OpenCloudOS-Kernel/net/ethernet/eth.c

428 lines
11 KiB
C
Raw Normal View History

/*
* 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.
*
* Ethernet-type device handling.
*
* Version: @(#)eth.c 1.0.7 05/25/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Florian La Roche, <rzsfl@rz.uni-sb.de>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
*
* Fixes:
* Mr Linux : Arp problems
* Alan Cox : Generic queue tidyup (very tiny here)
* Alan Cox : eth_header ntohs should be htons
* Alan Cox : eth_rebuild_header missing an htons and
* minor other things.
* Tegge : Arp bug fixes.
* Florian : Removed many unnecessary functions, code cleanup
* and changes for new arp and skbuff.
* Alan Cox : Redid header building to reflect new format.
* Alan Cox : ARP only when compiled with CONFIG_INET
* Greg Page : 802.2 and SNAP stuff.
* Alan Cox : MAC layer pointers/new format.
* Paul Gortmaker : eth_copy_and_sum shouldn't csum padding.
* Alan Cox : Protect against forwarding explosions with
* older network drivers and IFF_ALLMULTI.
* Christer Weinigel : Better rebuild header message.
* Andrew Morton : 26Feb01: kill ether_setup() - use netdev_boot_setup().
*
* 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/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <net/dst.h>
#include <net/arp.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
#include <asm/uaccess.h>
__setup("ether=", netdev_boot_setup);
/**
* eth_header - create the Ethernet header
* @skb: buffer to alter
* @dev: source device
* @type: Ethernet type field
* @daddr: destination address (NULL leave destination address)
* @saddr: source address (NULL use device source address)
* @len: packet length (<= skb->len)
*
*
* Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length
* in here instead.
*/
int eth_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr, unsigned int len)
{
struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN);
if (type != ETH_P_802_3 && type != ETH_P_802_2)
eth->h_proto = htons(type);
else
eth->h_proto = htons(len);
/*
* Set the source hardware address.
*/
if (!saddr)
saddr = dev->dev_addr;
memcpy(eth->h_source, saddr, ETH_ALEN);
if (daddr) {
memcpy(eth->h_dest, daddr, ETH_ALEN);
[NET] ethernet: Fix first packet goes out with MAC 00:00:00:00:00:00 When you turn off ARP on a netdevice then the first packet always goes out with a dstMAC of all zeroes. This is because the first packet is used to resolve ARP entries. Even though the ARP entry may be resolved (I tried by setting a static ARP entry for a host i was pinging from), it gets overwritten by virtue of having the netdevice disabling ARP. Subsequent packets go out fine with correct dstMAC address (which may be why people have ignored reporting this issue). To cut the story short: the culprit code is in net/ethernet/eth.c::eth_header() ---- /* * Anyway, the loopback-device should never use this function... */ if (dev->flags & (IFF_LOOPBACK|IFF_NOARP)) { memset(eth->h_dest, 0, dev->addr_len); return ETH_HLEN; } if(daddr) { memcpy(eth->h_dest,daddr,dev->addr_len); return ETH_HLEN; } ---- Note how the h_dest is being reset when device has IFF_NOARP. As a note: All devices including loopback pass a daddr. loopback in fact passes a 0 all the time ;-> This means i can delete the check totaly or i can remove the IFF_NOARP Alexey says: -------------------- I think, it was me who did this crap. It was so long ago I do not remember why it was made. I remember some troubles with dummy device. It tried to resolve addresses, apparently, without success and generated errors instead of blackholing. I think the problem was eventually solved at neighbour level. After some thinking I suspect the deletion of this chunk could change behaviour of some parts which do not use neighbour cache f.e. packet socket. I think safer approach would be to move this chunk after if (daddr). And the possibility to remove this completely could be analyzed later. -------------------- Patch updated with Alexey's safer suggestions. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Acked-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-24 08:18:01 +08:00
return ETH_HLEN;
}
/*
* Anyway, the loopback-device should never use this function...
*/
if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) {
memset(eth->h_dest, 0, ETH_ALEN);
return ETH_HLEN;
}
return -ETH_HLEN;
}
EXPORT_SYMBOL(eth_header);
/**
* eth_rebuild_header- rebuild the Ethernet MAC header.
