tcp: Initial support for RFC5925 auth option

index 48d8a363319e..50038f35ba51 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 3166dc15d7d6..bb76554e8fe5 100644
@@ -182,10 +182,11 @@ 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

63 lines not on this page · raw message

99 lines not on this page · raw message

index e8b48df73c85..9966acf259e2 100644
@@ -271,10 +271,11 @@
 
 #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>

@@ -3574,10 +3575,16 @@ 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)

@@ -4220,10 +4227,33 @@ 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))

260 lines not on this page · raw message

index 2e62e0d6373a..1348615c7576 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>

@@ -2256,10 +2257,11 @@ 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 19d304de18f8..f6d7d6fa50c0 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.

@@ -18,10 +32,11 @@ struct tcp_authopt_key_info {
 	u8 send_id, recv_id;
 	u8 alg_id;
 	u8 keylen;
 	u8 key[TCP_AUTHOPT_MAXKEYLEN];
 	struct sockaddr_storage addr;
+	struct tcp_authopt_alg_imp *alg;
 };
 
 /**
  * struct tcp_authopt_info - Per-socket information regarding tcp_authopt
  *

207 lines not on this page · raw message

index a682f88509aa..e2fd851b687b 100644
@@ -423,5 +423,515 @@ int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	memcpy(&key_info->addr, &opt.addr, sizeof(key_info->addr));
 	hlist_add_head_rcu(&key_info->node, &info->head);
 
