OpenCloudOS-Kernel/net/ipv6/syncookies.c

267 lines
7.4 KiB
C
Raw Normal View History

/*
* IPv6 Syncookies implementation for the Linux kernel
*
* Authors:
* Glenn Griffin <ggriffin.kernel@gmail.com>
*
* Based on IPv4 implementation by Andi Kleen
* linux/net/ipv4/syncookies.c
*
* 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/tcp.h>
#include <linux/random.h>
#include <linux/cryptohash.h>
#include <linux/kernel.h>
#include <net/ipv6.h>
#include <net/tcp.h>
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
/* RFC 2460, Section 8.3:
* [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
*
* Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
* using higher values than ipv4 tcp syncookies.
* The other values are chosen based on ethernet (1500 and 9k MTU), plus
* one that accounts for common encap (PPPoe) overhead. Table must be sorted.
*/
static __u16 const msstab[] = {
1280 - 60, /* IPV6_MIN_MTU - 60 */
1480 - 60,
1500 - 60,
9000 - 60,
};
static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
if (child)
inet_csk_reqsk_queue_add(sk, req, child);
else
reqsk_free(req);
return child;
}
static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
ipv6_cookie_scratch);
static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
__be16 sport, __be16 dport, u32 count, int c)
{
__u32 *tmp = __get_cpu_var(ipv6_cookie_scratch);
/*
* we have 320 bits of information to hash, copy in the remaining
* 192 bits required for sha_transform, from the syncookie_secret
* and overwrite the digest with the secret
*/
memcpy(tmp + 10, syncookie_secret[c], 44);
memcpy(tmp, saddr, 16);
memcpy(tmp + 4, daddr, 16);
tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
tmp[9] = count;
sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5);
return tmp[17];
}
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, __u32 sseq,
__u32 data)
{
u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
& COOKIEMASK));
}
static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
const struct in6_addr *daddr, __be16 sport,
__be16 dport, __u32 sseq)
{
__u32 diff, count = tcp_cookie_time();
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
& COOKIEMASK;
}
u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
const struct tcphdr *th, __u16 *mssp)
{
int mssind;
const __u16 mss = *mssp;
for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--)
if (mss >= msstab[mssind])
break;
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
th->dest, ntohl(th->seq), mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
tcp_synq_overflow(sk);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
return __cookie_v6_init_sequence(iph, th, mssp);
}
int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
__u32 cookie)
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
EXPORT_SYMBOL_GPL(__cookie_v6_check);
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
struct tcp_options_received tcp_opt;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
const struct tcphdr *th = tcp_hdr(skb);
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
int mss;
struct dst_entry *dst;
__u8 rcv_wscale;
bool ecn_ok = false;
if (!sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk) ||
(mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie)) == 0) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
goto out;
}
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(skb, &tcp_opt, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
ret = NULL;
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (!req)
goto out;
ireq = inet_rsk(req);
ireq6 = inet6_rsk(req);
treq = tcp_rsk(req);
treq->listener = NULL;
if (security_inet_conn_request(sk, skb, req))
goto out_free;
req->mss = mss;
ireq->rmt_port = th->source;
ireq->loc_port = th->dest;
ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
ireq6->loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
ireq6->pktopts = skb;
}
ireq6->iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq6->iif = inet6_iif(skb);
req->expires = 0UL;
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 07:16:46 +08:00
req->num_retrans = 0;
ireq->ecn_ok = ecn_ok;
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
ireq->wscale_ok = tcp_opt.wscale_ok;
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
/*
* We need to lookup the dst_entry to get the correct window size.
* This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten
* me if there is a preferred way.
*/
{
struct in6_addr *final_p, final;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = ireq6->rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst))
goto out_free;
}
req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rcv_wnd, &req->window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
ret = get_cookie_sock(sk, skb, req, dst);
out:
return ret;
out_free:
reqsk_free(req);
return NULL;
}