kevin/linux
1
Fork 0
Code
3b004569d8
linux/include/net/route.h
David S. Miller 6431cbc25f inet: Create a mechanism for upward inetpeer propagation into routes. 
If we didn't have a routing cache, we would not be able to properly
propagate certain kinds of dynamic path attributes, for example
PMTU information and redirects.

The reason is that if we didn't have a routing cache, then there would
be no way to lookup all of the active cached routes hanging off of
sockets, tunnels, IPSEC bundles, etc.

Consider the case where we created a cached route, but no inetpeer
entry existed and also we were not asked to pre-COW the route metrics
and therefore did not force the creation a new inetpeer entry.

If we later get a PMTU message, or a redirect, and store this
information in a new inetpeer entry, there is no way to teach that
cached route about the newly existing inetpeer entry.

The facilities implemented here handle this problem.

First we create a generation ID.  When we create a cached route of any
kind, we remember the generation ID at the time of attachment.  Any
time we force-create an inetpeer entry in response to new path
information, we bump that generation ID.

The dst_ops->check() callback is where the knowledge of this event
is propagated.  If the global generation ID does not equal the one
stored in the cached route, and the cached route has not attached
to an inetpeer yet, we look it up and attach if one is found.  Now
that we've updated the cached route's information, we update the
route's generation ID too.

This clears the way for implementing PMTU and redirects directly in
the inetpeer cache.  There is absolutely no need to consult cached
route information in order to maintain this information.

At this point nothing bumps the inetpeer genids, that comes in the
later changes which handle PMTUs and redirects using inetpeers.

Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-10 13:33:41 -08:00

253 lines
6.8 KiB
C
Raw Blame 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.
*
* Definitions for the IP router.
*
* Version: @(#)route.h 1.0.4 05/27/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Fixes:
* Alan Cox : Reformatted. Added ip_rt_local()
* Alan Cox : Support for TCP parameters.
* Alexey Kuznetsov: Major changes for new routing code.
* Mike McLagan : Routing by source
* Robert Olsson : Added rt_cache statistics
*
* 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.
*/
#ifndef _ROUTE_H
#define _ROUTE_H
#include <net/dst.h>
#include <net/inetpeer.h>
#include <net/flow.h>
#include <net/inet_sock.h>
#include <linux/in_route.h>
#include <linux/rtnetlink.h>
#include <linux/route.h>
#include <linux/ip.h>
#include <linux/cache.h>
#include <linux/security.h>
#ifndef __KERNEL__
#warning This file is not supposed to be used outside of kernel.
#endif
#define RTO_ONLINK 0x01
#define RTO_CONN 0
/* RTO_CONN is not used (being alias for 0), but preserved not to break
* some modules referring to it. */
#define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
struct fib_nh;
struct inet_peer;
struct fib_info;
struct rtable {
struct dst_entry dst;
/* Cache lookup keys */
struct flowi fl;
int rt_genid;
unsigned rt_flags;
__u16 rt_type;
__be32 rt_dst; /* Path destination */
__be32 rt_src; /* Path source */
int rt_iif;
/* Info on neighbour */
__be32 rt_gateway;
/* Miscellaneous cached information */
__be32 rt_spec_dst; /* RFC1122 specific destination */
u32 rt_peer_genid;
struct inet_peer *peer; /* long-living peer info */
struct fib_info *fi; /* for client ref to shared metrics */
};
static inline bool rt_is_input_route(struct rtable *rt)
{
return rt->fl.iif != 0;
}
static inline bool rt_is_output_route(struct rtable *rt)
{
return rt->fl.iif == 0;
}
struct ip_rt_acct {
__u32 o_bytes;
__u32 o_packets;
__u32 i_bytes;
__u32 i_packets;
};
struct rt_cache_stat {
unsigned int in_hit;
unsigned int in_slow_tot;
unsigned int in_slow_mc;
unsigned int in_no_route;
unsigned int in_brd;
unsigned int in_martian_dst;
unsigned int in_martian_src;
unsigned int out_hit;
unsigned int out_slow_tot;
unsigned int out_slow_mc;
unsigned int gc_total;
unsigned int gc_ignored;
unsigned int gc_goal_miss;
unsigned int gc_dst_overflow;
unsigned int in_hlist_search;
unsigned int out_hlist_search;
};
extern struct ip_rt_acct __percpu *ip_rt_acct;
struct in_device;
extern int ip_rt_init(void);
extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
__be32 src, struct net_device *dev);
extern void rt_cache_flush(struct net *net, int how);
extern void rt_cache_flush_batch(struct net *net);
extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin, bool noref);
static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin)
{
return ip_route_input_common(skb, dst, src, tos, devin, false);
}
static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin)
{
return ip_route_input_common(skb, dst, src, tos, devin, true);
}
extern unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev);
extern void ip_rt_send_redirect(struct sk_buff *skb);
extern unsigned inet_addr_type(struct net *net, __be32 addr);
extern unsigned inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr);
extern void ip_rt_multicast_event(struct in_device *);
extern int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
extern void ip_rt_get_source(u8 *src, struct rtable *rt);
extern int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb);
struct in_ifaddr;
extern void fib_add_ifaddr(struct in_ifaddr *);
static inline void ip_rt_put(struct rtable * rt)
{
if (rt)
dst_release(&rt->dst);
}
#define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3)
extern const __u8 ip_tos2prio[16];
static inline char rt_tos2priority(u8 tos)
{
return ip_tos2prio[IPTOS_TOS(tos)>>1];
}
static inline int ip_route_connect(struct rtable **rp, __be32 dst,
__be32 src, u32 tos, int oif, u8 protocol,
__be16 sport, __be16 dport, struct sock *sk,
int flags)
{
struct flowi fl = { .oif = oif,
.mark = sk->sk_mark,
.fl4_dst = dst,
.fl4_src = src,
.fl4_tos = tos,
.proto = protocol,
.fl_ip_sport = sport,
.fl_ip_dport = dport };
int err;
struct net *net = sock_net(sk);
if (inet_sk(sk)->transparent)
fl.flags |= FLOWI_FLAG_ANYSRC;
if (protocol == IPPROTO_TCP)
fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
if (!dst || !src) {
err = __ip_route_output_key(net, rp, &fl);
if (err)
return err;
fl.fl4_dst = (*rp)->rt_dst;
fl.fl4_src = (*rp)->rt_src;
ip_rt_put(*rp);
*rp = NULL;
}
security_sk_classify_flow(sk, &fl);
return ip_route_output_flow(net, rp, &fl, sk, flags);
}
static inline int ip_route_newports(struct rtable **rp, u8 protocol,
__be16 sport, __be16 dport, struct sock *sk)
{
if (sport != (*rp)->fl.fl_ip_sport ||
dport != (*rp)->fl.fl_ip_dport) {
struct flowi fl;
memcpy(&fl, &(*rp)->fl, sizeof(fl));
fl.fl_ip_sport = sport;
fl.fl_ip_dport = dport;
fl.proto = protocol;
if (inet_sk(sk)->transparent)
fl.flags |= FLOWI_FLAG_ANYSRC;
if (protocol == IPPROTO_TCP)
fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
ip_rt_put(*rp);
*rp = NULL;
security_sk_classify_flow(sk, &fl);
return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0);
}
return 0;
}
extern void rt_bind_peer(struct rtable *rt, int create);
static inline struct inet_peer *rt_get_peer(struct rtable *rt)
{
if (rt->peer)
return rt->peer;
rt_bind_peer(rt, 0);
return rt->peer;
}
static inline int inet_iif(const struct sk_buff *skb)
{
return skb_rtable(skb)->rt_iif;
}
extern int sysctl_ip_default_ttl;
static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
if (hoplimit == 0)
hoplimit = sysctl_ip_default_ttl;
return hoplimit;
}
#endif /* _ROUTE_H */
View Git Blame Copy Permalink