From a2d91241a80ec9bbc5ab24b9a2c4d730b3fa5730 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 31 Jan 2012 01:04:42 +0000
Subject: tcp: md5: remove obsolete md5_add() method

We no longer use md5_add() method from struct tcp_sock_af_ops

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3edd05ae438..f37769ea637 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -626,13 +626,6 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
 	return 0;
 }
 
-static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk,
-			       u8 *newkey, __u8 newkeylen)
-{
-	return tcp_v6_md5_do_add(sk, &inet6_sk(addr_sk)->daddr,
-				 newkey, newkeylen);
-}
-
 static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1898,7 +1891,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
 static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
 	.md5_lookup	=	tcp_v6_md5_lookup,
 	.calc_md5_hash	=	tcp_v6_md5_hash_skb,
-	.md5_add	=	tcp_v6_md5_add_func,
 	.md5_parse	=	tcp_v6_parse_md5_keys,
 };
 #endif
@@ -1930,7 +1922,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = {
 	.md5_lookup	=	tcp_v4_md5_lookup,
 	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
-	.md5_add	=	tcp_v6_md5_add_func,
 	.md5_parse	=	tcp_v6_parse_md5_keys,
 };
 #endif
-- 
cgit v1.2.3-70-g09d2


From a915da9b69273815527ccb3789421cb7027b545b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 31 Jan 2012 05:18:33 +0000
Subject: tcp: md5: rcu conversion

In order to be able to support proper RST messages for TCP MD5 flows, we
need to allow access to MD5 keys without locking listener socket.

This conversion is a nice cleanup, and shrinks size of timewait sockets
by 80 bytes.

IPv6 code reuses generic code found in IPv4 instead of duplicating it.

Control path uses GFP_KERNEL allocations instead of GFP_ATOMIC.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Shawn Lu <shawn.lu@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |   3 +-
 include/net/tcp.h        |  61 ++++++-------
 net/ipv4/tcp_ipv4.c      | 227 +++++++++++++++++++----------------------------
 net/ipv4/tcp_minisocks.c |  12 +--
 net/ipv6/tcp_ipv6.c      | 173 +++---------------------------------
 5 files changed, 141 insertions(+), 335 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 46a85c9e1f2..c2025f15964 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -486,8 +486,7 @@ struct tcp_timewait_sock {
 	u32			  tw_ts_recent;
 	long			  tw_ts_recent_stamp;
 #ifdef CONFIG_TCP_MD5SIG
-	u16			  tw_md5_keylen;
-	u8			  tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
+	struct tcp_md5sig_key	*tw_md5_key;
 #endif
 	/* Few sockets in timewait have cookies; in that case, then this
 	 * object holds a reference to them (tw_cookie_values->kref).
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3c903462adf..10ae4c7b6b4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1130,35 +1130,26 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
 /* MD5 Signature */
 struct crypto_hash;
 
+union tcp_md5_addr {
+	struct in_addr  a4;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr	a6;
+#endif
+};
+
 /* - key database */
 struct tcp_md5sig_key {
-	u8			*key;
+	struct hlist_node	node;
 	u8			keylen;
-};
-
-struct tcp4_md5sig_key {
-	struct tcp_md5sig_key	base;
-	__be32			addr;
-};
-
-struct tcp6_md5sig_key {
-	struct tcp_md5sig_key	base;
-#if 0
-	u32			scope_id;	/* XXX */
-#endif
-	struct in6_addr		addr;
+	u8			family; /* AF_INET or AF_INET6 */
+	union tcp_md5_addr	addr;
+	u8			key[TCP_MD5SIG_MAXKEYLEN];
+	struct rcu_head		rcu;
 };
 
 /* - sock block */
 struct tcp_md5sig_info {
-	struct tcp4_md5sig_key	*keys4;
-#if IS_ENABLED(CONFIG_IPV6)
-	struct tcp6_md5sig_key	*keys6;
-	u32			entries6;
-	u32			alloced6;
-#endif
-	u32			entries4;
-	u32			alloced4;
+	struct hlist_head	head;
 };
 
