1 files changed, 194 insertions, 105 deletions

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f470fe4511d..c86624b36a6 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -8,10 +8,6 @@
  *      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.
- *
- *  $Id: syncookies.c,v 1.18 2002/02/01 22:01:04 davem Exp $
- *
- *  Missing: IPv6 support.
  */
 
 #include <linux/tcp.h>
@@ -19,28 +15,33 @@
 #include <linux/random.h>
 #include <linux/cryptohash.h>
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <net/tcp.h>
+#include <net/route.h>
 
-extern int sysctl_tcp_syncookies;
+/* Timestamps: lowest bits store TCP options */
+#define TSBITS 6
+#define TSMASK (((__u32)1 << TSBITS) - 1)
 
-static __u32 syncookie_secret[2][16-3+SHA_DIGEST_WORDS];
+extern int sysctl_tcp_syncookies;
 
-static __init int init_syncookies(void)
-{
-	get_random_bytes(syncookie_secret, sizeof(syncookie_secret));
-	return 0;
-}
-module_init(init_syncookies);
+static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
 
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
+		      ipv4_cookie_scratch);
+
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
 {
-	__u32 tmp[16 + 5 + SHA_WORKSPACE_WORDS];
+	__u32 *tmp;
+
+	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
 
-	memcpy(tmp + 3, syncookie_secret[c], sizeof(syncookie_secret[c]));
+	tmp  = __get_cpu_var(ipv4_cookie_scratch);
+	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
 	tmp[0] = (__force u32)saddr;
 	tmp[1] = (__force u32)daddr;
 	tmp[2] = ((__force u32)sport << 16) + (__force u32)dport;
@@ -50,9 +51,40 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 	return tmp[17];
 }
 
+
+/*
+ * when syncookies are in effect and tcp timestamps are enabled we encode
+ * tcp options in the lower bits of the timestamp value that will be
+ * sent in the syn-ack.
+ * Since subsequent timestamps use the normal tcp_time_stamp value, we
+ * must make sure that the resulting initial timestamp is <= tcp_time_stamp.
+ */
+__u32 cookie_init_timestamp(struct request_sock *req)
+{
+	struct inet_request_sock *ireq;
+	u32 ts, ts_now = tcp_time_stamp;
+	u32 options = 0;
+
+	ireq = inet_rsk(req);
+
+	options = ireq->wscale_ok ? ireq->snd_wscale : 0xf;
+	options |= ireq->sack_ok << 4;
+	options |= ireq->ecn_ok << 5;
+
+	ts = ts_now & ~TSMASK;
+	ts |= options;
+	if (ts > ts_now) {
+		ts >>= TSBITS;
+		ts--;
+		ts <<= TSBITS;
+		ts |= options;
+	}
+	return ts;
+}
+
+
 static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
-				   __be16 dport, __u32 sseq, __u32 count,
-				   __u32 data)
+				   __be16 dport, __u32 sseq, __u32 data)
 {
 	/*
 	 * Compute the secure sequence number.
@@ -64,7 +96,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
 	 * As an extra hack, we add a small "data" value that encodes the
 	 * MSS into the second hash value.
 	 */
-
+	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)
@@ -76,22 +108,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
  * If the syncookie is bad, the data returned will be out of
  * range.  This must be checked by the caller.
  *
- * The count value used to generate the cookie must be within
- * "maxdiff" if the current (passed-in) "count".  The return value
- * is (__u32)-1 if this test fails.
+ * The count value used to generate the cookie must be less than
+ * MAX_SYNCOOKIE_AGE minutes in the past.
+ * The return value (__u32)-1 if this test fails.
  */
 static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
-				  __be16 sport, __be16 dport, __u32 sseq,
-				  __u32 count, __u32 maxdiff)
+				  __be16 sport, __be16 dport, __u32 sseq)
 {
-	__u32 diff;
+	u32 diff, count = tcp_cookie_time();
 
