tcp: Initial support for RFC5925 auth option

index a9fbe22732c3..551942883f06 100644
@@ -170,10 +170,12 @@ struct tcp_request_sock {
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 {
 	return (struct tcp_request_sock *)req;
 }
 
+struct tcp_authopt_info;
+
 struct tcp_sock {
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
 	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
 	u16	gso_segs;	/* Max number of segs per GSO packet	*/

@@ -434,10 +436,14 @@ struct tcp_sock {
 
 /* TCP MD5 Signature Option information */
 	struct tcp_md5sig_info	__rcu *md5sig_info;
 #endif
 
+#ifdef CONFIG_TCP_AUTHOPT
+	struct tcp_authopt_info	__rcu *authopt_info;
+#endif
+
 /* TCP fastopen related information */
 	struct tcp_fastopen_request *fastopen_req;
 	/* fastopen_rsk points to request_sock that resulted in this big
 	 * socket. Used to retransmit SYNACKs etc.
 	 */

@@ -484,10 +490,13 @@ struct tcp_timewait_sock {
 	int			  tw_ts_recent_stamp;
 	u32			  tw_tx_delay;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	  *tw_md5_key;
 #endif
+#ifdef CONFIG_TCP_AUTHOPT
+	struct tcp_authopt_info	  *tw_authopt_info;
+#endif
 };
 
 static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
 {
 	return (struct tcp_timewait_sock *)sk;

index 8c3587d5c308..30964366951d 100644
@@ -35,10 +35,11 @@
 #include <net/netns/can.h>
 #include <net/netns/xdp.h>
 #include <net/netns/smc.h>
 #include <net/netns/bpf.h>
 #include <net/netns/mctp.h>
+#include <net/netns/tcp_authopt.h>
 #include <net/net_trackers.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
 #include <linux/notifier.h>

@@ -184,10 +185,13 @@ struct net {
 #endif
 	struct sock		*diag_nlsk;
 #if IS_ENABLED(CONFIG_SMC)
 	struct netns_smc	smc;
 #endif
+#if IS_ENABLED(CONFIG_TCP_AUTHOPT)
+	struct netns_tcp_authopt	tcp_authopt;
+#endif
 } __randomize_layout;
 
 #include <linux/seq_file_net.h>
 
 /* Init's network namespace */

new file mode 100644
index 000000000000..03b7f4e58448
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NETNS_TCP_AUTHOPT_H__
+#define __NETNS_TCP_AUTHOPT_H__
+
+#include <linux/mutex.h>
+
+struct netns_tcp_authopt {
+	struct hlist_head head;
+	struct mutex mutex;
+};
+
+#endif /* __NETNS_TCP_AUTHOPT_H__ */

index d10962b9f0d0..9955a88faf9b 100644
@@ -184,10 +184,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_WINDOW		3	/* Window scaling */
 #define TCPOPT_SACK_PERM        4       /* SACK Permitted */
 #define TCPOPT_SACK             5       /* SACK Block */
 #define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
 #define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
+#define TCPOPT_AUTHOPT		29	/* Auth Option (RFC5925) */
 #define TCPOPT_MPTCP		30	/* Multipath TCP (RFC6824) */
 #define TCPOPT_FASTOPEN		34	/* Fast open (RFC7413) */
 #define TCPOPT_EXP		254	/* Experimental */
 /* Magic number to be after the option value for sharing TCP
  * experimental options. See draft-ietf-tcpm-experimental-options-00.txt

70 lines not on this page · raw message

101 lines not on this page · raw message

index 970e9a2cca4a..1e9eaf805e4c 100644
@@ -270,10 +270,11 @@
 
 #include <net/icmp.h>
 #include <net/inet_common.h>
 #include <net/tcp.h>
 #include <net/mptcp.h>
+#include <net/tcp_authopt.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
 #include <net/sock.h>
 
 #include <linux/uaccess.h>

@@ -3706,10 +3707,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
 		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
+#endif
+#ifdef CONFIG_TCP_AUTHOPT
+	case TCP_AUTHOPT:
+		err = tcp_set_authopt(sk, optval, optlen);
+		break;
+	case TCP_AUTHOPT_KEY:
+		err = tcp_set_authopt_key(sk, optval, optlen);
+		break;
 #endif
 	case TCP_USER_TIMEOUT:
 		/* Cap the max time in ms TCP will retry or probe the window
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */

@@ -4357,10 +4366,33 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		if (!err && copy_to_user(optval, &zc, len))
 			err = -EFAULT;
 		return err;
 	}
 #endif
+#ifdef CONFIG_TCP_AUTHOPT
+	case TCP_AUTHOPT: {
+		struct tcp_authopt info;
+		int err;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		lock_sock(sk);
+		err = tcp_get_authopt_val(sk, &info);
+		release_sock(sk);
+
+		if (err)
+			return err;
+		len = min_t(unsigned int, len, sizeof(info));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &info, len))
+			return -EFAULT;
+		return 0;
+	}
+#endif
+
 	default:
 		return -ENOPROTOOPT;
 	}
 
 	if (put_user(len, optlen))

317 lines not on this page · raw message

index 0c83780dc9bf..e8b2ab088828 100644
@@ -60,10 +60,11 @@
 
 #include <net/net_namespace.h>
 #include <net/icmp.h>
 #include <net/inet_hashtables.h>
 #include <net/tcp.h>
+#include <net/tcp_authopt.h>
 #include <net/transp_v6.h>
 #include <net/ipv6.h>
 #include <net/inet_common.h>
 #include <net/timewait_sock.h>
 #include <net/xfrm.h>

@@ -2248,10 +2249,11 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		tcp_clear_md5_list(sk);
 		kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu);
 		tp->md5sig_info = NULL;
 	}
 #endif
+	tcp_authopt_clear(sk);
 
 	/* Clean up a referenced TCP bind bucket. */
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 

index bc2cff82830d..ed9995c8d486 100644
@@ -4,10 +4,24 @@
 
 #include <uapi/linux/tcp.h>
 #include <net/netns/tcp_authopt.h>
 #include <linux/tcp.h>
 
+/* According to RFC5925 the length of the authentication option varies based on
+ * the signature algorithm. Linux only implements the algorithms defined in
+ * RFC5926 which have a constant length of 16.
+ *
+ * This is used in stack allocation of tcp option buffers for output. It is
+ * shorter than the length of the MD5 option.
+ *
+ * Input packets can have authentication options of different lengths but they
+ * will always be flagged as invalid (since no such algorithms are supported).
+ */
+#define TCPOLEN_AUTHOPT_OUTPUT	16
+
+struct tcp_authopt_alg_imp;
+
 /**
  * struct tcp_authopt_key_info - Representation of a Master Key Tuple as per RFC5925
  *
  * Key structure lifetime is protected by RCU so send/recv code needs to hold a
  * single rcu_read_lock until they're done with the key.

@@ -33,10 +47,12 @@ struct tcp_authopt_key_info {
 	u8 keylen;
 	/** @key: Same as &tcp_authopt_key.key */
 	u8 key[TCP_AUTHOPT_MAXKEYLEN];
 	/** @addr: Same as &tcp_authopt_key.addr */
 	struct sockaddr_storage addr;
+	/** @alg: Algorithm implementation matching alg_id */
+	struct tcp_authopt_alg_imp *alg;
 };
 
 /**
  * struct tcp_authopt_info - Per-socket information regarding tcp_authopt
  *

254 lines not on this page · raw message

index 9955a88faf9b..fbe18b5bf576 100644
@@ -1718,11 +1718,11 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void);
 static inline void tcp_put_md5sig_pool(void)
 {
 	local_bh_enable();
 }
 
-int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *,
+int tcp_sig_hash_skb_data(struct ahash_request *, const struct sk_buff *,
 			  unsigned int header_len);
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
 		     const struct tcp_md5sig_key *key);
 
 /* From tcp_fastopen.c */

index 1e9eaf805e4c..4c61c32ccf49 100644
@@ -4508,16 +4508,19 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	local_bh_enable();
 	return NULL;
 }
 EXPORT_SYMBOL(tcp_get_md5sig_pool);
 
-int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
+#endif /* CONFIG_TCP_MD5SIG */
+
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
+
+int tcp_sig_hash_skb_data(struct ahash_request *req,
 			  const struct sk_buff *skb, unsigned int header_len)
 {
 	struct scatterlist sg;
 	const struct tcphdr *tp = tcp_hdr(skb);
-	struct ahash_request *req = hp->md5_req;
 	unsigned int i;
 	const unsigned int head_data_len = skb_headlen(skb) > header_len ?
 					   skb_headlen(skb) - header_len : 0;
 	const struct skb_shared_info *shi = skb_shinfo(skb);
 	struct sk_buff *frag_iter;

@@ -4540,16 +4543,20 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 		if (crypto_ahash_update(req))
 			return 1;
 	}
 
 	skb_walk_frags(skb, frag_iter)
-		if (tcp_md5_hash_skb_data(hp, frag_iter, 0))
+		if (tcp_sig_hash_skb_data(req, frag_iter, 0))
 			return 1;
 
 	return 0;
 }
-EXPORT_SYMBOL(tcp_md5_hash_skb_data);
+EXPORT_SYMBOL(tcp_sig_hash_skb_data);
+
+#endif /* defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT) */
+
+#ifdef CONFIG_TCP_MD5SIG
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
 	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;

@@ -4636,11 +4643,11 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 	}
 	return SKB_NOT_DROPPED_YET;
 }
 EXPORT_SYMBOL(tcp_inbound_md5_hash);
 
-#endif
+#endif /* CONFIG_TCP_MD5SIG */
 
 void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
 

index e8b2ab088828..46ba754afd2b 100644
@@ -1388,11 +1388,11 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 	if (crypto_ahash_init(req))
 		goto clear_hash;
 
 	if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len))
 		goto clear_hash;
-	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
+	if (tcp_sig_hash_skb_data(hp->md5_req, skb, th->doff << 2))
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
 	ahash_request_set_crypt(req, NULL, md5_hash, 0);
 	if (crypto_ahash_final(req))

index e54eee80ce5f..30dc9d4eec83 100644
@@ -751,11 +751,11 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 	if (crypto_ahash_init(req))
 		goto clear_hash;
 
 	if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
 		goto clear_hash;
-	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
+	if (tcp_sig_hash_skb_data(hp->md5_req, skb, th->doff << 2))
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
 	ahash_request_set_crypt(req, NULL, md5_hash, 0);
 	if (crypto_ahash_final(req))

index ed9995c8d486..e303ef53e1a3 100644
@@ -68,10 +68,19 @@ struct tcp_authopt_info {
 	u32 src_isn;
 	/** @dst_isn: Remote Initial Sequence Number */
 	u32 dst_isn;
 };
 
+/* TCP authopt as found in header */
+struct tcphdr_authopt {
+	u8 num;
+	u8 len;
+	u8 keyid;
+	u8 rnextkeyid;
+	u8 mac[0];
+};
+
 #ifdef CONFIG_TCP_AUTHOPT
 DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed_key);
 #define tcp_authopt_needed (static_branch_unlikely(&tcp_authopt_needed_key))
 void tcp_authopt_clear(struct sock *sk);
 int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen);