 	return 0;
 }
+
+static int tcp_authopt_get_isn(struct sock *sk,
+			       struct sk_buff *skb,
+			       int input,
+			       __be32 *sisn,
+			       __be32 *disn)
+{
+	struct tcp_authopt_info *authopt_info;
+	struct tcphdr *th = tcp_hdr(skb);
+
+	/* special cases for SYN and SYN/ACK */
+	if (th->syn && !th->ack) {
+		*sisn = th->seq;
+		*disn = 0;
+		return 0;
+	}
+	if (th->syn && th->ack) {
+		*sisn = th->seq;
+		*disn = htonl(ntohl(th->ack_seq) - 1);
+		return 0;
+	}
+
+	/* Fetching authopt_info like this should be safe because authopt_info
+	 * is never released intil the socket is being closed
+	 *
+	 * tcp_timewait_sock is handled but not tcp_request_sock.
+	 * for the synack case sk should be the listen socket.
+	 */
+	rcu_read_lock();
+	if (sk->sk_state == TCP_TIME_WAIT)
+		authopt_info = tcp_twsk(sk)->tw_authopt_info;
+	else if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV)) {
+		/* should never happen, sk should be the listen socket */
+		authopt_info = NULL;
+		WARN_ONCE(1, "TCP-AO can't sign with request sock\n");
+		return -EINVAL;
+	} else if (sk->sk_state == TCP_LISTEN) {
+		/* Signature computation for non-syn packet on a listen
+		 * socket is not possible because we lack the initial
+		 * sequence numbers.
+		 *
+		 * Input segments that are not matched by any request,
+		 * established or timewait socket will get here. These
+		 * are not normally sent by peers.
+		 *
+		 * Their signature might be valid but we don't have
+		 * enough state to determine that. TCP-MD5 can attempt
+		 * to validate and reply with a signed RST because it
+		 * doesn't care about ISNs.
+		 *
+		 * Reporting an error from signature code causes the
+		 * packet to be discarded which is good.
+		 */
+		if (input) {
+			/* Assume this is an ACK to a SYN/ACK
+			 * This will incorrectly report "failed
+			 * signature" for segments without a connection.
+			 */
+			*sisn = htonl(ntohl(th->seq) - 1);
+			*disn = htonl(ntohl(th->ack_seq) - 1);
+			rcu_read_unlock();
+			return 0;
+		} else {
+			/* This would be an internal bug. */
+			authopt_info = NULL;
+			WARN_ONCE(1, "TCP-AO can't sign non-syn from TCP_LISTEN sock\n");
+			return -EINVAL;
+		}
+	} else
+		authopt_info = rcu_dereference(tcp_sk(sk)->authopt_info);
+	if (!authopt_info) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	/* Initial sequence numbers for ESTABLISHED connections from info */
+	if (input) {
+		*sisn = htonl(authopt_info->dst_isn);
+		*disn = htonl(authopt_info->src_isn);
+	} else {
+		*sisn = htonl(authopt_info->src_isn);
+		*disn = htonl(authopt_info->dst_isn);
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+/* feed traffic key into shash */
+static int tcp_authopt_shash_traffic_key(struct shash_desc *desc,
+					 struct sock *sk,
+					 struct sk_buff *skb,
+					 bool input,
+					 bool ipv6)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+	int err;
+	__be32 sisn, disn;
+	__be16 digestbits = htons(crypto_shash_digestsize(desc->tfm) * 8);
+
+	// RFC5926 section 3.1.1.1
+	err = crypto_shash_update(desc, "\x01TCP-AO", 7);
+	if (err)
+		return err;
+
+	/* Addresses from packet on input and from sk_common on output
+	 * This is because on output MAC is computed before prepending IP header
+	 */
+	if (input) {
+		if (ipv6)
+			err = crypto_shash_update(desc, (u8 *)&ipv6_hdr(skb)->saddr, 32);
+		else
+			err = crypto_shash_update(desc, (u8 *)&ip_hdr(skb)->saddr, 8);
+		if (err)
+			return err;
+	} else {
+		if (ipv6) {
+			err = crypto_shash_update(desc, (u8 *)&sk->sk_v6_rcv_saddr, 16);
+			if (err)
+				return err;
+			err = crypto_shash_update(desc, (u8 *)&sk->sk_v6_daddr, 16);
+			if (err)
+				return err;
+		} else {
+			err = crypto_shash_update(desc, (u8 *)&sk->sk_rcv_saddr, 4);
+			if (err)
+				return err;
+			err = crypto_shash_update(desc, (u8 *)&sk->sk_daddr, 4);
+			if (err)
+				return err;
+		}
+	}
+
+	/* TCP ports from header */
+	err = crypto_shash_update(desc, (u8 *)&th->source, 4);
+	if (err)
+		return err;
+	err = tcp_authopt_get_isn(sk, skb, input, &sisn, &disn);
+	if (err)
+		return err;
+	err = crypto_shash_update(desc, (u8 *)&sisn, 4);
+	if (err)
+		return err;
+	err = crypto_shash_update(desc, (u8 *)&disn, 4);
+	if (err)