 /* - pseudo header */
@@ -1195,19 +1186,25 @@ extern int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 			       const struct sock *sk,
 			       const struct request_sock *req,
 			       const struct sk_buff *skb);
-extern struct tcp_md5sig_key * tcp_v4_md5_lookup(struct sock *sk,
-						 struct sock *addr_sk);
-extern int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, u8 *newkey,
-			     u8 newkeylen);
-extern int tcp_v4_md5_do_del(struct sock *sk, __be32 addr);
+extern int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
+			  int family, const u8 *newkey,
+			  u8 newkeylen, gfp_t gfp);
+extern int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
+			  int family);
+extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+					 struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-#define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_keylen ? 		 \
-				 &(struct tcp_md5sig_key) {		 \
-					.key = (twsk)->tw_md5_key,	 \
-					.keylen = (twsk)->tw_md5_keylen, \
-				} : NULL)
+extern struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+			const union tcp_md5_addr *addr, int family);
+#define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_key)
 #else
+static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+					 const union tcp_md5_addr *addr,
+					 int family)
+{
+	return NULL;
+}
 #define tcp_twsk_md5_key(twsk)	NULL
 #endif
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 345e24928fa..1d5fd82c5c0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -90,16 +90,8 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
 
 #ifdef CONFIG_TCP_MD5SIG
-static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
-						   __be32 addr);
-static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
-#else
-static inline
-struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
-{
-	return NULL;
-}
 #endif
 
 struct inet_hashinfo tcp_hashinfo;
@@ -631,7 +623,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
 #ifdef CONFIG_TCP_MD5SIG
-	key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL;
+	key = sk ? tcp_md5_do_lookup(sk,
+				     (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
+				     AF_INET) : NULL;
 	if (key) {
 		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
 				   (TCPOPT_NOP << 16) |
@@ -759,7 +753,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
 			req->ts_recent,
 			0,
-			tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
+			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+					  AF_INET),
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			ip_hdr(skb)->tos);
 }
@@ -876,146 +871,124 @@ static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk,
  */
 
 /* Find the Key structure for an address.  */
-static struct tcp_md5sig_key *
-			tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
+struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+					 const union tcp_md5_addr *addr,
+					 int family)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int i;
+	struct tcp_md5sig_key *key;
+	struct hlist_node *pos;
+	unsigned int size = sizeof(struct in_addr);
 
-	if (!tp->md5sig_info || !tp->md5sig_info->entries4)
+	if (!tp->md5sig_info)
 		return NULL;
-	for (i = 0; i < tp->md5sig_info->entries4; i++) {
-		if (tp->md5sig_info->keys4[i].addr == addr)
-			return &tp->md5sig_info->keys4[i].base;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == AF_INET6)
+		size = sizeof(struct in6_addr);
+#endif
+	hlist_for_each_entry_rcu(key, pos, &tp->md5sig_info->head, node) {
+		if (key->family != family)
+			continue;
+		if (!memcmp(&key->addr, addr, size))
+			return key;
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(tcp_md5_do_lookup);
 
 struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
 					 struct sock *addr_sk)
 {
-	return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr);
+	union tcp_md5_addr *addr;
+
+	addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr;
+	return tcp_md5_do_lookup(sk, addr, AF_INET);
 }
 EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
 static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
 						      struct request_sock *req)
 {
-	return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
+	union tcp_md5_addr *addr;
+
+	addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr;
+	return tcp_md5_do_lookup(sk, addr, AF_INET);
 }
 
 /* This can be called on a newly created socket, from other files */
-int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
-		      u8 *newkey, u8 newkeylen)
+int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
+		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
 {
 	/* Add Key to the list */
 	struct tcp_md5sig_key *key;
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp4_md5sig_key *keys;
+	struct tcp_md5sig_info *md5sig;
 
-	key = tcp_v4_md5_do_lookup(sk, addr);
+	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
 	if (key) {
 		/* Pre-existing entry - just update that one. */
-		kfree(key->key);
-		key->key = newkey;
+		memcpy(key->key, newkey, newkeylen);
 		key->keylen = newkeylen;
-	} else {
-		struct tcp_md5sig_info *md5sig;
-
-		if (!tp->md5sig_info) {
-			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
-						  GFP_ATOMIC);
-			if (!tp->md5sig_info) {
-				kfree(newkey);
-				return -ENOMEM;
-			}
-			sk_nocaps_add(sk, NETIF_F_GSO_MASK);
-		}
+		return 0;
+	}
 
-		md5sig = tp->md5sig_info;
-		if (md5sig->entries4 == 0 &&
-		    tcp_alloc_md5sig_pool(sk) == NULL) {
-			kfree(newkey);
+	md5sig = tp->md5sig_info;
+	if (!md5sig) {
+		md5sig = kmalloc(sizeof(*md5sig), gfp);
+		if (!md5sig)
 			return -ENOMEM;
-		}
-
-		if (md5sig->alloced4 == md5sig->entries4) {
-			keys = kmalloc((sizeof(*keys) *
-					(md5sig->entries4 + 1)), GFP_ATOMIC);
-			if (!keys) {
-				kfree(newkey);
-				if (md5sig->entries4 == 0)
-					tcp_free_md5sig_pool();
-				return -ENOMEM;
-			}
 