496 lines not on this page · raw message

index fae9b40e54fa..c5397c24296c 100644
@@ -229,10 +229,14 @@ enum skb_drop_reason {
 	/**
 	 * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the
 	 * MTU)
 	 */
 	SKB_DROP_REASON_PKT_TOO_BIG,
+	/**
+	 * @SKB_DROP_REASON_TCP_BOTHAOMD5: Both AO and MD5 found in packet.
+	 */
+	SKB_DROP_REASON_TCP_BOTHAOMD5,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be
 	 * used as a real 'reason'
 	 */
 	SKB_DROP_REASON_MAX,

91 lines not on this page · raw message

index 4c61c32ccf49..0611a2160b63 100644
@@ -4568,24 +4568,24 @@ int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *ke
 	return data_race(crypto_ahash_update(hp->md5_req));
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
 /* Called with rcu_read_lock() */
-enum skb_drop_reason
+static enum skb_drop_reason
 tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		     const void *saddr, const void *daddr,
-		     int family, int dif, int sdif)
+		     int family, int dif, int sdif,
+		     const u8 *hash_location)
 {
 	/*
 	 * This gets called for each TCP segment that arrives
 	 * so we want to be efficient.
 	 * We have 3 drop cases:
 	 * o No MD5 hash and one expected.
 	 * o MD5 hash and we're not expecting one.
 	 * o MD5 hash and its wrong.
 	 */
-	const __u8 *hash_location = NULL;
 	struct tcp_md5sig_key *hash_expected;
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int genhash, l3index;
 	u8 newhash[16];

@@ -4594,11 +4594,10 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 	 * in an L3 domain and dif is set to the l3mdev
 	 */
 	l3index = sdif ? dif : 0;
 
 	hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family);
-	hash_location = tcp_parse_md5sig_option(th);
 
 	/* We've parsed the options - do we have a hash? */
 	if (!hash_expected && !hash_location)
 		return SKB_NOT_DROPPED_YET;
 

@@ -4641,14 +4640,44 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		}
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
 	}
 	return SKB_NOT_DROPPED_YET;
 }
-EXPORT_SYMBOL(tcp_inbound_md5_hash);
 
 #endif /* CONFIG_TCP_MD5SIG */
 
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
+
+enum skb_drop_reason
+tcp_inbound_sig_hash(const struct sock *sk, const struct sk_buff *skb,
+		     const void *saddr, const void *daddr,
+		     int family, int dif, int sdif)
+{
+	/* FIXME: Restore reqsk handling */
+	const u8 *md5, *ao;
+	enum skb_drop_reason ret;
+	const struct sock *parent_sk;
+
+	if (sk->sk_state == TCP_NEW_SYN_RECV)
+		parent_sk = inet_reqsk(sk)->rsk_listener;
+	else
+		parent_sk = sk;
+
+	ret = tcp_parse_sig_options(tcp_hdr(skb), &md5, &ao);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_TCP_MD5SIG
+	return tcp_inbound_md5_hash(parent_sk, skb, saddr, daddr, family, dif, sdif, md5);
+#else
+	return SKB_NOT_DROPPED_YET;
+#endif
+}
+EXPORT_SYMBOL(tcp_inbound_sig_hash);
+
+#endif /* defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT) */
+
 void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
 
 	/* We might be called with a new socket, after

index ab5f0ea166f1..fa20afd15248 100644
@@ -4186,43 +4186,62 @@ static bool tcp_fast_parse_options(const struct net *net,
 		tp->rx_opt.rcv_tsecr -= tp->tsoffset;
 
 	return true;
 }
 
-#ifdef CONFIG_TCP_MD5SIG
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
 /*
- * Parse MD5 Signature option
+ * Parse MD5 and AO options
+ *
+ * md5ptr: pointer to content of MD5 option (16-byte hash)
+ * aoptr: pointer to start of AO option (variable length)
  */
-const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
+enum skb_drop_reason tcp_parse_sig_options(const struct tcphdr *th,
+					   const u8 **md5ptr,
+					   const u8 **aoptr)
 {
 	int length = (th->doff << 2) - sizeof(*th);
 	const u8 *ptr = (const u8 *)(th + 1);
 
+	*md5ptr = NULL;
+	*aoptr = NULL;
+
 	/* If not enough data remaining, we can short cut */
-	while (length >= TCPOLEN_MD5SIG) {
+	while (length >= 4) {
 		int opcode = *ptr++;
 		int opsize;
 
 		switch (opcode) {
 		case TCPOPT_EOL:
-			return NULL;
+			goto out;
 		case TCPOPT_NOP:
 			length--;
 			continue;
 		default:
 			opsize = *ptr++;
 			if (opsize < 2 || opsize > length)
-				return NULL;
-			if (opcode == TCPOPT_MD5SIG)
-				return opsize == TCPOLEN_MD5SIG ? ptr : NULL;
+				goto out;
+			if (opcode == TCPOPT_MD5SIG && opsize == TCPOLEN_MD5SIG)
+				*md5ptr = ptr;
+			if (opcode == TCPOPT_AUTHOPT)
+				*aoptr = ptr - 2;
 		}
 		ptr += opsize - 2;
 		length -= opsize;
 	}
-	return NULL;
+
+out:
+	/* RFC5925 2.2: An endpoint MUST NOT use TCP-AO for the same connection
+	 * in which TCP MD5 is used. When both options appear, TCP MUST silently
+	 * discard the segment.
+	 */
+	if (*md5ptr && *aoptr)
+		return SKB_DROP_REASON_TCP_BOTHAOMD5;
+
+	return SKB_NOT_DROPPED_YET;
 }
-EXPORT_SYMBOL(tcp_parse_md5sig_option);
+EXPORT_SYMBOL(tcp_parse_sig_options);
 #endif
 
 /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
  *
  * It is not fatal. If this ACK does _not_ change critical state (seqs, window)

index 46ba754afd2b..58b5f197bde1 100644
@@ -1964,17 +1964,17 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
 		bool req_stolen = false;
 		struct sock *nsk;
 
-		sk = req->rsk_listener;
-		if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+		if (!xfrm4_policy_check(req->rsk_listener, XFRM_POLICY_IN, skb))
 			drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		else
-			drop_reason = tcp_inbound_md5_hash(sk, skb,
-						   &iph->saddr, &iph->daddr,
-						   AF_INET, dif, sdif);
+			drop_reason = tcp_inbound_sig_hash(sk, skb,
+							   &iph->saddr, &iph->daddr,
+							   AF_INET, dif, sdif);
+		sk = req->rsk_listener;
 		if (unlikely(drop_reason)) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
 		}

@@ -2046,11 +2046,11 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
 		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		goto discard_and_relse;
 	}
 
-	drop_reason = tcp_inbound_md5_hash(sk, skb, &iph->saddr,
+	drop_reason = tcp_inbound_sig_hash(sk, skb, &iph->saddr,
 					   &iph->daddr, AF_INET, dif, sdif);
 	if (drop_reason)
 		goto discard_and_relse;
 
 	nf_reset_ct(skb);

index 30dc9d4eec83..2edfe631878e 100644
@@ -1632,14 +1632,14 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
 		bool req_stolen = false;
 		struct sock *nsk;
 
-		sk = req->rsk_listener;
-		drop_reason = tcp_inbound_md5_hash(sk, skb,
+		drop_reason = tcp_inbound_sig_hash(sk, skb,
 						   &hdr->saddr, &hdr->daddr,
 						   AF_INET6, dif, sdif);
+		sk = req->rsk_listener;
 		if (drop_reason) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
 		}

@@ -1707,12 +1707,12 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
 		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		goto discard_and_relse;
 	}
 
-	drop_reason = tcp_inbound_md5_hash(sk, skb, &hdr->saddr, &hdr->daddr,
-					   AF_INET6, dif, sdif);
+	drop_reason = tcp_inbound_sig_hash(sk, skb, &hdr->saddr,
+					   &hdr->daddr, AF_INET6, dif, sdif);
 	if (drop_reason)
 		goto discard_and_relse;
 
 	if (tcp_filter(sk, skb)) {
 		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;

index c5397c24296c..d5dd92affde8 100644
@@ -233,10 +233,22 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_PKT_TOO_BIG,
 	/**
 	 * @SKB_DROP_REASON_TCP_BOTHAOMD5: Both AO and MD5 found in packet.
 	 */
 	SKB_DROP_REASON_TCP_BOTHAOMD5,
+	/**
+	 * @SKB_DROP_REASON_TCP_AONOTFOUND: No AO signature and one expected.
+	 */
+	SKB_DROP_REASON_TCP_AONOTFOUND,
+	/**
+	 * @SKB_DROP_REASON_TCP_AOUNEXPECTED: AO hash and we're not expecting
+	 */
+	SKB_DROP_REASON_TCP_AOUNEXPECTED,
+	/**
+	 * @SKB_DROP_REASON_TCP_AOFAILURE: AO hash incorrect
+	 */
+	SKB_DROP_REASON_TCP_AOFAILURE,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be
 	 * used as a real 'reason'
 	 */
 	SKB_DROP_REASON_MAX,

101 lines not on this page · raw message

index 4d7470036a8b..ae2738a7992b 100644
@@ -290,10 +290,11 @@ enum
 	LINUX_MIB_TCPDUPLICATEDATAREHASH,	/* TCPDuplicateDataRehash */
 	LINUX_MIB_TCPDSACKRECVSEGS,		/* TCPDSACKRecvSegs */
 	LINUX_MIB_TCPDSACKIGNOREDDUBIOUS,	/* TCPDSACKIgnoredDubious */
 	LINUX_MIB_TCPMIGRATEREQSUCCESS,		/* TCPMigrateReqSuccess */
 	LINUX_MIB_TCPMIGRATEREQFAILURE,		/* TCPMigrateReqFailure */
+	LINUX_MIB_TCPAUTHOPTFAILURE,		/* TCPAuthOptFailure */
 	__LINUX_MIB_MAX
 };
 
 /* linux Xfrm mib definitions */
 enum

index 0088a4c64d77..e48c7245c571 100644
@@ -295,10 +295,11 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH),
 	SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS),
 	SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS),
 	SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS),
 	SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE),
+	SNMP_MIB_ITEM("TCPAuthOptFailure", LINUX_MIB_TCPAUTHOPTFAILURE),
 	SNMP_MIB_SENTINEL
 };
 
 static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals,
 			     unsigned short *type, int count)

index 0611a2160b63..205534d501ec 100644
@@ -4664,10 +4664,27 @@ tcp_inbound_sig_hash(const struct sock *sk, const struct sk_buff *skb,
 
 	ret = tcp_parse_sig_options(tcp_hdr(skb), &md5, &ao);
 	if (ret)
 		return ret;
 
+#if defined(CONFIG_TCP_AUTHOPT)
+	if (tcp_authopt_needed) {
+		struct tcp_authopt_info *info = rcu_dereference(tcp_sk(parent_sk)->authopt_info);
+		int aoret;
+
+		if (info) {
+			aoret = __tcp_authopt_inbound_check((struct sock *)sk,
+							    (struct sk_buff *)skb,
+							    info, ao);
+			/* Don't do MD5 lookup if AO found */
+			if (aoret == 1)
+				return SKB_NOT_DROPPED_YET;
+			if (aoret < 0)
+				return -aoret;
+		}
+	}
+#endif
 #ifdef CONFIG_TCP_MD5SIG
 	return tcp_inbound_md5_hash(parent_sk, skb, saddr, daddr, family, dif, sdif, md5);
 #else
 	return SKB_NOT_DROPPED_YET;
 #endif