+		return err;
+	err = crypto_shash_update(desc, (u8 *)&digestbits, 2);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/* Convert a variable-length key to a 16-byte fixed-length key for AES-CMAC
+ * This is described in RFC5926 section 3.1.1.2
+ */
+static int aes_setkey_derived(struct crypto_shash *tfm, u8 *key, size_t keylen)
+{
+	static const u8 zeros[16] = {0};
+	u8 derived_key[16];
+	int err;
+
+	if (WARN_ON_ONCE(crypto_shash_digestsize(tfm) != 16))
+		return -EINVAL;
+	err = crypto_shash_setkey(tfm, zeros, sizeof(zeros));
+	if (err)
+		return err;
+	err = crypto_shash_tfm_digest(tfm, key, keylen, derived_key);
+	if (err)
+		return err;
+	return crypto_shash_setkey(tfm, derived_key, sizeof(derived_key));
+}
+
+static int tcp_authopt_setkey(struct crypto_shash *tfm, struct tcp_authopt_key_info *key)
+{
+	if (key->alg_id == TCP_AUTHOPT_ALG_AES_128_CMAC_96 && key->keylen != 16)
+		return aes_setkey_derived(tfm, key->key, key->keylen);
+	else
+		return crypto_shash_setkey(tfm, key->key, key->keylen);
+}
+
+static int tcp_authopt_get_traffic_key(struct sock *sk,
+				       struct sk_buff *skb,
+				       struct tcp_authopt_key_info *key,
+				       bool input,
+				       bool ipv6,
+				       u8 *traffic_key)
+{
+	SHASH_DESC_ON_STACK(desc, kdf_tfm);
+	struct crypto_shash *kdf_tfm;
+	int err;
+
+	kdf_tfm = tcp_authopt_get_kdf_shash(key);
+	if (IS_ERR(kdf_tfm))
+		return PTR_ERR(kdf_tfm);
+
+	err = tcp_authopt_setkey(kdf_tfm, key);
+	if (err)
+		goto out;
+
+	desc->tfm = kdf_tfm;
+	err = crypto_shash_init(desc);
+	if (err)
+		goto out;
+
+	err = tcp_authopt_shash_traffic_key(desc, sk, skb, input, ipv6);
+	if (err)
+		goto out;
+
+	err = crypto_shash_final(desc, traffic_key);
+	if (err)
+		goto out;
+
+out:
+	tcp_authopt_put_kdf_shash(key, kdf_tfm);
+	return err;
+}
+
+static int crypto_shash_update_zero(struct shash_desc *desc, int len)
+{
+	u8 zero = 0;
+	int i, err;
+
+	for (i = 0; i < len; ++i) {
+		err = crypto_shash_update(desc, &zero, 1);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int tcp_authopt_hash_tcp4_pseudoheader(struct shash_desc *desc,
+					      __be32 saddr,
+					      __be32 daddr,
+					      int nbytes)
+{
+	struct tcp4_pseudohdr phdr = {
+		.saddr = saddr,
+		.daddr = daddr,
+		.pad = 0,
+		.protocol = IPPROTO_TCP,
+		.len = htons(nbytes)
+	};
+	return crypto_shash_update(desc, (u8 *)&phdr, sizeof(phdr));
+}
+
+static int tcp_authopt_hash_tcp6_pseudoheader(struct shash_desc *desc,
+					      struct in6_addr *saddr,
+					      struct in6_addr *daddr,
+					      u32 plen)
+{
+	int err;
+	__be32 buf[2];
+
+	buf[0] = htonl(plen);
+	buf[1] = htonl(IPPROTO_TCP);
+
+	err = crypto_shash_update(desc, (u8 *)saddr, sizeof(*saddr));
+	if (err)
+		return err;
+	err = crypto_shash_update(desc, (u8 *)daddr, sizeof(*daddr));
+	if (err)
+		return err;
+	return crypto_shash_update(desc, (u8 *)&buf, sizeof(buf));
+}
+
+/* TCP authopt as found in header */
+struct tcphdr_authopt {
+	u8 num;
+	u8 len;
+	u8 keyid;
+	u8 rnextkeyid;
+	u8 mac[0];
+};
+
+/* Find TCP_AUTHOPT in header.
+ *
+ * Returns pointer to TCP_AUTHOPT or NULL if not found.
+ */
+static u8 *tcp_authopt_find_option(struct tcphdr *th)
+{
+	int length = (th->doff << 2) - sizeof(*th);
+	u8 *ptr = (u8 *)(th + 1);
+
+	while (length >= 2) {
+		int opcode = *ptr++;
+		int opsize;
+
+		switch (opcode) {
+		case TCPOPT_EOL:
+			return NULL;
+		case TCPOPT_NOP:
+			length--;
+			continue;
+		default:
+			if (length < 2)
+				return NULL;
+			opsize = *ptr++;
+			if (opsize < 2)
+				return NULL;
+			if (opsize > length)
+				return NULL;
+			if (opcode == TCPOPT_AUTHOPT)
+				return ptr - 2;
+		}
+		ptr += opsize - 2;
+		length -= opsize;
+	}
+	return NULL;
+}
+
+/** Hash tcphdr options.
+ *  If include_options is false then only the TCPOPT_AUTHOPT option itself is hashed
+ *  Maybe we could skip option parsing by assuming the AUTHOPT header is at hash_location-4?
+ */
+static int tcp_authopt_hash_opts(struct shash_desc *desc,
+				 struct tcphdr *th,
+				 bool include_options)
+{
+	int err;
+	/* start of options */
+	u8 *tcp_opts = (u8 *)(th + 1);
+	/* end of options */
+	u8 *tcp_data = ((u8 *)th) + th->doff * 4;
+	/* pointer to TCPOPT_AUTHOPT */
