linux-stable/include/net/route.h

349 lines
9.9 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.
*
* 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 <net/ip_fib.h>
#include <linux/in_route.h>
#include <linux/rtnetlink.h>
#include <linux/rcupdate.h>
#include <linux/route.h>
#include <linux/ip.h>
#include <linux/cache.h>
#include <linux/security.h>
ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: John Heffner <johnwheffner@gmail.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-09 09:01:15 +00:00
/* IPv4 datagram length is stored into 16bit field (tot_len) */
#define IP_MAX_MTU 0xFFFFU
#define RTO_ONLINK 0x01
#define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
#define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
struct fib_nh;
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
struct fib_info;
struct uncached_list;
struct rtable {
struct dst_entry dst;
int rt_genid;
unsigned int rt_flags;
__u16 rt_type;
__u8 rt_is_input;
__u8 rt_uses_gateway;
int rt_iif;
/* Info on neighbour */
__be32 rt_gateway;
/* Miscellaneous cached information */
u32 rt_pmtu;
u32 rt_table_id;
struct list_head rt_uncached;
struct uncached_list *rt_uncached_list;
};
static inline bool rt_is_input_route(const struct rtable *rt)
{
return rt->rt_is_input != 0;
}
static inline bool rt_is_output_route(const struct rtable *rt)
{
return rt->rt_is_input == 0;
}
static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
{
if (rt->rt_gateway)
return rt->rt_gateway;
return daddr;
}
struct ip_rt_acct {
__u32 o_bytes;
__u32 o_packets;
__u32 i_bytes;
__u32 i_packets;
};
struct rt_cache_stat {
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_slow_tot;
unsigned int out_slow_mc;
};
extern struct ip_rt_acct __percpu *ip_rt_acct;
struct in_device;
int ip_rt_init(void);
void rt_cache_flush(struct net *net);
void rt_flush_dev(struct net_device *dev);
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
const struct sk_buff *skb);
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
struct fib_result *res,
const struct sk_buff *skb);
static inline struct rtable *__ip_route_output_key(struct net *net,
struct flowi4 *flp)
{
return ip_route_output_key_hash(net, flp, NULL);
}
struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
const struct sock *sk);
struct dst_entry *ipv4_blackhole_route(struct net *net,
struct dst_entry *dst_orig);
static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp)
{
return ip_route_output_flow(net, flp, NULL);
}
static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
__be32 saddr, u8 tos, int oif)
{
struct flowi4 fl4 = {
.flowi4_oif = oif,
.flowi4_tos = tos,
.daddr = daddr,
.saddr = saddr,
};
return ip_route_output_key(net, &fl4);
}
static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
struct sock *sk,
__be32 daddr, __be32 saddr,
__be16 dport, __be16 sport,
__u8 proto, __u8 tos, int oif)
{
flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
RT_SCOPE_UNIVERSE, proto,
sk ? inet_sk_flowi_flags(sk) : 0,
daddr, saddr, dport, sport, sock_net_uid(net, sk));
if (sk)
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
}
static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4,
__be32 daddr, __be32 saddr,
__be32 gre_key, __u8 tos, int oif)
{
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_oif = oif;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->flowi4_tos = tos;
fl4->flowi4_proto = IPPROTO_GRE;
fl4->fl4_gre_key = gre_key;
return ip_route_output_key(net, fl4);
}
int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev,
struct in_device *in_dev, u32 *itag);
int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin);
int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin,
struct fib_result *res);
static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
u8 tos, struct net_device *devin)
{
int err;
rcu_read_lock();
err = ip_route_input_noref(skb, dst, src, tos, devin);
if (!err) {
net: prevent dst uses after free In linux-4.13, Wei worked hard to convert dst to a traditional refcounted model, removing GC. We now want to make sure a dst refcount can not transition from 0 back to 1. The problem here is that input path attached a not refcounted dst to an skb. Then later, because packet is forwarded and hits skb_dst_force() before exiting RCU section, we might try to take a refcount on one dst that is about to be freed, if another cpu saw 1 -> 0 transition in dst_release() and queued the dst for freeing after one RCU grace period. Lets unify skb_dst_force() and skb_dst_force_safe(), since we should always perform the complete check against dst refcount, and not assume it is not zero. Bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=197005 [ 989.919496] skb_dst_force+0x32/0x34 [ 989.919498] __dev_queue_xmit+0x1ad/0x482 [ 989.919501] ? eth_header+0x28/0xc6 [ 989.919502] dev_queue_xmit+0xb/0xd [ 989.919504] neigh_connected_output+0x9b/0xb4 [ 989.919507] ip_finish_output2+0x234/0x294 [ 989.919509] ? ipt_do_table+0x369/0x388 [ 989.919510] ip_finish_output+0x12c/0x13f [ 989.919512] ip_output+0x53/0x87 [ 989.919513] ip_forward_finish+0x53/0x5a [ 989.919515] ip_forward+0x2cb/0x3e6 [ 