mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Michal Kubeček](/assets/img/avatar_default.png)
If an IPv6 host route with metrics exists, an attempt to add a new route for the same target with different metrics fails but rewrites the metrics anyway: 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1s 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1500 RTNETLINK answers: File exists 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 rto_min lock 1.5s This is caused by all IPv6 host routes using the metrics in their inetpeer (or the shared default). This also holds for the new route created in ip6_route_add() which shares the metrics with the already existing route and thus ip6_route_add() rewrites the metrics even if the new route ends up not being used at all. Another problem is that old metrics in inetpeer can reappear unexpectedly for a new route, e.g. 12sp0:~ # ip route add fec0::1 dev eth0 rto_min 1000 12sp0:~ # ip route del fec0::1 12sp0:~ # ip route add fec0::1 dev eth0 12sp0:~ # ip route change fec0::1 dev eth0 hoplimit 10 12sp0:~ # ip -6 route show fe80::/64 dev eth0 proto kernel metric 256 fec0::1 dev eth0 metric 1024 hoplimit 10 rto_min lock 1s Resolve the first problem by moving the setting of metrics down into fib6_add_rt2node() to the point we are sure we are inserting the new route into the tree. Second problem is addressed by introducing new flag DST_METRICS_FORCE_OVERWRITE which is set for a new host route in ip6_route_add() and makes ipv6_cow_metrics() always overwrite the metrics in inetpeer (even if they are not "new"); it is reset after that. v5: use a flag in _metrics member rather than one in flags v4: fix a typo making a condition always true (thanks to Hannes Frederic Sowa) v3: rewritten based on David Miller's idea to move setting the metrics (and allocation in non-host case) down to the point we already know the route is to be inserted. Also rebased to net-next as it is quite late in the cycle. Signed-off-by: Michal Kubecek <mkubecek@suse.cz> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
315 lines
7.1 KiB
C
315 lines
7.1 KiB
C
/*
|
|
* Linux INET6 implementation
|
|
*
|
|
* Authors:
|
|
* Pedro Roque <roque@di.fc.ul.pt>
|
|
*
|
|
* 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 _IP6_FIB_H
|
|
#define _IP6_FIB_H
|
|
|
|
#include <linux/ipv6_route.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/spinlock.h>
|
|
#include <net/dst.h>
|
|
#include <net/flow.h>
|
|
#include <net/netlink.h>
|
|
#include <net/inetpeer.h>
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
#define FIB6_TABLE_HASHSZ 256
|
|
#else
|
|
#define FIB6_TABLE_HASHSZ 1
|
|
#endif
|
|
|
|
struct rt6_info;
|
|
|
|
struct fib6_config {
|
|
u32 fc_table;
|
|
u32 fc_metric;
|
|
int fc_dst_len;
|
|
int fc_src_len;
|
|
int fc_ifindex;
|
|
u32 fc_flags;
|
|
u32 fc_protocol;
|
|
u32 fc_type; /* only 8 bits are used */
|
|
|
|
struct in6_addr fc_dst;
|
|
struct in6_addr fc_src;
|
|
struct in6_addr fc_prefsrc;
|
|
struct in6_addr fc_gateway;
|
|
|
|
unsigned long fc_expires;
|
|
struct nlattr *fc_mx;
|
|
int fc_mx_len;
|
|
int fc_mp_len;
|
|
struct nlattr *fc_mp;
|
|
|
|
struct nl_info fc_nlinfo;
|
|
};
|
|
|
|
struct fib6_node {
|
|
struct fib6_node *parent;
|
|
struct fib6_node *left;
|
|
struct fib6_node *right;
|
|
#ifdef CONFIG_IPV6_SUBTREES
|
|
struct fib6_node *subtree;
|
|
#endif
|
|
struct rt6_info *leaf;
|
|
|
|
__u16 fn_bit; /* bit key */
|
|
__u16 fn_flags;
|
|
__u32 fn_sernum;
|
|
struct rt6_info *rr_ptr;
|
|
};
|
|
|
|
#ifndef CONFIG_IPV6_SUBTREES
|
|
#define FIB6_SUBTREE(fn) NULL
|
|
#else
|
|
#define FIB6_SUBTREE(fn) ((fn)->subtree)
|
|
#endif
|
|
|
|
/*
|
|
* routing information
|
|
*
|
|
*/
|
|
|
|
struct rt6key {
|
|
struct in6_addr addr;
|
|
int plen;
|
|
};
|
|
|
|
struct fib6_table;
|
|
|
|
struct rt6_info {
|
|
struct dst_entry dst;
|
|
|
|
/*
|
|
* Tail elements of dst_entry (__refcnt etc.)