-			if (md5sig->entries4)
-				memcpy(keys, md5sig->keys4,
-				       sizeof(*keys) * md5sig->entries4);
+		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
+		INIT_HLIST_HEAD(&md5sig->head);
+		tp->md5sig_info = md5sig;
+	}
 
-			/* Free old key list, and reference new one */
-			kfree(md5sig->keys4);
-			md5sig->keys4 = keys;
-			md5sig->alloced4++;
-		}
-		md5sig->entries4++;
-		md5sig->keys4[md5sig->entries4 - 1].addr        = addr;
-		md5sig->keys4[md5sig->entries4 - 1].base.key    = newkey;
-		md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen;
+	key = kmalloc(sizeof(*key), gfp);
+	if (!key)
+		return -ENOMEM;
+	if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) {
+		kfree(key);
+		return -ENOMEM;
 	}
+
+	memcpy(key->key, newkey, newkeylen);
+	key->keylen = newkeylen;
+	key->family = family;
+	memcpy(&key->addr, addr,
+	       (family == AF_INET6) ? sizeof(struct in6_addr) :
+				      sizeof(struct in_addr));
+	hlist_add_head_rcu(&key->node, &md5sig->head);
 	return 0;
 }
-EXPORT_SYMBOL(tcp_v4_md5_do_add);
+EXPORT_SYMBOL(tcp_md5_do_add);
 
-int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
+int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int i;
-
-	for (i = 0; i < tp->md5sig_info->entries4; i++) {
-		if (tp->md5sig_info->keys4[i].addr == addr) {
-			/* Free the key */
-			kfree(tp->md5sig_info->keys4[i].base.key);
-			tp->md5sig_info->entries4--;
-
-			if (tp->md5sig_info->entries4 == 0) {
-				kfree(tp->md5sig_info->keys4);
-				tp->md5sig_info->keys4 = NULL;
-				tp->md5sig_info->alloced4 = 0;
-				tcp_free_md5sig_pool();
-			} else if (tp->md5sig_info->entries4 != i) {
-				/* Need to do some manipulation */
-				memmove(&tp->md5sig_info->keys4[i],
-					&tp->md5sig_info->keys4[i+1],
-					(tp->md5sig_info->entries4 - i) *
-					 sizeof(struct tcp4_md5sig_key));
-			}
-			return 0;
-		}
-	}
-	return -ENOENT;
+	struct tcp_md5sig_key *key;
+
+	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
+	if (!key)
+		return -ENOENT;
+	hlist_del_rcu(&key->node);
+	kfree_rcu(key, rcu);
+	if (hlist_empty(&tp->md5sig_info->head))
+		tcp_free_md5sig_pool();
+	return 0;
 }
-EXPORT_SYMBOL(tcp_v4_md5_do_del);
+EXPORT_SYMBOL(tcp_md5_do_del);
 
-static void tcp_v4_clear_md5_list(struct sock *sk)
+void tcp_clear_md5_list(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_md5sig_key *key;
+	struct hlist_node *pos, *n;
 
-	/* Free each key, then the set of key keys,
-	 * the crypto element, and then decrement our
-	 * hold on the last resort crypto.
-	 */
-	if (tp->md5sig_info->entries4) {
-		int i;
-		for (i = 0; i < tp->md5sig_info->entries4; i++)
-			kfree(tp->md5sig_info->keys4[i].base.key);
-		tp->md5sig_info->entries4 = 0;
+	if (!hlist_empty(&tp->md5sig_info->head))
 		tcp_free_md5sig_pool();
-	}
-	if (tp->md5sig_info->keys4) {
-		kfree(tp->md5sig_info->keys4);
-		tp->md5sig_info->keys4 = NULL;
-		tp->md5sig_info->alloced4  = 0;
+	hlist_for_each_entry_safe(key, pos, n, &tp->md5sig_info->head, node) {
+		hlist_del_rcu(&key->node);
+		kfree_rcu(key, rcu);
 	}
 }
 
@@ -1024,7 +997,6 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 {
 	struct tcp_md5sig cmd;
 	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
-	u8 *newkey;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -1038,29 +1010,16 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 	if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
 		if (!tcp_sk(sk)->md5sig_info)
 			return -ENOENT;
-		return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
+		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
+				      AF_INET);
 	}
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
 
-	if (!tcp_sk(sk)->md5sig_info) {
-		struct tcp_sock *tp = tcp_sk(sk);
-		struct tcp_md5sig_info *p;
-
-		p = kzalloc(sizeof(*p), sk->sk_allocation);
-		if (!p)
-			return -EINVAL;
-
-		tp->md5sig_info = p;
-		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
-	}
-
-	newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation);
-	if (!newkey)
-		return -ENOMEM;
-	return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr,
-				 newkey, cmd.tcpm_keylen);
+	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
+			      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
+			      GFP_KERNEL);
 }
 
 static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
@@ -1086,7 +1045,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 	return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
 }
 
