1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * INET An implementation of the TCP/IP protocol suite for the LINUX
4 * operating system. INET is implemented using the BSD Socket
5 * interface as the means of communication with the user level.
6 *
7 * Pseudo-driver for the loopback interface.
8 *
9 * Version: @(#)loopback.c 1.0.4b 08/16/93
10 *
11 * Authors: Ross Biro
12 * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
13 * Donald Becker, <becker@scyld.com>
14 *
15 * Alan Cox : Fixed oddments for NET3.014
16 * Alan Cox : Rejig for NET3.029 snap #3
17 * Alan Cox : Fixed NET3.029 bugs and sped up
18 * Larry McVoy : Tiny tweak to double performance
19 * Alan Cox : Backed out LMV's tweak - the linux mm
20 * can't take it...
21 * Michael Griffith: Don't bother computing the checksums
22 * on packets received on the loopback
23 * interface.
24 * Alexey Kuznetsov: Potential hang under some extreme
25 * cases removed.
26 */
27 #include <linux/kernel.h>
28 #include <linux/jiffies.h>
29 #include <linux/module.h>
30 #include <linux/interrupt.h>
31 #include <linux/fs.h>
32 #include <linux/types.h>
33 #include <linux/string.h>
34 #include <linux/socket.h>
35 #include <linux/errno.h>
36 #include <linux/fcntl.h>
37 #include <linux/in.h>
38
39 #include <linux/uaccess.h>
40 #include <linux/io.h>
41
42 #include <linux/inet.h>
43 #include <linux/netdevice.h>
44 #include <linux/etherdevice.h>
45 #include <linux/skbuff.h>
46 #include <linux/ethtool.h>
47 #include <net/sch_generic.h>
48 #include <net/sock.h>
49 #include <net/checksum.h>
50 #include <linux/if_ether.h> /* For the statistics structure. */
51 #include <linux/if_arp.h> /* For ARPHRD_ETHER */
52 #include <linux/ip.h>
53 #include <linux/tcp.h>
54 #include <linux/percpu.h>
55 #include <linux/net_tstamp.h>
56 #include <net/net_namespace.h>
57 #include <linux/u64_stats_sync.h>
58
59 /* blackhole_netdev - a device used for dsts that are marked expired!
60 * This is global device (instead of per-net-ns) since it's not needed
61 * to be per-ns and gets initialized at boot time.
62 */
63 struct net_device *blackhole_netdev;
64 EXPORT_SYMBOL(blackhole_netdev);
65
66 /* The higher levels take care of making this non-reentrant (it's
67 * called with bh's disabled).
68 */
loopback_xmit(struct sk_buff * skb,struct net_device * dev)69 static netdev_tx_t loopback_xmit(struct sk_buff *skb,
70 struct net_device *dev)
71 {
72 int len;
73
74 skb_tx_timestamp(skb);
75
76 /* do not fool net_timestamp_check() with various clock bases */
77 skb_clear_tstamp(skb);
78
79 skb_orphan(skb);
80
81 /* Before queueing this packet to __netif_rx(),
82 * make sure dst is refcounted.
83 */
84 skb_dst_force(skb);
85
86 skb->protocol = eth_type_trans(skb, dev);
87
88 len = skb->len;
89 if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
90 dev_lstats_add(dev, len);
91
92 return NETDEV_TX_OK;
93 }
94
dev_lstats_read(struct net_device * dev,u64 * packets,u64 * bytes)95 void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes)
96 {
97 int i;
98
99 *packets = 0;
100 *bytes = 0;
101
102 for_each_possible_cpu(i) {
103 const struct pcpu_lstats *lb_stats;
104 u64 tbytes, tpackets;
105 unsigned int start;
106
107 lb_stats = per_cpu_ptr(dev->lstats, i);
108 do {
109 start = u64_stats_fetch_begin(&lb_stats->syncp);
110 tpackets = u64_stats_read(&lb_stats->packets);
111 tbytes = u64_stats_read(&lb_stats->bytes);
112 } while (u64_stats_fetch_retry(&lb_stats->syncp, start));
113 *bytes += tbytes;
114 *packets += tpackets;
115 }
116 }
117 EXPORT_SYMBOL(dev_lstats_read);
118
loopback_get_stats64(struct net_device * dev,struct rtnl_link_stats64 * stats)119 static void loopback_get_stats64(struct net_device *dev,
120 struct rtnl_link_stats64 *stats)
121 {
122 u64 packets, bytes;
123
124 dev_lstats_read(dev, &packets, &bytes);
125
126 stats->rx_packets = packets;
127 stats->tx_packets = packets;
128 stats->rx_bytes = bytes;
129 stats->tx_bytes = bytes;
130 }
131
always_on(struct net_device * dev)132 static u32 always_on(struct net_device *dev)
133 {
134 return 1;
135 }
136
137 static const struct ethtool_ops loopback_ethtool_ops = {
138 .get_link = always_on,
139 .get_ts_info = ethtool_op_get_ts_info,
140 };
141
loopback_dev_init(struct net_device * dev)142 static int loopback_dev_init(struct net_device *dev)