+	u8 *authopt_ptr = tcp_authopt_find_option(th);
+	u8 authopt_len;
+
+	if (!authopt_ptr)
+		return -EINVAL;
+	authopt_len = *(authopt_ptr + 1);
+
+	if (include_options) {
+		err = crypto_shash_update(desc, tcp_opts, authopt_ptr - tcp_opts + 4);
+		if (err)
+			return err;
+		err = crypto_shash_update_zero(desc, authopt_len - 4);
+		if (err)
+			return err;
+		err = crypto_shash_update(desc,
+					  authopt_ptr + authopt_len,
+					  tcp_data - (authopt_ptr + authopt_len));
+		if (err)
+			return err;
+	} else {
+		err = crypto_shash_update(desc, authopt_ptr, 4);
+		if (err)
+			return err;
+		err = crypto_shash_update_zero(desc, authopt_len - 4);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int skb_shash_frags(struct shash_desc *desc,
+			   struct sk_buff *skb)
+{
+	struct sk_buff *frag_iter;
+	int err, i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+		u32 p_off, p_len, copied;
+		struct page *p;
+		u8 *vaddr;
+
+		skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f),
+				      p, p_off, p_len, copied) {
+			vaddr = kmap_atomic(p);
+			err = crypto_shash_update(desc, vaddr + p_off, p_len);
+			kunmap_atomic(vaddr);
+			if (err)
+				return err;
+		}
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		err = skb_shash_frags(desc, frag_iter);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int tcp_authopt_hash_packet(struct crypto_shash *tfm,
+				   struct sock *sk,
+				   struct sk_buff *skb,
+				   bool input,
+				   bool ipv6,
+				   bool include_options,
+				   u8 *macbuf)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+	SHASH_DESC_ON_STACK(desc, tfm);
+	int err;
+
+	/* NOTE: SNE unimplemented */
+	__be32 sne = 0;
+
+	desc->tfm = tfm;
+	err = crypto_shash_init(desc);
+	if (err)
+		return err;
+
+	err = crypto_shash_update(desc, (u8 *)&sne, 4);
+	if (err)
+		return err;
+
+	if (ipv6) {
+		struct in6_addr *saddr;
+		struct in6_addr *daddr;
+
+		if (input) {
+			saddr = &ipv6_hdr(skb)->saddr;
+			daddr = &ipv6_hdr(skb)->daddr;
+		} else {
+			saddr = &sk->sk_v6_rcv_saddr;
+			daddr = &sk->sk_v6_daddr;
+		}
+		err = tcp_authopt_hash_tcp6_pseudoheader(desc, saddr, daddr, skb->len);
+		if (err)
+			return err;
+	} else {
+		__be32 saddr;
+		__be32 daddr;
+
+		if (input) {
+			saddr = ip_hdr(skb)->saddr;
+			daddr = ip_hdr(skb)->daddr;
+		} else {
+			saddr = sk->sk_rcv_saddr;
+			daddr = sk->sk_daddr;
+		}
+		err = tcp_authopt_hash_tcp4_pseudoheader(desc, saddr, daddr, skb->len);
+		if (err)
+			return err;
+	}
+
+	// TCP header with checksum set to zero
+	{
+		struct tcphdr hashed_th = *th;
+
+		hashed_th.check = 0;
+		err = crypto_shash_update(desc, (u8 *)&hashed_th, sizeof(hashed_th));
+		if (err)
+			return err;
+	}
+
+	// TCP options
+	err = tcp_authopt_hash_opts(desc, th, include_options);
+	if (err)
+		return err;
+
+	// Rest of SKB->data
+	err = crypto_shash_update(desc, (u8 *)th + th->doff * 4, skb_headlen(skb) - th->doff * 4);
+	if (err)
+		return err;
+
+	err = skb_shash_frags(desc, skb);
+	if (err)
+		return err;
+
+	return crypto_shash_final(desc, macbuf);
+}
+
+/**
+ * __tcp_authopt_calc_mac - Compute packet MAC using key
+ *
+ * @macbuf: output buffer. Must be large enough to fit the digestsize of the
+ *          underlying transform before truncation. Please use TCP_AUTHOPT_MAXMACBUF
+ */
+static int __tcp_authopt_calc_mac(struct sock *sk,
+				  struct sk_buff *skb,
+				  struct tcp_authopt_key_info *key,
+				  bool input,
+				  char *macbuf)
+{
+	struct crypto_shash *mac_tfm;
+	u8 traffic_key[TCP_AUTHOPT_MAX_TRAFFIC_KEY_LEN];
+	int err;
+	bool ipv6 = (sk->sk_family != AF_INET);
+
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+		return -EINVAL;
+
+	err = tcp_authopt_get_traffic_key(sk, skb, key, input, ipv6, traffic_key);
+	if (err)
+		return err;
+
+	mac_tfm = tcp_authopt_get_mac_shash(key);
+	if (IS_ERR(mac_tfm))
+		return PTR_ERR(mac_tfm);
+	err = crypto_shash_setkey(mac_tfm, traffic_key, key->alg->traffic_key_len);
+	if (err)
+		goto out;
+
+	err = tcp_authopt_hash_packet(mac_tfm,
+				      sk,
+				      skb,
+				      input,
+				      ipv6,
+				      !(key->flags & TCP_AUTHOPT_KEY_EXCLUDE_OPTS),
+				      macbuf);
+
+out:
+	tcp_authopt_put_mac_shash(key, mac_tfm);
+	return err;
+}

