summaryrefslogtreecommitdiff
path: root/net/openvswitch/vport-netdev.c
blob: 2f61d5bdce1a73f657193dd343a99804a44f9256 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2007-2012 Nicira, Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/if_arp.h>
#include <linux/if_bridge.h>
#include <linux/if_vlan.h>
#include <linux/kernel.h>
#include <linux/llc.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <linux/openvswitch.h>
#include <linux/export.h>

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

#include "datapath.h"
#include "vport.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"

static struct vport_ops ovs_netdev_vport_ops;

/* Must be called with rcu_read_lock. */
static void netdev_port_receive(struct sk_buff *skb)
{
	struct vport *vport;

	vport = ovs_netdev_get_vport(skb->dev);
	if (unlikely(!vport))
		goto error;

	if (unlikely(skb_warn_if_lro(skb)))
		goto error;

	/* Make our own copy of the packet.  Otherwise we will mangle the
	 * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
	 */
	skb = skb_share_check(skb, GFP_ATOMIC);
	if (unlikely(!skb))
		return;

	if (skb->dev->type == ARPHRD_ETHER)
		skb_push_rcsum(skb, ETH_HLEN);

	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
	return;
error:
	kfree_skb(skb);
}

/* Called with rcu_read_lock and bottom-halves disabled. */
static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
{
	struct sk_buff *skb = *pskb;

	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
		return RX_HANDLER_PASS;

	netdev_port_receive(skb);
	return RX_HANDLER_CONSUMED;
}

static struct net_device *get_dpdev(const struct datapath *dp)
{
	struct vport *local;

	local = ovs_vport_ovsl(dp, OVSP_LOCAL);
	return local->dev;
}

struct vport *ovs_netdev_link(struct vport *vport, const char *name)
{
	int err;

	vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name);
	if (!vport->dev) {
		err = -ENODEV;
		goto error_free_vport;
	}
	netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL);
	if (vport->dev->flags & IFF_LOOPBACK ||
	    (vport->dev->type != ARPHRD_ETHER &&
	     vport->dev->type != ARPHRD_NONE) ||
	    ovs_is_internal_dev(vport->dev)) {
		err = -EINVAL;
		goto error_put;
	}

	rtnl_lock();
	err = netdev_master_upper_dev_link(vport->dev,
					   get_dpdev(vport->dp),
					   NULL, NULL, NULL);
	if (err)
		goto error_unlock;

	err = netdev_rx_handler_register(vport->dev, netdev_frame_hook,
					 vport);
	if (err)
		goto error_master_upper_dev_unlink;

	dev_disable_lro(vport->dev);
	dev_set_promiscuity(vport->dev, 1);
	vport->dev->priv_flags |= IFF_OVS_DATAPATH;
	rtnl_unlock();

	return vport;

error_master_upper_dev_unlink:
	netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp));
error_unlock:
	rtnl_unlock();
error_put:
	netdev_put(vport->dev, &vport->dev_tracker);
error_free_vport:
	ovs_vport_free(vport);
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(ovs_netdev_link);

static struct vport *netdev_create(const struct vport_parms *parms)
{
	struct vport *vport;

	vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms);
	if (IS_ERR(vport))
		return vport;

	return ovs_netdev_link(vport, parms->name);
}

static void vport_netdev_free(struct rcu_head *rcu)
{
	struct vport *vport = container_of(rcu, struct vport, rcu);

	netdev_put(vport->dev, &vport->dev_tracker);
	ovs_vport_free(vport);
}

void ovs_netdev_detach_dev(struct vport *vport)
{
	ASSERT_RTNL();
	vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
	netdev_rx_handler_unregister(vport->dev);
	netdev_upper_dev_unlink(vport->dev,
				netdev_master_upper_dev_get(vport->dev));
	dev_set_promiscuity(vport->dev, -1);
}

static void netdev_destroy(struct vport *vport)
{
	rtnl_lock();
	if (netif_is_ovs_port(vport->dev))
		ovs_netdev_detach_dev(vport);
	rtnl_unlock();

	call_rcu(&vport->rcu, vport_netdev_free);
}

void ovs_netdev_tunnel_destroy(struct vport *vport)
{
	rtnl_lock();
	if (netif_is_ovs_port(vport->dev))
		ovs_netdev_detach_dev(vport);

	/* We can be invoked by both explicit vport deletion and
	 * underlying netdev deregistration; delete the link only
	 * if it's not already shutting down.
	 */
	if (vport->dev->reg_state == NETREG_REGISTERED)
		rtnl_delete_link(vport->dev);
	netdev_put(vport->dev, &vport->dev_tracker);
	vport->dev = NULL;
	rtnl_unlock();

	call_rcu(&vport->rcu, vport_netdev_free);
}
EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy);

/* Returns null if this device is not attached to a datapath. */
struct vport *ovs_netdev_get_vport(struct net_device *dev)
{
	if (likely(netif_is_ovs_port(dev)))
		return (struct vport *)
			rcu_dereference_rtnl(dev->rx_handler_data);
	else
		return NULL;
}

static struct vport_ops ovs_netdev_vport_ops = {
	.type		= OVS_VPORT_TYPE_NETDEV,
	.create		= netdev_create,
	.destroy	= netdev_destroy,
	.send		= dev_queue_xmit,
};

int __init ovs_netdev_init(void)
{
	return ovs_vport_ops_register(&ovs_netdev_vport_ops);
}

void ovs_netdev_exit(void)
{
	ovs_vport_ops_unregister(&ovs_netdev_vport_ops);
}