* @skb: socket buffer to update
*
* This is called after an ARP or IPV6 ndisc it's resolution on this
* sk_buff. We now let protocol (ARP) fill in the other fields.
*
* This routine CANNOT use cached dst->neigh!
* Really, it is used only when dst->neigh is wrong.
*/
int eth_rebuild_header(struct sk_buff *skb)
{
struct ethhdr *eth = (struct ethhdr *)skb->data;
struct net_device *dev = skb->dev;
switch (eth->h_proto) {
#ifdef CONFIG_INET
case htons(ETH_P_IP):
return arp_find(eth->h_dest, skb);
#endif
default:
printk(KERN_DEBUG
"%s: unable to resolve type %X addresses.\n",
dev->name, ntohs(eth->h_proto));
memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
break;
}
return 0;
}
EXPORT_SYMBOL(eth_rebuild_header);
/**
* eth_type_trans - determine the packet's protocol ID.
* @skb: received socket data
* @dev: receiving network device
*
* The rule here is that we
* assume 802.3 if the type field is short enough to be a length.
* This is normal practice and works for any 'now in use' protocol.
*/
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
{
struct ethhdr *eth;
skb->dev = dev;
skb_reset_mac_header(skb);
skb_pull_inline(skb, ETH_HLEN);
eth = eth_hdr(skb);
if (unlikely(is_multicast_ether_addr(eth->h_dest))) {
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
}
/*
* This ALLMULTI check should be redundant by 1.4
* so don't forget to remove it.
*
* Seems, you forgot to remove it. All silly devices
* seems to set IFF_PROMISC.
*/
else if (1 /*dev->flags&IFF_PROMISC */ ) {
if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
dev->dev_addr)))
skb->pkt_type = PACKET_OTHERHOST;
}
/*
* Some variants of DSA tagging don't have an ethertype field
* at all, so we check here whether one of those tagging
* variants has been configured on the receiving interface,
* and if so, set skb->protocol without looking at the packet.
*/
if (netdev_uses_dsa_tags(dev))
return htons(ETH_P_DSA);
if (netdev_uses_trailer_tags(dev))
return htons(ETH_P_TRAILER);
if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN)
return eth->h_proto;
/*
* This is a magic hack to spot IPX packets. Older Novell breaks
* the protocol design and runs IPX over 802.3 without an 802.2 LLC
* layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
* won't work for fault tolerant netware but does for the rest.
*/
if (skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF)
return htons(ETH_P_802_3);
/*
* Real 802.2 LLC
*/
return htons(ETH_P_802_2);
}
EXPORT_SYMBOL(eth_type_trans);
/**
* eth_header_parse - extract hardware address from packet
* @skb: packet to extract header from
* @haddr: destination buffer
*/
int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
const struct ethhdr *eth = eth_hdr(skb);
memcpy(haddr, eth->h_source, ETH_ALEN);
return ETH_ALEN;
}
EXPORT_SYMBOL(eth_header_parse);
/**
* eth_header_cache - fill cache entry from neighbour
* @neigh: source neighbour
* @hh: destination cache entry
* @type: Ethernet type field
*
* Create an Ethernet header template from the neighbour.
*/
int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type)
{
struct ethhdr *eth;
const struct net_device *dev = neigh->dev;
eth = (struct ethhdr *)
(((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth))));
if (type == htons(ETH_P_802_3))
return -1;
eth->h_proto = type;
memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
memcpy(eth->h_dest, neigh->ha, ETH_ALEN);
hh->hh_len = ETH_HLEN;
return 0;
}
EXPORT_SYMBOL(eth_header_cache);
/**
* eth_header_cache_update - update cache entry
* @hh: destination cache entry
* @dev: network device
* @haddr: new hardware address
*
* Called by Address Resolution module to notify changes in address.