-static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th)
 {
 	struct tcp_md5sig_pool *hp;
@@ -1186,7 +1145,8 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
 	int genhash;
 	unsigned char newhash[16];
 
-	hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
+	hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr,
+					  AF_INET);
 	hash_location = tcp_parse_md5sig_option(th);
 
 	/* We've parsed the options - do we have a hash? */
@@ -1474,7 +1434,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Copy over the MD5 key from the original socket */
-	key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
+	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
+				AF_INET);
 	if (key != NULL) {
 		/*
 		 * We're using one, so create a matching key
@@ -1482,10 +1443,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
-		if (newkey != NULL)
-			tcp_v4_md5_do_add(newsk, newinet->inet_daddr,
-					  newkey, key->keylen);
+		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
+			       AF_INET, key->key, key->keylen, GFP_ATOMIC);
 		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
 	}
 #endif
@@ -1934,7 +1893,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 #ifdef CONFIG_TCP_MD5SIG
 	/* Clean up the MD5 key list, if any */
 	if (tp->md5sig_info) {
-		tcp_v4_clear_md5_list(sk);
+		tcp_clear_md5_list(sk);
 		kfree(tp->md5sig_info);
 		tp->md5sig_info = NULL;
 	}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 550e755747e..3cabafb5cdd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -359,13 +359,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		 */
 		do {
 			struct tcp_md5sig_key *key;
-			memset(tcptw->tw_md5_key, 0, sizeof(tcptw->tw_md5_key));
-			tcptw->tw_md5_keylen = 0;
+			tcptw->tw_md5_key = NULL;
 			key = tp->af_specific->md5_lookup(sk, sk);
 			if (key != NULL) {
-				memcpy(&tcptw->tw_md5_key, key->key, key->keylen);
-				tcptw->tw_md5_keylen = key->keylen;
-				if (tcp_alloc_md5sig_pool(sk) == NULL)
+				tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
+				if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL)
 					BUG();
 			}
 		} while (0);
@@ -405,8 +403,10 @@ void tcp_twsk_destructor(struct sock *sk)
 {
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_timewait_sock *twsk = tcp_twsk(sk);
-	if (twsk->tw_md5_keylen)
+	if (twsk->tw_md5_key) {
 		tcp_free_md5sig_pool();
+		kfree_rcu(twsk->tw_md5_key, rcu);
+	}
 #endif
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f37769ea637..bec41f9a641 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -540,19 +540,7 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req)
 static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 						   const struct in6_addr *addr)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	int i;
-
-	BUG_ON(tp == NULL);
-
-	if (!tp->md5sig_info || !tp->md5sig_info->entries6)
-		return NULL;
-
-	for (i = 0; i < tp->md5sig_info->entries6; i++) {
-		if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, addr))
-			return &tp->md5sig_info->keys6[i].base;
-	}
-	return NULL;
+	return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6);
 }
 
 static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
@@ -567,129 +555,11 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
 	return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr);
 }
 
