*
* The Internet Protocol (IP) module.
*
- * Version: $Id: ip_input.c,v 1.55 2002/01/12 07:39:45 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
* Stefan Becker, <stefanb@yello.ping.de>
* Jorge Cwik, <jorge@laser.satlink.net>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
- *
+ *
*
* Fixes:
* Alan Cox : Commented a couple of minor bits of surplus code
* Jos Vos : Do accounting *before* call_in_firewall
* Willy Konynenberg : Transparent proxying support
*
- *
+ *
*
* To Fix:
* IP fragmentation wants rewriting cleanly. The RFC815 algorithm is much more efficient
* and could be made very efficient with the addition of some virtual memory hacks to permit
* the allocation of a buffer that can then be 'grown' by twiddling page tables.
- * Output fragmentation wants updating along with the buffer management to use a single
+ * Output fragmentation wants updating along with the buffer management to use a single
* interleaved copy algorithm so that fragmenting has a one copy overhead. Actual packet
* output should probably do its own fragmentation at the UDP/RAW layer. TCP shouldn't cause
* fragmentation anyway.
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
-#include <linux/config.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
+#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
* SNMP management statistics
*/
-DEFINE_SNMP_STAT(struct ipstats_mib, ip_statistics);
+DEFINE_SNMP_STAT(struct ipstats_mib, ip_statistics) __read_mostly;
/*
* Process Router Attention IP option
- */
+ */
int ip_call_ra_chain(struct sk_buff *skb)
{
struct ip_ra_chain *ra;
- u8 protocol = skb->nh.iph->protocol;
+ u8 protocol = ip_hdr(skb)->protocol;
struct sock *last = NULL;
+ struct net_device *dev = skb->dev;
read_lock(&ip_ra_lock);
for (ra = ip_ra_chain; ra; ra = ra->next) {
*/
if (sk && inet_sk(sk)->num == protocol &&
(!sk->sk_bound_dev_if ||
- sk->sk_bound_dev_if == skb->dev->ifindex)) {
- if (skb->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) {
- skb = ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN);
- if (skb == NULL) {
+ sk->sk_bound_dev_if == dev->ifindex) &&
+ sock_net(sk) == dev_net(dev)) {
+ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
+ if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) {
read_unlock(&ip_ra_lock);
return 1;
}
raw_rcv(last, skb2);
}
last = sk;
- nf_reset(skb);
}
}
return 0;
}
-static inline int ip_local_deliver_finish(struct sk_buff *skb)
+static int ip_local_deliver_finish(struct sk_buff *skb)
{
- int ihl = skb->nh.iph->ihl*4;
-
- __skb_pull(skb, ihl);
+ struct net *net = dev_net(skb->dev);
- /* Free reference early: we don't need it any more, and it may
- hold ip_conntrack module loaded indefinitely. */
- nf_reset(skb);
+ __skb_pull(skb, ip_hdrlen(skb));
- /* Point into the IP datagram, just past the header. */
- skb->h.raw = skb->data;
+ /* Point into the IP datagram, just past the header. */
+ skb_reset_transport_header(skb);
rcu_read_lock();
{
- /* Note: See raw.c and net/raw.h, RAWV4_HTABLE_SIZE==MAX_INET_PROTOS */
- int protocol = skb->nh.iph->protocol;
- int hash;
- struct sock *raw_sk;
+ int protocol = ip_hdr(skb)->protocol;
+ int hash, raw;
struct net_protocol *ipprot;
resubmit:
- hash = protocol & (MAX_INET_PROTOS - 1);
- raw_sk = sk_head(&raw_v4_htable[hash]);
+ raw = raw_local_deliver(skb, protocol);
- /* If there maybe a raw socket we must check - if not we
- * don't care less
- */
- if (raw_sk && !raw_v4_input(skb, skb->nh.iph, hash))
- raw_sk = NULL;
-
- if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
+ hash = protocol & (MAX_INET_PROTOS - 1);
+ ipprot = rcu_dereference(inet_protos[hash]);
+ if (ipprot != NULL && (net == &init_net || ipprot->netns_ok)) {
int ret;
- if (!ipprot->no_policy &&
- !xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- kfree_skb(skb);
- goto out;
+ if (!ipprot->no_policy) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+ kfree_skb(skb);
+ goto out;
+ }
+ nf_reset(skb);
}
ret = ipprot->handler(skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
- IP_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
} else {
- if (!raw_sk) {
+ if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- IP_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
} else
- IP_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
/*
* Deliver IP Packets to the higher protocol layers.
- */
+ */
int ip_local_deliver(struct sk_buff *skb)
{
/*
* Reassemble IP fragments.
*/
- if (skb->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) {
- skb = ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER);
- if (!skb)
+ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
+ if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER))
return 0;
}
- return NF_HOOK(PF_INET, NF_IP_LOCAL_IN, skb, skb->dev, NULL,
+ return NF_HOOK(PF_INET, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
-static inline int ip_rcv_finish(struct sk_buff *skb)
+static inline int ip_rcv_options(struct sk_buff *skb)
{
+ struct ip_options *opt;
+ struct iphdr *iph;
struct net_device *dev = skb->dev;
- struct iphdr *iph = skb->nh.iph;
- int err;
+
+ /* It looks as overkill, because not all
+ IP options require packet mangling.
