net/tcp: Add TCP-AO getsockopt()s

Introduce getsockopt(TCP_AO_GET_KEYS) that lets a user get TCP-AO keys
and their properties from a socket. The user can provide a filter
to match the specific key to be dumped or ::get_all = 1 may be
used to dump all keys in one syscall.

Add another getsockopt(TCP_AO_INFO) for providing per-socket/per-ao_info
stats: packet counters, Current_key/RNext_key and flags like
::ao_required and ::accept_icmps.

Co-developed-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Co-developed-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Acked-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 308 insertions, 0 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1be6467a059a..ce33eee9d0f2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4284,6 +4284,19 @@ zerocopy_rcv_out:
 		return err;
 	}
 #endif
+	case TCP_AO_GET_KEYS:
+	case TCP_AO_INFO: {
+		int err;
+
+		sockopt_lock_sock(sk);
+		if (optname == TCP_AO_GET_KEYS)
+			err = tcp_ao_get_mkts(sk, optval, optlen);
+		else
+			err = tcp_ao_get_sock_info(sk, optval, optlen);
+		sockopt_release_sock(sk);
+
+		return err;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 10cc6be4d537..cbc1ee0f5b9a 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1894,3 +1894,298 @@ int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen)
 	return tcp_parse_ao(sk, cmd, AF_INET, optval, optlen);
 }
 
+/* tcp_ao_copy_mkts_to_user(ao_info, optval, optlen)
+ *
+ * @ao_info:	struct tcp_ao_info on the socket that
+ *		socket getsockopt(TCP_AO_GET_KEYS) is executed on
+ * @optval:	pointer to array of tcp_ao_getsockopt structures in user space.
+ *		Must be != NULL.
+ * @optlen:	pointer to size of tcp_ao_getsockopt structure.
+ *		Must be != NULL.
+ *
+ * Return value: 0 on success, a negative error number otherwise.
+ *
+ * optval points to an array of tcp_ao_getsockopt structures in user space.
+ * optval[0] is used as both input and output to getsockopt. It determines
+ * which keys are returned by the kernel.
+ * optval[0].nkeys is the size of the array in user space. On return it contains
+ * the number of keys matching the search criteria.
+ * If tcp_ao_getsockopt::get_all is set, then all keys in the socket are
+ * returned, otherwise only keys matching <addr, prefix, sndid, rcvid>
+ * in optval[0] are returned.
+ * optlen is also used as both input and output. The user provides the size
+ * of struct tcp_ao_getsockopt in user space, and the kernel returns the size
+ * of the structure in kernel space.
+ * The size of struct tcp_ao_getsockopt may differ between user and kernel.
+ * There are three cases to consider:
+ *  * If usize == ksize, then keys are copied verbatim.
+ *  * If usize < ksize, then the userspace has passed an old struct to a
+ *    newer kernel. The rest of the trailing bytes in optval[0]
+ *    (ksize - usize) are interpreted as 0 by the kernel.
+ *  * If usize > ksize, then the userspace has passed a new struct to an
+ *    older kernel. The trailing bytes unknown to the kernel (usize - ksize)
+ *    are checked to ensure they are zeroed, otherwise -E2BIG is returned.
+ * On return the kernel fills in min(usize, ksize) in each entry of the array.
+ * The layout of the fields in the user and kernel structures is expected to
+ * be the same (including in the 32bit vs 64bit case).
