summaryrefslogtreecommitdiffstats
path: root/drivers/net/loopback.c
blob: 0f9d8c60c964d85b7b32161bcc282f524ddec28f (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
/*
 * 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.
 *
 *		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.
 */
#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/init.h>

#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/io.h>

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/ethtool.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 <net/net_namespace.h>

struct pcpu_lstats {
	unsigned long packets;
	unsigned long bytes;
};

#define LOOPBACK_OVERHEAD (128 + MAX_HEADER + 16 + 16)

/* KISS: just allocate small chunks and copy bits.
 *
 * So, in fact, this is documentation, explaining what we expect
 * of largesending device modulo TCP checksum, which is ignored for loopback.
 */

#ifdef LOOPBACK_TSO
static void emulate_large_send_offload(struct sk_buff *skb)
{
	struct iphdr *iph = ip_hdr(skb);
	struct tcphdr *th = (struct tcphdr *)(skb_network_header(skb) +
					      (iph->ihl * 4));
	unsigned int doffset = (iph->ihl + th->doff) * 4;
	unsigned int mtu = skb_shinfo(skb)->gso_size + doffset;
	unsigned int offset = 0;
	u32 seq = ntohl(th->seq);
	u16 id  = ntohs(iph->id);

	while (offset + doffset < skb->len) {
		unsigned int frag_size = min(mtu, skb->len - offset) - doffset;
		struct sk_buff *nskb = alloc_skb(mtu + 32, GFP_ATOMIC);

		if (!nskb)
			break;
		skb_reserve(nskb, 32);
		skb_set_mac_header(nskb, -ETH_HLEN);
		skb_reset_network_header(nskb);
		iph = ip_hdr(nskb);
		skb_copy_to_linear_data(nskb, skb_network_header(skb),
					doffset);
		if (skb_copy_bits(skb,
				  doffset + offset,
				  nskb->data + doffset,
				  frag_size))
			BUG();
		skb_put(nskb, doffset + frag_size);
		nskb->ip_summed = CHECKSUM_UNNECESSARY;
		nskb->dev = skb->dev;
		nskb->priority = skb->priority;
		nskb->protocol = skb->protocol;
		nskb->dst = dst_clone(skb->dst);
		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		nskb->pkt_type = skb->pkt_type;

		th = (struct tcphdr *)(skb_network_header(nskb) + iph->ihl * 4);
		iph->tot_len = htons(frag_size + doffset);
		iph->id = htons(id);
		iph->check = 0;
		iph->check = ip_fast_csum((unsigned char *) iph, iph->ihl);
		th->seq = htonl(seq);
		if (offset + doffset + frag_size < skb->len)
			th->fin = th->psh = 0;
		netif_rx(nskb);
		offset += frag_size;
		seq += frag_size;
		id++;
	}

	dev_kfree_skb(skb);
}
#endif /* LOOPBACK_TSO */

/*
 * The higher levels take care of making this non-reentrant (it's
 * called with bh's disabled).
 */
static int loopback_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct pcpu_lstats *pcpu_lstats, *lb_stats;

	skb_orphan(skb);

	skb->protocol = eth_type_trans(skb,dev);
#ifndef LOOPBACK_MUST_CHECKSUM
	skb->ip_summed = CHECKSUM_UNNECESSARY;
#endif

#ifdef LOOPBACK_TSO
	if (skb_is_gso(skb)) {
		BUG_ON(skb->protocol != htons(ETH_P_IP));
		BUG_ON(ip_hdr(skb)->protocol != IPPROTO_TCP);

		emulate_large_send_offload(skb);
		return 0;
	}
#endif
	dev->last_rx = jiffies;

	/* it's OK to use __get_cpu_var() because BHs are off */
	pcpu_lstats = netdev_priv(dev);
	lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id());
	lb_stats->bytes += skb->len;
	lb_stats->packets++;

	netif_rx(skb);

	return 0;
}

static struct net_device_stats *get_stats(struct net_device *dev)
{
	const struct pcpu_lstats *pcpu_lstats;
	struct net_device_stats *stats = &dev->stats;
	unsigned long bytes = 0;
	unsigned long packets = 0;
	int i;

	pcpu_lstats = netdev_priv(dev);
	for_each_possible_cpu(i) {
		const struct pcpu_lstats *lb_stats;

		lb_stats = per_cpu_ptr(pcpu_lstats, i);
		bytes   += lb_stats->bytes;
		packets += lb_stats->packets;
	}
	stats->rx_packets = packets;
	stats->tx_packets = packets;
	stats->rx_bytes = bytes;
	stats->tx_bytes = bytes;
	return stats;
}

static u32 always_on(struct net_device *dev)
{
	return 1;
}

static const struct ethtool_ops loopback_ethtool_ops = {
	.get_link		= always_on,
	.set_tso		= ethtool_op_set_tso,
	.get_tx_csum		= always_on,
	.get_sg			= always_on,
	.get_rx_csum		= always_on,
};

static int loopback_dev_init(struct net_device *dev)
{
	struct pcpu_lstats *lstats;

	lstats = alloc_percpu(struct pcpu_lstats);
	if (!lstats)
		return -ENOMEM;

	dev->priv = lstats;
	return 0;
}

static void loopback_dev_free(struct net_device *dev)
{
	struct pcpu_lstats *lstats = netdev_priv(dev);

	free_percpu(lstats);
	free_netdev(dev);
}

/*
 * The loopback device is special. There is only one instance and
 * it is statically allocated. Don't do this for other devices.
 */
static void loopback_setup(struct net_device *dev)
{
	dev->get_stats		= &get_stats;
	dev->mtu		= (16 * 1024) + 20 + 20 + 12;
	dev->hard_start_xmit	= loopback_xmit;
	dev->hard_header	= eth_header;
	dev->hard_header_cache	= eth_header_cache;
	dev->header_cache_update = eth_header_cache_update;
	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
	dev->addr_len		= ETH_ALEN;	/* 6	*/
	dev->tx_queue_len	= 0;
	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
	dev->rebuild_header	= eth_rebuild_header;
	dev->flags		= IFF_LOOPBACK;
	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
#ifdef LOOPBACK_TSO
		| NETIF_F_TSO
#endif
		| NETIF_F_NO_CSUM
		| NETIF_F_HIGHDMA
		| NETIF_F_LLTX
		| NETIF_F_NETNS_LOCAL,
	dev->ethtool_ops	= &loopback_ethtool_ops;
	dev->init = loopback_dev_init;
	dev->destructor = loopback_dev_free;
}

/* Setup and register the loopback device. */
static int loopback_net_init(struct net *net)
{
	struct net_device *dev;
	int err;

	err = -ENOMEM;
	dev = alloc_netdev(0, "lo", loopback_setup);
	if (!dev)
		goto out;

	dev->nd_net = net;
	err = register_netdev(dev);
	if (err)
		goto out_free_netdev;

	err = 0;
	net->loopback_dev = dev;

out:
	if (err)
		panic("loopback: Failed to register netdevice: %d\n", err);
	return err;

out_free_netdev:
	free_netdev(dev);
	goto out;
}

static void loopback_net_exit(struct net *net)
{
	struct net_device *dev = net->loopback_dev;

	unregister_netdev(dev);
}

static struct pernet_operations loopback_net_ops = {
       .init = loopback_net_init,
       .exit = loopback_net_exit,
};

static int __init loopback_init(void)
{
	return register_pernet_device(&loopback_net_ops);
}

fs_initcall(loopback_init);