-static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
-			     char *newkey, u8 newkeylen)
-{
-	/* Add key to the list */
-	struct tcp_md5sig_key *key;
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp6_md5sig_key *keys;
-
-	key = tcp_v6_md5_do_lookup(sk, peer);
-	if (key) {
-		/* modify existing entry - just update that one */
-		kfree(key->key);
-		key->key = newkey;
-		key->keylen = newkeylen;
-	} else {
-		/* reallocate new list if current one is full. */
-		if (!tp->md5sig_info) {
-			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC);
-			if (!tp->md5sig_info) {
-				kfree(newkey);
-				return -ENOMEM;
-			}
-			sk_nocaps_add(sk, NETIF_F_GSO_MASK);
-		}
-		if (tp->md5sig_info->entries6 == 0 &&
-			tcp_alloc_md5sig_pool(sk) == NULL) {
-			kfree(newkey);
-			return -ENOMEM;
-		}
-		if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) {
-			keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) *
-				       (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC);
-
-			if (!keys) {
-				kfree(newkey);
-				if (tp->md5sig_info->entries6 == 0)
-					tcp_free_md5sig_pool();
-				return -ENOMEM;
-			}
-
-			if (tp->md5sig_info->entries6)
-				memmove(keys, tp->md5sig_info->keys6,
-					(sizeof (tp->md5sig_info->keys6[0]) *
-					 tp->md5sig_info->entries6));
-
-			kfree(tp->md5sig_info->keys6);
-			tp->md5sig_info->keys6 = keys;
-			tp->md5sig_info->alloced6++;
-		}
-
-		tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer;
-		tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey;
-		tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen;
-
-		tp->md5sig_info->entries6++;
-	}
-	return 0;
-}
-
-static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int i;
-
-	for (i = 0; i < tp->md5sig_info->entries6; i++) {
-		if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, peer)) {
-			/* Free the key */
-			kfree(tp->md5sig_info->keys6[i].base.key);
-			tp->md5sig_info->entries6--;
-
-			if (tp->md5sig_info->entries6 == 0) {
-				kfree(tp->md5sig_info->keys6);
-				tp->md5sig_info->keys6 = NULL;
-				tp->md5sig_info->alloced6 = 0;
-				tcp_free_md5sig_pool();
-			} else {
-				/* shrink the database */
-				if (tp->md5sig_info->entries6 != i)
-					memmove(&tp->md5sig_info->keys6[i],
-						&tp->md5sig_info->keys6[i+1],
-						(tp->md5sig_info->entries6 - i)
-						* sizeof (tp->md5sig_info->keys6[0]));
-			}
-			return 0;
-		}
-	}
-	return -ENOENT;
-}
-
-static void tcp_v6_clear_md5_list (struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int i;
-
-	if (tp->md5sig_info->entries6) {
-		for (i = 0; i < tp->md5sig_info->entries6; i++)
-			kfree(tp->md5sig_info->keys6[i].base.key);
-		tp->md5sig_info->entries6 = 0;
-		tcp_free_md5sig_pool();
-	}
-
-	kfree(tp->md5sig_info->keys6);
-	tp->md5sig_info->keys6 = NULL;
-	tp->md5sig_info->alloced6 = 0;
-
-	if (tp->md5sig_info->entries4) {
-		for (i = 0; i < tp->md5sig_info->entries4; i++)
-			kfree(tp->md5sig_info->keys4[i].base.key);
-		tp->md5sig_info->entries4 = 0;
-		tcp_free_md5sig_pool();
-	}
-
-	kfree(tp->md5sig_info->keys4);
-	tp->md5sig_info->keys4 = NULL;
-	tp->md5sig_info->alloced4 = 0;
-}
-
 static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
 				  int optlen)
 {
 	struct tcp_md5sig cmd;
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
-	u8 *newkey;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -704,33 +574,21 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
 		if (!tcp_sk(sk)->md5sig_info)
 			return -ENOENT;
 		if (ipv6_addr_v4mapped(&sin6->sin6_addr))
-			return tcp_v4_md5_do_del(sk, sin6->sin6_addr.s6_addr32[3]);
-		return tcp_v6_md5_do_del(sk, &sin6->sin6_addr);
+			return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
+					      AF_INET);
+		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
+				      AF_INET6);
 	}
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
 
-	if (!tcp_sk(sk)->md5sig_info) {
-		struct tcp_sock *tp = tcp_sk(sk);
-		struct tcp_md5sig_info *p;
-
-		p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-
-		tp->md5sig_info = p;
-		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
-	}
+	if (ipv6_addr_v4mapped(&sin6->sin6_addr))
+		return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
+				      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 
-	newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
-	if (!newkey)
-		return -ENOMEM;
-	if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
-		return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3],
-					 newkey, cmd.tcpm_keylen);
-	}
-	return tcp_v6_md5_do_add(sk, &sin6->sin6_addr, newkey, cmd.tcpm_keylen);
+	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
+			      AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
 static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
@@ -1503,10 +1361,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
-		if (newkey != NULL)
-			tcp_v6_md5_do_add(newsk, &newnp->daddr,
-					  newkey, key->keylen);
+		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr,
+			       AF_INET6, key->key, key->keylen, GFP_ATOMIC);
 	}
 #endif
 
@@ -1995,11 +1851,6 @@ static int tcp_v6_init_sock(struct sock *sk)
 
 static void tcp_v6_destroy_sock(struct sock *sk)
 {
-#ifdef CONFIG_TCP_MD5SIG
-	/* Clean up the MD5 key list */
-	if (tcp_sk(sk)->md5sig_info)
-		tcp_v6_clear_md5_list(sk);
-#endif
 	tcp_v4_destroy_sock(sk);
 	inet6_destroy_sock(sk);
 }
-- 
cgit v1.2.3-70-g09d2


From a8afca032998850ec63e83d555cdcf0eb5680cd6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 31 Jan 2012 18:45:40 +0000
Subject: tcp: md5: protects md5sig_info with RCU

