[PATCH v7 26/26] tcp: authopt: Initial implementation of TCP_REPAIR_AUTHOPT

[Leonard Crestez]

In order to support TCP_REPAIR for connections using RFC5925
Authentication Option add a sockopt to get/set ISN and SNE values.

The TCP_REPAIR_AUTHOxpTP sockopt is only allowed when the socket is
already in "repair" mode, this behavior is shared with other sockopts
relevant to TCP_REPAIR.

The setsockopt further requires the TCP_ESTABLISHED state, this is
because it relies on snd_nxt which is only initialized after connect().

For SNE restoration we provide a full 64-bit sequence number on "get" and
handle any recent 64-bit sequence number on "set", where recent means
"within ~2GB to the current window".

Linux tracks snd_sne and rcv_sne as the extension of snd_nxt and
rcv_nxt but this is an implementation detail and snd_nxt doesn't even
seem to be one of the values that can be read by userspace. Handling SNE
with 64-bit values means userspace doesn't need to worry about matching
snd_nxt.

Signed-off-by: Leonard Crestez <cdleonard@xxxxxxxxx>
---
 include/net/tcp_authopt.h |  2 ++
 include/uapi/linux/tcp.h  | 19 +++++++++++
 net/ipv4/tcp.c            | 23 ++++++++++++++
 net/ipv4/tcp_authopt.c    | 66 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 110 insertions(+)

diff --git a/include/net/tcp_authopt.h b/include/net/tcp_authopt.h
index 4f83d8e54fef..fda6dc4b5d57 100644
--- a/include/net/tcp_authopt.h
+++ b/include/net/tcp_authopt.h
@@ -231,10 +231,12 @@ static inline void tcp_authopt_update_snd_sne(struct tcp_sock *tp, u32 seq)
 						 lockdep_sock_is_held((struct sock *)tp));
 		if (info)
 			__tcp_authopt_update_snd_sne(tp, info, seq);
 	}
 }
+int tcp_get_authopt_repair_val(struct sock *sk, struct tcp_authopt_repair *opt);
+int tcp_set_authopt_repair(struct sock *sk, sockptr_t optval, unsigned int optlen);
 #else
 static inline void tcp_authopt_clear(struct sock *sk)
 {
 }
 static inline int tcp_authopt_openreq(struct sock *newsk,
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 5ca8aa9d5e43..ee6836f87cf8 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -128,10 +128,11 @@ enum {
 #define TCP_CM_INQ		TCP_INQ
 
 #define TCP_TX_DELAY		37	/* delay outgoing packets by XX usec */
 #define TCP_AUTHOPT		38	/* TCP Authentication Option (RFC5925) */
 #define TCP_AUTHOPT_KEY		39	/* TCP Authentication Option Key (RFC5925) */
+#define TCP_REPAIR_AUTHOPT	40
 
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
 #define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
@@ -490,10 +491,28 @@ struct tcp_authopt_key {
 	 * address match is performed.
 	 */
 	int	prefixlen;
 };
 
+/**
+ * struct tcp_authopt_repair - TCP_REPAIR information related to Authentication Option
+ * @src_isn: Local Initial Sequence Number
+ * @dst_isn: Remote Initial Sequence Number
+ * @snd_sne: Sequence Number Extension for Send (upper 32 bits of snd_seq)
+ * @rcv_sne: Sequence Number Extension for Recv (upper 32 bits of rcv_seq)
+ * @snd_seq: Recent Send Sequence Number (lower 32 bits of snd_sne)
+ * @rcv_seq: Recent Recv Sequence Number (lower 32 bits of rcv_sne)
+ */
+struct tcp_authopt_repair {
+	__u32	src_isn;
+	__u32	dst_isn;
+	__u32	snd_sne;
+	__u32	rcv_sne;
+	__u32	snd_seq;
+	__u32	rcv_seq;
+};
+
 /* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
 
 #define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1
 struct tcp_zerocopy_receive {
 	__u64 address;		/* in: address of mapping */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 205534d501ec..ad0af4efd265 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3715,10 +3715,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		err = tcp_set_authopt(sk, optval, optlen);
 		break;
 	case TCP_AUTHOPT_KEY:
 		err = tcp_set_authopt_key(sk, optval, optlen);
 		break;
+	case TCP_REPAIR_AUTHOPT:
+		err = tcp_set_authopt_repair(sk, optval, optlen);
+		break;
 #endif
 	case TCP_USER_TIMEOUT:
 		/* Cap the max time in ms TCP will retry or probe the window
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */
@@ -4387,10 +4390,30 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			return -EFAULT;
 		if (copy_to_user(optval, &info, len))
 			return -EFAULT;
 		return 0;
 	}
+	case TCP_REPAIR_AUTHOPT: {
+		struct tcp_authopt_repair val;
+		int err;
+
+		if (get_user(len, optlen))
+			return -EFAULT;
+
+		lock_sock(sk);
+		err = tcp_get_authopt_repair_val(sk, &val);
+		release_sock(sk);
+
+		if (err)
+			return err;
+		len = min_t(unsigned int, len, sizeof(val));
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &val, len))
+			return -EFAULT;
+		return 0;
+	}
 #endif
 
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/ipv4/tcp_authopt.c b/net/ipv4/tcp_authopt.c
index 933a4bbddb70..a77067c0498b 100644
--- a/net/ipv4/tcp_authopt.c
+++ b/net/ipv4/tcp_authopt.c
@@ -1775,10 +1775,76 @@ int __tcp_authopt_inbound_check(struct sock *sk, struct sk_buff *skb,
 
 	return 1;
 }
 EXPORT_SYMBOL(__tcp_authopt_inbound_check);
 
+int tcp_get_authopt_repair_val(struct sock *sk, struct tcp_authopt_repair *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;
+	if (!tp->repair)
+		return -EPERM;
+
+	info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
+	if (!info)
+		return -ENOENT;
+
+	opt->dst_isn = info->dst_isn;
+	opt->src_isn = info->src_isn;
+	opt->rcv_sne = info->rcv_sne;
+	opt->snd_sne = info->snd_sne;
+	opt->rcv_seq = tp->rcv_nxt;
+	opt->snd_seq = tp->snd_nxt;
+
+	return 0;
+}
+
+int tcp_set_authopt_repair(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_authopt_info *info;
+	struct tcp_authopt_repair val;
+	int err;
+
+	sock_owned_by_me(sk);
+	err = check_sysctl_tcp_authopt();
+	if (err)
+		return err;
+
+	if (optlen != sizeof(val))
+		return -EFAULT;
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
+		return -EFAULT;
+
+	/* tcp_authopt repair relies on fields that are only initialized after
+	 * tcp_connect. Doing this setsockopt before connect() can't be correct
+	 * so return an error.
+	 */
+	if (sk->sk_state != TCP_ESTABLISHED)
+		return -EPERM;
+
+	info = rcu_dereference_check(tp->authopt_info, lockdep_sock_is_held(sk));
+	if (!info)
+		return -ENOENT;
+	if (!tp->repair)
+		return -EPERM;
+
+	info->dst_isn = val.dst_isn;
+	info->src_isn = val.src_isn;
+	info->rcv_sne = compute_sne(val.rcv_sne, val.rcv_seq, tp->rcv_nxt);
+	info->snd_sne = compute_sne(val.snd_sne, val.snd_seq, tp->snd_nxt);
+
+	return 0;
+}
+
 #ifdef CONFIG_PROC_FS
 struct tcp_authopt_iter_state {
 	struct seq_net_private p;
 };
 
-- 
2.25.1