index f6d7d6fa50c0..263f98c3a1a8 100644
@@ -51,28 +51,131 @@ struct tcp_authopt_info {
 	u32 src_isn;
 	u32 dst_isn;
 };
 
 #ifdef CONFIG_TCP_AUTHOPT
+DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed);
+
+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);
+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);
+static inline struct tcp_authopt_key_info *tcp_authopt_select_key(
+		const struct sock *sk,
+		const struct sock *addr_sk,
+		u8 *rnextkeyid)
+{
+	if (static_branch_unlikely(&tcp_authopt_needed)) {
+		struct tcp_authopt_info *info = rcu_dereference(tcp_sk(sk)->authopt_info);
+
+		if (info)
+			return __tcp_authopt_select_key(sk, info, addr_sk, rnextkeyid);
+	}
+	return NULL;
+}
+int tcp_authopt_hash(
+		char *hash_location,
+		struct tcp_authopt_key_info *key,
+		struct sock *sk, struct sk_buff *skb);
+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)
+{
+	if (!rcu_dereference(tcp_sk(oldsk)->authopt_info))
+		return 0;
+	else
+		return __tcp_authopt_openreq(newsk, oldsk, req);
+}
+static inline void tcp_authopt_time_wait(
+		struct tcp_timewait_sock *tcptw,
+		struct tcp_sock *tp)
+{
+	if (static_branch_unlikely(&tcp_authopt_needed)) {
+		/* Transfer ownership of authopt_info to the twsk
+		 * This requires no other users of the origin sock.
+		 */
+		sock_owned_by_me((struct sock *)tp);
+		tcptw->tw_authopt_info = tp->authopt_info;
+		tp->authopt_info = NULL;
+	} else {
+		tcptw->tw_authopt_info = NULL;
+	}
+}
+int __tcp_authopt_inbound_check(
+		struct sock *sk,
+		struct sk_buff *skb,
+		struct tcp_authopt_info *info);
+/** tcp_authopt_inbound_check - check for valid TCP-AO signature.
+ *
+ * Return negative ERRNO on error, 0 if not present and 1 if present and valid
+ * If both TCP-AO and MD5 signatures are found this is reported as an error.
+ */
+static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb)
+{
+	if (static_branch_unlikely(&tcp_authopt_needed)) {
+		struct tcp_authopt_info *info = rcu_dereference(tcp_sk(sk)->authopt_info);
+
+		if (info)
+			return __tcp_authopt_inbound_check(sk, skb, info);
+	}
+
+	return 0;
+}
 #else
 static inline int tcp_set_authopt(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
 static inline int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *key)
 {
 	return -ENOPROTOOPT;
 }
+static inline void tcp_authopt_free(struct sock *sk, struct tcp_authopt_info *info)
+{
+}
 static inline void tcp_authopt_clear(struct sock *sk)
 {
 }
 static inline int tcp_set_authopt_key(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	return -ENOPROTOOPT;
 }
+static inline struct tcp_authopt_key_info *tcp_authopt_select_key(
+		const struct sock *sk,
+		const struct sock *addr_sk,
+		u8 *rnextkeyid)
+{
+	return NULL;
+}
+static inline int tcp_authopt_hash(
+		char *hash_location,
+		struct tcp_authopt_key_info *key,
+		struct sock *sk, struct sk_buff *skb)
+{
+	return -EINVAL;
+}
+static inline int tcp_authopt_openreq(struct sock *newsk,
+				      const struct sock *oldsk,
+				      struct request_sock *req)
+{
+	return 0;
+}
+static inline void tcp_authopt_time_wait(
+		struct tcp_timewait_sock *tcptw,
+		struct tcp_sock *tp);
+{
+}
+static inline int tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb)
+{
+	return 0;
+}
 #endif
 