+ */
+static int tcp_ao_copy_mkts_to_user(struct tcp_ao_info *ao_info,
+				    sockptr_t optval, sockptr_t optlen)
+{
+	struct tcp_ao_getsockopt opt_in, opt_out;
+	struct tcp_ao_key *key, *current_key;
+	bool do_address_matching = true;
+	union tcp_ao_addr *addr = NULL;
+	unsigned int max_keys;	/* maximum number of keys to copy to user */
+	size_t out_offset = 0;
+	size_t bytes_to_write;	/* number of bytes to write to user level */
+	int err, user_len;
+	u32 matched_keys;	/* keys from ao_info matched so far */
+	int optlen_out;
+	__be16 port = 0;
+
+	if (copy_from_sockptr(&user_len, optlen, sizeof(int)))
+		return -EFAULT;
+
+	if (user_len <= 0)
+		return -EINVAL;
+
+	memset(&opt_in, 0, sizeof(struct tcp_ao_getsockopt));
+	err = copy_struct_from_sockptr(&opt_in, sizeof(opt_in),
+				       optval, user_len);
+	if (err < 0)
+		return err;
+
+	if (opt_in.pkt_good || opt_in.pkt_bad)
+		return -EINVAL;
+
+	if (opt_in.reserved != 0)
+		return -EINVAL;
+
+	max_keys = opt_in.nkeys;
+
+	if (opt_in.get_all || opt_in.is_current || opt_in.is_rnext) {
+		if (opt_in.get_all && (opt_in.is_current || opt_in.is_rnext))
+			return -EINVAL;
+		do_address_matching = false;
+	}
+
+	switch (opt_in.addr.ss_family) {
+	case AF_INET: {
+		struct sockaddr_in *sin;
+		__be32 mask;
+
+		sin = (struct sockaddr_in *)&opt_in.addr;
+		port = sin->sin_port;
+		addr = (union tcp_ao_addr *)&sin->sin_addr;
+
+		if (opt_in.prefix > 32)
+			return -EINVAL;
+
+		if (ntohl(sin->sin_addr.s_addr) == INADDR_ANY &&
+		    opt_in.prefix != 0)
+			return -EINVAL;
+
+		mask = inet_make_mask(opt_in.prefix);
+		if (sin->sin_addr.s_addr & ~mask)
+			return -EINVAL;
+
+		break;
+	}
+	case AF_INET6: {
+		struct sockaddr_in6 *sin6;
+		struct in6_addr *addr6;
+
+		sin6 = (struct sockaddr_in6 *)&opt_in.addr;
+		addr = (union tcp_ao_addr *)&sin6->sin6_addr;
+		addr6 = &sin6->sin6_addr;
+		port = sin6->sin6_port;
+
+		/* We don't have to change family and @addr here if
+		 * ipv6_addr_v4mapped() like in key adding:
+		 * tcp_ao_key_cmp() does it. Do the sanity checks though.
+		 */
+		if (opt_in.prefix != 0) {
+			if (ipv6_addr_v4mapped(addr6)) {
+				__be32 mask, addr4 = addr6->s6_addr32[3];
+
+				if (opt_in.prefix > 32 ||
+				    ntohl(addr4) == INADDR_ANY)
+					return -EINVAL;
+				mask = inet_make_mask(opt_in.prefix);
+				if (addr4 & ~mask)
+					return -EINVAL;
+			} else {
+				struct in6_addr pfx;
+
+				if (ipv6_addr_any(addr6) ||
+				    opt_in.prefix > 128)
+					return -EINVAL;
+
+				ipv6_addr_prefix(&pfx, addr6, opt_in.prefix);
+				if (ipv6_addr_cmp(&pfx, addr6))
+					return -EINVAL;
+			}
+		} else if (!ipv6_addr_any(addr6)) {
+			return -EINVAL;
+		}
+		break;
+	}
+	case 0:
+		if (!do_address_matching)
+			break;
+		fallthrough;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	if (!do_address_matching) {
+		/* We could just ignore those, but let's do stricter checks */
+		if (addr || port)
+			return -EINVAL;
+		if (opt_in.prefix || opt_in.sndid || opt_in.rcvid)
+			return -EINVAL;
+	}
+
+	bytes_to_write = min_t(int, user_len, sizeof(struct tcp_ao_getsockopt));
+	matched_keys = 0;
+	/* May change in RX, while we're dumping, pre-fetch it */
+	current_key = READ_ONCE(ao_info->current_key);
+
+	hlist_for_each_entry_rcu(key, &ao_info->head, node) {
+		if (opt_in.get_all)
+			goto match;
+
+		if (opt_in.is_current || opt_in.is_rnext) {
+			if (opt_in.is_current && key == current_key)
+				goto match;
+			if (opt_in.is_rnext && key == ao_info->rnext_key)
+				goto match;
