net: WireGuard secure network tunnel

WireGuard is a layer 3 secure networking tunnel made specifically for
the kernel, that aims to be much simpler and easier to audit than IPsec.
Extensive documentation and description of the protocol and
considerations, along with formal proofs of the cryptography, are
available at:

  * https://www.wireguard.com/
  * https://www.wireguard.com/papers/wireguard.pdf

This commit implements WireGuard as a simple network device driver,
accessible in the usual RTNL way used by virtual network drivers. It
makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of
networking subsystem APIs. It has a somewhat novel multicore queueing
system designed for maximum throughput and minimal latency of encryption
operations, but it is implemented modestly using workqueues and NAPI.
Configuration is done via generic Netlink, and following a review from
the Netlink maintainer a year ago, several high profile userspace tools
have already implemented the API.

This commit also comes with several different tests, both in-kernel
tests and out-of-kernel tests based on network namespaces, taking profit
of the fact that sockets used by WireGuard intentionally stay in the
namespace the WireGuard interface was originally created, exactly like
the semantics of userspace tun devices. See wireguard.com/netns/ for
pictures and examples.

The source code is fairly short, but rather than combining everything
into a single file, WireGuard is developed as cleanly separable files,
making auditing and comprehension easier. Things are laid out as
follows:

  * noise.[ch], cookie.[ch], messages.h: These implement the bulk of the
    cryptographic aspects of the protocol, and are mostly data-only in
    nature, taking in buffers of bytes and spitting out buffers of
    bytes. They also handle reference counting for their various shared
    pieces of data, like keys and key lists.

  * ratelimiter.[ch]: Used as an integral part of cookie.[ch] for
    ratelimiting certain types of cryptographic operations in accordance
    with particular WireGuard semantics.

  * allowedips.[ch], peerlookup.[ch]: The main lookup structures of
    WireGuard, the former being trie-like with particular semantics, an
    integral part of the design of the protocol, and the latter just
    being nice helper functions around the various hashtables we use.

  * device.[ch]: Implementation of functions for the netdevice and for
    rtnl, responsible for maintaining the life of a given interface and
    wiring it up to the rest of WireGuard.

  * peer.[ch]: Each interface has a list of peers, with helper functions
    available here for creation, destruction, and reference counting.

  * socket.[ch]: Implementation of functions related to udp_socket and
    the general set of kernel socket APIs, for sending and receiving
    ciphertext UDP packets, and taking care of WireGuard-specific sticky
    socket routing semantics for the automatic roaming.

  * netlink.[ch]: Userspace API entry point for configuring WireGuard
    peers and devices. The API has been implemented by several userspace
    tools and network management utility, and the WireGuard project
    distributes the basic wg(8) tool.

  * queueing.[ch]: Shared function on the rx and tx path for handling
    the various queues used in the multicore algorithms.

  * send.c: Handles encrypting outgoing packets in parallel on
    multiple cores, before sending them in order on a single core, via
    workqueues and ring buffers. Also handles sending handshake and cookie
    messages as part of the protocol, in parallel.

  * receive.c: Handles decrypting incoming packets in parallel on
    multiple cores, before passing them off in order to be ingested via
    the rest of the networking subsystem with GRO via the typical NAPI
    poll function. Also handles receiving handshake and cookie messages
    as part of the protocol, in parallel.

  * timers.[ch]: Uses the timer wheel to implement protocol particular
    event timeouts, and gives a set of very simple event-driven entry
    point functions for callers.

  * main.c, version.h: Initialization and deinitialization of the module.

  * selftest/*.h: Runtime unit tests for some of the most security
    sensitive functions.

  * tools/testing/selftests/wireguard/netns.sh: Aforementioned testing
    script using network namespaces.

This commit aims to be as self-contained as possible, implementing
WireGuard as a standalone module not needing much special handling or
coordination from the network subsystem. I expect for future
optimizations to the network stack to positively improve WireGuard, and
vice-versa, but for the time being, this exists as intentionally
standalone.