 	/* Strip away the layers from the cookie */
 	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
 
 	/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
-	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
-	if (diff >= maxdiff)
+	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
+	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
 	return (cookie -
@@ -100,73 +131,70 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
 }
 
 /*
- * 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.
+ * MSS Values are chosen based on the 2011 paper
+ * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
+ * Values ..
+ *  .. lower than 536 are rare (< 0.2%)
+ *  .. between 537 and 1299 account for less than < 1.5% of observed values
+ *  .. in the 1300-1349 range account for about 15 to 20% of observed mss values
+ *  .. exceeding 1460 are very rare (< 0.04%)
+ *
+ *  1460 is the single most frequently announced mss value (30 to 46% depending
+ *  on monitor location).  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
+	536,
+	1300,
+	1440,	/* 1440, 1452: PPPoE */
+	1460,
 };
-/* The number doesn't include the -1 terminator */
-#define NUM_MSS (ARRAY_SIZE(msstab) - 1)
 
 /*
  * Generate a syncookie.  mssp points to the mss, which is returned
  * rounded down to the value encoded in the cookie.
  */
-__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
+u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
+			      u16 *mssp)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	const struct iphdr *iph = ip_hdr(skb);
-	const struct tcphdr *th = tcp_hdr(skb);
 	int mssind;
 	const __u16 mss = *mssp;
 
-	tp->last_synq_overflow = jiffies;
-
-	/* XXX sort msstab[] by probability?  Binary search? */
-	for (mssind = 0; mss > msstab[mssind + 1]; mssind++)
-		;
-	*mssp = msstab[mssind] + 1;
-
-	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESSENT);
+	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),
-				     jiffies / (HZ * 60), mssind);
+				     mssind);
+}
+EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
+
+__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
+{
+	const struct iphdr *iph = ip_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_v4_init_sequence(iph, th, mssp);
 }
 
-/*
- * 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
 /*
  * Check if a ack sequence number is a valid syncookie.
  * Return the decoded mss if it is, or 0 if not.
  */
-static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
+		      u32 cookie)
 {
-	const struct iphdr *iph = ip_hdr(skb);
-	const struct tcphdr *th = tcp_hdr(skb);
 	__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_v4_check);
 
 static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 					   struct request_sock *req,
@@ -184,9 +212,52 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	return child;
 }
 
+
+/*
+ * when syncookies are in effect and tcp timestamps are enabled we stored
+ * additional tcp options in the timestamp.
+ * This extracts these options from the timestamp echo.
+ *
+ * The lowest 4 bits store snd_wscale.
+ * next 2 bits indicate SACK and ECN support.
+ *
+ * return false if we decode an option that should not be.
+ */
+bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
+			struct net *net, bool *ecn_ok)
+{
+	/* echoed timestamp, lowest bits contain options */
+	u32 options = tcp_opt->rcv_tsecr & TSMASK;
+
+	if (!tcp_opt->saw_tstamp)  {
+		tcp_clear_options(tcp_opt);
+		return true;
+	}
+
+	if (!sysctl_tcp_timestamps)
+		return false;
+
+	tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0;
+	*ecn_ok = (options >> 5) & 1;
+	if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn)
+		return false;
+
+	if (tcp_opt->sack_ok && !sysctl_tcp_sack)
+		return false;
+
+	if ((options & 0xf) == 0xf)
+		return true; /* no window scaling */
+
+	tcp_opt->wscale_ok = 1;
+	tcp_opt->snd_wscale = options & 0xf;
+	return sysctl_tcp_window_scaling != 0;
+}
+EXPORT_SYMBOL(cookie_check_timestamp);
+
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt)
 {
+	struct tcp_options_received tcp_opt;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -197,54 +268,71 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	int mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
+	bool ecn_ok = false;
+	struct flowi4 fl4;
 
-	if (!sysctl_tcp_syncookies || !th->ack)
+	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
 