+ But it is the easiest for now, especially taking
+ into account that combination of IP options
+ and running sniffer is extremely rare condition.
+ --ANK (980813)
+ */
+ if (skb_cow(skb, skb_headroom(skb))) {
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
+ goto drop;
+ }
+
+ iph = ip_hdr(skb);
+ opt = &(IPCB(skb)->opt);
+ opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
+
+ if (ip_options_compile(dev_net(dev), opt, skb)) {
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
+ goto drop;
+ }
+
+ if (unlikely(opt->srr)) {
+ struct in_device *in_dev = in_dev_get(dev);
+ if (in_dev) {
+ if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
+ if (IN_DEV_LOG_MARTIANS(in_dev) &&
+ net_ratelimit())
+ printk(KERN_INFO "source route option "
+ NIPQUAD_FMT " -> " NIPQUAD_FMT "\n",
+ NIPQUAD(iph->saddr),
+ NIPQUAD(iph->daddr));
+ in_dev_put(in_dev);
+ goto drop;
+ }
+
+ in_dev_put(in_dev);
+ }
+
+ if (ip_options_rcv_srr(skb))
+ goto drop;
+ }
+
+ return 0;
+drop:
+ return -1;
+}
+
+static int ip_rcv_finish(struct sk_buff *skb)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct rtable *rt;
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
- */
+ */
if (skb->dst == NULL) {
- if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
+ int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
+ skb->dev);
+ if (unlikely(err)) {
if (err == -EHOSTUNREACH)
- IP_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
- goto drop;
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INADDRERRORS);
+ else if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INNOROUTES);
+ goto drop;
}
}
#ifdef CONFIG_NET_CLS_ROUTE
- if (skb->dst->tclassid) {
- struct ip_rt_acct *st = ip_rt_acct + 256*smp_processor_id();
+ if (unlikely(skb->dst->tclassid)) {
+ struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id());
u32 idx = skb->dst->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes+=skb->len;
}
#endif
- if (iph->ihl > 5) {
- struct ip_options *opt;
+ if (iph->ihl > 5 && ip_rcv_options(skb))
+ goto drop;
- /* It looks as overkill, because not all
- IP options require packet mangling.
- But it is the easiest for now, especially taking
- into account that combination of IP options
- and running sniffer is extremely rare condition.
- --ANK (980813)
- */
-
- if (skb_cow(skb, skb_headroom(skb))) {
- IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
- goto drop;
- }
- iph = skb->nh.iph;
-
- if (ip_options_compile(NULL, skb))
- goto inhdr_error;
-
- opt = &(IPCB(skb)->opt);
- if (opt->srr) {
- struct in_device *in_dev = in_dev_get(dev);
- if (in_dev) {
- if (!IN_DEV_SOURCE_ROUTE(in_dev)) {
- if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
- printk(KERN_INFO "source route option %u.%u.%u.%u -> %u.%u.%u.%u\n",
- NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));
- in_dev_put(in_dev);
- goto drop;
- }
- in_dev_put(in_dev);
- }
- if (ip_options_rcv_srr(skb))
- goto drop;
- }
- }
+ rt = skb->rtable;
+ if (rt->rt_type == RTN_MULTICAST)
+ IP_INC_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCASTPKTS);
+ else if (rt->rt_type == RTN_BROADCAST)
+ IP_INC_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INBCASTPKTS);
return dst_input(skb);
-inhdr_error:
- IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
drop:
- kfree_skb(skb);
- return NET_RX_DROP;
+ kfree_skb(skb);
+ return NET_RX_DROP;
}
/*
* Main IP Receive routine.
- */
+ */
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct iphdr *iph;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
- IP_INC_STATS_BH(IPSTATS_MIB_INRECEIVES);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
- IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error;
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
/*
- * RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails the checksum.
+ * RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum.
*
* Is the datagram acceptable?
*
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
- if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
+ if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error;
len = ntohs(iph->tot_len);
- if (skb->len < len || len < (iph->ihl*4))
+ if (skb->len < len) {
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS);
+ goto drop;
+ } else if (len < (iph->ihl*4))
goto inhdr_error;
/* Our transport medium may have padded the buffer out. Now we know it
* Note this now means skb->len holds ntohs(iph->tot_len).
*/
if (pskb_trim_rcsum(skb, len)) {
- IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS);
goto drop;
}
- return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
+ /* Remove any debris in the socket control block */
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+
+ return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish);
inhdr_error:
- IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS);
drop:
- kfree_skb(skb);
+ kfree_skb(skb);
out:
- return NET_RX_DROP;
+ return NET_RX_DROP;
}
-EXPORT_SYMBOL(ip_rcv);
EXPORT_SYMBOL(ip_statistics);
Code Review / linux-2.6.git / blobdiff