352 lines not on this page · raw message

index fa20afd15248..b0c883521b1a 100644
@@ -70,10 +70,11 @@
 #include <linux/sysctl.h>
 #include <linux/kernel.h>
 #include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/tcp.h>
+#include <net/tcp_authopt.h>
 #include <net/inet_common.h>
 #include <linux/ipsec.h>
 #include <asm/unaligned.h>
 #include <linux/errqueue.h>
 #include <trace/events/tcp.h>

@@ -6059,10 +6060,12 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
 	icsk->icsk_ack.lrcvtime = tcp_jiffies32;
 
+	tcp_authopt_finish_connect(sk, skb);
+
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
 		security_inet_conn_established(sk, skb);
 		sk_mark_napi_id(sk, skb);
 	}

index cb95d88497ae..64357bf5ede2 100644
@@ -18,10 +18,11 @@
  *		Arnt Gulbrandsen, <[email protected]>
  *		Jorge Cwik, <[email protected]>
  */
 
 #include <net/tcp.h>
+#include <net/tcp_authopt.h>
 #include <net/xfrm.h>
 #include <net/busy_poll.h>
 
 static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 {

@@ -300,10 +301,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 					BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
 				}
 			}
 		} while (0);
 #endif
+		tcp_authopt_time_wait(tcptw, tcp_sk(sk));
 
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
 			timeo = rto;
 

@@ -342,10 +344,19 @@ void tcp_twsk_destructor(struct sock *sk)
 
 		if (twsk->tw_md5_key)
 			kfree_rcu(twsk->tw_md5_key, rcu);
 	}
 #endif
+#ifdef CONFIG_TCP_AUTHOPT
+	if (tcp_authopt_needed) {
+		struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+
+		/* twsk only contains sock_common so pass NULL as sk. */
+		if (twsk->tw_authopt_info)
+			tcp_authopt_free(NULL, twsk->tw_authopt_info);
+	}
+#endif
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
 /* Warning : This function is called without sk_listener being locked.
  * Be sure to read socket fields once, as their value could change under us.

@@ -532,10 +543,11 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 #ifdef CONFIG_TCP_MD5SIG
 	newtp->md5sig_info = NULL;	/*XXX*/
 	if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req)))
 		newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
+	tcp_authopt_openreq(newsk, sk, req);
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 	newtp->rx_opt.mss_clamp = req->mss;
 	tcp_ecn_openreq_child(newtp, req);
 	newtp->fastopen_req = NULL;

228 lines not on this page · raw message

index 7ad34a6987ec..1f5020b790dd 100644
@@ -80,10 +80,11 @@ struct tcphdr_authopt {
 };
 
 #ifdef CONFIG_TCP_AUTHOPT
 DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed_key);
 #define tcp_authopt_needed (static_branch_unlikely(&tcp_authopt_needed_key))
+extern int sysctl_tcp_authopt;
 void tcp_authopt_free(struct sock *sk, struct tcp_authopt_info *info);
 void tcp_authopt_clear(struct sock *sk);
 int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen);
 int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key);
 int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen);

index 5490c285668b..908a3ef15b47 100644
@@ -17,10 +17,11 @@
 #include <net/udp.h>
 #include <net/cipso_ipv4.h>
 #include <net/ping.h>
 #include <net/protocol.h>
 #include <net/netevent.h>
+#include <net/tcp_authopt.h>
 
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
 static int tcp_adv_win_scale_min = -31;

@@ -413,10 +414,37 @@ static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write,
 
 	return ret;
 }
 #endif
 
+#ifdef CONFIG_TCP_AUTHOPT
+static int proc_tcp_authopt(struct ctl_table *ctl,
+			    int write, void *buffer, size_t *lenp,
+			    loff_t *ppos)
+{
+	int val = sysctl_tcp_authopt;
+	struct ctl_table tmp = {
+		.data = &val,
+		.mode = ctl->mode,
+		.maxlen = sizeof(val),
+		.extra1 = SYSCTL_ZERO,
+		.extra2 = SYSCTL_ONE,
+	};
+	int err;
+
+	err = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (err)
+		return err;
+	if (sysctl_tcp_authopt && !val) {
+		net_warn_ratelimited("Enabling TCP Authentication Option is permanent\n");
+		return -EINVAL;
+	}
+	sysctl_tcp_authopt = val;
+	return 0;
+}
+#endif
+
 static struct ctl_table ipv4_table[] = {
 	{
 		.procname	= "tcp_max_orphans",
 		.data		= &sysctl_tcp_max_orphans,
 		.maxlen		= sizeof(int),

@@ -524,10 +552,21 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_douintvec_minmax,
 		.extra1		= &sysctl_fib_sync_mem_min,
 		.extra2		= &sysctl_fib_sync_mem_max,
 	},
+#ifdef CONFIG_TCP_AUTHOPT
+	{
+		.procname	= "tcp_authopt",
+		.data		= &sysctl_tcp_authopt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_tcp_authopt,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
 	{ }
 };
 
 static struct ctl_table ipv4_net_table[] = {
 	/* tcp_max_tw_buckets must be first in this table. */

index 9215a8377e4d..c470fce52f78 100644
@@ -4,10 +4,15 @@
 #include <net/ipv6.h>
 #include <net/tcp.h>
 #include <linux/kref.h>
 #include <crypto/hash.h>
 
+/* This is mainly intended to protect against local privilege escalations through
+ * a rarely used feature so it is deliberately not namespaced.
+ */
+int sysctl_tcp_authopt;
+
 /* This is enabled when first struct tcp_authopt_info is allocated and never released */
 DEFINE_STATIC_KEY_FALSE(tcp_authopt_needed_key);
 EXPORT_SYMBOL(tcp_authopt_needed_key);
 
 /* All current algorithms have a mac length of 12 but crypto API digestsize can be larger */

@@ -441,17 +446,30 @@ static int _copy_from_sockptr_tolerant(u8 *dst,
 		memset(dst + srclen, 0, dstlen - srclen);
 
 	return err;
 }
 
+static int check_sysctl_tcp_authopt(void)
+{
+	if (!sysctl_tcp_authopt) {
+		net_warn_ratelimited("TCP Authentication Option disabled by sysctl.\n");
+		return -EPERM;
+	}
+
+	return 0;
+}
+
 int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	struct tcp_authopt opt;
 	struct tcp_authopt_info *info;
 	int err;
 
 	sock_owned_by_me(sk);
+	err = check_sysctl_tcp_authopt();
+	if (err)
+		return err;
 
 	err = _copy_from_sockptr_tolerant((u8 *)&opt, sizeof(opt), optval, optlen);
 	if (err)
 		return err;
 

@@ -469,13 +487,17 @@ int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 
 int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_authopt_info *info;
+	int err;
 
 	memset(opt, 0, sizeof(*opt));
 	sock_owned_by_me(sk);
+	err = check_sysctl_tcp_authopt();
+	if (err)
+		return err;
 
 	info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
 	if (!info)
 		return -ENOENT;
 

@@ -497,10 +519,13 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	struct netns_tcp_authopt *net = sock_net_tcp_authopt(sk);
 	struct tcp_authopt_alg_imp *alg;
 	int err;
 
 	sock_owned_by_me(sk);
+	err = check_sysctl_tcp_authopt();
+	if (err)
+		return err;
 	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = _copy_from_sockptr_tolerant((u8 *)&opt, sizeof(opt), optval, optlen);
 	if (err)

index 1f5020b790dd..1fa1b968c80c 100644
@@ -66,10 +66,14 @@ struct tcp_authopt_info {
 	u32 flags;
 	/** @src_isn: Local Initial Sequence Number */
 	u32 src_isn;
 	/** @dst_isn: Remote Initial Sequence Number */
 	u32 dst_isn;
+	/** @rcv_sne: Recv-side Sequence Number Extension tracking tcp_sock.rcv_nxt */
+	u32 rcv_sne;
+	/** @snd_sne: Send-side Sequence Number Extension tracking tcp_sock.snd_nxt */
+	u32 snd_sne;
 };
 
 /* TCP authopt as found in header */
 struct tcphdr_authopt {
 	u8 num;

@@ -156,10 +160,34 @@ static inline void tcp_authopt_time_wait(
 int __tcp_authopt_inbound_check(
 		struct sock *sk,
 		struct sk_buff *skb,
 		struct tcp_authopt_info *info,
 		const u8 *opt);
+void __tcp_authopt_update_rcv_sne(struct tcp_sock *tp, struct tcp_authopt_info *info, u32 seq);
+static inline void tcp_authopt_update_rcv_sne(struct tcp_sock *tp, u32 seq)
+{
+	struct tcp_authopt_info *info;
+
+	if (tcp_authopt_needed) {
+		info = rcu_dereference_protected(tp->authopt_info,
+						 lockdep_sock_is_held((struct sock *)tp));
+		if (info)
+			__tcp_authopt_update_rcv_sne(tp, info, seq);
+	}
+}
+void __tcp_authopt_update_snd_sne(struct tcp_sock *tp, struct tcp_authopt_info *info, u32 seq);
+static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq)
+{
+	struct tcp_authopt_info *info;
+
+	if (tcp_authopt_needed) {
+		info = rcu_dereference_protected(tp->authopt_info,
+						 lockdep_sock_is_held((struct sock *)tp));
+		if (info)
+			__tcp_authopt_update_snd_sne(tp, info, seq);
+	}
+}
 #else
 static inline void tcp_authopt_clear(struct sock *sk)
 {
 }
 static inline int tcp_authopt_openreq(struct sock *newsk,

@@ -174,8 +202,14 @@ static inline void tcp_authopt_finish_connect(struct sock *sk, struct sk_buff *s
 static inline void tcp_authopt_time_wait(
 		struct tcp_timewait_sock *tcptw,
 		struct tcp_sock *tp)
 {
 }
+static inline void tcp_authopt_update_rcv_sne(struct tcp_sock *tp, u32 seq)
+{
+}
+static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq)
+{
+}
 #endif
 
 #endif /* _LINUX_TCP_AUTHOPT_H */

140 lines not on this page · raw message

index b0c883521b1a..d901e27801d1 100644
@@ -3527,10 +3527,11 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 {
 	u32 delta = seq - tp->rcv_nxt;
 
 	sock_owned_by_me((struct sock *)tp);
+	tcp_authopt_update_rcv_sne(tp, seq);
 	tp->bytes_received += delta;
 	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
 /* Update our send window.

index ae69936947f3..74c3ef86f0bc 100644
@@ -67,10 +67,11 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
+	tcp_authopt_update_snd_sne(tp, TCP_SKB_CB(skb)->end_seq);
 	WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);
 
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
 

index e64b97db927e..2a216356d280 100644
@@ -385,10 +385,11 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 {
 	struct netns_tcp_authopt *net = sock_net_tcp_authopt(sk);
 
 	return tcp_authopt_lookup_send(net, addr_sk, -1);
 }
+EXPORT_SYMBOL(__tcp_authopt_select_key);
 
 static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_authopt_info *info;

