freebsd-dev/sys/net/route.h
Sam Leffler d1dd20be6e Locking for updates to routing table entries. Each rtentry gets a mutex
that covers updates to the contents.  Note this is separate from holding
a reference and/or locking the routing table itself.

Other/related changes:

o rtredirect loses the final parameter by which an rtentry reference
  may be returned; this was never used and added unwarranted complexity
  for locking.
o minor style cleanups to routing code (e.g. ansi-fy function decls)
o remove the logic to bump the refcnt on the parent of cloned routes,
  we assume the parent will remain as long as the clone; doing this avoids
  a circularity in locking during delete
o convert some timeouts to MPSAFE callouts

Notes:

1. rt_mtx in struct rtentry is guarded by #ifdef _KERNEL as user-level
   applications cannot/do-no know about mutex's.  Doing this requires
   that the mutex be the last element in the structure.  A better solution
   is to introduce an externalized version of struct rtentry but this is
   a major task because of the intertwining of rtentry and other data
   structures that are visible to user applications.
2. There are known LOR's that are expected to go away with forthcoming
   work to eliminate many held references.  If not these will be resolved
   prior to release.
3. ATM changes are untested.

Sponsored by:	FreeBSD Foundation
Obtained from:	BSD/OS (partly)
2003-10-04 03:44:50 +00:00