We introduce a menu option for CONFIG_WIREGUARD, as well as providing a
verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: David Miller <davem@davemloft.net>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: linux-crypto@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 458 insertions, 0 deletions

diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
new file mode 100644
index 000000000000..16b19824b9ad
--- /dev/null
+++ b/drivers/net/wireguard/device.c
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include "queueing.h"
+#include "socket.h"
+#include "timers.h"
+#include "device.h"
+#include "ratelimiter.h"
+#include "peer.h"
+#include "messages.h"
+
+#include <linux/module.h>
+#include <linux/rtnetlink.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/if_arp.h>
+#include <linux/icmp.h>
+#include <linux/suspend.h>
+#include <net/icmp.h>
+#include <net/rtnetlink.h>
+#include <net/ip_tunnels.h>
+#include <net/addrconf.h>
+
+static LIST_HEAD(device_list);
+
+static int wg_open(struct net_device *dev)
+{
+	struct in_device *dev_v4 = __in_dev_get_rtnl(dev);
+	struct inet6_dev *dev_v6 = __in6_dev_get(dev);
+	struct wg_device *wg = netdev_priv(dev);
+	struct wg_peer *peer;
+	int ret;
+
+	if (dev_v4) {
+		/* At some point we might put this check near the ip_rt_send_
+		 * redirect call of ip_forward in net/ipv4/ip_forward.c, similar
+		 * to the current secpath check.
+		 */
+		IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
+		IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false;
+	}
+	if (dev_v6)
+		dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
+
+	ret = wg_socket_init(wg, wg->incoming_port);
+	if (ret < 0)
+		return ret;
+	mutex_lock(&wg->device_update_lock);
+	list_for_each_entry(peer, &wg->peer_list, peer_list) {
+		wg_packet_send_staged_packets(peer);
+		if (peer->persistent_keepalive_interval)
+			wg_packet_send_keepalive(peer);
+	}
+	mutex_unlock(&wg->device_update_lock);
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int wg_pm_notification(struct notifier_block *nb, unsigned long action,
+			      void *data)
+{
+	struct wg_device *wg;
+	struct wg_peer *peer;
+
+	/* If the machine is constantly suspending and resuming, as part of
+	 * its normal operation rather than as a somewhat rare event, then we
+	 * don't actually want to clear keys.
+	 */
+	if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_ANDROID))
+		return 0;
+
+	if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE)
+		return 0;
+
+	rtnl_lock();
+	list_for_each_entry(wg, &device_list, device_list) {
+		mutex_lock(&wg->device_update_lock);
+		list_for_each_entry(peer, &wg->peer_list, peer_list) {
+			del_timer(&peer->timer_zero_key_material);
+			wg_noise_handshake_clear(&peer->handshake);
+			wg_noise_keypairs_clear(&peer->keypairs);
+		}
+		mutex_unlock(&wg->device_update_lock);
+	}
+	rtnl_unlock();
+	rcu_barrier();
+	return 0;
+}
+
+static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification };
+#endif
+
+static int wg_stop(struct net_device *dev)
+{
+	struct wg_device *wg = netdev_priv(dev);
+	struct wg_peer *peer;
+
+	mutex_lock(&wg->device_update_lock);
+	list_for_each_entry(peer, &wg->peer_list, peer_list) {
+		wg_packet_purge_staged_packets(peer);
+		wg_timers_stop(peer);
+		wg_noise_handshake_clear(&peer->handshake);
+		wg_noise_keypairs_clear(&peer->keypairs);
+		wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
+	}
+	mutex_unlock(&wg->device_update_lock);
+	skb_queue_purge(&wg->incoming_handshakes);
+	wg_socket_reinit(wg, NULL, NULL);
+	return 0;
+}
+
+static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct wg_device *wg = netdev_priv(dev);
+	struct sk_buff_head packets;
+	struct wg_peer *peer;
+	struct sk_buff *next;
+	sa_family_t family;
+	u32 mtu;
+	int ret;
+
+	if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) {
+		ret = -EPROTONOSUPPORT;
+		net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
+		goto err;
+	}
+
+	peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb);
+	if (unlikely(!peer)) {
+		ret = -ENOKEY;
+		if (skb->protocol == htons(ETH_P_IP))
+			net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n",
+					    dev->name, &ip_hdr(skb)->daddr);
+		else if (skb->protocol == htons(ETH_P_IPV6))
+			net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
+					    dev->name, &ipv6_hdr(skb)->daddr);
+		goto err;
+	}
+