@@ -1210,10 +1211,11 @@ int tcp_authopt_hash(char *hash_location,
 	 * try to make it obvious inside the packet.
 	 */
 	memset(hash_location, 0, TCP_AUTHOPT_MACLEN);
 	return err;
 }
+EXPORT_SYMBOL(tcp_authopt_hash);
 
 /**
  * tcp_authopt_lookup_recv - lookup key for receive
  *
  * @sk: Receive socket

103 lines not on this page · raw message

index 1fa1b968c80c..9bc0f58a78cb 100644
@@ -114,10 +114,17 @@ static inline struct tcp_authopt_key_info *tcp_authopt_select_key(
 int tcp_authopt_hash(
 		char *hash_location,
 		struct tcp_authopt_key_info *key,
 		struct tcp_authopt_info *info,
 		struct sock *sk, struct sk_buff *skb);
+int tcp_v4_authopt_hash_reply(
+		char *hash_location,
+		struct tcp_authopt_info *info,
+		struct tcp_authopt_key_info *key,
+		__be32 saddr,
+		__be32 daddr,
+		struct tcphdr *th);
 int __tcp_authopt_openreq(struct sock *newsk, const struct sock *oldsk, struct request_sock *req);
 static inline int tcp_authopt_openreq(
 		struct sock *newsk,
 		const struct sock *oldsk,
 		struct request_sock *req)

164 lines not on this page · raw message

index 2af6265041b4..f7635a37b972 100644
@@ -966,10 +966,11 @@ static int tcp_v4_authopt_get_traffic_key_noskb(struct tcp_authopt_key_info *key
 						u8 *traffic_key)
 {
 	int err;
 	struct tcp_authopt_alg_pool *pool;
 	struct tcp_v4_authopt_context_data data;
+	char traffic_key_context_header[7] = "\x01TCP-AO";
 
 	BUILD_BUG_ON(sizeof(data) != 22);
 
 	pool = tcp_authopt_get_kdf_pool(key);
 	if (IS_ERR(pool))

@@ -982,11 +983,11 @@ static int tcp_v4_authopt_get_traffic_key_noskb(struct tcp_authopt_key_info *key
 	if (err)
 		goto out;
 
 	// RFC5926 section 3.1.1.1
 	// Separate to keep alignment semi-sane
-	err = crypto_ahash_buf(pool->req, "\x01TCP-AO", 7);
+	err = crypto_ahash_buf(pool->req, traffic_key_context_header, 7);
 	if (err)
 		return err;
 	data.saddr = saddr;
 	data.daddr = daddr;
 	data.sport = sport;

166 lines not on this page · raw message

index 9bc0f58a78cb..6b4329a18a1f 100644
@@ -70,10 +70,45 @@ struct tcp_authopt_info {
 	u32 dst_isn;
 	/** @rcv_sne: Recv-side Sequence Number Extension tracking tcp_sock.rcv_nxt */
 	u32 rcv_sne;
 	/** @snd_sne: Send-side Sequence Number Extension tracking tcp_sock.snd_nxt */
 	u32 snd_sne;
+
+	/**
+	 * @send_keyid: keyid currently being sent
+	 *
+	 * This is controlled by userspace by userspace if
+	 * TCP_AUTHOPT_FLAG_LOCK_KEYID, otherwise we try to match recv_rnextkeyid
+	 */
+	u8 send_keyid;
+	/**
+	 * @send_rnextkeyid: rnextkeyid currently being sent
+	 *
+	 * This is controlled by userspace if TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID is set
+	 */
+	u8 send_rnextkeyid;
+	/**
+	 * @recv_keyid: last keyid received from remote
+	 *
+	 * This is reported to userspace but has no other special behavior attached.
+	 */
+	u8 recv_keyid;
+	/**
+	 * @recv_rnextkeyid: last rnextkeyid received from remote
+	 *
+	 * Linux tries to honor this unless TCP_AUTHOPT_FLAG_LOCK_KEYID is set
+	 */
+	u8 recv_rnextkeyid;
+
+	/**
+	 * @send_key: Current key used for sending, cached.
+	 *
+	 * Once a key is found it only changes by user or remote request.
+	 *
+	 * Field is protected by the socket lock and holds a kref to the key.
+	 */
+	struct tcp_authopt_key_info __rcu *send_key;
 };
 
 /* TCP authopt as found in header */
 struct tcphdr_authopt {
 	u8 num;

@@ -94,22 +129,23 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key);
 int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen);
 struct tcp_authopt_key_info *__tcp_authopt_select_key(
 		const struct sock *sk,
 		struct tcp_authopt_info *info,
 		const struct sock *addr_sk,
-		u8 *rnextkeyid);
+		u8 *rnextkeyid,
+		bool locked);
 static inline struct tcp_authopt_key_info *tcp_authopt_select_key(
 		const struct sock *sk,
 		const struct sock *addr_sk,
 		struct tcp_authopt_info **info,
 		u8 *rnextkeyid)
 {
 	if (tcp_authopt_needed) {
 		*info = rcu_dereference(tcp_sk(sk)->authopt_info);
 
 		if (*info)
-			return __tcp_authopt_select_key(sk, *info, addr_sk, rnextkeyid);
+			return __tcp_authopt_select_key(sk, *info, addr_sk, rnextkeyid, true);
 	}
 	return NULL;
 }
 int tcp_authopt_hash(
 		char *hash_location,

index 76d7be6b27f4..e02176390519 100644
@@ -346,10 +346,24 @@ struct tcp_diag_md5sig {
 
 /**
  * enum tcp_authopt_flag - flags for `tcp_authopt.flags`
  */
 enum tcp_authopt_flag {
+	/**
+	 * @TCP_AUTHOPT_FLAG_LOCK_KEYID: keyid controlled by sockopt
+	 *
+	 * If this is set `tcp_authopt.send_keyid` is used to determined sending
+	 * key. Otherwise a key with send_id == recv_rnextkeyid is preferred.
+	 */
+	TCP_AUTHOPT_FLAG_LOCK_KEYID = (1 << 0),
+	/**
+	 * @TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID: Override rnextkeyid from userspace
+	 *
+	 * If this is set then `tcp_authopt.send_rnextkeyid` is sent on outbound
+	 * packets. Other the recv_id of the current sending key is sent.
+	 */
+	TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID = (1 << 1),
 	/**
 	 * @TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED:
 	 *	Configure behavior of segments with TCP-AO coming from hosts for which no
 	 *	key is configured. The default recommended by RFC is to silently accept
 	 *	such connections.

@@ -361,10 +375,27 @@ enum tcp_authopt_flag {
  * struct tcp_authopt - Per-socket options related to TCP Authentication Option
  */
 struct tcp_authopt {
 	/** @flags: Combination of &enum tcp_authopt_flag */
 	__u32	flags;
+	/**
+	 * @send_keyid: `tcp_authopt_key.send_id` of preferred send key
+	 *
+	 * This is only used if `TCP_AUTHOPT_FLAG_LOCK_KEYID` is set.
+	 */
+	__u8	send_keyid;
+	/**
+	 * @send_rnextkeyid: The rnextkeyid to send in packets
+	 *
+	 * This is controlled by the user iff TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID is
+	 * set. Otherwise rnextkeyid is the recv_id of the current key.
+	 */
+	__u8	send_rnextkeyid;
+	/** @recv_keyid: A recently-received keyid value. Only for getsockopt. */
+	__u8	recv_keyid;
+	/** @recv_rnextkeyid: A recently-received rnextkeyid value. Only for getsockopt. */
+	__u8	recv_rnextkeyid;
 };
 
 /**
  * enum tcp_authopt_key_flag - flags for `tcp_authopt.flags`
  *

185 lines not on this page · raw message

index acce593bb7c9..720ae16303c4 100644
@@ -665,11 +665,11 @@ static int tcp_v4_authopt_handle_reply(const struct sock *sk,
 		info = tcp_twsk(sk)->tw_authopt_info;
 	else
 		info = rcu_dereference_check(tcp_sk(sk)->authopt_info, lockdep_sock_is_held(sk));
 	if (!info)
 		return 0;
-	key_info = __tcp_authopt_select_key(sk, info, sk, &rnextkeyid);
+	key_info = __tcp_authopt_select_key(sk, info, sk, &rnextkeyid, false);
 	if (!key_info)
 		return 0;
 	*optptr = htonl((TCPOPT_AUTHOPT << 24) |
 			(TCPOLEN_AUTHOPT_OUTPUT << 16) |
 			(key_info->send_id << 8) |

index 151254345dee..e983a0e680ae 100644
@@ -852,11 +852,11 @@ static int tcp_v6_send_response_init_authopt(const struct sock *sk,
 		*info = tcp_twsk(sk)->tw_authopt_info;
 	else
 		*info = rcu_dereference(tcp_sk(sk)->authopt_info);
 	if (!*info)
 		return 0;
-	*key = __tcp_authopt_select_key(sk, *info, sk, rnextkeyid);
+	*key = __tcp_authopt_select_key(sk, *info, sk, rnextkeyid, false);
 	if (*key)
 		return TCPOLEN_AUTHOPT_OUTPUT;
 	return 0;
 }
 

index 6b4329a18a1f..1630fc2aa082 100644
@@ -45,10 +45,12 @@ struct tcp_authopt_key_info {
 	u8 alg_id;
 	/** @keylen: Same as &tcp_authopt_key.keylen */
 	u8 keylen;
 	/** @key: Same as &tcp_authopt_key.key */
 	u8 key[TCP_AUTHOPT_MAXKEYLEN];
+	/** @l3index: Same as &tcp_authopt_key.ifindex */
+	int l3index;
 	/** @addr: Same as &tcp_authopt_key.addr */
 	struct sockaddr_storage addr;
 	/** @alg: Algorithm implementation matching alg_id */
 	struct tcp_authopt_alg_imp *alg;
 };

index e02176390519..a7f5f918ed5a 100644
@@ -400,15 +400,17 @@ struct tcp_authopt {
  * enum tcp_authopt_key_flag - flags for `tcp_authopt.flags`
  *
  * @TCP_AUTHOPT_KEY_DEL: Delete the key and ignore non-id fields
  * @TCP_AUTHOPT_KEY_EXCLUDE_OPTS: Exclude TCP options from signature
  * @TCP_AUTHOPT_KEY_ADDR_BIND: Key only valid for `tcp_authopt.addr`
+ * @TCP_AUTHOPT_KEY_IFINDEX: Key only valid for `tcp_authopt.ifindex`
  */
 enum tcp_authopt_key_flag {
 	TCP_AUTHOPT_KEY_DEL = (1 << 0),
 	TCP_AUTHOPT_KEY_EXCLUDE_OPTS = (1 << 1),
 	TCP_AUTHOPT_KEY_ADDR_BIND = (1 << 2),
+	TCP_AUTHOPT_KEY_IFINDEX = (1 << 3),
 };
 