 #endif /* _LINUX_TCP_AUTHOPT_H */

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 b0d3a09dc84e..61dd06f8389c 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)

318 lines not on this page · raw message

index 141e85e6422b..7691eac93051 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>

@@ -5967,18 +5968,34 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 	if (!icsk->icsk_ca_initialized)
 		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
+static void tcp_authopt_finish_connect(struct sock *sk, struct sk_buff *skb)
+{
+#ifdef CONFIG_TCP_AUTHOPT
+	struct tcp_authopt_info *info;
+
+	info = rcu_dereference_protected(tcp_sk(sk)->authopt_info, lockdep_sock_is_held(sk));
+	if (!info)
+		return;
+
+	info->src_isn = ntohl(tcp_hdr(skb)->ack_seq) - 1;
+	info->dst_isn = ntohl(tcp_hdr(skb)->seq);
+#endif
+}
+
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	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 1348615c7576..e5c790795662 100644
@@ -1933,10 +1933,26 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 	TCP_SKB_CB(skb)->sacked	 = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
 			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
 }
 
+static int tcp_v4_auth_inbound_check(
+		struct sock *sk,
+		struct sk_buff *skb,
+		int dif, int sdif)
+{
+	int aoret;
+
+	aoret = tcp_authopt_inbound_check(sk, skb);
+	if (aoret < 0)
+		return aoret;
+	if (aoret > 0)
+		return 0;
+
+	return tcp_v4_inbound_md5_hash(sk, skb, dif, sdif);
+}
+
 /*
  *	From tcp_input.c
  */
 
 int tcp_v4_rcv(struct sk_buff *skb)

@@ -1991,11 +2007,11 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		struct request_sock *req = inet_reqsk(sk);
 		bool req_stolen = false;
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
+		if (unlikely(tcp_v4_auth_inbound_check(sk, skb, dif, sdif))) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
 		}
 		if (tcp_checksum_complete(skb)) {

@@ -2057,11 +2073,11 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	}
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))
+	if (tcp_v4_auth_inbound_check(sk, skb, dif, sdif))
 		goto discard_and_relse;
 
 	nf_reset_ct(skb);
 
 	if (tcp_filter(sk, skb))

index cf913a66df17..d4828cf3d6d1 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 (static_branch_unlikely(&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;

223 lines not on this page · raw message

index 0ce52d46e4f8..724145ddf122 100644
@@ -40,10 +40,11 @@
 #include <linux/icmpv6.h>
 #include <linux/random.h>
 #include <linux/indirect_call_wrapper.h>
 
 #include <net/tcp.h>
+#include <net/tcp_authopt.h>
 #include <net/ndisc.h>
 #include <net/inet6_hashtables.h>
 #include <net/inet6_connection_sock.h>
 #include <net/ipv6.h>
 #include <net/transp_v6.h>

@@ -1614,10 +1615,26 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->sacked = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
 			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
 }
 
+static int tcp_v6_auth_inbound_check(
+		struct sock *sk,
+		struct sk_buff *skb,
+		int dif, int sdif)
+{
+	int aoret;
+
+	aoret = tcp_authopt_inbound_check(sk, skb);
+	if (aoret < 0)
+		return aoret;
+	if (aoret > 0)
+		return 0;
+
+	return tcp_v6_inbound_md5_hash(sk, skb, dif, sdif);
+}
+
 INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 {
 	struct sk_buff *skb_to_free;
 	int sdif = inet6_sdif(skb);
 	int dif = inet6_iif(skb);

@@ -1667,11 +1684,11 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 		struct request_sock *req = inet_reqsk(sk);
 		bool req_stolen = false;
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) {
+		if (tcp_v6_auth_inbound_check(sk, skb, dif, sdif)) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
 		}
 		if (tcp_checksum_complete(skb)) {

@@ -1730,11 +1747,11 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 	}
 
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif))
+	if (tcp_v6_auth_inbound_check(sk, skb, dif, sdif))
 		goto discard_and_relse;
 
 	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
 	th = (const struct tcphdr *)skb->data;

index 263f98c3a1a8..422f0034d32b 100644
@@ -51,10 +51,11 @@ struct tcp_authopt_info {
 	u32 src_isn;
 	u32 dst_isn;
 };
 
 #ifdef CONFIG_TCP_AUTHOPT
+extern int sysctl_tcp_authopt;
 DECLARE_STATIC_KEY_FALSE(tcp_authopt_needed);
 
 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);

index 4680268f2e59..365466fbca8b 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;

@@ -595,10 +596,19 @@ static struct ctl_table ipv4_table[] = {
 		.procname	= "tcp_tx_skb_cache",
 		.data		= &tcp_tx_skb_cache_key.key,
 		.mode		= 0644,
 		.proc_handler	= proc_do_static_key,
 	},
+#ifdef CONFIG_TCP_AUTHOPT
+	{
+		.procname	= "tcp_authopt",
+		.data		= &sysctl_tcp_authopt,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 	{ }
 };
 
 static struct ctl_table ipv4_net_table[] = {
 	{

index 0c32b8fb1d41..41f844d5d49a 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);
 /* only for CONFIG_IPV6=m */
 EXPORT_SYMBOL(tcp_authopt_needed);
 