+			continue;
+		}
+
+		if (tcp_ao_key_cmp(key, addr, opt_in.prefix,
+				   opt_in.addr.ss_family,
+				   opt_in.sndid, opt_in.rcvid) != 0)
+			continue;
+match:
+		matched_keys++;
+		if (matched_keys > max_keys)
+			continue;
+
+		memset(&opt_out, 0, sizeof(struct tcp_ao_getsockopt));
+
+		if (key->family == AF_INET) {
+			struct sockaddr_in *sin_out = (struct sockaddr_in *)&opt_out.addr;
+
+			sin_out->sin_family = key->family;
+			sin_out->sin_port = 0;
+			memcpy(&sin_out->sin_addr, &key->addr, sizeof(struct in_addr));
+		} else {
+			struct sockaddr_in6 *sin6_out = (struct sockaddr_in6 *)&opt_out.addr;
+
+			sin6_out->sin6_family = key->family;
+			sin6_out->sin6_port = 0;
+			memcpy(&sin6_out->sin6_addr, &key->addr, sizeof(struct in6_addr));
+		}
+		opt_out.sndid = key->sndid;
+		opt_out.rcvid = key->rcvid;
+		opt_out.prefix = key->prefixlen;
+		opt_out.keyflags = key->keyflags;
+		opt_out.is_current = (key == current_key);
+		opt_out.is_rnext = (key == ao_info->rnext_key);
+		opt_out.nkeys = 0;
+		opt_out.maclen = key->maclen;
+		opt_out.keylen = key->keylen;
+		opt_out.pkt_good = atomic64_read(&key->pkt_good);
+		opt_out.pkt_bad = atomic64_read(&key->pkt_bad);
+		memcpy(&opt_out.key, key->key, key->keylen);
+		tcp_sigpool_algo(key->tcp_sigpool_id, opt_out.alg_name, 64);
+
+		/* Copy key to user */
+		if (copy_to_sockptr_offset(optval, out_offset,
+					   &opt_out, bytes_to_write))
+			return -EFAULT;
+		out_offset += user_len;
+	}
+
+	optlen_out = (int)sizeof(struct tcp_ao_getsockopt);
+	if (copy_to_sockptr(optlen, &optlen_out, sizeof(int)))
+		return -EFAULT;
+
+	out_offset = offsetof(struct tcp_ao_getsockopt, nkeys);
+	if (copy_to_sockptr_offset(optval, out_offset,
+				   &matched_keys, sizeof(u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen)
+{
+	struct tcp_ao_info *ao_info;
+
+	ao_info = setsockopt_ao_info(sk);
+	if (IS_ERR(ao_info))
+		return PTR_ERR(ao_info);
+	if (!ao_info)
+		return -ENOENT;
+
+	return tcp_ao_copy_mkts_to_user(ao_info, optval, optlen);
+}
+
+int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen)
+{
+	struct tcp_ao_info_opt out, in = {};
+	struct tcp_ao_key *current_key;
+	struct tcp_ao_info *ao;
+	int err, len;
+
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
+		return -EFAULT;
+
+	if (len <= 0)
+		return -EINVAL;
+
+	/* Copying this "in" only to check ::reserved, ::reserved2,
+	 * that may be needed to extend (struct tcp_ao_info_opt) and
+	 * what getsockopt() provides in future.
+	 */
+	err = copy_struct_from_sockptr(&in, sizeof(in), optval, len);
+	if (err)
+		return err;
+
+	if (in.reserved != 0 || in.reserved2 != 0)
+		return -EINVAL;
+
+	ao = setsockopt_ao_info(sk);
+	if (IS_ERR(ao))
+		return PTR_ERR(ao);
+	if (!ao)
+		return -ENOENT;
+
+	memset(&out, 0, sizeof(out));
+	out.ao_required		= ao->ao_required;
+	out.accept_icmps	= ao->accept_icmps;
+	out.pkt_good		= atomic64_read(&ao->counters.pkt_good);
+	out.pkt_bad		= atomic64_read(&ao->counters.pkt_bad);
+	out.pkt_key_not_found	= atomic64_read(&ao->counters.key_not_found);
+	out.pkt_ao_required	= atomic64_read(&ao->counters.ao_required);
+	out.pkt_dropped_icmp	= atomic64_read(&ao->counters.dropped_icmp);
+
+	current_key = READ_ONCE(ao->current_key);
+	if (current_key) {
+		out.set_current = 1;
+		out.current_key = current_key->sndid;
+	}
+	if (ao->rnext_key) {
+		out.set_rnext = 1;
+		out.rnext = ao->rnext_key->rcvid;
+	}
+
+	if (copy_to_sockptr(optval, &out, min_t(int, len, sizeof(out))))
+		return -EFAULT;
+
+	return 0;
+}
+