 /**
  * enum tcp_authopt_alg - Algorithms for TCP Authentication Option
  */

@@ -450,10 +452,19 @@ struct tcp_authopt_key {
 	 * @addr: Key is only valid for this address
 	 *
 	 * Ignored unless TCP_AUTHOPT_KEY_ADDR_BIND flag is set
 	 */
 	struct __kernel_sockaddr_storage addr;
+	/**
+	 * @ifindex: ifindex of vrf (l3mdev_master) interface
+	 *
+	 * If the TCP_AUTHOPT_KEY_IFINDEX flag is set then key only applies for
+	 * connections through this interface. Interface must be an vrf master.
+	 *
+	 * This is similar to `tcp_msg5sig.tcpm_ifindex`
+	 */
+	int	ifindex;
 };
 
 /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
 
 #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1

174 lines not on this page · raw message

index a7f5f918ed5a..ed27feb93b0e 100644
@@ -401,16 +401,20 @@ struct tcp_authopt {
  *
  * @TCP_AUTHOPT_KEY_DEL: Delete the key and ignore non-id fields
  * @TCP_AUTHOPT_KEY_EXCLUDE_OPTS: Exclude TCP options from signature
  * @TCP_AUTHOPT_KEY_ADDR_BIND: Key only valid for `tcp_authopt.addr`
  * @TCP_AUTHOPT_KEY_IFINDEX: Key only valid for `tcp_authopt.ifindex`
+ * @TCP_AUTHOPT_KEY_NOSEND: Key invalid for send (expired)
+ * @TCP_AUTHOPT_KEY_NORECV: Key invalid for recv (expired)
  */
 enum tcp_authopt_key_flag {
 	TCP_AUTHOPT_KEY_DEL = (1 << 0),
 	TCP_AUTHOPT_KEY_EXCLUDE_OPTS = (1 << 1),
 	TCP_AUTHOPT_KEY_ADDR_BIND = (1 << 2),
 	TCP_AUTHOPT_KEY_IFINDEX = (1 << 3),
+	TCP_AUTHOPT_KEY_NOSEND = (1 << 4),
+	TCP_AUTHOPT_KEY_NORECV = (1 << 5),
 };
 
 /**
  * enum tcp_authopt_alg - Algorithms for TCP Authentication Option
  */

index bb26fb1c8af2..0ead961fcfe0 100644
@@ -374,10 +374,12 @@ static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct netns_tcp_aut
 	int l3index = -1;
 
 	hlist_for_each_entry_rcu(key, &net->head, node, 0) {
 		if (send_id >= 0 && key->send_id != send_id)
 			continue;
+		if (key->flags & TCP_AUTHOPT_KEY_NOSEND)
+			continue;
 		if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND)
 			if (!tcp_authopt_key_match_sk_addr(key, addr_sk))
 				continue;
 		if (key->flags & TCP_AUTHOPT_KEY_IFINDEX) {
 			if (l3index < 0)

@@ -623,11 +625,13 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
 
 #define TCP_AUTHOPT_KEY_KNOWN_FLAGS ( \
 	TCP_AUTHOPT_KEY_DEL | \
 	TCP_AUTHOPT_KEY_EXCLUDE_OPTS | \
 	TCP_AUTHOPT_KEY_ADDR_BIND | \
-	TCP_AUTHOPT_KEY_IFINDEX)
+	TCP_AUTHOPT_KEY_IFINDEX | \
+	TCP_AUTHOPT_KEY_NOSEND | \
+	TCP_AUTHOPT_KEY_NORECV)
 
 int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	struct tcp_authopt_key opt;
 	struct tcp_authopt_info *info;

@@ -1534,10 +1538,13 @@ static struct tcp_authopt_key_info *tcp_authopt_lookup_recv(struct sock *sk,
 
 			if (l3index != key->l3index)
 				continue;
 		}
 		*anykey = true;
+		// If only keys with norecv flag are present still consider that
+		if (key->flags & TCP_AUTHOPT_KEY_NORECV)
+			continue;
 		if (recv_id >= 0 && key->recv_id != recv_id)
 			continue;
 		if (better_key_match(result, key))
 			result = key;
 		else if (result)

index 1630fc2aa082..4f83d8e54fef 100644
@@ -47,10 +47,12 @@ struct tcp_authopt_key_info {
 	u8 keylen;
 	/** @key: Same as &tcp_authopt_key.key */
 	u8 key[TCP_AUTHOPT_MAXKEYLEN];
 	/** @l3index: Same as &tcp_authopt_key.ifindex */
 	int l3index;
+	/** @prefixlen: Length of addr match (default full) */
+	int prefixlen;
 	/** @addr: Same as &tcp_authopt_key.addr */
 	struct sockaddr_storage addr;
 	/** @alg: Algorithm implementation matching alg_id */
 	struct tcp_authopt_alg_imp *alg;
 };

index ed27feb93b0e..b1063e1e1b9f 100644
@@ -403,18 +403,21 @@ struct tcp_authopt {
  * @TCP_AUTHOPT_KEY_EXCLUDE_OPTS: Exclude TCP options from signature
  * @TCP_AUTHOPT_KEY_ADDR_BIND: Key only valid for `tcp_authopt.addr`
  * @TCP_AUTHOPT_KEY_IFINDEX: Key only valid for `tcp_authopt.ifindex`
  * @TCP_AUTHOPT_KEY_NOSEND: Key invalid for send (expired)
  * @TCP_AUTHOPT_KEY_NORECV: Key invalid for recv (expired)
+ * @TCP_AUTHOPT_KEY_PREFIXLEN: Valid value in `tcp_authopt.prefixlen`, otherwise
+ * match full address length
  */
 enum tcp_authopt_key_flag {
 	TCP_AUTHOPT_KEY_DEL = (1 << 0),
 	TCP_AUTHOPT_KEY_EXCLUDE_OPTS = (1 << 1),
 	TCP_AUTHOPT_KEY_ADDR_BIND = (1 << 2),
 	TCP_AUTHOPT_KEY_IFINDEX = (1 << 3),
 	TCP_AUTHOPT_KEY_NOSEND = (1 << 4),
 	TCP_AUTHOPT_KEY_NORECV = (1 << 5),
+	TCP_AUTHOPT_KEY_PREFIXLEN = (1 << 6),
 };
 
 /**
  * enum tcp_authopt_alg - Algorithms for TCP Authentication Option
  */

@@ -465,10 +468,17 @@ struct tcp_authopt_key {
 	 * connections through this interface. Interface must be an vrf master.
 	 *
 	 * This is similar to `tcp_msg5sig.tcpm_ifindex`
 	 */
 	int	ifindex;
+	/**
+	 * @prefixlen: length of prefix to match
+	 *
+	 * Without the TCP_AUTHOPT_KEY_PREFIXLEN flag this is ignored and a full
+	 * address match is performed.
+	 */
+	int	prefixlen;
 };
 
 /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
 
 #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1

164 lines not on this page · raw message

index 0b6cbd6f5491..06f8df1d80c9 100644
@@ -301,27 +301,30 @@ static bool tcp_authopt_key_match_skb_addr(struct tcp_authopt_key_info *key,
 		struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr;
 
 		return ipv6_prefix_equal(&ip6h->saddr,
 					 &key_addr->sin6_addr,
 					 key->prefixlen);
+	} else if (keyaf == AF_INET6 && iph->version == 4) {
+		struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr;
+
+		/* handle ipv6-mapped-ipv4-addresses */
+		if (ipv6_addr_v4mapped(&key_addr->sin6_addr)) {
+			__be32 mask = inet_make_mask(key->prefixlen);
+			__be32 ipv4 = key_addr->sin6_addr.s6_addr32[3];
+
+			return (ipv4 & mask) == ipv4;
+		}
 	}
 
-	/* This actually happens with ipv6-mapped-ipv4-addresses
-	 * IPv6 listen sockets will be asked to validate ipv4 packets.
-	 */
 	return false;
 }
 
 static bool tcp_authopt_key_match_sk_addr(struct tcp_authopt_key_info *key,
 					  const struct sock *addr_sk)
 {
 	u16 keyaf = key->addr.ss_family;
 
-	/* This probably can't happen even with ipv4-mapped-ipv6 */
-	if (keyaf != addr_sk->sk_family)
-		return false;
-
 	if (keyaf == AF_INET) {
 		struct sockaddr_in *key_addr = (struct sockaddr_in *)&key->addr;
 		__be32 mask = inet_make_mask(key->prefixlen);
 
 		return (addr_sk->sk_daddr & mask) == key_addr->sin_addr.s_addr;

@@ -330,10 +333,16 @@ static bool tcp_authopt_key_match_sk_addr(struct tcp_authopt_key_info *key,
 		struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr;
 
 		return ipv6_prefix_equal(&addr_sk->sk_v6_daddr,
 					 &key_addr->sin6_addr,
 					 key->prefixlen);
+	} else if (keyaf == AF_INET6 && addr_sk->sk_family == AF_INET) {
+		struct sockaddr_in6 *key_addr = (struct sockaddr_in6 *)&key->addr;
+		__be32 mask = inet_make_mask(key->prefixlen);
+		__be32 ipv4 = key_addr->sin6_addr.s6_addr32[3];
+
+		return (addr_sk->sk_daddr & mask) == ipv4;
 #endif
 	}
 
 	return false;
 }

@@ -1399,14 +1408,20 @@ static int __tcp_authopt_calc_mac(struct sock *sk,
 				  char *macbuf)
 {
 	struct tcp_authopt_alg_pool *mac_pool;
 	u8 traffic_key[TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN];
 	int err;
-	bool ipv6 = (sk->sk_family != AF_INET);
+	bool ipv6;
 
-	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
-		return -EINVAL;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (input)
+		ipv6 = (skb->protocol == htons(ETH_P_IPV6));
+	else
+		ipv6 = (sk->sk_family == AF_INET6) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr);
+#else
+	ipv6 = false;
+#endif
 
 	err = tcp_authopt_get_traffic_key(sk, skb, key, info, input, ipv6, traffic_key);
 	if (err)
 		return err;
 

137 lines not on this page · raw message

index d9a6fd2cd9d3..3841e5fec7c7 100644
@@ -94,17 +94,17 @@ struct sock_args {
 	const char *clientns;
 	const char *serverns;
 
 	const char *password;
 	const char *client_pw;
-	/* prefix for MD5 password */
-	const char *md5_prefix_str;
+	/* prefix for MD5/AO*/
+	const char *key_addr_prefix_str;
 	union {
 		struct sockaddr_in v4;
 		struct sockaddr_in6 v6;
-	} md5_prefix;
-	unsigned int prefix_len;
+	} key_addr;
+	unsigned int key_addr_prefix_len;
 	/* 0: default, -1: force off, +1: force on */
 	int bind_key_ifindex;
 
 	/* expected addresses and device index for connection */
 	const char *expected_dev;

@@ -264,16 +264,16 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args
 	int rc;
 
 	md5sig.tcpm_keylen = keylen;
 	memcpy(md5sig.tcpm_key, args->password, keylen);
 
-	if (args->prefix_len) {
+	if (args->key_addr_prefix_len) {
 		opt = TCP_MD5SIG_EXT;
 		md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_PREFIX;
 
-		md5sig.tcpm_prefixlen = args->prefix_len;
-		addr = &args->md5_prefix;
+		md5sig.tcpm_prefixlen = args->key_addr_prefix_len;
+		addr = &args->key_addr;
 	}
 	memcpy(&md5sig.tcpm_addr, addr, alen);
 
 	if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) {
 		opt = TCP_MD5SIG_EXT;