This patch makes sure we use appropriate memory barriers before
publishing tp->md5sig_info, allowing tcp_md5_do_lookup() being used from
tcp_v4_send_reset() without holding socket lock (upcoming patch from
Shawn Lu)

Note we also need to respect rcu grace period before its freeing, since
we can free socket without this grace period thanks to
SLAB_DESTROY_BY_RCU

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Shawn Lu <shawn.lu@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h |  2 +-
 include/net/tcp.h   |  1 +
 net/ipv4/tcp_ipv4.c | 32 ++++++++++++++++++++------------
 net/ipv6/tcp_ipv6.c |  2 --
 4 files changed, 22 insertions(+), 15 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index c2025f15964..115389e9b94 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -463,7 +463,7 @@ struct tcp_sock {
 	const struct tcp_sock_af_ops	*af_specific;
 
 /* TCP MD5 Signature Option information */
-	struct tcp_md5sig_info	*md5sig_info;
+	struct tcp_md5sig_info	__rcu *md5sig_info;
 #endif
 
 	/* When the cookie options are generated and exchanged, then this
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 10ae4c7b6b4..78880ba0f56 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1150,6 +1150,7 @@ struct tcp_md5sig_key {
 /* - sock block */
 struct tcp_md5sig_info {
 	struct hlist_head	head;
+	struct rcu_head		rcu;
 };
 
 /* - pseudo header */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index da5d3226771..567cca9b30d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -879,14 +879,18 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 	struct tcp_md5sig_key *key;
 	struct hlist_node *pos;
 	unsigned int size = sizeof(struct in_addr);
+	struct tcp_md5sig_info *md5sig;
 
-	if (!tp->md5sig_info)
+	/* caller either holds rcu_read_lock() or socket lock */
+	md5sig = rcu_dereference_check(tp->md5sig_info,
+				       sock_owned_by_user(sk));
+	if (!md5sig)
 		return NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (family == AF_INET6)
 		size = sizeof(struct in6_addr);
 #endif
-	hlist_for_each_entry_rcu(key, pos, &tp->md5sig_info->head, node) {
+	hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) {
 		if (key->family != family)
 			continue;
 		if (!memcmp(&key->addr, addr, size))
@@ -932,7 +936,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		return 0;
 	}
 
-	md5sig = tp->md5sig_info;
+	md5sig = rcu_dereference_protected(tp->md5sig_info,
+					   sock_owned_by_user(sk));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
@@ -940,7 +945,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 		sk_nocaps_add(sk, NETIF_F_GSO_MASK);
 		INIT_HLIST_HEAD(&md5sig->head);
-		tp->md5sig_info = md5sig;
+		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
 	key = sock_kmalloc(sk, sizeof(*key), gfp);
@@ -966,6 +971,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
+	struct tcp_md5sig_info *md5sig;
 
 	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
 	if (!key)
@@ -973,7 +979,9 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
 	hlist_del_rcu(&key->node);
 	atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
 	kfree_rcu(key, rcu);
-	if (hlist_empty(&tp->md5sig_info->head))
+	md5sig = rcu_dereference_protected(tp->md5sig_info,
+					   sock_owned_by_user(sk));
+	if (hlist_empty(&md5sig->head))
 		tcp_free_md5sig_pool();
 	return 0;
 }
@@ -984,10 +992,13 @@ void tcp_clear_md5_list(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
 	struct hlist_node *pos, *n;
+	struct tcp_md5sig_info *md5sig;
 
-	if (!hlist_empty(&tp->md5sig_info->head))
+	md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
+
+	if (!hlist_empty(&md5sig->head))
 		tcp_free_md5sig_pool();
-	hlist_for_each_entry_safe(key, pos, n, &tp->md5sig_info->head, node) {
+	hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) {
 		hlist_del_rcu(&key->node);
 		atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
 		kfree_rcu(key, rcu);
@@ -1009,12 +1020,9 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 	if (sin->sin_family != AF_INET)
 		return -EINVAL;
 
-	if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
-		if (!tcp_sk(sk)->md5sig_info)
-			return -ENOENT;
+	if (!cmd.tcpm_key || !cmd.tcpm_keylen)
 		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
 				      AF_INET);
-	}
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
@@ -1896,7 +1904,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	/* Clean up the MD5 key list, if any */
 	if (tp->md5sig_info) {
 		tcp_clear_md5_list(sk);
-		kfree(tp->md5sig_info);
+		kfree_rcu(tp->md5sig_info, rcu);
 		tp->md5sig_info = NULL;
 	}
 #endif
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bec41f9a641..c25018106ef 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -571,8 +571,6 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
 		return -EINVAL;
 
 	if (!cmd.tcpm_keylen) {
-		if (!tcp_sk(sk)->md5sig_info)
-			return -ENOENT;
 		if (ipv6_addr_v4mapped(&sin6->sin6_addr))
 			return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
 					      AF_INET);
-- 
cgit v1.2.3-70-g09d2


