tcp: Initial support for RFC5925 auth option

index 78b91bb92f0d..497604176119 100644
@@ -140,10 +140,12 @@ 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	*/

@@ -403,10 +405,14 @@ 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.
 	 */

@@ -453,10 +459,13 @@ 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 44e442bf23f9..6cc2eeb45deb 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

76 lines not on this page · raw message

101 lines not on this page · raw message

index 20054618c87e..022811dd705d 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>

@@ -3602,10 +3603,16 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
 		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
+	case TCP_AUTHOPT:
+		err = tcp_set_authopt(sk, optval, optlen);
+		break;
+	case TCP_AUTHOPT_KEY:
+		err = tcp_set_authopt_key(sk, optval, optlen);
+		break;
 	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.
 		 */
 		if (val < 0)

@@ -4251,10 +4258,33 @@ 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))

263 lines not on this page · raw message

index 3dd19a2bf06c..0aa5122b29e0 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>

@@ -2276,10 +2277,11 @@ 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 42ad764e98c2..5217b6c7c900 100644
@@ -2,10 +2,24 @@
 #ifndef _LINUX_TCP_AUTHOPT_H
 #define _LINUX_TCP_AUTHOPT_H
 
 #include <uapi/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 only protected by RCU so readers needs to hold a
  * single rcu_read_lock until they're done with the key.

@@ -27,10 +41,12 @@ 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
  *

206 lines not on this page · raw message

index 6cc2eeb45deb..1a0513b0ead0 100644
@@ -1688,11 +1688,11 @@ 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 022811dd705d..8e6cbb5a1da7 100644
@@ -4400,16 +4400,31 @@ 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,
+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;
+
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* We use data_race() because tcp_md5_do_add() might change key->key under us */
+	return data_race(crypto_ahash_update(hp->md5_req));
+}
+EXPORT_SYMBOL(tcp_md5_hash_key);
+#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;

@@ -4432,31 +4447,18 @@ 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);
 
-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;
-
-	sg_init_one(&sg, key->key, keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
-
-	/* We use data_race() because tcp_md5_do_add() might change key->key under us */
-	return data_race(crypto_ahash_update(hp->md5_req));
-}
-EXPORT_SYMBOL(tcp_md5_hash_key);
-
-#endif
+#endif /* defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT) */
 
 void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
 

index 0aa5122b29e0..91cad11db32e 100644
@@ -1381,11 +1381,11 @@ 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 3b7d6ede1364..e98fc6f12c61 100644
@@ -750,11 +750,11 @@ 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 5217b6c7c900..ce005f7ce797 100644
@@ -64,10 +64,19 @@ 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
 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);

631 lines not on this page · raw message

index 1a0513b0ead0..eed4bbfdca78 100644
@@ -422,11 +422,33 @@ int tcp_mmap(struct file *file, struct socket *sock,
 	     struct vm_area_struct *vma);
 #endif
 void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
 		       struct tcp_options_received *opt_rx,
 		       int estab, struct tcp_fastopen_cookie *foc);
-const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
+int tcp_parse_sig_options(const struct tcphdr *th,
+			  const u8 **md5ptr,
+			  const u8 **aoptr);
+#else
+static inline int tcp_parse_sig_options(const struct tcphdr *th,
+			  const u8 **md5ptr,
+			  const u8 **aoptr)
+{
+	aoptr = NULL;
+	md5ptr = NULL;
+	return 0;
+}
+#endif
+static inline const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
+{
+	const u8 *md5, *ao;
+	int ret;
+
+	ret = tcp_parse_sig_options(th, &md5, &ao);
+
+	return (md5 && !ao && !ret) ? md5 : NULL;
+}
 
 /*
  *	BPF SKB-less helpers
  */
 u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,

163 lines not on this page · raw message

index 904909d020e2..1d96030889a1 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 f30273afb539..70f7a8a47045 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)

367 lines not on this page · raw message

index 3658b9c3dd2b..4c9e403971fb 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>

@@ -4173,43 +4174,60 @@ 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)
+int 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 -EINVAL;
+
+	return 0;
 }
-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)

@@ -5992,10 +6010,12 @@ 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);
 	}

108 lines not on this page · raw message

index cf913a66df17..19f749b60231 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 (newtp->af_specific->md5_lookup(sk, newsk))
 		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

111 lines not on this page · raw message

index fb07394de261..4e872af7b180 100644
@@ -76,10 +76,11 @@ 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);

index 97eb54774924..07de2666314c 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 two = 2;
 static int three __maybe_unused = 3;
 static int four = 4;
 static int thousand = 1000;

@@ -472,10 +473,37 @@ 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),

@@ -583,10 +611,21 @@ 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[] = {
 	{

index dd9b89b1f137..85de430d3326 100644
@@ -3,10 +3,15 @@
 #include <linux/kernel.h>
 #include <net/tcp.h>
 #include <net/tcp_authopt.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 */

