kernel_optimize_test/net/ipv6/inet6_connection_sock.c
Eric Dumazet c191a836a9 tcp: disallow bind() to reuse addr/port
inet_csk_bind_conflict() logic currently disallows a bind() if
it finds a friend socket (a socket bound on same address/port)
satisfying a set of conditions :

1) Current (to be bound) socket doesnt have sk_reuse set
OR
2) other socket doesnt have sk_reuse set
OR
3) other socket is in LISTEN state

We should add the CLOSE state in the 3) condition, in order to avoid two
REUSEADDR sockets in CLOSE state with same local address/port, since
this can deny further operations.

Note : a prior patch tried to address the problem in a different (and
buggy) way. (commit fda48a0d7a tcp: bind() fix when many ports
are bound).

Reported-by: Gaspar Chilingarov <gasparch@gmail.com>
Reported-by: Daniel Baluta <daniel.baluta@gmail.com>
Tested-by: Daniel Baluta <daniel.baluta@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-11 14:03:07 -08:00

266 lines
6.9 KiB
C

/*
* 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.
*
* Support for INET6 connection oriented protocols.
*
* Authors: See the TCPv6 sources
*
* 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.
*/
#include <linux/module.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/jhash.h>
#include <linux/slab.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_ecn.h>
#include <net/inet_hashtables.h>
#include <net/ip6_route.h>
#include <net/sock.h>
#include <net/inet6_connection_sock.h>
int inet6_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb)
{
const struct sock *sk2;
const struct hlist_node *node;
/* We must walk the whole port owner list in this case. -DaveM */
/*
* See comment in inet_csk_bind_conflict about sock lookup
* vs net namespaces issues.
*/
sk_for_each_bound(sk2, node, &tb->owners) {
if (sk != sk2 &&
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
sk->sk_bound_dev_if == sk2->sk_bound_dev_if) &&
(!sk->sk_reuse || !sk2->sk_reuse ||
((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) &&
ipv6_rcv_saddr_equal(sk, sk2))
break;
}
return node != NULL;
}
EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
struct dst_entry *inet6_csk_route_req(struct sock *sk,
const struct request_sock *req)
{
struct inet6_request_sock *treq = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *final_p, final;
struct dst_entry *dst;
struct flowi fl;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
final_p = fl6_update_dst(&fl, np->opt, &final);
ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
fl.oif = sk->sk_bound_dev_if;
fl.mark = sk->sk_mark;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, &fl);
if (ip6_dst_lookup(sk, &dst, &fl))
return NULL;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
return NULL;
return dst;
}
/*
* request_sock (formerly open request) hash tables.
*/
static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport,
const u32 rnd, const u16 synq_hsize)
{
u32 c;
c = jhash_3words((__force u32)raddr->s6_addr32[0],
(__force u32)raddr->s6_addr32[1],
(__force u32)raddr->s6_addr32[2],
rnd);
c = jhash_2words((__force u32)raddr->s6_addr32[3],
(__force u32)rport,
c);
return c & (synq_hsize - 1);
}
struct request_sock *inet6_csk_search_req(const struct sock *sk,
struct request_sock ***prevp,
const __be16 rport,
const struct in6_addr *raddr,
const struct in6_addr *laddr,
const int iif)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
struct request_sock *req, **prev;
for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport,
lopt->hash_rnd,
lopt->nr_table_entries)];
(req = *prev) != NULL;
prev = &req->dl_next) {
const struct inet6_request_sock *treq = inet6_rsk(req);
if (inet_rsk(req)->rmt_port == rport &&
req->rsk_ops->family == AF_INET6 &&
ipv6_addr_equal(&treq->rmt_addr, raddr) &&
ipv6_addr_equal(&treq->loc_addr, laddr) &&
(!treq->iif || treq->iif == iif)) {
WARN_ON(req->sk != NULL);
*prevp = prev;
return req;
}
}
return NULL;
}
EXPORT_SYMBOL_GPL(inet6_csk_search_req);
void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
struct request_sock *req,
const unsigned long timeout)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
const u32 h = inet6_synq_hash(&inet6_rsk(req)->rmt_addr,
inet_rsk(req)->rmt_port,
lopt->hash_rnd, lopt->nr_table_entries);
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
inet_csk_reqsk_queue_added(sk, timeout);
}
EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
sin6->sin6_family = AF_INET6;
ipv6_addr_copy(&sin6->sin6_addr, &np->daddr);
sin6->sin6_port = inet_sk(sk)->inet_dport;
/* We do not store received flowlabel for TCP */
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = 0;
if (sk->sk_bound_dev_if &&
ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin6->sin6_scope_id = sk->sk_bound_dev_if;
}
EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
static inline
void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst,
struct in6_addr *daddr, struct in6_addr *saddr)
{
__ip6_dst_store(sk, dst, daddr, saddr);
#ifdef CONFIG_XFRM
{
struct rt6_info *rt = (struct rt6_info *)dst;
rt->rt6i_flow_cache_genid = atomic_read(&flow_cache_genid);
}
#endif
}
static inline
struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst;
dst = __sk_dst_check(sk, cookie);
#ifdef CONFIG_XFRM
if (dst) {
struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) {
__sk_dst_reset(sk);
dst = NULL;
}
}
#endif
return dst;
}
int inet6_csk_xmit(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct flowi fl;
struct dst_entry *dst;
struct in6_addr *final_p, final;
memset(&fl, 0, sizeof(fl));
fl.proto = sk->sk_protocol;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.fl6_flowlabel = np->flow_label;
IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
fl.oif = sk->sk_bound_dev_if;
fl.mark = sk->sk_mark;
fl.fl_ip_sport = inet->inet_sport;
fl.fl_ip_dport = inet->inet_dport;
security_sk_classify_flow(sk, &fl);
final_p = fl6_update_dst(&fl, np->opt, &final);
dst = __inet6_csk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
int err = ip6_dst_lookup(sk, &dst, &fl);
if (err) {
sk->sk_err_soft = -err;
kfree_skb(skb);
return err;
}
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) {
sk->sk_route_caps = 0;
kfree_skb(skb);
return err;
}
__inet6_csk_dst_store(sk, dst, NULL, NULL);
}
skb_dst_set(skb, dst_clone(dst));
/* Restore final destination back after routing done */
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
return ip6_xmit(sk, skb, &fl, np->opt);
}
EXPORT_SYMBOL_GPL(inet6_csk_xmit);