|
|
* and these elements (rarely used in hot path) are in
|
|
* the same cache line.
|
|
*/
|
|
struct fib6_table *rt6i_table;
|
|
struct fib6_node *rt6i_node;
|
|
|
|
struct in6_addr rt6i_gateway;
|
|
|
|
/* Multipath routes:
|
|
* siblings is a list of rt6_info that have the the same metric/weight,
|
|
* destination, but not the same gateway. nsiblings is just a cache
|
|
* to speed up lookup.
|
|
*/
|
|
struct list_head rt6i_siblings;
|
|
unsigned int rt6i_nsiblings;
|
|
|
|
atomic_t rt6i_ref;
|
|
|
|
/* These are in a separate cache line. */
|
|
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
|
|
u32 rt6i_flags;
|
|
struct rt6key rt6i_src;
|
|
struct rt6key rt6i_prefsrc;
|
|
u32 rt6i_metric;
|
|
|
|
struct inet6_dev *rt6i_idev;
|
|
unsigned long _rt6i_peer;
|
|
|
|
u32 rt6i_genid;
|
|
|
|
/* more non-fragment space at head required */
|
|
unsigned short rt6i_nfheader_len;
|
|
|
|
u8 rt6i_protocol;
|
|
};
|
|
|
|
static inline struct inet_peer *rt6_peer_ptr(struct rt6_info *rt)
|
|
{
|
|
return inetpeer_ptr(rt->_rt6i_peer);
|
|
}
|
|
|
|
static inline bool rt6_has_peer(struct rt6_info *rt)
|
|
{
|
|
return inetpeer_ptr_is_peer(rt->_rt6i_peer);
|
|
}
|
|
|
|
static inline void __rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
|
|
{
|
|
__inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
|
|
}
|
|
|
|
static inline bool rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer)
|
|
{
|
|
return inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer);
|
|
}
|
|
|
|
static inline void rt6_init_peer(struct rt6_info *rt, struct inet_peer_base *base)
|
|
{
|
|
inetpeer_init_ptr(&rt->_rt6i_peer, base);
|
|
}
|
|
|
|
static inline void rt6_transfer_peer(struct rt6_info *rt, struct rt6_info *ort)
|
|
{
|
|
inetpeer_transfer_peer(&rt->_rt6i_peer, &ort->_rt6i_peer);
|
|
}
|
|
|
|
static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
|
|
{
|
|
return ((struct rt6_info *)dst)->rt6i_idev;
|
|
}
|
|
|
|
static inline void rt6_clean_expires(struct rt6_info *rt)
|
|
{
|
|
rt->rt6i_flags &= ~RTF_EXPIRES;
|
|
rt->dst.expires = 0;
|
|
}
|
|
|
|
static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
|
|
{
|
|
rt->dst.expires = expires;
|
|
rt->rt6i_flags |= RTF_EXPIRES;
|
|
}
|
|
|
|
static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
|
|
{
|
|
struct rt6_info *rt;
|
|
|
|
for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES);
|
|
rt = (struct rt6_info *)rt->dst.from);
|
|
if (rt && rt != rt0)
|
|
rt0->dst.expires = rt->dst.expires;
|
|
|
|
dst_set_expires(&rt0->dst, timeout);
|
|
rt0->rt6i_flags |= RTF_EXPIRES;
|
|
}
|
|
|
|
static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
|
|
{
|
|
struct dst_entry *new = (struct dst_entry *) from;
|
|
|
|
rt->rt6i_flags &= ~RTF_EXPIRES;
|
|
dst_hold(new);
|
|
rt->dst.from = new;
|
|
}
|
|
|
|
static inline void ip6_rt_put(struct rt6_info *rt)
|
|
{
|
|
/* dst_release() accepts a NULL parameter.