@@ -377,17 +382,30 @@ 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;
 

@@ -405,14 +423,18 @@ 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;
 
-	memset(opt, 0, sizeof(*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;

@@ -475,10 +497,13 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	struct tcp_authopt_key_info *key_info, *old_key_info;
 	struct tcp_authopt_alg_imp *alg;
 	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;
 

index 4e872af7b180..d5d344d599f7 100644
@@ -62,10 +62,14 @@ 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;

@@ -180,10 +184,34 @@ static inline int tcp_authopt_inbound_check_req(struct request_sock *req, struct
 		if (info)
 			return __tcp_authopt_inbound_check((struct sock *)req, skb, info, opt);
 	}
 	return 0;
 }
+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 int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }

@@ -230,8 +258,14 @@ static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb
 static inline int tcp_authopt_inbound_check_req(struct request_sock *sk, struct sk_buff *skb,
 						const u8 *opt)
 {
 	return 0;
 }
+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 4c9e403971fb..bc0a90c72391 100644
@@ -3517,10 +3517,11 @@ 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 b959e8b949b6..6a6024a0b9e9 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 05234923cb9f..f1213c7db63b 100644
@@ -320,10 +320,11 @@ struct tcp_authopt_key_info *__tcp_authopt_select_key(const struct sock *sk,
 						      const struct sock *addr_sk,
 						      u8 *rnextkeyid)
 {
 	return tcp_authopt_lookup_send(info, 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;

@@ -1195,10 +1196,11 @@ 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);
 
 static struct tcp_authopt_key_info *tcp_authopt_lookup_recv(struct sock *sk,
 							    struct sk_buff *skb,
 							    struct tcp_authopt_info *info,
 							    int recv_id,

90 lines not on this page · raw message

index d5d344d599f7..411e7a0bdd43 100644
@@ -111,10 +111,17 @@ 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 b16f263c3121..be531e2f52ae 100644
@@ -644,10 +644,50 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 
 	__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
 }
 EXPORT_SYMBOL(tcp_v4_send_check);
 
+#ifdef CONFIG_TCP_AUTHOPT
+/** tcp_v4_authopt_handle_reply - Insert TCPOPT_AUTHOPT if required
+ *
+ * returns number of bytes (always aligned to 4) or zero
+ */
+static int tcp_v4_authopt_handle_reply(const struct sock *sk,
+				       struct sk_buff *skb,
+				       __be32 *optptr,
+				       struct tcphdr *th)
+{
+	struct tcp_authopt_info *info;
+	struct tcp_authopt_key_info *key_info;
+	u8 rnextkeyid;
+
+	if (sk->sk_state == TCP_TIME_WAIT)
+		info = tcp_twsk(sk)->tw_authopt_info;
+	else
+		info = tcp_sk(sk)->authopt_info;
+	if (!info)
+		return 0;
+	key_info = __tcp_authopt_select_key(sk, info, sk, &rnextkeyid);
+	if (!key_info)
+		return 0;
+	*optptr = htonl((TCPOPT_AUTHOPT << 24) |
+			(TCPOLEN_AUTHOPT_OUTPUT << 16) |
+			(key_info->send_id << 8) |
+			(rnextkeyid));
+	/* must update doff before signature computation */
+	th->doff += TCPOLEN_AUTHOPT_OUTPUT / 4;
+	tcp_v4_authopt_hash_reply((char *)(optptr + 1),
+				  info,
+				  key_info,
+				  ip_hdr(skb)->daddr,
+				  ip_hdr(skb)->saddr,
+				  th);
+
+	return TCPOLEN_AUTHOPT_OUTPUT;
+}
+#endif
+
 /*
  *	This routine will send an RST to the other tcp.
  *
  *	Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
  *		      for reset.

@@ -659,10 +699,12 @@ EXPORT_SYMBOL(tcp_v4_send_check);
  *	Exception: precedence violation. We do not implement it in any case.
  */
 
 #ifdef CONFIG_TCP_MD5SIG
 #define OPTION_BYTES TCPOLEN_MD5SIG_ALIGNED
+#elif defined(OPTION_BYTES_TCP_AUTHOPT)
+#define OPTION_BYTES TCPOLEN_AUTHOPT_OUTPUT
 #else
 #define OPTION_BYTES sizeof(__be32)
 #endif
 
 static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)

@@ -712,12 +754,29 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	memset(&arg, 0, sizeof(arg));
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
 	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
-#ifdef CONFIG_TCP_MD5SIG
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
 	rcu_read_lock();
+#endif
+#ifdef CONFIG_TCP_AUTHOPT
+	/* Unlike TCP-MD5 the signatures for TCP-AO depend on initial sequence
+	 * numbers so we can only handle established and time-wait sockets.
+	 */
+	if (tcp_authopt_needed && sk &&
+	    sk->sk_state != TCP_NEW_SYN_RECV &&
+	    sk->sk_state != TCP_LISTEN) {
+		int tcp_authopt_ret = tcp_v4_authopt_handle_reply(sk, skb, rep.opt, &rep.th);
+
+		if (tcp_authopt_ret) {
+			arg.iov[0].iov_len += tcp_authopt_ret;
+			goto skip_md5sig;
+		}
+	}
+#endif
+#ifdef CONFIG_TCP_MD5SIG
 	hash_location = tcp_parse_md5sig_option(th);
 	if (sk && sk_fullsock(sk)) {
 		const union tcp_md5_addr *addr;
 		int l3index;
 