From 658ddaaf6694adf63f67451dec9ddeb87a7cb2d7 Mon Sep 17 00:00:00 2001
From: Shawn Lu <shawn.lu@ericsson.com>
Date: Tue, 31 Jan 2012 22:35:48 +0000
Subject: tcp: md5: RST: getting md5 key from listener

TCP RST mechanism is broken in TCP md5(RFC2385). When
connection is gone, md5 key is lost, sending RST
without md5 hash is deem to ignored by peer. This can
be a problem since RST help protocal like bgp to fast
recove from peer crash.

In most case, users of tcp md5, such as bgp and ldp,
have listener on both sides to accept connection from peer.
md5 keys for peers are saved in listening socket.

There are two cases in finding md5 key when connection is
lost:
1.Passive receive RST: The message is send to well known port,
tcp will associate it with listner. md5 key is gotten from
listener.

2.Active receive RST (no sock): The message is send to ative
side, there is no socket associated with the message. In this
case, finding listener from source port, then find md5 key from
listener.

we are not loosing sercuriy here:
packet is checked with md5 hash. No RST is generated
if md5 hash doesn't match or no md5 key can be found.

Signed-off-by: Shawn Lu <shawn.lu@ericsson.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 45 ++++++++++++++++++++++++++++++++++++++++++---
 net/ipv6/tcp_ipv6.c | 43 +++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 83 insertions(+), 5 deletions(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 567cca9b30d..90e47931e21 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -593,6 +593,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	struct ip_reply_arg arg;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key *key;
+	const __u8 *hash_location = NULL;
+	unsigned char newhash[16];
+	int genhash;
+	struct sock *sk1 = NULL;
 #endif
 	struct net *net;
 
@@ -623,9 +627,36 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
 #ifdef CONFIG_TCP_MD5SIG
-	key = sk ? tcp_md5_do_lookup(sk,
-				     (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
-				     AF_INET) : NULL;
+	hash_location = tcp_parse_md5sig_option(th);
+	if (!sk && hash_location) {
+		/*
+		 * active side is lost. Try to find listening socket through
+		 * source port, and then find md5 key through listening socket.
+		 * we are not loose security here:
+		 * Incoming packet is checked with md5 hash with finding key,
+		 * no RST generated if md5 hash doesn't match.
+		 */
+		sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev),
+					     &tcp_hashinfo, ip_hdr(skb)->daddr,
+					     ntohs(th->source), inet_iif(skb));
+		/* don't send rst if it can't find key */
+		if (!sk1)
+			return;
+		rcu_read_lock();
+		key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *)
+					&ip_hdr(skb)->saddr, AF_INET);
+		if (!key)
+			goto release_sk1;
+
+		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb);
+		if (genhash || memcmp(hash_location, newhash, 16) != 0)
+			goto release_sk1;
+	} else {
+		key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
+					     &ip_hdr(skb)->saddr,
+					     AF_INET) : NULL;
+	}
+
 	if (key) {
 		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
 				   (TCPOPT_NOP << 16) |
@@ -653,6 +684,14 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
+
+#ifdef CONFIG_TCP_MD5SIG
+release_sk1:
+	if (sk1) {
+		rcu_read_unlock();
+		sock_put(sk1);
+	}
+#endif
 }
 
 /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c25018106ef..d16414cb342 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -923,6 +923,13 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	const struct tcphdr *th = tcp_hdr(skb);
 	u32 seq = 0, ack_seq = 0;
 	struct tcp_md5sig_key *key = NULL;
+#ifdef CONFIG_TCP_MD5SIG
+	const __u8 *hash_location = NULL;
+	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	unsigned char newhash[16];
+	int genhash;
+	struct sock *sk1 = NULL;
+#endif
 
 	if (th->rst)
 		return;
@@ -931,8 +938,32 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		return;
 
 #ifdef CONFIG_TCP_MD5SIG
-	if (sk)
-		key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr);
+	hash_location = tcp_parse_md5sig_option(th);
+	if (!sk && hash_location) {
+		/*
+		 * active side is lost. Try to find listening socket through
+		 * source port, and then find md5 key through listening socket.
+		 * we are not loose security here:
+		 * Incoming packet is checked with md5 hash with finding key,
+		 * no RST generated if md5 hash doesn't match.
+		 */
+		sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
+					   &tcp_hashinfo, &ipv6h->daddr,
+					   ntohs(th->source), inet6_iif(skb));
+		if (!sk1)
+			return;
+
+		rcu_read_lock();
+		key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
+		if (!key)
+			goto release_sk1;
+
+		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb);
+		if (genhash || memcmp(hash_location, newhash, 16) != 0)
+			goto release_sk1;
+	} else {
+		key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL;
+	}
 #endif
 
 	if (th->ack)
@@ -942,6 +973,14 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 			  (th->doff << 2);
 