*/
void eth_header_cache_update(struct hh_cache *hh,
const struct net_device *dev,
const unsigned char *haddr)
{
memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)),
haddr, ETH_ALEN);
}
EXPORT_SYMBOL(eth_header_cache_update);
/**
* eth_prepare_mac_addr_change - prepare for mac change
* @dev: network device
* @p: socket address
*/
int eth_prepare_mac_addr_change(struct net_device *dev, void *p)
{
struct sockaddr *addr = p;
if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
return -EBUSY;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
return 0;
}
EXPORT_SYMBOL(eth_prepare_mac_addr_change);
/**
* eth_commit_mac_addr_change - commit mac change
* @dev: network device
* @p: socket address
*/
void eth_commit_mac_addr_change(struct net_device *dev, void *p)
{
struct sockaddr *addr = p;
memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
}
EXPORT_SYMBOL(eth_commit_mac_addr_change);
/**
* eth_mac_addr - set new Ethernet hardware address
* @dev: network device
* @p: socket address
*
* Change hardware address of device.
*
* This doesn't change hardware matching, so needs to be overridden
* for most real devices.
*/
int eth_mac_addr(struct net_device *dev, void *p)
{
int ret;
ret = eth_prepare_mac_addr_change(dev, p);
if (ret < 0)
return ret;
eth_commit_mac_addr_change(dev, p);
return 0;
}
EXPORT_SYMBOL(eth_mac_addr);
/**
* eth_change_mtu - set new MTU size
* @dev: network device
* @new_mtu: new Maximum Transfer Unit
*
* Allow changing MTU size. Needs to be overridden for devices
* supporting jumbo frames.
*/
int eth_change_mtu(struct net_device *dev, int new_mtu)
{
if (new_mtu < 68 || new_mtu > ETH_DATA_LEN)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
EXPORT_SYMBOL(eth_change_mtu);
int eth_validate_addr(struct net_device *dev)
{
if (!is_valid_ether_addr(dev->dev_addr))
return -EADDRNOTAVAIL;
return 0;
}
EXPORT_SYMBOL(eth_validate_addr);
const struct header_ops eth_header_ops ____cacheline_aligned = {
.create = eth_header,
.parse = eth_header_parse,
.rebuild = eth_rebuild_header,
.cache = eth_header_cache,
.cache_update = eth_header_cache_update,
};
/**
* ether_setup - setup Ethernet network device
* @dev: network device
*
* Fill in the fields of the device structure with Ethernet-generic values.
*/
void ether_setup(struct net_device *dev)
{
dev->header_ops = &eth_header_ops;
dev->type = ARPHRD_ETHER;
dev->hard_header_len = ETH_HLEN;
dev->mtu = ETH_DATA_LEN;
dev->addr_len = ETH_ALEN;
dev->tx_queue_len = 1000; /* Ethernet wants good queues */
dev->flags = IFF_BROADCAST|IFF_MULTICAST;
dev->priv_flags |= IFF_TX_SKB_SHARING;
memset(dev->broadcast, 0xFF, ETH_ALEN);
}
EXPORT_SYMBOL(ether_setup);
/**
* alloc_etherdev_mqs - Allocates and sets up an Ethernet device
* @sizeof_priv: Size of additional driver-private structure to be allocated
* for this Ethernet device
* @txqs: The number of TX queues this device has.
* @rxqs: The number of RX queues this device has.
*
* Fill in the fields of the device structure with Ethernet-generic
* values. Basically does everything except registering the device.
*
* Constructs a new net device, complete with a private data area of
* size (sizeof_priv). A 32-byte (not bit) alignment is enforced for
* this private data area.
*/
struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
unsigned int rxqs)
{
return alloc_netdev_mqs(sizeof_priv, "eth%d", ether_setup, txqs, rxqs);
}
EXPORT_SYMBOL(alloc_etherdev_mqs);
static size_t _format_mac_addr(char *buf, int buflen,
const unsigned char *addr, int len)
{
int i;
char *cp = buf;
for (i = 0; i < len; i++) {
cp += scnprintf(cp, buflen - (cp - buf), "%02x", addr[i]);
if (i == len - 1)
break;
cp += scnprintf(cp, buflen - (cp - buf), ":");
}
return cp - buf;
}
ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
{
size_t l;
l = _format_mac_addr(buf, PAGE_SIZE, addr, len);
l += scnprintf(buf + l, PAGE_SIZE - l, "\n");
return (ssize_t)l;
}
EXPORT_SYMBOL(sysfs_format_mac);