@@ -755,11 +814,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr;
 		key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET);
 		if (!key)
 			goto out;
 
-
 		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto out;
 
 	}

@@ -775,10 +833,13 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 		tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1],
 				     key, ip_hdr(skb)->saddr,
 				     ip_hdr(skb)->daddr, &rep.th);
 	}
+#endif
+#ifdef CONFIG_TCP_AUTHOPT
+skip_md5sig:
 #endif
 	/* Can't co-exist with TCPMD5, hence check rep.opt[0] */
 	if (rep.opt[0] == 0) {
 		__be32 mrst = mptcp_reset_option(skb);
 

@@ -828,12 +889,14 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	ctl_sk->sk_mark = 0;
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
 	local_bh_enable();
 
-#ifdef CONFIG_TCP_MD5SIG
+#if defined(CONFIG_TCP_MD5SIG)
 out:
+#endif
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AUTHOPT)
 	rcu_read_unlock();
 #endif
 }
 
 /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states

@@ -850,10 +913,12 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	struct {
 		struct tcphdr th;
 		__be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
 #ifdef CONFIG_TCP_MD5SIG
 			   + (TCPOLEN_MD5SIG_ALIGNED >> 2)
+#elif defined(CONFIG_TCP_AUTHOPT)
+			   + (TCPOLEN_AUTHOPT_OUTPUT >> 2)
 #endif
 			];
 	} rep;
 	struct net *net = sock_net(sk);
 	struct ip_reply_arg arg;

@@ -881,10 +946,21 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	rep.th.seq     = htonl(seq);
 	rep.th.ack_seq = htonl(ack);
 	rep.th.ack     = 1;
 	rep.th.window  = htons(win);
 
+#ifdef CONFIG_TCP_AUTHOPT
+	if (tcp_authopt_needed) {
+		int aoret, offset = (tsecr) ? 3 : 0;
+
+		aoret = tcp_v4_authopt_handle_reply(sk, skb, &rep.opt[offset], &rep.th);
+		if (aoret) {
+			arg.iov[0].iov_len += aoret;
+			key = NULL;
+		}
+	}
+#endif
 #ifdef CONFIG_TCP_MD5SIG
 	if (key) {
 		int offset = (tsecr) ? 3 : 0;
 
 		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |

index 411e7a0bdd43..020637265ce9 100644
@@ -66,10 +66,43 @@ 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.
+	 */
+	struct tcp_authopt_key_info *send_key;
 };
 
 /* TCP authopt as found in header */
 struct tcphdr_authopt {
 	u8 num;

@@ -91,22 +124,23 @@ 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`
  *

182 lines not on this page · raw message

index be531e2f52ae..edfb76f76485 100644
@@ -664,11 +664,11 @@ static int tcp_v4_authopt_handle_reply(const struct sock *sk,
 		info = tcp_twsk(sk)->tw_authopt_info;
 	else
 		info = tcp_sk(sk)->authopt_info;
 	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 cd8544d08a36..6ed13f8f489f 100644
@@ -901,11 +901,11 @@ 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 020637265ce9..e57bc732f737 100644
@@ -39,10 +39,12 @@ 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

168 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 b3fd12fcb948..946d598258b1 100644
@@ -311,10 +311,12 @@ static struct tcp_authopt_key_info *tcp_authopt_lookup_send(struct tcp_authopt_i
 	int l3index = -1;
 
 	hlist_for_each_entry_rcu(key, &info->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)

@@ -593,11 +595,13 @@ void tcp_authopt_clear(struct sock *sk)
 
 #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;

@@ -1496,10 +1500,13 @@ 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 e57bc732f737..6c50395c0412 100644
@@ -41,10 +41,12 @@ 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;
+	/** @prefix: 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 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..5fe7354c40cf 100644
@@ -104,10 +104,12 @@ 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 +256,54 @@ static int switch_ns(const char *ns)
 	close(fd);
 
 	return ret;
 }
 
+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;
+
+	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);
+	}
+
+	rc = setsockopt(sd, IPPROTO_TCP, TCP_AUTHOPT_KEY, &key, sizeof(key));
+	if (rc < 0)
+		log_err_errno("setsockopt(TCP_AUTHOPT_KEY)");
+
+	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 +1587,15 @@ 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 +1714,13 @@ 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 +1906,11 @@ 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 +1951,15 @@ 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"

@@ -2022,10 +2077,13 @@ 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 +2143,17 @@ 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");