@@ -309,17 +309,17 @@ static int tcp_md5_remote(int sd, struct sock_args *args)
 	int alen;
 
 	switch (args->version) {
 	case AF_INET:
 		sin.sin_port = htons(args->port);
-		sin.sin_addr = args->md5_prefix.v4.sin_addr;
+		sin.sin_addr = args->key_addr.v4.sin_addr;
 		addr = &sin;
 		alen = sizeof(sin);
 		break;
 	case AF_INET6:
 		sin6.sin6_port = htons(args->port);
-		sin6.sin6_addr = args->md5_prefix.v6.sin6_addr;
+		sin6.sin6_addr = args->key_addr.v6.sin6_addr;
 		addr = &sin6;
 		alen = sizeof(sin6);
 		break;
 	default:
 		log_error("unknown address family\n");

@@ -705,11 +705,11 @@ enum addr_type {
 	ADDR_TYPE_LOCAL,
 	ADDR_TYPE_REMOTE,
 	ADDR_TYPE_MCAST,
 	ADDR_TYPE_EXPECTED_LOCAL,
 	ADDR_TYPE_EXPECTED_REMOTE,
-	ADDR_TYPE_MD5_PREFIX,
+	ADDR_TYPE_KEY_PREFIX,
 };
 
 static int convert_addr(struct sock_args *args, const char *_str,
 			enum addr_type atype)
 {

@@ -745,32 +745,32 @@ static int convert_addr(struct sock_args *args, const char *_str,
 		break;
 	case ADDR_TYPE_EXPECTED_REMOTE:
 		desc = "expected remote";
 		addr = &args->expected_raddr;
 		break;
-	case ADDR_TYPE_MD5_PREFIX:
-		desc = "md5 prefix";
+	case ADDR_TYPE_KEY_PREFIX:
+		desc = "key addr prefix";
 		if (family == AF_INET) {
-			args->md5_prefix.v4.sin_family = AF_INET;
-			addr = &args->md5_prefix.v4.sin_addr;
+			args->key_addr.v4.sin_family = AF_INET;
+			addr = &args->key_addr.v4.sin_addr;
 		} else if (family == AF_INET6) {
-			args->md5_prefix.v6.sin6_family = AF_INET6;
-			addr = &args->md5_prefix.v6.sin6_addr;
+			args->key_addr.v6.sin6_family = AF_INET6;
+			addr = &args->key_addr.v6.sin6_addr;
 		} else
 			return 1;
 
 		sep = strchr(str, '/');
 		if (sep) {
 			*sep = '\0';
 			sep++;
 			if (str_to_uint(sep, 1, pfx_len_max,
-					&args->prefix_len) != 0) {
-				fprintf(stderr, "Invalid port\n");
+					&args->key_addr_prefix_len) != 0) {
+				fprintf(stderr, "Invalid prefix\n");
 				return 1;
 			}
 		} else {
-			args->prefix_len = 0;
+			args->key_addr_prefix_len = 0;
 		}
 		break;
 	default:
 		log_error("unknown address type\n");
 		exit(1);

@@ -835,13 +835,13 @@ static int validate_addresses(struct sock_args *args)
 
 	if (args->remote_addr_str &&
 	    convert_addr(args, args->remote_addr_str, ADDR_TYPE_REMOTE) < 0)
 		return 1;
 
-	if (args->md5_prefix_str &&
-	    convert_addr(args, args->md5_prefix_str,
-			 ADDR_TYPE_MD5_PREFIX) < 0)
+	if (args->key_addr_prefix_str &&
+	    convert_addr(args, args->key_addr_prefix_str,
+			 ADDR_TYPE_KEY_PREFIX) < 0)
 		return 1;
 
 	if (args->expected_laddr_str &&
 	    convert_addr(args, args->expected_laddr_str,
 			 ADDR_TYPE_EXPECTED_LOCAL))

@@ -2020,11 +2020,11 @@ int main(int argc, char *argv[])
 			break;
 		case 'X':
 			args.client_pw = optarg;
 			break;
 		case 'm':
-			args.md5_prefix_str = optarg;
+			args.key_addr_prefix_str = optarg;
 			break;
 		case 'S':
 			args.use_setsockopt = 1;
 			break;
 		case 'f':

@@ -2079,17 +2079,17 @@ int main(int argc, char *argv[])
 			return 1;
 		}
 	}
 
 	if (args.password &&
-	    ((!args.has_remote_ip && !args.md5_prefix_str) ||
+	    ((!args.has_remote_ip && !args.key_addr_prefix_str) ||
 	      args.type != SOCK_STREAM)) {
 		log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n");
 		return 1;
 	}
 
-	if (args.md5_prefix_str && !args.password) {
+	if (args.key_addr_prefix_str && !args.password) {
 		log_error("Prefix range for MD5 protection specified without a password\n");
 		return 1;
 	}
 
 	if (iter == 0) {

index 3841e5fec7c7..9615489230f8 100644
@@ -27,10 +27,11 @@
 #include <string.h>
 #include <unistd.h>
 #include <time.h>
 #include <errno.h>
 #include <getopt.h>
+#include <stdbool.h>
 
 #include <linux/xfrm.h>
 #include <linux/ipsec.h>
 #include <linux/pfkeyv2.h>
 

@@ -104,10 +105,12 @@ struct sock_args {
 	} key_addr;
 	unsigned int key_addr_prefix_len;
 	/* 0: default, -1: force off, +1: force on */
 	int bind_key_ifindex;
 
+	const char *authopt_password;
+
 	/* expected addresses and device index for connection */
 	const char *expected_dev;
 	const char *expected_server_dev;
 	int expected_ifindex;
 

@@ -254,10 +257,75 @@ static int switch_ns(const char *ns)
 	close(fd);
 
 	return ret;
 }
 
+/* Fill key identification fields: address and ifindex */
+static void tcp_authopt_key_fill_id(struct tcp_authopt_key *key, struct sock_args *args)
+{
+	if (args->key_addr_prefix_str) {
+		key->flags |= TCP_AUTHOPT_KEY_ADDR_BIND;
+		switch (args->version) {
+		case AF_INET:
+			memcpy(&key->addr, &args->key_addr.v4, sizeof(args->key_addr.v4));
+			break;
+		case AF_INET6:
+			memcpy(&key->addr, &args->key_addr.v6, sizeof(args->key_addr.v6));
+			break;
+		default:
+			log_error("unknown address family\n");
+			exit(1);
+		}
+		if (args->key_addr_prefix_len) {
+			key->flags |= TCP_AUTHOPT_KEY_PREFIXLEN;
+			key->prefixlen = args->key_addr_prefix_len;
+		}
+	}
+
+	if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) {
+		key->flags |= TCP_AUTHOPT_KEY_IFINDEX;
+		key->ifindex = args->ifindex;
+		log_msg("TCP_AUTHOPT_KEY_IFINDEX set ifindex=%d\n", key->ifindex);
+	} else {
+		log_msg("TCP_AUTHOPT_KEY_IFINDEX off\n", key->ifindex);
+	}
+}
+
+static int tcp_del_authopt(int sd, struct sock_args *args)
+{
+	struct tcp_authopt_key key;
+	int rc;
+
+	memset(&key, 0, sizeof(key));
+	key.flags |= TCP_AUTHOPT_KEY_DEL;
+	tcp_authopt_key_fill_id(&key, args);
+
+	rc = setsockopt(sd, IPPROTO_TCP, TCP_AUTHOPT_KEY, &key, sizeof(key));
+	if (rc < 0)
+		log_err_errno("setsockopt(TCP_AUTHOPT_KEY) del fail");
+
+	return rc;
+}
+
+static int tcp_set_authopt(int sd, struct sock_args *args)
+{
+	struct tcp_authopt_key key;
+	int rc;
+
+	memset(&key, 0, sizeof(key));
+	strcpy((char *)key.key, args->authopt_password);
+	key.keylen = strlen(args->authopt_password);
+	key.alg = TCP_AUTHOPT_ALG_HMAC_SHA_1_96;
+	tcp_authopt_key_fill_id(&key, args);
+
+	rc = setsockopt(sd, IPPROTO_TCP, TCP_AUTHOPT_KEY, &key, sizeof(key));
+	if (rc < 0)
+		log_err_errno("setsockopt(TCP_AUTHOPT_KEY) add fail");
+
+	return rc;
+}
+
 static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args)
 {
 	int keylen = strlen(args->password);
 	struct tcp_md5sig md5sig = {};
 	int opt = TCP_MD5SIG;

@@ -1541,10 +1609,15 @@ static int do_server(struct sock_args *args, int ipc_fd)
 	if (args->password && tcp_md5_remote(lsd, args)) {
 		close(lsd);
 		goto err_exit;
 	}
 
+	if (args->authopt_password && tcp_set_authopt(lsd, args)) {
+		close(lsd);
+		goto err_exit;
+	}
+
 	ipc_write(ipc_fd, 1);
 	while (1) {
 		log_msg("waiting for client connection.\n");
 		FD_ZERO(&rfds);
 		FD_SET(lsd, &rfds);

@@ -1663,10 +1736,13 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args)
 		goto out;
 
 	if (args->password && tcp_md5sig(sd, addr, alen, args))
 		goto err;
 
+	if (args->authopt_password && tcp_set_authopt(sd, args))
+		goto err;
+
 	if (args->bind_test_only)
 		goto out;
 
 	if (connect(sd, addr, alen) < 0) {
 		if (errno != EINPROGRESS) {

@@ -1852,11 +1928,11 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 
 	wait(&status);
 	return client_status;
 }
 
-#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbqf"
+#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:A:d:I:BN:O:SCi6xL:0:1:2:3:Fbqf"
 #define OPT_FORCE_BIND_KEY_IFINDEX 1001
 #define OPT_NO_BIND_KEY_IFINDEX 1002
 
 static struct option long_opts[] = {
 	{"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX},

@@ -1897,14 +1973,15 @@ static void print_usage(char *prog)
 	"    -L len        send random message of given length\n"
 	"    -n num        number of times to send message\n"
 	"\n"
 	"    -M password   use MD5 sum protection\n"
 	"    -X password   MD5 password for client mode\n"
-	"    -m prefix/len prefix and length to use for MD5 key\n"
-	"    --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n"
-	"    --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n"
+	"    -m prefix/len prefix and length to use for MD5/AO key\n"
+	"    --no-bind-key-ifindex: Force disable binding key to ifindex\n"
+	"    --force-bind-key-ifindex: Force enable binding key to ifindex\n"
 	"        (default: only if -I is passed)\n"
+	"    -A password   use RFC5925 TCP Authentication Option with password\n"
 	"\n"
 	"    -g grp        multicast group (e.g., 239.1.1.1)\n"
 	"    -i            interactive mode (default is echo and terminate)\n"
 	"\n"
 	"    -0 addr       Expected local address\n"

@@ -1915,17 +1992,64 @@ static void print_usage(char *prog)
 	"    -b            Bind test only.\n"
 	"    -q            Be quiet. Run test without printing anything.\n"
 	, prog, DEFAULT_PORT);
 }
 