312 lines
12 KiB
C

/*
* Copyright (c) 1980, 1986, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)route.h 8.4 (Berkeley) 1/9/95
* $FreeBSD$
*/
#ifndef _NET_ROUTE_H_
#define _NET_ROUTE_H_
/*
* Kernel resident routing tables.
*
* The routing tables are initialized when interface addresses
* are set by making entries for all directly connected interfaces.
*/
/*
* A route consists of a destination address and a reference
* to a routing entry. These are often held by protocols
* in their control blocks, e.g. inpcb.
*/
struct route {
struct rtentry *ro_rt;
struct sockaddr ro_dst;
};
/*
* These numbers are used by reliable protocols for determining
* retransmission behavior and are included in the routing structure.
*/
struct rt_metrics {
u_long rmx_locks; /* Kernel must leave these values alone */
u_long rmx_mtu; /* MTU for this path */
u_long rmx_hopcount; /* max hops expected */
u_long rmx_expire; /* lifetime for route, e.g. redirect */
u_long rmx_recvpipe; /* inbound delay-bandwidth product */
u_long rmx_sendpipe; /* outbound delay-bandwidth product */
u_long rmx_ssthresh; /* outbound gateway buffer limit */
u_long rmx_rtt; /* estimated round trip time */
u_long rmx_rttvar; /* estimated rtt variance */
u_long rmx_pksent; /* packets sent using this route */
u_long rmx_filler[4]; /* will be used for T/TCP later */
};
/*
* rmx_rtt and rmx_rttvar are stored as microseconds;
* RTTTOPRHZ(rtt) converts to a value suitable for use
* by a protocol slowtimo counter.
*/
#define RTM_RTTUNIT 1000000 /* units for rtt, rttvar, as units per sec */
#define RTTTOPRHZ(r) ((r) / (RTM_RTTUNIT / PR_SLOWHZ))
/*
* XXX kernel function pointer `rt_output' is visible to applications.
*/
struct mbuf;
/*
* We distinguish between routes to hosts and routes to networks,
* preferring the former if available. For each route we infer
* the interface to use from the gateway address supplied when
* the route was entered. Routes that forward packets through
* gateways are marked so that the output routines know to address the
* gateway rather than the ultimate destination.
*/
#ifndef RNF_NORMAL
#include <net/radix.h>
#endif
struct rtentry {
struct radix_node rt_nodes[2]; /* tree glue, and other values */
#define rt_key(r) ((struct sockaddr *)((r)->rt_nodes->rn_key))
#define rt_mask(r) ((struct sockaddr *)((r)->rt_nodes->rn_mask))
struct sockaddr *rt_gateway; /* value */
long rt_refcnt; /* # held references */
u_long rt_flags; /* up/down?, host/net */
struct ifnet *rt_ifp; /* the answer: interface to use */
struct ifaddr *rt_ifa; /* the answer: interface to use */
struct sockaddr *rt_genmask; /* for generation of cloned routes */
caddr_t rt_llinfo; /* pointer to link level info cache */
struct rt_metrics rt_rmx; /* metrics used by rx'ing protocols */
struct rtentry *rt_gwroute; /* implied entry for gatewayed routes */
int (*rt_output)(struct ifnet *, struct mbuf *, struct sockaddr *,
struct rtentry *);
/* output routine for this (rt,if) */
struct rtentry *rt_parent; /* cloning parent of this route */
#ifdef _KERNEL
/* XXX ugly, user apps use this definition but don't have a mtx def */
struct mtx rt_mtx; /* mutex for routing entry */
#endif
};
/*
* Following structure necessary for 4.3 compatibility;
* We should eventually move it to a compat file.
*/
struct ortentry {
u_long rt_hash; /* to speed lookups */
struct sockaddr rt_dst; /* key */
struct sockaddr rt_gateway; /* value */
short rt_flags; /* up/down?, host/net */
short rt_refcnt; /* # held references */
u_long rt_use; /* raw # packets forwarded */
struct ifnet *rt_ifp; /* the answer: interface to use */
};
#define rt_use rt_rmx.rmx_pksent
#define RTF_UP 0x1 /* route usable */
#define RTF_GATEWAY 0x2 /* destination is a gateway */
#define RTF_HOST 0x4 /* host entry (net otherwise) */
#define RTF_REJECT 0x8 /* host or net unreachable */
#define RTF_DYNAMIC 0x10 /* created dynamically (by redirect) */
#define RTF_MODIFIED 0x20 /* modified dynamically (by redirect) */
#define RTF_DONE 0x40 /* message confirmed */
/* 0x80 unused, was RTF_DELCLONE */
#define RTF_CLONING 0x100 /* generate new routes on use */
#define RTF_XRESOLVE 0x200 /* external daemon resolves name */
#define RTF_LLINFO 0x400 /* generated by link layer (e.g. ARP) */
#define RTF_STATIC 0x800 /* manually added */
#define RTF_BLACKHOLE 0x1000 /* just discard pkts (during updates) */
#define RTF_PROTO2 0x4000 /* protocol specific routing flag */
#define RTF_PROTO1 0x8000 /* protocol specific routing flag */
#define RTF_PRCLONING 0x10000 /* protocol requires cloning */
#define RTF_WASCLONED 0x20000 /* route generated through cloning */
#define RTF_PROTO3 0x40000 /* protocol specific routing flag */
/* 0x80000 unused */
#define RTF_PINNED 0x100000 /* future use */
#define RTF_LOCAL 0x200000 /* route represents a local address */
#define RTF_BROADCAST 0x400000 /* route represents a bcast address */
#define RTF_MULTICAST 0x800000 /* route represents a mcast address */
/* 0x1000000 and up unassigned */
/*
* Routing statistics.
*/
struct rtstat {
short rts_badredirect; /* bogus redirect calls */
short rts_dynamic; /* routes created by redirects */