|
|
* We rely on dst being first structure in struct rt6_info
|
|
*/
|
|
BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0);
|
|
dst_release(&rt->dst);
|
|
}
|
|
|
|
struct fib6_walker_t {
|
|
struct list_head lh;
|
|
struct fib6_node *root, *node;
|
|
struct rt6_info *leaf;
|
|
unsigned char state;
|
|
unsigned char prune;
|
|
unsigned int skip;
|
|
unsigned int count;
|
|
int (*func)(struct fib6_walker_t *);
|
|
void *args;
|
|
};
|
|
|
|
struct rt6_statistics {
|
|
__u32 fib_nodes;
|
|
__u32 fib_route_nodes;
|
|
__u32 fib_rt_alloc; /* permanent routes */
|
|
__u32 fib_rt_entries; /* rt entries in table */
|
|
__u32 fib_rt_cache; /* cache routes */
|
|
__u32 fib_discarded_routes;
|
|
};
|
|
|
|
#define RTN_TL_ROOT 0x0001
|
|
#define RTN_ROOT 0x0002 /* tree root node */
|
|
#define RTN_RTINFO 0x0004 /* node with valid routing info */
|
|
|
|
/*
|
|
* priority levels (or metrics)
|
|
*
|
|
*/
|
|
|
|
|
|
struct fib6_table {
|
|
struct hlist_node tb6_hlist;
|
|
u32 tb6_id;
|
|
rwlock_t tb6_lock;
|
|
struct fib6_node tb6_root;
|
|
struct inet_peer_base tb6_peers;
|
|
};
|
|
|
|
#define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC
|
|
#define RT6_TABLE_MAIN RT_TABLE_MAIN
|
|
#define RT6_TABLE_DFLT RT6_TABLE_MAIN
|
|
#define RT6_TABLE_INFO RT6_TABLE_MAIN
|
|
#define RT6_TABLE_PREFIX RT6_TABLE_MAIN
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
#define FIB6_TABLE_MIN 1
|
|
#define FIB6_TABLE_MAX RT_TABLE_MAX
|
|
#define RT6_TABLE_LOCAL RT_TABLE_LOCAL
|
|
#else
|
|
#define FIB6_TABLE_MIN RT_TABLE_MAIN
|
|
#define FIB6_TABLE_MAX FIB6_TABLE_MIN
|
|
#define RT6_TABLE_LOCAL RT6_TABLE_MAIN
|
|
#endif
|
|
|
|
typedef struct rt6_info *(*pol_lookup_t)(struct net *,
|
|
struct fib6_table *,
|
|
struct flowi6 *, int);
|
|
|
|
/*
|
|
* exported functions
|
|
*/
|
|
|
|
struct fib6_table *fib6_get_table(struct net *net, u32 id);
|
|
struct fib6_table *fib6_new_table(struct net *net, u32 id);
|
|
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
|
|
int flags, pol_lookup_t lookup);
|
|
|
|
struct fib6_node *fib6_lookup(struct fib6_node *root,
|
|
const struct in6_addr *daddr,
|
|
const struct in6_addr *saddr);
|
|
|
|
struct fib6_node *fib6_locate(struct fib6_node *root,
|
|
const struct in6_addr *daddr, int dst_len,
|
|
const struct in6_addr *saddr, int src_len);
|
|
|
|
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
|
|
void *arg);
|
|
|
|
int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
|
|
struct nlattr *mx, int mx_len);
|
|
|
|
int fib6_del(struct rt6_info *rt, struct nl_info *info);
|
|
|
|
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
|
|
|
|
void fib6_run_gc(unsigned long expires, struct net *net, bool force);
|
|
|
|
void fib6_gc_cleanup(void);
|
|
|
|
int fib6_init(void);
|
|
|
|
int ipv6_route_open(struct inode *inode, struct file *file);
|
|
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
int fib6_rules_init(void);
|
|
void fib6_rules_cleanup(void);
|
|
#else
|
|
static inline int fib6_rules_init(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void fib6_rules_cleanup(void)
|
|
{
|
|
return ;
|
|
}
|
|
#endif
|
|
#endif
|