-int main(int argc, char *argv[])
+/* Needs explicit cleanup because keys are global per-namespace */
+void cleanup_tcp_authopt(struct sock_args *args)
+{
+	int fd;
+
+	if (!args->authopt_password)
+		return;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (fd < 0) {
+		log_err_errno("Failed to create socket");
+		return;
+	}
+	tcp_del_authopt(fd, args);
+	close(fd);
+}
+
+static bool cleanup_done;
+static struct sock_args args = {
+	.version = AF_INET,
+	.type    = SOCK_STREAM,
+	.port    = DEFAULT_PORT,
+};
+
+void cleanup(void)
+{
+	if (cleanup_done)
+		return;
+	cleanup_done = true;
+	cleanup_tcp_authopt(&args);
+}
+
+void signal_handler(int num)
+{
+	cleanup();
+}
+
+void atexit_handler(void)
+{
+	cleanup();
+}
+
+/* Explicit cleanup is required for TCP-AO because keys are global. */
+static void register_cleanup(void)
 {
-	struct sock_args args = {
-		.version = AF_INET,
-		.type    = SOCK_STREAM,
-		.port    = DEFAULT_PORT,
+	struct sigaction sa = {
+		.sa_handler = signal_handler,
 	};
+	sigaction(SIGINT, &sa, NULL);
+	atexit(atexit_handler);
+}
+
+int main(int argc, char *argv[])
+{
 	struct protoent *pe;
 	int both_mode = 0;
 	unsigned int tmp;
 	int forever = 0;
 	int fd[2];

@@ -2022,10 +2146,13 @@ int main(int argc, char *argv[])
 			args.client_pw = optarg;
 			break;
 		case 'm':
 			args.key_addr_prefix_str = optarg;
 			break;
+		case 'A':
+			args.authopt_password = optarg;
+			break;
 		case 'S':
 			args.use_setsockopt = 1;
 			break;
 		case 'f':
 			args.use_freebind = 1;

@@ -2085,12 +2212,17 @@ int main(int argc, char *argv[])
 	      args.type != SOCK_STREAM)) {
 		log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n");
 		return 1;
 	}
 
-	if (args.key_addr_prefix_str && !args.password) {
-		log_error("Prefix range for MD5 protection specified without a password\n");
+	if (args.key_addr_prefix_str && !args.password && !args.authopt_password) {
+		log_error("Prefix range for authentication requires -M or -A\n");
+		return 1;
+	}
+
+	if (args.key_addr_prefix_len && args.authopt_password) {
+		log_error("TCP-AO does not support prefix match, only full address\n");
 		return 1;
 	}
 
 	if (iter == 0) {
 		fprintf(stderr, "Invalid number of messages to send\n");

@@ -2113,10 +2245,12 @@ int main(int argc, char *argv[])
 		fprintf(stderr,
 			"Local (server mode) or remote IP (client IP) required\n");
 		return 1;
 	}
 
+	register_cleanup();
+
 	if (interactive) {
 		prog_timeout = 0;
 		msg = NULL;
 	}
 

index 551942883f06..6a4ff0ed55c6 100644
@@ -125,10 +125,13 @@ struct tcp_options_received {
 	u8	saw_unknown:1,	/* Received unknown option		*/
 		unused:7;
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
+#if IS_ENABLED(CONFIG_TCP_AUTHOPT)
+	u8	rnextkeyid;
+#endif
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
 	rx_opt->tstamp_ok = rx_opt->sack_ok = 0;

@@ -163,10 +166,13 @@ struct tcp_request_sock {
 	u32				rcv_nxt; /* the ack # by SYNACK. For
 						  * FastOpen it's the seq#
 						  * after data-in-SYN.
 						  */
 	u8				syn_tos;
+#if IS_ENABLED(CONFIG_TCP_AUTHOPT)
+	u8				recv_rnextkeyid;
+#endif
 };
 
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 {
 	return (struct tcp_request_sock *)req;

index 0a273ad239ec..de1390273ef3 100644
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "linux/tcp.h"
+#include "net/tcp_states.h"
 #include <net/tcp_authopt.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
 #include <linux/kref.h>

@@ -444,21 +446,33 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 {
 	struct tcp_authopt_key_info *key, *new_key = NULL;
 	struct netns_tcp_authopt *net = sock_net_tcp_authopt(sk);
 
 	/* Listen sockets don't refer to any specific connection so we don't try
-	 * to keep using the same key and ignore any received keyids.
+	 * to keep using the same key.
+	 * The rnextkeyid is stored in tcp_request_sock
 	 */
 	if (sk->sk_state == TCP_LISTEN) {
-		int send_keyid = -1;
-
+		int send_id = -1;
+		struct tcp_request_sock *rsk;
+
+		if (WARN_ONCE(addr_sk->sk_state != TCP_NEW_SYN_RECV, "bad socket state"))
+			return NULL;
+		rsk = tcp_rsk((struct request_sock *)addr_sk);
+		/* Forcing a specific send_keyid on a listen socket forces it for
+		 * all clients so is unlikely to be useful.
+		 */
 		if (info->flags & TCP_AUTHOPT_FLAG_LOCK_KEYID)
-			send_keyid = info->send_keyid;
-		key = tcp_authopt_lookup_send(net, addr_sk, send_keyid);
+			send_id = info->send_keyid;
+		else
+			send_id = rsk->recv_rnextkeyid;
+		key = tcp_authopt_lookup_send(net, addr_sk, send_id);
+		/* If no key found with specific send_id try anything else. */
+		if (!key)
+			key = tcp_authopt_lookup_send(net, addr_sk, -1);
 		if (key)
 			*rnextkeyid = key->recv_id;
-
 		return key;
 	}
 
 	if (locked) {
 		sock_owned_by_me(sk);

index d901e27801d1..579562de4551 100644
@@ -4107,10 +4107,18 @@ void tcp_parse_options(const struct net *net,
 				/*
 				 * The MD5 Hash has already been
 				 * checked (see tcp_v{4,6}_do_rcv()).
 				 */
 				break;
+#endif
+#ifdef CONFIG_TCP_AUTHOPT
+			case TCPOPT_AUTHOPT:
+				/* Hash has already been checked.
+				 * We parse rnextkeyid here so we can match it on synack
+				 */
+				opt_rx->rnextkeyid = ptr[1];
+				break;
 #endif
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
 					ptr, th->syn, foc, false);

@@ -6963,10 +6971,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		tcp_clear_options(&tmp_opt);
 
 	if (IS_ENABLED(CONFIG_SMC) && want_cookie)
 		tmp_opt.smc_ok = 0;
 
+#if IS_ENABLED(CONFIG_TCP_AUTHOPT)
+	tcp_rsk(req)->recv_rnextkeyid = tmp_opt.rnextkeyid;
+#endif
+
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb, sk);
 	inet_rsk(req)->no_srccheck = inet_sk(sk)->transparent;
 
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */

index de1390273ef3..9aa3aea25a97 100644
@@ -387,38 +387,42 @@ static bool better_key_match(struct tcp_authopt_key_info *old, struct tcp_authop
  * tcp_authopt_lookup_send - lookup key for sending
  *
  * @net: Per-namespace information containing keys
  * @addr_sk: Socket used for destination address lookup
  * @send_id: Optional send_id. If >= 0 then only return keys that match
+ * @anykey: Set to true if any keys are present for the peer
  *
  * If anykey is false then authentication is not required for peer.
  *
  * If anykey is true but no key was found then all our keys must be expired and sending should fail.
  */
 static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct netns_tcp_authopt *net,
 							    const struct sock *addr_sk,
-							    int send_id)
+							    int send_id,
+							    bool *anykey)
 {
 	struct tcp_authopt_key_info *result = NULL;
 	struct tcp_authopt_key_info *key;
 	int l3index = -1;
 
 	hlist_for_each_entry_rcu(key, &net->head, node, 0) {
-		if (send_id >= 0 && key->send_id != send_id)
-			continue;
-		if (key->flags & TCP_AUTHOPT_KEY_NOSEND)
-			continue;
 		if (key->flags & TCP_AUTHOPT_KEY_ADDR_BIND)
 			if (!tcp_authopt_key_match_sk_addr(key, addr_sk))
 				continue;
 		if (key->flags & TCP_AUTHOPT_KEY_IFINDEX) {
 			if (l3index < 0)
 				l3index = l3mdev_master_ifindex_by_index(sock_net(addr_sk),
 									 addr_sk->sk_bound_dev_if);
 			if (l3index != key->l3index)
 				continue;
 		}
+		if (anykey)
+			*anykey = true;
+		if (key->flags & TCP_AUTHOPT_KEY_NOSEND)
+			continue;
+		if (send_id >= 0 && key->send_id != send_id)
+			continue;
 		if (better_key_match(result, key))
 			result = key;
 		else if (result)
 			net_warn_ratelimited("ambiguous tcp authentication keys configured for send\n");
 	}

@@ -463,14 +467,14 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 		 */
 		if (info->flags & TCP_AUTHOPT_FLAG_LOCK_KEYID)
 			send_id = info->send_keyid;
 		else
 			send_id = rsk->recv_rnextkeyid;
-		key = tcp_authopt_lookup_send(net, addr_sk, send_id);
+		key = tcp_authopt_lookup_send(net, addr_sk, send_id, NULL);
 		/* If no key found with specific send_id try anything else. */
 		if (!key)
-			key = tcp_authopt_lookup_send(net, addr_sk, -1);
+			key = tcp_authopt_lookup_send(net, addr_sk, -1, NULL);
 		if (key)
 			*rnextkeyid = key->recv_id;
 		return key;
 	}
 

@@ -491,18 +495,22 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 	 */
 	if (info->flags & TCP_AUTHOPT_FLAG_LOCK_KEYID) {
 		int send_keyid = info->send_keyid;
 
 		if (!key || key->send_id != send_keyid)
-			new_key = tcp_authopt_lookup_send(net, addr_sk, send_keyid);
+			new_key = tcp_authopt_lookup_send(net, addr_sk,
+							  send_keyid,
+							  NULL);
 	} else {
 		if (!key || key->send_id != info->recv_rnextkeyid)
-			new_key = tcp_authopt_lookup_send(net, addr_sk, info->recv_rnextkeyid);
+			new_key = tcp_authopt_lookup_send(net, addr_sk,
+							  info->recv_rnextkeyid,
+							  NULL);
 	}
 	/* If no key found with specific send_id try anything else. */
 	if (!key && !new_key)
-		new_key = tcp_authopt_lookup_send(net, addr_sk, -1);
+		new_key = tcp_authopt_lookup_send(net, addr_sk, -1, NULL);
 
 	/* Update current key only if we hold the socket lock. */
 	if (new_key && key != new_key) {
 		if (locked) {
 			if (kref_get_unless_zero(&new_key->ref)) {

index b1063e1e1b9f..5ca8aa9d5e43 100644
@@ -367,10 +367,23 @@ enum tcp_authopt_flag {
 	 *	Configure behavior of segments with TCP-AO coming from hosts for which no
 	 *	key is configured. The default recommended by RFC is to silently accept
 	 *	such connections.
 	 */
 	TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED = (1 << 2),
+	/**
+	 * @TCP_AUTHOPT_FLAG_ACTIVE: If authentication is active for a specific socket.
+	 *
+	 * TCP Authentication can be enabled but inactive on a socket if keys are
+	 * only configured for destinations other than the peer.
+	 *
+	 * A listen socket with authentication enabled will return other sockets
+	 * with authentication enabled on accept(). If no key is configured for the
+	 * peer of an accepted socket then authentication will be inactive.
+	 *
+	 * This flag is readonly and the value is determined at connection establishment time.
+	 */
+	TCP_AUTHOPT_FLAG_ACTIVE = (1 << 3),
 };
 
