->flags &= ~IFF_MULTICAST;
	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
	netif_keep_dst(dev);
	eth_hw_addr_random(dev);
	dev->needs_free_netdev = true;
	dev->priv_destructor = ifb_dev_free;
}

static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ifb_dev_private *dp = netdev_priv(dev);
	struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb);

	u64_stats_update_begin(&txp->rsync);
	txp->rx_packets++;
	txp->rx_bytes += skb->len;
	u64_stats_update_end(&txp->rsync);

	if (!skb->tc_redirected || !skb->skb_iif) {
		dev_kfree_skb(skb);
		dev->stats.rx_dropped++;
		return NETDEV_TX_OK;
	}

	if (skb_queue_len(&txp->rq) >= dev->tx_queue_len)
		netif_tx_stop_queue(netdev_get_tx_queue(dev, txp->txqnum));

	__skb_queue_tail(&txp->rq, skb);
	if (!txp->tasklet_pending) {
		txp->tasklet_pending = 1;
		tasklet_schedule(&txp->ifb_tasklet);
	}

	return NETDEV_TX_OK;
}

static int ifb_close(struct net_device *dev)
{
	netif_tx_stop_all_queues(dev);
	return 0;
}

static int ifb_open(struct net_device *dev)
{
	netif_tx_start_all_queues(dev);
	return 0;
}

static int ifb_validate(struct nlattr *tb[], struct nlattr *data[],
			struct netlink_ext_ack *extack)
{
	if (tb[IFLA_ADDRESS]) {
		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
			return -EINVAL;
		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
			return -EADDRNOTAVAIL;
	}
	return 0;
}

static struct rtnl_link_ops ifb_link_ops __read_mostly = {
	.kind		= "ifb",
	.priv_size	= sizeof(struct ifb_dev_private),
	.setup		= ifb_setup,
	.validate	= ifb_validate,
};

/* Number of ifb devices to be set up by this module.
 * Note that these legacy devices have one queue.
 * Prefer something like : ip link add ifb10 numtxqueues 8 type ifb
 */
static int numifbs = 2;
module_param(numifbs, int, 0);
MODULE_PARM_DESC(numifbs, "Number of ifb devices");

static int __init ifb_init_one(int index)
{
	struct net_device *dev_ifb;
	int err;

	dev_ifb = alloc_netdev(sizeof(struct ifb_dev_private), "ifb%d",
			       NET_NAME_UNKNOWN, ifb_setup);

	if (!dev_ifb)
		return -ENOMEM;

	dev_ifb->rtnl_link_ops = &ifb_link_ops;
	err = register_netdevice(dev_ifb);
	if (err < 0)
		goto err;

	return 0;

err:
	free_netdev(dev_ifb);
	return err;
}

static int __init ifb_init_module(void)
{
	int i, err;

	rtnl_lock();
	err = __rtnl_link_register(&ifb_link_ops);
	if (err < 0)
		goto out;

	for (i = 0; i < numifbs && !err; i++) {
		err = ifb_init_one(i);
		cond_resched();
	}
	if (err)
		__rtnl_link_unregister(&ifb_link_ops);

out:
	rtnl_unlock();

	return err;
}

static void __exit ifb_cleanup_module(void)
{
	rtnl_link_unregister(&ifb_link_ops);
}

module_init(ifb_init_module);
module_exit(ifb_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jamal Hadi Salim");
MODULE_ALIAS_RTNL_LINK("ifb");