-	if (time_after(jiffies, tp->last_synq_overflow + TCP_TIMEOUT_INIT) ||
-	    (mss = cookie_check(skb, cookie)) == 0) {
-		NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESFAILED);
+	if (tcp_synq_no_recent_overflow(sk) ||
+	    (mss = __cookie_v4_check(ip_hdr(skb), th, cookie)) == 0) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
 
-	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV);
+	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 = reqsk_alloc(&tcp_request_sock_ops); /* for safety */
+	req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
 	if (!req)
 		goto out;
 
-	if (security_inet_conn_request(sk, skb, req)) {
-		reqsk_free(req);
-		goto out;
-	}
 	ireq = inet_rsk(req);
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	req->mss		= mss;
-	ireq->rmt_port		= th->source;
-	ireq->loc_addr		= ip_hdr(skb)->daddr;
-	ireq->rmt_addr		= ip_hdr(skb)->saddr;
-	ireq->opt		= NULL;
+	ireq->ir_num		= ntohs(th->dest);
+	ireq->ir_rmt_port	= th->source;
+	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
+	ireq->ir_mark		= inet_request_mark(sk, skb);
+	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->listener		= NULL;
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
 	if (opt && opt->optlen) {
-		int opt_size = sizeof(struct ip_options) + opt->optlen;
+		int opt_size = sizeof(struct ip_options_rcu) + opt->optlen;
 
 		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
-		if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) {
+		if (ireq->opt != NULL && ip_options_echo(&ireq->opt->opt, skb)) {
 			kfree(ireq->opt);
 			ireq->opt = NULL;
 		}
 	}
 
-	ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0;
-	ireq->wscale_ok	 = ireq->sack_ok = 0;
+	if (security_inet_conn_request(sk, skb, req)) {
+		reqsk_free(req);
+		goto out;
+	}
+
 	req->expires	= 0UL;
-	req->retrans	= 0;
+	req->num_retrans = 0;
 
 	/*
 	 * We need to lookup the route here to get at the correct
@@ -252,32 +340,33 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	{
-		struct flowi fl = { .nl_u = { .ip4_u =
-					      { .daddr = ((opt && opt->srr) ?
-							  opt->faddr :
-							  ireq->rmt_addr),
-						.saddr = ireq->loc_addr,
-						.tos = RT_CONN_FLAGS(sk) } },
-				    .proto = IPPROTO_TCP,
-				    .uli_u = { .ports =
-					       { .sport = th->dest,
-						 .dport = th->source } } };
-		security_req_classify_flow(req, &fl);
-		if (ip_route_output_key(&init_net, &rt, &fl)) {
-			reqsk_free(req);
-			goto out;
-		}
+	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
+			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+			   inet_sk_flowi_flags(sk),
+			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, th->source, th->dest);
+	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_key(sock_net(sk), &fl4);
+	if (IS_ERR(rt)) {
+		reqsk_free(req);
+		goto out;
 	}
 
 	/* Try to redo what tcp_v4_send_synack did. */
-	req->window_clamp = dst_metric(&rt->u.dst, RTAX_WINDOW);
+	req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+
 	tcp_select_initial_window(tcp_full_space(sk), req->mss,
 				  &req->rcv_wnd, &req->window_clamp,
-				  0, &rcv_wscale);
-	/* BTW win scale with syncookies is 0 by definition */
+				  ireq->wscale_ok, &rcv_wscale,
+				  dst_metric(&rt->dst, RTAX_INITRWND));
+
 	ireq->rcv_wscale  = rcv_wscale;
 
-	ret = get_cookie_sock(sk, skb, req, &rt->u.dst);
+	ret = get_cookie_sock(sk, skb, req, &rt->dst);
+	/* ip_queue_xmit() depends on our flow being setup
+	 * Normal sockets get it right from inet_csk_route_child_sock()
+	 */
+	if (ret)
+		inet_sk(ret)->cork.fl.u.ip4 = fl4;
 out:	return ret;
 }