 /**
  * struct tcp_authopt - Per-socket options related to TCP Authentication Option
  */

index 9aa3aea25a97..bbdc5f68ab56 100644
@@ -554,15 +554,23 @@ static struct tcp_authopt_info *__tcp_authopt_info_get_or_create(struct sock *sk
 	rcu_assign_pointer(tp->authopt_info, info);
 
 	return info;
 }
 
-#define TCP_AUTHOPT_KNOWN_FLAGS ( \
+/* Flags fully controlled by user: */
+#define TCP_AUTHOPT_USER_FLAGS ( \
 	TCP_AUTHOPT_FLAG_LOCK_KEYID | \
 	TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID | \
 	TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED)
 
+/* All known flags */
+#define TCP_AUTHOPT_KNOWN_FLAGS ( \
+	TCP_AUTHOPT_FLAG_LOCK_KEYID | \
+	TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID | \
+	TCP_AUTHOPT_FLAG_REJECT_UNEXPECTED | \
+	TCP_AUTHOPT_FLAG_ACTIVE)
+
 /* Like copy_from_sockptr except tolerate different optlen for compatibility reasons
  *
  * If the src is shorter then it's from an old userspace and the rest of dst is
  * filled with zeros.
  *

@@ -627,11 +635,11 @@ int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 
 	info = __tcp_authopt_info_get_or_create(sk);
 	if (IS_ERR(info))
 		return PTR_ERR(info);
 
-	info->flags = opt.flags & TCP_AUTHOPT_KNOWN_FLAGS;
+	info->flags = opt.flags & TCP_AUTHOPT_USER_FLAGS;
 	if (opt.flags & TCP_AUTHOPT_FLAG_LOCK_KEYID)
 		info->send_keyid = opt.send_keyid;
 	if (opt.flags & TCP_AUTHOPT_FLAG_LOCK_RNEXTKEYID)
 		info->send_rnextkeyid = opt.send_rnextkeyid;
 

@@ -641,10 +649,11 @@ int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_authopt_info *info;
 	struct tcp_authopt_key_info *send_key;
+	bool anykey = false;
 	int err;
 
 	memset(opt, 0, sizeof(*opt));
 	sock_owned_by_me(sk);
 	err = check_sysctl_tcp_authopt();

@@ -653,11 +662,18 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
 
 	info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
 	if (!info)
 		return -ENOENT;
 
-	opt->flags = info->flags & TCP_AUTHOPT_KNOWN_FLAGS;
+	opt->flags = info->flags & TCP_AUTHOPT_USER_FLAGS;
+
+	rcu_read_lock();
+	tcp_authopt_lookup_send(sock_net_tcp_authopt(sk), sk, -1, &anykey);
+	if (anykey)
+		opt->flags |= TCP_AUTHOPT_FLAG_ACTIVE;
+	rcu_read_unlock();
+
 	/* These keyids might be undefined, for example before connect.
 	 * Reporting zero is not strictly correct because there are no reserved
 	 * values.
 	 */
 	send_key = rcu_dereference_check(info->send_key, lockdep_sock_is_held(sk));

index bbdc5f68ab56..933a4bbddb70 100644
@@ -448,10 +448,11 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 						      u8 *rnextkeyid,
 						      bool locked)
 {
 	struct tcp_authopt_key_info *key, *new_key = NULL;
 	struct netns_tcp_authopt *net = sock_net_tcp_authopt(sk);
+	bool anykey = false;
 
 	/* Listen sockets don't refer to any specific connection so we don't try
 	 * to keep using the same key.
 	 * The rnextkeyid is stored in tcp_request_sock
 	 */

@@ -470,11 +471,13 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 		else
 			send_id = rsk->recv_rnextkeyid;
 		key = tcp_authopt_lookup_send(net, addr_sk, send_id, NULL);
 		/* If no key found with specific send_id try anything else. */
 		if (!key)
-			key = tcp_authopt_lookup_send(net, addr_sk, -1, NULL);
+			key = tcp_authopt_lookup_send(net, addr_sk, -1, &anykey);
+		if (!key && anykey)
+			return ERR_PTR(-ENOKEY);
 		if (key)
 			*rnextkeyid = key->recv_id;
 		return key;
 	}
 

@@ -506,11 +509,13 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 							  info->recv_rnextkeyid,
 							  NULL);
 	}
 	/* If no key found with specific send_id try anything else. */
 	if (!key && !new_key)
-		new_key = tcp_authopt_lookup_send(net, addr_sk, -1, NULL);
+		new_key = tcp_authopt_lookup_send(net, addr_sk, -1, &anykey);
+	if (!new_key && anykey)
+		return ERR_PTR(-ENOKEY);
 
 	/* Update current key only if we hold the socket lock. */
 	if (new_key && key != new_key) {
 		if (locked) {
 			if (kref_get_unless_zero(&new_key->ref)) {

index 74c3ef86f0bc..a1c2d4d2c426 100644
@@ -411,10 +411,11 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_SACK_ADVERTISE	BIT(0)
 #define OPTION_TS		BIT(1)
 #define OPTION_MD5		BIT(2)
 #define OPTION_WSCALE		BIT(3)
 #define OPTION_AUTHOPT		BIT(4)
+#define OPTION_AUTHOPT_FAIL	BIT(5)
 #define OPTION_FAST_OPEN_COOKIE	BIT(8)
 #define OPTION_SMC		BIT(9)
 #define OPTION_MPTCP		BIT(10)
 
 static void smc_options_write(__be32 *ptr, u16 *options)

@@ -783,10 +784,14 @@ static int tcp_authopt_init_options(const struct sock *sk,
 {
 #ifdef CONFIG_TCP_AUTHOPT
 	struct tcp_authopt_key_info *key;
 
 	key = tcp_authopt_select_key(sk, addr_sk, &opts->authopt_info, &opts->authopt_rnextkeyid);
+	if (IS_ERR(key)) {
+		opts->options |= OPTION_AUTHOPT_FAIL;
+		return TCPOLEN_AUTHOPT_OUTPUT;
+	}
 	if (key) {
 		opts->options |= OPTION_AUTHOPT;
 		opts->authopt_key = key;
 		return TCPOLEN_AUTHOPT_OUTPUT;
 	}

@@ -1342,10 +1347,18 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		 * release the following packet.
 		 */
 		if (tcp_skb_pcount(skb) > 1)
 			tcb->tcp_flags |= TCPHDR_PSH;
 	}
+#ifdef CONFIG_TCP_AUTHOPT
+	if (opts.options & OPTION_AUTHOPT_FAIL) {
+		rcu_read_unlock();
+		sk->sk_err = ENOKEY;
+		sk_error_report(sk);
+		return -ENOKEY;
+	}
+#endif
 	tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
 	/* if no packet is in qdisc/device queue, then allow XPS to select
 	 * another queue. We can be called from tcp_tsq_handler()
 	 * which holds one reference to sk.

@@ -3652,10 +3665,17 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	/* bpf program will be interested in the tcp_flags */
 	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
 					     foc, synack_type,
 					     syn_skb) + sizeof(*th);
+#ifdef CONFIG_TCP_AUTHOPT
+	if (opts.options & OPTION_AUTHOPT_FAIL) {
+		rcu_read_unlock();
+		kfree_skb(skb);
+		return NULL;
+	}
+#endif
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
 
 	th = (struct tcphdr *)skb->data;

index 4f83d8e54fef..fda6dc4b5d57 100644
@@ -231,10 +231,12 @@ static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq)
 						 lockdep_sock_is_held((struct sock *)tp));
 		if (info)
 			__tcp_authopt_update_snd_sne(tp, info, seq);
 	}
 }
+int tcp_get_authopt_repair_val(struct sock *sk, struct tcp_authopt_repair *opt);
+int tcp_set_authopt_repair(struct sock *sk, sockptr_t optval, unsigned int optlen);
 #else
 static inline void tcp_authopt_clear(struct sock *sk)
 {
 }
 static inline int tcp_authopt_openreq(struct sock *newsk,

index 5ca8aa9d5e43..ee6836f87cf8 100644
@@ -128,10 +128,11 @@ enum {
 #define TCP_CM_INQ		TCP_INQ
 
 #define TCP_TX_DELAY		37	/* delay outgoing packets by XX usec */
 #define TCP_AUTHOPT		38	/* TCP Authentication Option (RFC5925) */
 #define TCP_AUTHOPT_KEY		39	/* TCP Authentication Option Key (RFC5925) */
+#define TCP_REPAIR_AUTHOPT	40
 
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
 #define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */

@@ -490,10 +491,28 @@ struct tcp_authopt_key {
 	 * address match is performed.
 	 */
 	int	prefixlen;
 };
 
+/**
+ * struct tcp_authopt_repair - TCP_REPAIR information related to Authentication Option
+ * @src_isn: Local Initial Sequence Number
+ * @dst_isn: Remote Initial Sequence Number
+ * @snd_sne: Sequence Number Extension for Send (upper 32 bits of snd_seq)
+ * @rcv_sne: Sequence Number Extension for Recv (upper 32 bits of rcv_seq)
+ * @snd_seq: Recent Send Sequence Number (lower 32 bits of snd_sne)
+ * @rcv_seq: Recent Recv Sequence Number (lower 32 bits of rcv_sne)
+ */
+struct tcp_authopt_repair {
+	__u32	src_isn;
+	__u32	dst_isn;
+	__u32	snd_sne;
+	__u32	rcv_sne;
+	__u32	snd_seq;
+	__u32	rcv_seq;
+};
+
 /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
 
 #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1
 struct tcp_zerocopy_receive {
 	__u64 address;		/* in: address of mapping */

index 205534d501ec..ad0af4efd265 100644
@@ -3715,10 +3715,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		err = tcp_set_authopt(sk, optval, optlen);
 		break;
 	case TCP_AUTHOPT_KEY:
 		err = tcp_set_authopt_key(sk, optval, optlen);
 		break;
+	case TCP_REPAIR_AUTHOPT:
+		err = tcp_set_authopt_repair(sk, optval, optlen);
+		break;
 #endif
 	case TCP_USER_TIMEOUT:
 		/* Cap the max time in ms TCP will retry or probe the window
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */

@@ -4387,10 +4390,30 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		if (copy_to_user(optval, &info, len))
 			return -EFAULT;
 		return 0;
 	}
+	case TCP_REPAIR_AUTHOPT: {
+		struct tcp_authopt_repair val;
+		int err;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		lock_sock(sk);
+		err = tcp_get_authopt_repair_val(sk, &val);
+		release_sock(sk);
+
+		if (err)
+			return err;
+		len = min_t(unsigned int, len, sizeof(val));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &val, len))
+			return -EFAULT;
+		return 0;
+	}
 #endif
 
 	default:
 		return -ENOPROTOOPT;
 	}

76 lines not on this page · raw message