 	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1, 0);
+
+#ifdef CONFIG_TCP_MD5SIG
+release_sk1:
+	if (sk1) {
+		rcu_read_unlock();
+		sock_put(sk1);
+	}
+#endif
 }
 
 static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts,
-- 
cgit v1.2.3-70-g09d2


From 4c507d2897bd9be810b3403ade73b04cf6fdfd4a Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Thu, 9 Feb 2012 09:35:49 +0000
Subject: net: implement IP_RECVTOS for IP_PKTOPTIONS

Currently, it is not easily possible to get TOS/DSCP value of packets from
an incoming TCP stream. The mechanism is there, IP_PKTOPTIONS getsockopt
with IP_RECVTOS set, the same way as incoming TTL can be queried. This is
not actually implemented for TOS, though.

This patch adds this functionality, both for IPv4 (IP_PKTOPTIONS) and IPv6
(IPV6_2292PKTOPTIONS). For IPv4, like in the IP_RECVTTL case, the value of
the TOS field is stored from the other party's ACK.

This is needed for proxies which require DSCP transparency. One such example
is at http://zph.bratcheda.org/.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h     | 2 +-
 include/net/inet_sock.h  | 1 +
 net/ipv4/af_inet.c       | 1 +
 net/ipv4/ip_sockglue.c   | 4 ++++
 net/ipv4/tcp_ipv4.c      | 1 +
 net/ipv6/af_inet6.c      | 1 +
 net/ipv6/ipv6_sockglue.c | 4 ++++
 net/ipv6/tcp_ipv6.c      | 4 ++++
 8 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'net/ipv6/tcp_ipv6.c')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 4847a64d3c0..8260ef77976 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -366,7 +366,7 @@ struct ipv6_pinfo {
 				dontfrag:1;
 	__u8			min_hopcount;
 	__u8			tclass;
-	__u8			padding;
+	__u8			rcv_tclass;
 
 	__u32			dst_cookie;
 
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 022f772c0eb..ae17e1352d7 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -168,6 +168,7 @@ struct inet_sock {
 				transparent:1,
 				mc_all:1,
 				nodefrag:1;
+	__u8			rcv_tos;
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f7b5670744f..e588a34e85c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -381,6 +381,7 @@ lookup_protocol:
 	inet->mc_all	= 1;
 	inet->mc_index	= 0;
 	inet->mc_list	= NULL;
+	inet->rcv_tos	= 0;
 
 	sk_refcnt_debug_inc(sk);
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9125529dab9..ca50d9f9f8c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1289,6 +1289,10 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			int hlim = inet->mc_ttl;
 			put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
 		}
+		if (inet->cmsg_flags & IP_CMSG_TOS) {
+			int tos = inet->rcv_tos;
+			put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
+		}
 		len -= msg.msg_controllen;
 		return put_user(len, optlen);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4d6f81c818d..94abee8cf56 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1463,6 +1463,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	ireq->opt	      = NULL;
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
+	newinet->rcv_tos      = ip_hdr(skb)->tos;
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 273f48d1df2..5605f9dca87 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -214,6 +214,7 @@ lookup_protocol:
 	inet->mc_ttl	= 1;
 	inet->mc_index	= 0;
 	inet->mc_list	= NULL;
+	inet->rcv_tos	= 0;
 
 	if (ipv4_config.no_pmtu_disc)
 		inet->pmtudisc = IP_PMTUDISC_DONT;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 6d6b65fdaa1..63dd1f89ed7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1017,6 +1017,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				int hlim = np->mcast_hops;
 				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
 			}
+			if (np->rxopt.bits.rxtclass) {
+				int tclass = np->rcv_tclass;
+				put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
+			}
 			if (np->rxopt.bits.rxoinfo) {
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d16414cb342..12c6ece67f3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1282,6 +1282,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->opt	   = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
+		newnp->rcv_tclass  = ipv6_tclass(ipv6_hdr(skb));
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1360,6 +1361,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
+	newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb));
 
 	/* Clone native IPv6 options from listening socket (if any)
 
@@ -1562,6 +1564,8 @@ ipv6_pktoptions:
 			np->mcast_oif = inet6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
+		if (np->rxopt.bits.rxtclass)
+			np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb));
 		if (ipv6_opt_accepted(sk, opt_skb)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
-- 
cgit v1.2.3-70-g09d2