989.919516] ? pskb_trim_rcsum.part.9+0x4b/0x4b [ 989.919518] ip_rcv_finish+0x2e2/0x321 [ 989.919519] ip_rcv+0x26f/0x2eb [ 989.919522] ? vlan_do_receive+0x4f/0x289 [ 989.919523] __netif_receive_skb_core+0x467/0x50b [ 989.919526] ? tcp_gro_receive+0x239/0x239 [ 989.919529] ? inet_gro_receive+0x226/0x238 [ 989.919530] __netif_receive_skb+0x4d/0x5f [ 989.919532] netif_receive_skb_internal+0x5c/0xaf [ 989.919533] napi_gro_receive+0x45/0x81 [ 989.919536] ixgbe_poll+0xc8a/0xf09 [ 989.919539] ? kmem_cache_free_bulk+0x1b6/0x1f7 [ 989.919540] net_rx_action+0xf4/0x266 [ 989.919543] __do_softirq+0xa8/0x19d [ 989.919545] irq_exit+0x5d/0x6b [ 989.919546] do_IRQ+0x9c/0xb5 [ 989.919548] common_interrupt+0x93/0x93 [ 989.919548] </IRQ> Similarly dst_clone() can use dst_hold() helper to have additional debugging, as a follow up to commit 44ebe79149ff ("net: add debug atomic_inc_not_zero() in dst_hold()") In net-next we will convert dst atomic_t to refcount_t for peace of mind. Fixes: a4c2fd7f7891 ("net: remove DST_NOCACHE flag") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Wei Wang <weiwan@google.com> Reported-by: Paweł Staszewski <pstaszewski@itcare.pl> Bisected-by: Paweł Staszewski <pstaszewski@itcare.pl> Acked-by: Wei Wang <weiwan@google.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-21 16:15:46 +00:00
skb_dst_force(skb);
if (!skb_dst(skb))
err = -EINVAL;
}
rcu_read_unlock();
return err;
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
u32 mark, u8 protocol, int flow_flags);
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
u8 protocol, int flow_flags);
void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
void ip_rt_send_redirect(struct sk_buff *skb);
unsigned int inet_addr_type(struct net *net, __be32 addr);
unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr);
unsigned int inet_addr_type_dev_table(struct net *net,
const struct net_device *dev,
__be32 addr);
void ip_rt_multicast_event(struct in_device *);
int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
struct rtable *rt_dst_alloc(struct net_device *dev,
unsigned int flags, u16 type,
bool nopolicy, bool noxfrm, bool will_cache);
struct in_ifaddr;
void fib_add_ifaddr(struct in_ifaddr *);
void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
static inline void ip_rt_put(struct rtable *rt)
{
/* dst_release() accepts a NULL parameter.
* We rely on dst being first structure in struct rtable
*/
BUILD_BUG_ON(offsetof(struct rtable, dst) != 0);
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];
}
/* ip_route_connect() and ip_route_newports() work in tandem whilst
* binding a socket for a new outgoing connection.
*
* In order to use IPSEC properly, we must, in the end, have a
* route that was looked up using all available keys including source
* and destination ports.
*
* However, if a source port needs to be allocated (the user specified
* a wildcard source port) we need to obtain addressing information
* in order to perform that allocation.
*
* So ip_route_connect() looks up a route using wildcarded source and
* destination ports in the key, simply so that we can get a pair of
* addresses to use for port allocation.
*
* Later, once the ports are allocated, ip_route_newports() will make
* another route lookup if needed to make sure we catch any IPSEC
* rules keyed on the port information.
*
* The callers allocate the flow key on their stack, and must pass in
* the same flowi4 object to both the ip_route_connect() and the
* ip_route_newports() calls.
*/
static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src,
u32 tos, int oif, u8 protocol,
__be16 sport, __be16 dport,
struct sock *sk)
{
__u8 flow_flags = 0;
if (inet_sk(sk)->transparent)
flow_flags |= FLOWI_FLAG_ANYSRC;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
protocol, flow_flags, dst, src, dport, sport,
sk->sk_uid);
}
static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
__be32 dst, __be32 src, u32 tos,
int oif, u8 protocol,
__be16 sport, __be16 dport,
struct sock *sk)
{
struct net *net = sock_net(sk);
struct rtable *rt;
ip_route_connect_init(fl4, dst, src, tos, oif, protocol,
sport, dport, sk);
if (!dst || !src) {
rt = __ip_route_output_key(net, fl4);
if (IS_ERR(rt))
return rt;
ip_rt_put(rt);
flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr);
}
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
}
static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt,
__be16 orig_sport, __be16 orig_dport,
__be16 sport, __be16 dport,
struct sock *sk)
{
if (sport != orig_sport || dport != orig_dport) {
fl4->fl4_dport = dport;
fl4->fl4_sport = sport;
ip_rt_put(rt);
flowi4_update_output(fl4, sk->sk_bound_dev_if,
RT_CONN_FLAGS(sk), fl4->daddr,
fl4->saddr);
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(sock_net(sk), fl4, sk);
}
return rt;
}
static inline int inet_iif(const struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
if (rt && rt->rt_iif)
return rt->rt_iif;
return skb->skb_iif;
}
static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
struct net *net = dev_net(dst->dev);
if (hoplimit == 0)
hoplimit = net->ipv4.sysctl_ip_default_ttl;
return hoplimit;
}
#endif /* _ROUTE_H */