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
|
/* 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_private {
struct tasklet_struct ifb_tasklet;
int tasklet_pending;
struct u64_stats_sync rsync;
struct sk_buff_head rq;
u64 rx_packets;
u64 rx_bytes;
struct u64_stats_sync tsync;
struct sk_buff_head tq;
u64 tx_packets;
u64 tx_bytes;
};
static int numifbs = 2;
static void ri_tasklet(unsigned long dev);
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 ri_tasklet(unsigned long dev)
{
struct net_device *_dev = (struct net_device *)dev;
struct ifb_private *dp = netdev_priv(_dev);
struct netdev_queue *txq;
struct sk_buff *skb;
txq = netdev_get_tx_queue(_dev, 0);
if ((skb = skb_peek(&dp->tq)) == NULL) {
if (__netif_tx_trylock(txq)) {
skb_queue_splice_tail_init(&dp->rq, &dp->tq);
__netif_tx_unlock(txq);
} else {
/* reschedule */
goto resched;
}
}
while ((skb = __skb_dequeue(&dp->tq)) != NULL) {
u32 from = G_TC_FROM(skb->tc_verd);
skb->tc_verd = 0;
skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
u64_stats_update_begin(&dp->tsync);
dp->tx_packets++;
dp->tx_bytes += skb->len;
u64_stats_update_end(&dp->tsync);
rcu_read_lock();
skb->dev = dev_get_by_index_rcu(&init_net, skb->skb_iif);
if (!skb->dev) {
rcu_read_unlock();
dev_kfree_skb(skb);
_dev->stats.tx_dropped++;
if (skb_queue_len(&dp->tq) != 0)
goto resched;
break;
}
rcu_read_unlock();
skb->skb_iif = _dev->ifindex;
if (from & AT_EGRESS) {
dev_queue_xmit(skb);
} else if (from & AT_INGRESS) {
skb_pull(skb, skb->dev->hard_header_len);
netif_receive_skb(skb);
} else
BUG();
}
if (__netif_tx_trylock(txq)) {
if ((skb = skb_peek(&dp->rq)) == NULL) {
dp->tasklet_pending = 0;
if (netif_queue_stopped(_dev))
netif_wake_queue(_dev);
} else {
__netif_tx_unlock(txq);
goto resched;
}
__netif_tx_unlock(txq);
} else {
resched:
dp->tasklet_pending = 1;
tasklet_schedule(&dp->ifb_tasklet);
}
}
static struct rtnl_link_stats64 *ifb_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct ifb_private *dp = netdev_priv(dev);
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&dp->rsync);
stats->rx_packets = dp->rx_packets;
stats->rx_bytes = dp->rx_bytes;
} while (u64_stats_fetch_retry_bh(&dp->rsync, start));
do {
start = u64_stats_fetch_begin_bh(&dp->tsync);
stats->tx_packets = dp->tx_packets;
stats->tx_bytes = dp->tx_bytes;
} while (u64_stats_fetch_retry_bh(&dp->tsync, start));
stats->rx_dropped = dev->stats.rx_dropped;
stats->tx_dropped = dev->stats.tx_dropped;
return stats;
}
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,
};
#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_HIGHDMA | NETIF_F_HW_VLAN_TX)
static void ifb_setup(struct net_device *dev)
{
/* Initialize the device structure. */
dev->destructor = free_netdev;
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->vlan_features |= IFB_FEATURES;
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
random_ether_addr(dev->dev_addr);
}
static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
u32 from = G_TC_FROM(skb->tc_verd);
u64_stats_update_begin(&dp->rsync);
dp->rx_packets++;
dp->rx_bytes += skb->len;
u64_stats_update_end(&dp->rsync);
if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->skb_iif) {
dev_kfree_skb(skb);
dev->stats.rx_dropped++;
return NETDEV_TX_OK;
}
if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) {
netif_stop_queue(dev);
}
__skb_queue_tail(&dp->rq, skb);
if (!dp->tasklet_pending) {
dp->tasklet_pending = 1;
tasklet_schedule(&dp->ifb_tasklet);
}
return NETDEV_TX_OK;
}
static int ifb_close(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
tasklet_kill(&dp->ifb_tasklet);
netif_stop_queue(dev);
__skb_queue_purge(&dp->rq);
__skb_queue_purge(&dp->tq);
return 0;
}
static int ifb_open(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev);
__skb_queue_head_init(&dp->rq);
__skb_queue_head_init(&dp->tq);
netif_start_queue(dev);
return 0;
}
static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
{
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_private),
.setup = ifb_setup,
.validate = ifb_validate,
};
/* Number of ifb devices to be set up by this module. */
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_private),
"ifb%d", 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);
for (i = 0; i < numifbs && !err; i++)
err = ifb_init_one(i);
if (err)
__rtnl_link_unregister(&ifb_link_ops);
rtnl_unlock();
return err;
}
static<
|