@@ -361,10 +366,12 @@ 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);
+	if (!sysctl_tcp_authopt)
+		return -EPERM;
 
 	err = _copy_from_sockptr_tolerant((u8*)&opt, sizeof(opt), optval, optlen);
 	if (err)
 		return err;
 

@@ -384,10 +391,12 @@ int tcp_get_authopt_val(struct sock *sk, struct tcp_authopt *opt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_authopt_info *info;
 
 	sock_owned_by_me(sk);
+	if (!sysctl_tcp_authopt)
+		return -EPERM;
 
 	memset(opt, 0, sizeof(*opt));
 	info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
 	if (!info)
 		return -ENOENT;

@@ -452,10 +461,12 @@ 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);
+	if (!sysctl_tcp_authopt)
+		return -EPERM;
 
 	err = _copy_from_sockptr_tolerant((u8*)&opt, sizeof(opt), optval, optlen);
 	if (err)
 		return err;
 

index 724145ddf122..d922219af20e 100644
@@ -896,13 +896,37 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
 	__be32 mrst = 0, *topt;
 	struct dst_entry *dst;
 	__u32 mark = 0;
+#ifdef CONFIG_TCP_AUTHOPT
+	struct tcp_authopt_info *authopt_info = NULL;
+	struct tcp_authopt_key_info *authopt_key_info = NULL;
+	u8 authopt_rnextkeyid;
+#endif
 
 	if (tsecr)
 		tot_len += TCPOLEN_TSTAMP_ALIGNED;
+#ifdef CONFIG_TCP_AUTHOPT
+	/* Key lookup before SKB allocation */
+	if (static_branch_unlikely(&tcp_authopt_needed) && sk)
+	{
+		if (sk->sk_state == TCP_TIME_WAIT)
+			authopt_info = tcp_twsk(sk)->tw_authopt_info;
+		else
+			authopt_info = rcu_dereference(tcp_sk(sk)->authopt_info);
+
+		if (authopt_info) {
+			authopt_key_info = __tcp_authopt_select_key(sk, authopt_info, sk, &authopt_rnextkeyid);
+			if (authopt_key_info) {
+				tot_len += TCPOLEN_AUTHOPT_OUTPUT;
+				/* Don't use MD5 */
+				key = NULL;
+			}
+		}
+	}
+#endif
 #ifdef CONFIG_TCP_MD5SIG
 	if (key)
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
 

@@ -955,10 +979,21 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 		tcp_v6_md5_hash_hdr((__u8 *)topt, key,
 				    &ipv6_hdr(skb)->saddr,
 				    &ipv6_hdr(skb)->daddr, t1);
 	}
 #endif
+#ifdef CONFIG_TCP_AUTHOPT
+	/* Compute the TCP-AO mac. Unlike in the ipv4 case we have a real SKB */
+	if (static_branch_unlikely(&tcp_authopt_needed) && authopt_key_info)
+	{
+		*topt++ = htonl((TCPOPT_AUTHOPT << 24) |
+				(TCPOLEN_AUTHOPT_OUTPUT << 16) |
+				(authopt_key_info->send_id << 8) |
+				(authopt_rnextkeyid));
+		tcp_authopt_hash((char*)topt, authopt_key_info, (struct sock*)sk, buff);
+	}
+#endif
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.daddr = ipv6_hdr(skb)->saddr;
 	fl6.saddr = ipv6_hdr(skb)->daddr;
 	fl6.flowlabel = label;

index 422f0034d32b..b012eaaf416f 100644
@@ -81,10 +81,17 @@ 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 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)

167 lines not on this page · raw message

index e5c790795662..2d5fbe7690aa 100644
@@ -641,10 +641,50 @@ 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);
 
+/** 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;
+}
+
 /*
  *	This routine will send an RST to the other tcp.
  *
  *	Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
  *		      for reset.

