summaryrefslogtreecommitdiff
path: root/include/net/udp_tunnel.h
blob: ee34619e4cfad16923148917c2eae242956de2ae (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_UDP_TUNNEL_H
#define __NET_UDP_TUNNEL_H

#include <net/ip_tunnels.h>
#include <net/udp.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ipv6_stubs.h>
#endif

struct udp_port_cfg {
	u8			family;

	/* Used only for kernel-created sockets */
	union {
		struct in_addr		local_ip;
#if IS_ENABLED(CONFIG_IPV6)
		struct in6_addr		local_ip6;
#endif
	};

	union {
		struct in_addr		peer_ip;
#if IS_ENABLED(CONFIG_IPV6)
		struct in6_addr		peer_ip6;
#endif
	};

	__be16			local_udp_port;
	__be16			peer_udp_port;
	int			bind_ifindex;
	unsigned int		use_udp_checksums:1,
				use_udp6_tx_checksums:1,
				use_udp6_rx_checksums:1,
				ipv6_v6only:1;
};

int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
		     struct socket **sockp);

#if IS_ENABLED(CONFIG_IPV6)
int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
		     struct socket **sockp);
#else
static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
				   struct socket **sockp)
{
	return 0;
}
#endif

static inline int udp_sock_create(struct net *net,
				  struct udp_port_cfg *cfg,
				  struct socket **sockp)
{
	if (cfg->family == AF_INET)
		return udp_sock_create4(net, cfg, sockp);

	if (cfg->family == AF_INET6)
		return udp_sock_create6(net, cfg, sockp);

	return -EPFNOSUPPORT;
}

typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
					     struct sk_buff *skb);
typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
						    struct list_head *head,
						    struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
					 int nhoff);

struct udp_tunnel_sock_cfg {
	void *sk_user_data;     /* user data used by encap_rcv call back */
	/* Used for setting up udp_sock fields, see udp.h for details */
	__u8  encap_type;
	udp_tunnel_encap_rcv_t encap_rcv;
	udp_tunnel_encap_err_lookup_t encap_err_lookup;
	udp_tunnel_encap_destroy_t encap_destroy;
	udp_tunnel_gro_receive_t gro_receive;
	udp_tunnel_gro_complete_t gro_complete;
};

/* Setup the given (UDP) sock to receive UDP encapsulated packets */
void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
			   struct udp_tunnel_sock_cfg *sock_cfg);

/* -- List of parsable UDP tunnel types --
 *
 * Adding to this list will result in serious debate.  The main issue is
 * that this list is essentially a list of workarounds for either poorly
 * designed tunnels, or poorly designed device offloads.
 *
 * The parsing supported via these types should really be used for Rx
 * traffic only as the network stack will have already inserted offsets for
 * the location of the headers in the skb.  In addition any ports that are
 * pushed should be kept within the namespace without leaking to other
 * devices such as VFs or other ports on the same device.
 *
 * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the
 * need to use this for Rx checksum offload.  It should not be necessary to
 * call this function to perform Tx offloads on outgoing traffic.
 */
enum udp_parsable_tunnel_type {
	UDP_TUNNEL_TYPE_VXLAN	  = BIT(0), /* RFC 7348 */
	UDP_TUNNEL_TYPE_GENEVE	  = BIT(1), /* draft-ietf-nvo3-geneve */
	UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */
};

struct udp_tunnel_info {
	unsigned short type;
	sa_family_t sa_family;
	__be16 port;
	u8 hw_priv;
};

/* Notify network devices of offloadable types */
void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
			     unsigned short type);
void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock,
			     unsigned short type);
void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);

static inline void udp_tunnel_get_rx_info(struct net_device *dev)
{
	ASSERT_RTNL();
	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
}

static inline void udp_tunnel_drop_rx_info(struct net_device *dev)
{
	ASSERT_RTNL();
	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev);
}

/* Transmit the skb using UDP encapsulation. */
void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
			 __be16 df, __be16 src_port, __be16 dst_port,
			 bool xnet, bool nocheck);

int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
			 struct sk_buff *skb,
			 struct net_device *dev, struct in6_addr *saddr,
			 struct in6_addr *daddr,
			 __u8 prio, __u8 ttl, __be32 label,
			 __be16 src_port, __be16 dst_port, bool nocheck);

void udp_tunnel_sock_release(struct socket *sock);

struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
				    __be16 flags, __be64 tunnel_id,
				    int md_size);

#ifdef CONFIG_INET
static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
{
	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;

	return iptunnel_handle_offloads(skb, type);
}
#endif

static inline void udp_tunnel_encap_enable(struct socket *sock)
{
	struct udp_sock *up = udp_sk(sock->sk);

	if (up->encap_enabled)
		return;

	up->encap_enabled = 1;
#if IS_ENABLED(CONFIG_IPV6)
	if (sock->sk->sk_family == PF_INET6)
		ipv6_stub->udpv6_encap_enable();
	else
#endif
		udp_encap_enable();
}