short rts_newgateway; /* routes modified by redirects */
short rts_unreach; /* lookups which failed */
short rts_wildcard; /* lookups satisfied by a wildcard */
};
/*
* Structures for routing messages.
*/
struct rt_msghdr {
u_short rtm_msglen; /* to skip over non-understood messages */
u_char rtm_version; /* future binary compatibility */
u_char rtm_type; /* message type */
u_short rtm_index; /* index for associated ifp */
int rtm_flags; /* flags, incl. kern & message, e.g. DONE */
int rtm_addrs; /* bitmask identifying sockaddrs in msg */
pid_t rtm_pid; /* identify sender */
int rtm_seq; /* for sender to identify action */
int rtm_errno; /* why failed */
int rtm_use; /* from rtentry */
u_long rtm_inits; /* which metrics we are initializing */
struct rt_metrics rtm_rmx; /* metrics themselves */
};
#define RTM_VERSION 5 /* Up the ante and ignore older versions */
/*
* Message types.
*/
#define RTM_ADD 0x1 /* Add Route */
#define RTM_DELETE 0x2 /* Delete Route */
#define RTM_CHANGE 0x3 /* Change Metrics or flags */
#define RTM_GET 0x4 /* Report Metrics */
#define RTM_LOSING 0x5 /* Kernel Suspects Partitioning */
#define RTM_REDIRECT 0x6 /* Told to use different route */
#define RTM_MISS 0x7 /* Lookup failed on this address */
#define RTM_LOCK 0x8 /* fix specified metrics */
#define RTM_OLDADD 0x9 /* caused by SIOCADDRT */
#define RTM_OLDDEL 0xa /* caused by SIOCDELRT */
#define RTM_RESOLVE 0xb /* req to resolve dst to LL addr */
#define RTM_NEWADDR 0xc /* address being added to iface */
#define RTM_DELADDR 0xd /* address being removed from iface */
#define RTM_IFINFO 0xe /* iface going up/down etc. */
#define RTM_NEWMADDR 0xf /* mcast group membership being added to if */
#define RTM_DELMADDR 0x10 /* mcast group membership being deleted */
#define RTM_IFANNOUNCE 0x11 /* iface arrival/departure */
/*
* Bitmask values for rtm_inits and rmx_locks.
*/
#define RTV_MTU 0x1 /* init or lock _mtu */
#define RTV_HOPCOUNT 0x2 /* init or lock _hopcount */
#define RTV_EXPIRE 0x4 /* init or lock _expire */
#define RTV_RPIPE 0x8 /* init or lock _recvpipe */
#define RTV_SPIPE 0x10 /* init or lock _sendpipe */
#define RTV_SSTHRESH 0x20 /* init or lock _ssthresh */
#define RTV_RTT 0x40 /* init or lock _rtt */
#define RTV_RTTVAR 0x80 /* init or lock _rttvar */
/*
* Bitmask values for rtm_addrs.
*/
#define RTA_DST 0x1 /* destination sockaddr present */
#define RTA_GATEWAY 0x2 /* gateway sockaddr present */
#define RTA_NETMASK 0x4 /* netmask sockaddr present */
#define RTA_GENMASK 0x8 /* cloning mask sockaddr present */
#define RTA_IFP 0x10 /* interface name sockaddr present */
#define RTA_IFA 0x20 /* interface addr sockaddr present */
#define RTA_AUTHOR 0x40 /* sockaddr for author of redirect */
#define RTA_BRD 0x80 /* for NEWADDR, broadcast or p-p dest addr */
/*
* Index offsets for sockaddr array for alternate internal encoding.
*/
#define RTAX_DST 0 /* destination sockaddr present */
#define RTAX_GATEWAY 1 /* gateway sockaddr present */
#define RTAX_NETMASK 2 /* netmask sockaddr present */
#define RTAX_GENMASK 3 /* cloning mask sockaddr present */
#define RTAX_IFP 4 /* interface name sockaddr present */
#define RTAX_IFA 5 /* interface addr sockaddr present */
#define RTAX_AUTHOR 6 /* sockaddr for author of redirect */
#define RTAX_BRD 7 /* for NEWADDR, broadcast or p-p dest addr */
#define RTAX_MAX 8 /* size of array to allocate */
struct rt_addrinfo {
int rti_addrs;
struct sockaddr *rti_info[RTAX_MAX];
int rti_flags;
struct ifaddr *rti_ifa;
struct ifnet *rti_ifp;
};
#ifdef _KERNEL
#define RT_LOCK_INIT(_rt) \
mtx_init(&(_rt)->rt_mtx, "rtentry", NULL, MTX_DEF | MTX_DUPOK)
#define RT_LOCK(_rt) mtx_lock(&(_rt)->rt_mtx)
#define RT_UNLOCK(_rt) mtx_unlock(&(_rt)->rt_mtx)
#define RT_LOCK_DESTROY(_rt) mtx_destroy(&(_rt)->rt_mtx)
#define RT_LOCK_ASSERT(_rt) mtx_assert(&(_rt)->rt_mtx, MA_OWNED)
#define RTFREE_LOCKED(_rt) do { \
if ((_rt)->rt_refcnt <= 1) \
rtfree(_rt); \
else { \
(_rt)->rt_refcnt--; \
RT_UNLOCK(_rt); \
} \
/* guard against invalid refs */ \
_rt = 0; \
} while (0)
#define RTFREE(_rt) do { \
RT_LOCK(_rt); \
RTFREE_LOCKED(_rt); \
} while (0)
extern struct radix_node_head *rt_tables[AF_MAX+1];
struct ifmultiaddr;
void route_init(void);
int rt_getifa(struct rt_addrinfo *);
void rt_ifannouncemsg(struct ifnet *, int);
void rt_ifmsg(struct ifnet *);
void rt_missmsg(int, struct rt_addrinfo *, int, int);
void rt_newaddrmsg(int, struct ifaddr *, int, struct rtentry *);
void rt_newmaddrmsg(int, struct ifmultiaddr *);
void rtalloc(struct route *);
int rt_setgate(struct rtentry *, struct sockaddr *, struct sockaddr *);
void rtalloc_ign(struct route *, u_long);
/* NB: the rtentry is returned locked */
struct rtentry *rtalloc1(struct sockaddr *, int, u_long);
void rtfree(struct rtentry *);
int rtinit(struct ifaddr *, int, int);
int rtioctl(u_long, caddr_t);
void rtredirect(struct sockaddr *, struct sockaddr *,
struct sockaddr *, int, struct sockaddr *);
int rtrequest(int, struct sockaddr *,
struct sockaddr *, struct sockaddr *, int, struct rtentry **);
int rtrequest1(int, struct rt_addrinfo *, struct rtentry **);
int rt_check(struct rtentry **, struct rtentry **, struct sockaddr *);
#endif
#endif