@@ -656,10 +696,12 @@ 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)

@@ -709,12 +751,28 @@ 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.
+	 *
+	 * FIXME: What about RST in response to SYN?
+	 */
+	if (static_branch_unlikely(&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;
 

@@ -752,11 +810,10 @@ 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;
 
 	}

@@ -773,10 +830,11 @@ 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
+skip_md5sig:
 	/* Can't co-exist with TCPMD5, hence check rep.opt[0] */
 	if (rep.opt[0] == 0) {
 		__be32 mrst = mptcp_reset_option(skb);
 
 		if (mrst) {

@@ -825,11 +883,11 @@ 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) || defined(CONFIG_TCP_AUTHOPT)
 out:
 	rcu_read_unlock();
 #endif
 }
 

@@ -847,10 +905,12 @@ 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;

@@ -878,10 +938,22 @@ 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 (static_branch_unlikely(&tcp_authopt_needed))
+	{
+		int offset = (tsecr) ? 3 : 0;
+
+		int tcp_authopt_ret = tcp_v4_authopt_handle_reply(sk, skb, &rep.opt[offset], &rep.th);
+		if (tcp_authopt_ret) {
+			arg.iov[0].iov_len += tcp_authopt_ret;
+			goto skip_md5sig;
+		}
+	}
+#endif
 #ifdef CONFIG_TCP_MD5SIG
 	if (key) {
 		int offset = (tsecr) ? 3 : 0;
 
 		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |

@@ -894,10 +966,11 @@ static void tcp_v4_send_ack(const struct sock *sk,
 		tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset],
 				    key, ip_hdr(skb)->saddr,
 				    ip_hdr(skb)->daddr, &rep.th);
 	}
 #endif
+skip_md5sig:
 	arg.flags = reply_flags;
 	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
 				      ip_hdr(skb)->saddr, /* XXX */
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;

index bd6288302094..f04c6af79129 100644
@@ -100,10 +100,12 @@ struct sock_args {
 		struct sockaddr_in v4;
 		struct sockaddr_in6 v6;
 	} md5_prefix;
 	unsigned int prefix_len;
 
+	const char *authopt_password;
+
 	/* expected addresses and device index for connection */
 	const char *expected_dev;
 	const char *expected_server_dev;
 	int expected_ifindex;
 

@@ -250,10 +252,27 @@ 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;
+
+	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;

@@ -1508,10 +1527,15 @@ 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);

@@ -1630,10 +1654,13 @@ 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) {

@@ -1819,11 +1846,11 @@ 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:Fbq"
+#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:A:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
 
 static void print_usage(char *prog)
 {
 	printf(
 	"usage: %s OPTS\n"

@@ -1856,10 +1883,12 @@ static void print_usage(char *prog)
 	"    -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"
+	"    -A password   use RFC5925 TCP Authentication option\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"
 	"    -1 addr       Expected remote address\n"

@@ -1970,10 +1999,13 @@ int main(int argc, char *argv[])
 			args.client_pw = optarg;
 			break;
 		case 'm':
 			args.md5_prefix_str = optarg;
 			break;
+		case 'A':
+			args.authopt_password = optarg;
+			break;
 		case 'S':
 			args.use_setsockopt = 1;
 			break;
 		case 'C':
 			args.use_cmsg = 1;

index b012eaaf416f..c7d6a51fa5c5 100644
@@ -45,11 +45,21 @@ struct tcp_authopt_key_info {
  */
 struct tcp_authopt_info {
 	/** @head: List of tcp_authopt_key_info */
 	struct hlist_head head;
 	struct rcu_head rcu;
+	/**
+	 * @send_keyid - 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;
 	u32 flags;
+	u8 send_keyid;
+	u8 send_rnextkeyid;
+	u8 recv_keyid;
+	u8 recv_rnextkeyid;
 	u32 src_isn;
 	u32 dst_isn;
 };
 
 #ifdef CONFIG_TCP_AUTHOPT

@@ -63,21 +73,22 @@ 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,
 		u8 *rnextkeyid)
 {
 	if (static_branch_unlikely(&tcp_authopt_needed)) {
 		struct tcp_authopt_info *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 c68ecd617774..6357966bada9 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`
  *

181 lines not on this page · raw message

index 2d5fbe7690aa..6b44bf0ca053 100644
@@ -661,11 +661,11 @@ static int tcp_v4_authopt_handle_reply(
 		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 d922219af20e..3dcf0ba4a215 100644
@@ -914,11 +914,11 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 			authopt_info = tcp_twsk(sk)->tw_authopt_info;
 		else
 			authopt_info = rcu_dereference(tcp_sk(sk)->authopt_info);
 
 		if (authopt_info) {
-			authopt_key_info = __tcp_authopt_select_key(sk, authopt_info, sk, &authopt_rnextkeyid);
+			authopt_key_info = __tcp_authopt_select_key(sk, authopt_info, sk, &authopt_rnextkeyid, false);
 			if (authopt_key_info) {
 				tot_len += TCPOLEN_AUTHOPT_OUTPUT;
 				/* Don't use MD5 */
 				key = NULL;
 			}