1 files changed, 89 insertions, 100 deletions

diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7208a06576c..a822b880689 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -21,42 +21,25 @@
 #include <net/ipv6.h>
 #include <net/tcp.h>
 
-extern int sysctl_tcp_syncookies;
-extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
-
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-/*
- * This table has to be sorted and terminated with (__u16)-1.
- * XXX generate a better table.
- * Unresolved Issues: HIPPI with a 64k MSS is not well supported.
+static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS];
+
+/* RFC 2460, Section 8.3:
+ * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
  *
- * Taken directly from ipv4 implementation.
- * Should this list be modified for ipv6 use or is it close enough?
- * rfc 2460 8.3 suggests mss values 20 bytes less than ipv4 counterpart
+ * 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[] = {
-	64 - 1,
-	256 - 1,
-	512 - 1,
-	536 - 1,
-	1024 - 1,
-	1440 - 1,
-	1460 - 1,
-	4312 - 1,
-	(__u16)-1
+	1280 - 60, /* IPV6_MIN_MTU - 60 */
+	1480 - 60,
+	1500 - 60,
+	9000 - 60,
 };
-/* The number doesn't include the -1 terminator */
-#define NUM_MSS (ARRAY_SIZE(msstab) - 1)
-
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
 
 static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 					   struct request_sock *req,
@@ -77,17 +60,21 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
 		      ipv6_cookie_scratch);
 
-static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
+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);
+	__u32 *tmp;
+
+	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
+
+	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
+	 * 192 bits required for sha_transform, from the syncookie6_secret
 	 * and overwrite the digest with the secret
 	 */
-	memcpy(tmp + 10, syncookie_secret[c], 44);
+	memcpy(tmp + 10, syncookie6_secret[c], 44);
 	memcpy(tmp, saddr, 16);
 	memcpy(tmp + 4, daddr, 16);
 	tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
@@ -97,27 +84,28 @@ static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
 	return tmp[17];
 }
 
-static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *daddr,
+static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
+				   const struct in6_addr *daddr,
 				   __be16 sport, __be16 dport, __u32 sseq,
-				   __u32 count, __u32 data)
+				   __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, struct in6_addr *saddr,
-				  struct in6_addr *daddr, __be16 sport,
-				  __be16 dport, __u32 sseq, __u32 count,
-				  __u32 maxdiff)
+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;
+	__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 >= maxdiff)
+	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
 	return (cookie -
@@ -125,44 +113,49 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr,
 		& COOKIEMASK;
 }
 
-__u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
+u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
+			      const struct tcphdr *th, __u16 *mssp)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
-	const struct tcphdr *th = tcp_hdr(skb);
 	int mssind;
 	const __u16 mss = *mssp;
 
-	tcp_synq_overflow(sk);
-
-	for (mssind = 0; mss > msstab[mssind + 1]; mssind++)
-		;
-	*mssp = msstab[mssind] + 1;
+	for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--)
+		if (mss >= msstab[mssind])
+			break;
 
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
+	*mssp = msstab[mssind];
 
 	return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
-				     th->dest, ntohl(th->seq),
-				     jiffies / (HZ * 60), mssind);
+				     th->dest, ntohl(th->seq), mssind);
 }
+EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
 
-static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
+__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	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,
-					    jiffies / (HZ * 60), COUNTER_TRIES);
+					    th->source, th->dest, seq);
 
-	return mssind < NUM_MSS ? msstab[mssind] + 1 : 0;
+	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;
-	u8 *hash_location;
 	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);
@@ -173,12 +166,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
+	bool ecn_ok = false;
 
-	if (!sysctl_tcp_syncookies || !th->ack)
+	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
 	if (tcp_synq_no_recent_overflow(sk) ||
-		(mss = cookie_check(skb, cookie)) == 0) {
+		(mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie)) == 0) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
@@ -187,10 +181,10 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	/* check for timestamp cookie support */
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
-	tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
-	if (tcp_opt.saw_tstamp)
-		cookie_check_timestamp(&tcp_opt);
+	if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
+		goto out;
 
 	ret = NULL;
 	req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
@@ -198,39 +192,41 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		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;
-	ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+	ireq->ir_rmt_port = th->source;
+	ireq->ir_num = ntohs(th->dest);
+	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq->ir_v6_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;
+		ireq->pktopts = skb;
 	}
 
-	ireq6->iif = sk->sk_bound_dev_if;
+	ireq->ir_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);
+	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		ireq->ir_iif = inet6_iif(skb);
+
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	req->expires = 0UL;
-	req->retrans = 0;
-	ireq->ecn_ok		= 0;
+	req->num_retrans = 0;
+	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
-	ireq->rcv_wscale	= tcp_opt.rcv_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;
 
@@ -240,36 +236,29 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	 * me if there is a preferred way.
 	 */
 	{
-		struct in6_addr *final_p = NULL, final;
-		struct flowi fl;
-		memset(&fl, 0, sizeof(fl));
-		fl.proto = IPPROTO_TCP;
-		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-		if (np->opt && np->opt->srcrt) {
-			struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
-			ipv6_addr_copy(&final, &fl.fl6_dst);
-			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
-			final_p = &final;
-		}
-		ipv6_addr_copy(&fl.fl6_src, &ireq6->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_sk(sk)->inet_sport;
-		security_req_classify_flow(req, &fl);
-		if (ip6_dst_lookup(sk, &dst, &fl))
-			goto out_free;
-
-		if (final_p)
-			ipv6_addr_copy(&fl.fl6_dst, final_p);
-		if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
+		struct in6_addr *final_p, final;
+		struct flowi6 fl6;
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_TCP;
+		fl6.daddr = ireq->ir_v6_rmt_addr;
+		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		fl6.saddr = ireq->ir_v6_loc_addr;
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+		fl6.flowi6_mark = ireq->ir_mark;
+		fl6.fl6_dport = ireq->ir_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);
+		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);
+				  ireq->wscale_ok, &rcv_wscale,
+				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;