vport-netdev.c 4.8 KB
Newer Older
1
/*
2
 * Copyright (c) 2007-2012 Nicira, Inc.
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
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#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 <net/llc.h>

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

/* Must be called with rcu_read_lock. */
static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
{
	if (unlikely(!vport)) {
		kfree_skb(skb);
		return;
	}

	/* 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).
	 * (No one comes after us, since we tell handle_bridge() that we took
	 * the packet.) */
	skb = skb_share_check(skb, GFP_ATOMIC);
	if (unlikely(!skb))
		return;

	skb_push(skb, ETH_HLEN);
	ovs_vport_receive(vport, 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;
	struct vport *vport;

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

	vport = ovs_netdev_get_vport(skb->dev);

	netdev_port_receive(vport, skb);

	return RX_HANDLER_CONSUMED;
}

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

	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
				&ovs_netdev_vport_ops, parms);
	if (IS_ERR(vport)) {
		err = PTR_ERR(vport);
		goto error;
	}

	netdev_vport = netdev_vport_priv(vport);

	netdev_vport->dev = dev_get_by_name(&init_net, parms->name);
	if (!netdev_vport->dev) {
		err = -ENODEV;
		goto error_free_vport;
	}

	if (netdev_vport->dev->flags & IFF_LOOPBACK ||
	    netdev_vport->dev->type != ARPHRD_ETHER ||
	    ovs_is_internal_dev(netdev_vport->dev)) {
		err = -EINVAL;
		goto error_put;
	}

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

	dev_set_promiscuity(netdev_vport->dev, 1);
	netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;

	return vport;

error_put:
	dev_put(netdev_vport->dev);
error_free_vport:
	ovs_vport_free(vport);
error:
	return ERR_PTR(err);
}

static void netdev_destroy(struct vport *vport)
{
	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);

	netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
	netdev_rx_handler_unregister(netdev_vport->dev);
	dev_set_promiscuity(netdev_vport->dev, -1);

	synchronize_rcu();

	dev_put(netdev_vport->dev);
	ovs_vport_free(vport);
}

const char *ovs_netdev_get_name(const struct vport *vport)
{
	const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
	return netdev_vport->dev->name;
}

int ovs_netdev_get_ifindex(const struct vport *vport)
{
	const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
	return netdev_vport->dev->ifindex;
}

static unsigned packet_length(const struct sk_buff *skb)
{
	unsigned length = skb->len - ETH_HLEN;

	if (skb->protocol == htons(ETH_P_8021Q))
		length -= VLAN_HLEN;

	return length;
}

static int netdev_send(struct vport *vport, struct sk_buff *skb)
{
	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
	int mtu = netdev_vport->dev->mtu;
	int len;

	if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
		if (net_ratelimit())
			pr_warn("%s: dropped over-mtu packet: %d > %d\n",
				ovs_dp_name(vport->dp), packet_length(skb), mtu);
		goto error;
	}

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

	skb->dev = netdev_vport->dev;
	len = skb->len;
	dev_queue_xmit(skb);

	return len;

error:
	kfree_skb(skb);
	ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
	return 0;
}

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

const struct vport_ops ovs_netdev_vport_ops = {
	.type		= OVS_VPORT_TYPE_NETDEV,
	.create		= netdev_create,
	.destroy	= netdev_destroy,
	.get_name	= ovs_netdev_get_name,
	.get_ifindex	= ovs_netdev_get_ifindex,
	.send		= netdev_send,
};