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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Pseudo-driver for the loopback interface.
*
* Version: @(#)loopback.c 1.0.4b 08/16/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@scyld.com>
*
* Alan Cox : Fixed oddments for NET3.014
* Alan Cox : Rejig for NET3.029 snap #3
* Alan Cox : Fixed NET3.029 bugs and sped up
* Larry McVoy : Tiny tweak to double performance
* Alan Cox : Backed out LMV's tweak - the linux mm
* can't take it...
* Michael Griffith: Don't bother computing the checksums
* on packets received on the loopback
* interface.
* Alexey Kuznetsov: Potential hang under some extreme
* cases removed.
*/
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/in.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/ethtool.h>
#include <net/sch_generic.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <linux/if_ether.h> /* For the statistics structure. */
#include <linux/if_arp.h> /* For ARPHRD_ETHER */
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/percpu.h>
#include <linux/net_tstamp.h>
#include <net/net_namespace.h>
#include <linux/u64_stats_sync.h>
/* blackhole_netdev - a device used for dsts that are marked expired!
* This is global device (instead of per-net-ns) since it's not needed
* to be per-ns and gets initialized at boot time.
*/
struct net_device *blackhole_netdev;
EXPORT_SYMBOL(blackhole_netdev);
/* The higher levels take care of making this non-reentrant (it's
* called with bh's disabled).
*/
static netdev_tx_t loopback_xmit(struct sk_buff *skb,
struct net_device *dev)
{
int len;
skb_tx_timestamp(skb);
/* do not fool net_timestamp_check() with various clock bases */
skb_clear_tstamp(skb);
skb_orphan(skb);
/* Before queueing this packet to __netif_rx(),
* make sure dst is refcounted.
*/
skb_dst_force(skb);
skb->protocol = eth_type_trans(skb, dev);
len = skb->len;
if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
dev_lstats_add(dev, len);
return NETDEV_TX_OK;
}
void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes)
{
int i;
*packets = 0;
*bytes = 0;
for_each_possible_cpu(i) {
const struct pcpu_lstats *lb_stats;
u64 tbytes, tpackets;
unsigned int start;
lb_stats = per_cpu_ptr(dev->lstats, i);
do {
start = u64_stats_fetch_begin(&lb_stats->syncp);
tpackets = u64_stats_read(&lb_stats->packets);
tbytes = u64_stats_read(&lb_stats->bytes);
} while (u64_stats_fetch_retry(&lb_stats->syncp, start));
*bytes += tbytes;
*packets += tpackets;
}
}
EXPORT_SYMBOL(dev_lstats_read);
static void loopback_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
u64 packets, bytes;
dev_lstats_read(dev, &packets, &bytes);
stats->rx_packets = packets;
stats->tx_packets = packets;
stats->rx_bytes = bytes;
stats->tx_bytes = bytes;
}
static u32 always_on(struct net_device *dev)
{
return 1;
}
static const struct ethtool_ops loopback_ethtool_ops = {
.get_link = always_on,
.get_ts_info = ethtool_op_get_ts_info,
};
static int loopback_dev_init(struct net_device *dev)
{
netdev_lockdep_set_classes(dev);
return 0;
}
static void loopback_dev_free(struct net_device *dev)
{
dev_net(dev)->loopback_dev = NULL;
}
static const struct net_device_ops loopback_ops = {
.ndo_init = loopback_dev_init,
.ndo_start_xmit = loopback_xmit,
.ndo_get_stats64 = loopback_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
};
static void gen_lo_setup(struct net_device *dev,
unsigned int mtu,
const struct ethtool_ops *eth_ops,
const struct header_ops *hdr_ops,
const struct net_device_ops *dev_ops,
void (*dev_destructor)(struct net_device *dev))
{
dev->mtu = mtu;
dev->hard_header_len = ETH_HLEN; /* 14 */
dev->min_header_len = ETH_HLEN; /* 14 */
dev->addr_len = ETH_ALEN; /* 6 */
dev->type = ARPHRD_LOOPBACK; /* 0x0001*/
dev->flags = IFF_LOOPBACK;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
dev->lltx = true;
dev->netns_local = true;
netif_keep_dst(dev);
dev->hw_features = NETIF_F_GSO_SOFTWARE;
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
| NETIF_F_GSO_SOFTWARE
| NETIF_F_HW_CSUM
| NETIF_F_RXCSUM
| NETIF_F_SCTP_CRC
| NETIF_F_HIGHDMA
| NETIF_F_VLAN_CHALLENGED
| NETIF_F_LOOPBACK;
dev->ethtool_ops = eth_ops;
dev->header_ops = hdr_ops;
dev->netdev_ops = dev_ops;
dev->needs_free_netdev = true;
dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS;
dev->priv_destructor = dev_destructor;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
}
/* The loopback device is special. There is only one instance
* per network namespace.
*/
static void loopback_setup(struct net_device *dev)
{
gen_lo_setup(dev, (64 * 1024), &loopback_ethtool_ops, ð_header_ops,
&loopback_ops, loopback_dev_free);
}
/* Setup and register the loopback device. */
static __net_init int loopback_net_init(struct net *net)
{
struct net_device *dev;
int err;
err = -ENOMEM;
dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup);
if (!dev)
goto out;
dev_net_set(dev, net);
err = register_netdev(dev);
if (err)
goto out_free_netdev;
BUG_ON(dev->ifindex != LOOPBACK_IFINDEX);
net->loopback_dev = dev;
return 0;
out_free_netdev:
free_netdev(dev);
out:
if (net_eq(net, &init_net))
panic("loopback: Failed to register netdevice: %d\n", err);
return err;
}
/* Registered in net/core/dev.c */
struct pernet_operations __net_initdata loopback_net_ops = {
.init = loopback_net_init,
};
/* blackhole netdevice */
static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
struct net_device *dev)
{
kfree_skb(skb);
net_warn_ratelimited("%s(): Dropping skb.\n", __func__);
return NETDEV_TX_OK;
}
static const struct net_device_ops blackhole_netdev_ops = {
.ndo_start_xmit = blackhole_netdev_xmit,
};
/* This is a dst-dummy device used specifically for invalidated
* DSTs and unlike loopback, this is not per-ns.
*/
static void blackhole_netdev_setup(struct net_device *dev)
{
gen_lo_setup(dev, ETH_MIN_MTU, NULL, NULL, &blackhole_netdev_ops, NULL);
}
/* Setup and register the blackhole_netdev. */
static int __init blackhole_netdev_init(void)
{
blackhole_netdev = alloc_netdev(0, "blackhole_dev", NET_NAME_UNKNOWN,
blackhole_netdev_setup);
if (!blackhole_netdev)
return -ENOMEM;
rtnl_lock();
dev_init_scheduler(blackhole_netdev);
dev_activate(blackhole_netdev);
rtnl_unlock();
blackhole_netdev->flags |= IFF_UP | IFF_RUNNING;
dev_net_set(blackhole_netdev, &init_net);
return 0;
}
device_initcall(blackhole_netdev_init);
|