143 {
144 dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
145 if (!dev->lstats)
146 return -ENOMEM;
147 return 0;
148 }
149
loopback_dev_free(struct net_device * dev)150 static void loopback_dev_free(struct net_device *dev)
151 {
152 dev_net(dev)->loopback_dev = NULL;
153 free_percpu(dev->lstats);
154 }
155
156 static const struct net_device_ops loopback_ops = {
157 .ndo_init = loopback_dev_init,
158 .ndo_start_xmit = loopback_xmit,
159 .ndo_get_stats64 = loopback_get_stats64,
160 .ndo_set_mac_address = eth_mac_addr,
161 };
162
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))163 static void gen_lo_setup(struct net_device *dev,
164 unsigned int mtu,
165 const struct ethtool_ops *eth_ops,
166 const struct header_ops *hdr_ops,
167 const struct net_device_ops *dev_ops,
168 void (*dev_destructor)(struct net_device *dev))
169 {
170 dev->mtu = mtu;
171 dev->hard_header_len = ETH_HLEN; /* 14 */
172 dev->min_header_len = ETH_HLEN; /* 14 */
173 dev->addr_len = ETH_ALEN; /* 6 */
174 dev->type = ARPHRD_LOOPBACK; /* 0x0001*/
175 dev->flags = IFF_LOOPBACK;
176 dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
177 netif_keep_dst(dev);
178 dev->hw_features = NETIF_F_GSO_SOFTWARE;
179 dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
180 | NETIF_F_GSO_SOFTWARE
181 | NETIF_F_HW_CSUM
182 | NETIF_F_RXCSUM
183 | NETIF_F_SCTP_CRC
184 | NETIF_F_HIGHDMA
185 | NETIF_F_LLTX
186 | NETIF_F_NETNS_LOCAL
187 | NETIF_F_VLAN_CHALLENGED
188 | NETIF_F_LOOPBACK;
189 dev->ethtool_ops = eth_ops;
190 dev->header_ops = hdr_ops;
191 dev->netdev_ops = dev_ops;
192 dev->needs_free_netdev = true;
193 dev->priv_destructor = dev_destructor;
194
195 netif_set_tso_max_size(dev, GSO_MAX_SIZE);
196 }
197
198 /* The loopback device is special. There is only one instance
199 * per network namespace.
200 */
loopback_setup(struct net_device * dev)201 static void loopback_setup(struct net_device *dev)
202 {
203 gen_lo_setup(dev, (64 * 1024), &loopback_ethtool_ops, ð_header_ops,
204 &loopback_ops, loopback_dev_free);
205 }
206
207 /* Setup and register the loopback device. */
loopback_net_init(struct net * net)208 static __net_init int loopback_net_init(struct net *net)
209 {
210 struct net_device *dev;
211 int err;
212
213 err = -ENOMEM;
214 dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup);
215 if (!dev)
216 goto out;
217
218 dev_net_set(dev, net);
219 err = register_netdev(dev);
220 if (err)
221 goto out_free_netdev;
222
223 BUG_ON(dev->ifindex != LOOPBACK_IFINDEX);
224 net->loopback_dev = dev;
225 return 0;
226
227 out_free_netdev:
228 free_netdev(dev);
229 out:
230 if (net_eq(net, &init_net))
231 panic("loopback: Failed to register netdevice: %d\n", err);
232 return err;
233 }
234
235 /* Registered in net/core/dev.c */
236 struct pernet_operations __net_initdata loopback_net_ops = {
237 .init = loopback_net_init,
238 };
239
240 /* blackhole netdevice */
blackhole_netdev_xmit(struct sk_buff * skb,struct net_device * dev)241 static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
242 struct net_device *dev)
243 {
244 kfree_skb(skb);
245 net_warn_ratelimited("%s(): Dropping skb.\n", __func__);
246 return NETDEV_TX_OK;
247 }
248
249 static const struct net_device_ops blackhole_netdev_ops = {
250 .ndo_start_xmit = blackhole_netdev_xmit,
251 };
252
253 /* This is a dst-dummy device used specifically for invalidated
254 * DSTs and unlike loopback, this is not per-ns.
255 */
blackhole_netdev_setup(struct net_device * dev)256 static void blackhole_netdev_setup(struct net_device *dev)
257 {
258 gen_lo_setup(dev, ETH_MIN_MTU, NULL, NULL, &blackhole_netdev_ops, NULL);
259 }
260
261 /* Setup and register the blackhole_netdev. */
blackhole_netdev_init(void)262 static int __init blackhole_netdev_init(void)
263 {
264 blackhole_netdev = alloc_netdev(0, "blackhole_dev", NET_NAME_UNKNOWN,
265 blackhole_netdev_setup);
266 if (!blackhole_netdev)
267 return -ENOMEM;
268
269 rtnl_lock();
270 dev_init_scheduler(blackhole_netdev);
271 dev_activate(blackhole_netdev);
272 rtnl_unlock();
273
274 blackhole_netdev->flags |= IFF_UP | IFF_RUNNING;
275 dev_net_set(blackhole_netdev, &init_net);
276
277 return 0;
278 }
279
280 device_initcall(blackhole_netdev_init);
281