#define UDP_TUNNEL_NIC_MAX_TABLES	4

enum udp_tunnel_nic_info_flags {
	/* Device callbacks may sleep */
	UDP_TUNNEL_NIC_INFO_MAY_SLEEP	= BIT(0),
	/* Device only supports offloads when it's open, all ports
	 * will be removed before close and re-added after open.
	 */
	UDP_TUNNEL_NIC_INFO_OPEN_ONLY	= BIT(1),
	/* Device supports only IPv4 tunnels */
	UDP_TUNNEL_NIC_INFO_IPV4_ONLY	= BIT(2),
};

/**
 * struct udp_tunnel_nic_info - driver UDP tunnel offload information
 * @set_port:	callback for adding a new port
 * @unset_port:	callback for removing a port
 * @sync_table:	callback for syncing the entire port table at once
 * @flags:	device flags from enum udp_tunnel_nic_info_flags
 * @tables:	UDP port tables this device has
 * @tables.n_entries:		number of entries in this table
 * @tables.tunnel_types:	types of tunnels this table accepts
 *
 * Drivers are expected to provide either @set_port and @unset_port callbacks
 * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
 *
 * Known limitations:
 *  - UDP tunnel port notifications are fundamentally best-effort -
 *    it is likely the driver will both see skbs which use a UDP tunnel port,
 *    while not being a tunneled skb, and tunnel skbs from other ports -
 *    drivers should only use these ports for non-critical RX-side offloads,
 *    e.g. the checksum offload;
 *  - none of the devices care about the socket family at present, so we don't
 *    track it. Please extend this code if you care.
 */
struct udp_tunnel_nic_info {
	/* one-by-one */
	int (*set_port)(struct net_device *dev,
			unsigned int table, unsigned int entry,
			struct udp_tunnel_info *ti);
	int (*unset_port)(struct net_device *dev,
			  unsigned int table, unsigned int entry,
			  struct udp_tunnel_info *ti);

	/* all at once */
	int (*sync_table)(struct net_device *dev, unsigned int table);

	unsigned int flags;

	struct udp_tunnel_nic_table_info {
		unsigned int n_entries;
		unsigned int tunnel_types;
	} tables[UDP_TUNNEL_NIC_MAX_TABLES];
};

/* UDP tunnel module dependencies
 *
 * Tunnel drivers are expected to have a hard dependency on the udp_tunnel
 * module. NIC drivers are not, they just attach their
 * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come.
 * Loading a tunnel driver will cause the udp_tunnel module to be loaded
 * and only then will all the required state structures be allocated.
 * Since we want a weak dependency from the drivers and the core to udp_tunnel
 * we call things through the following stubs.
 */
struct udp_tunnel_nic_ops {
	void (*get_port)(struct net_device *dev, unsigned int table,
			 unsigned int idx, struct udp_tunnel_info *ti);
	void (*set_port_priv)(struct net_device *dev, unsigned int table,
			      unsigned int idx, u8 priv);
	void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti);
	void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti);
	void (*reset_ntf)(struct net_device *dev);
};

#ifdef CONFIG_INET
extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops;
#else
#define udp_tunnel_nic_ops	((struct udp_tunnel_nic_ops *)NULL)
#endif

static inline void
udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table,
			unsigned int idx, struct udp_tunnel_info *ti)
{
	/* This helper is used from .sync_table, we indicate empty entries
	 * by zero'ed @ti. Drivers which need to know the details of a port
	 * when it gets deleted should use the .set_port / .unset_port
	 * callbacks.
	 * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings.
	 */
	memset(ti, 0, sizeof(*ti));

	if (udp_tunnel_nic_ops)
		udp_tunnel_nic_ops->get_port(dev, table, idx, ti);
}

static inline void
udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table,
			     unsigned int idx, u8 priv)
{
	if (udp_tunnel_nic_ops)
		udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv);
}

static inline void
udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
	if (udp_tunnel_nic_ops)
		udp_tunnel_nic_ops->add_port(dev, ti);
}

static inline void
udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti)
{
	if (udp_tunnel_nic_ops)
		udp_tunnel_nic_ops->del_port(dev, ti);
}

/**
 * udp_tunnel_nic_reset_ntf() - device-originating reset notification
 * @dev: network interface device structure
 *
 * Called by the driver to inform the core that the entire UDP tunnel port
 * state has been lost, usually due to device reset. Core will assume device
 * forgot all the ports and issue .set_port and .sync_table callbacks as
 * necessary.
 *
 * This function must be called with rtnl lock held, and will issue all
 * the callbacks before returning.
 */
static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev)
{
	if (udp_tunnel_nic_ops)
		udp_tunnel_nic_ops->reset_ntf(dev);
}
#endif