+	family = READ_ONCE(peer->endpoint.addr.sa_family);
+	if (unlikely(family != AF_INET && family != AF_INET6)) {
+		ret = -EDESTADDRREQ;
+		net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n",
+				    dev->name, peer->internal_id);
+		goto err_peer;
+	}
+
+	mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+
+	__skb_queue_head_init(&packets);
+	if (!skb_is_gso(skb)) {
+		skb_mark_not_on_list(skb);
+	} else {
+		struct sk_buff *segs = skb_gso_segment(skb, 0);
+
+		if (unlikely(IS_ERR(segs))) {
+			ret = PTR_ERR(segs);
+			goto err_peer;
+		}
+		dev_kfree_skb(skb);
+		skb = segs;
+	}
+
+	skb_list_walk_safe(skb, skb, next) {
+		skb_mark_not_on_list(skb);
+
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (unlikely(!skb))
+			continue;
+
+		/* We only need to keep the original dst around for icmp,
+		 * so at this point we're in a position to drop it.
+		 */
+		skb_dst_drop(skb);
+
+		PACKET_CB(skb)->mtu = mtu;
+
+		__skb_queue_tail(&packets, skb);
+	}
+
+	spin_lock_bh(&peer->staged_packet_queue.lock);
+	/* If the queue is getting too big, we start removing the oldest packets
+	 * until it's small again. We do this before adding the new packet, so
+	 * we don't remove GSO segments that are in excess.
+	 */
+	while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
+		dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
+		++dev->stats.tx_dropped;
+	}
+	skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
+	spin_unlock_bh(&peer->staged_packet_queue.lock);
+
+	wg_packet_send_staged_packets(peer);
+
+	wg_peer_put(peer);
+	return NETDEV_TX_OK;
+
+err_peer:
+	wg_peer_put(peer);
+err:
+	++dev->stats.tx_errors;
+	if (skb->protocol == htons(ETH_P_IP))
+		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+	kfree_skb(skb);
+	return ret;
+}
+
+static const struct net_device_ops netdev_ops = {
+	.ndo_open		= wg_open,
+	.ndo_stop		= wg_stop,
+	.ndo_start_xmit		= wg_xmit,
+	.ndo_get_stats64	= ip_tunnel_get_stats64
+};
+
+static void wg_destruct(struct net_device *dev)
+{
+	struct wg_device *wg = netdev_priv(dev);
+
+	rtnl_lock();
+	list_del(&wg->device_list);
+	rtnl_unlock();
+	mutex_lock(&wg->device_update_lock);
+	wg->incoming_port = 0;
+	wg_socket_reinit(wg, NULL, NULL);
+	/* The final references are cleared in the below calls to destroy_workqueue. */
+	wg_peer_remove_all(wg);
+	destroy_workqueue(wg->handshake_receive_wq);
+	destroy_workqueue(wg->handshake_send_wq);
+	destroy_workqueue(wg->packet_crypt_wq);
+	wg_packet_queue_free(&wg->decrypt_queue, true);
+	wg_packet_queue_free(&wg->encrypt_queue, true);
+	rcu_barrier(); /* Wait for all the peers to be actually freed. */
+	wg_ratelimiter_uninit();
+	memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
+	skb_queue_purge(&wg->incoming_handshakes);
+	free_percpu(dev->tstats);
+	free_percpu(wg->incoming_handshakes_worker);
+	if (wg->have_creating_net_ref)
+		put_net(wg->creating_net);
+	kvfree(wg->index_hashtable);
+	kvfree(wg->peer_hashtable);
+	mutex_unlock(&wg->device_update_lock);
+
+	pr_debug("%s: Interface deleted\n", dev->name);
+	free_netdev(dev);
+}
+
+static const struct device_type device_type = { .name = KBUILD_MODNAME };
+
+static void wg_setup(struct net_device *dev)
+{
+	struct wg_device *wg = netdev_priv(dev);
+	enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+				    NETIF_F_SG | NETIF_F_GSO |
+				    NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
+
+	dev->netdev_ops = &netdev_ops;
+	dev->hard_header_len = 0;
+	dev->addr_len = 0;
+	dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
+	dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE);
+	dev->type = ARPHRD_NONE;
+	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
+	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->features |= NETIF_F_LLTX;
+	dev->features |= WG_NETDEV_FEATURES;
+	dev->hw_features |= WG_NETDEV_FEATURES;
+	dev->hw_enc_features |= WG_NETDEV_FEATURES;
+	dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
+		   sizeof(struct udphdr) -
+		   max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+
+	SET_NETDEV_DEVTYPE(dev, &device_type);
+
+	/* We need to keep the dst around in case of icmp replies. */
+	netif_keep_dst(dev);
+
+	memset(wg, 0, sizeof(*wg));
+	wg->dev = dev;
+}
+
+static int wg_newlink(struct net *src_net, struct net_device *dev,
+		      struct nlattr *tb[], struct nlattr *data[],
+		      struct netlink_ext_ack *extack)
+{
+	struct wg_device *wg = netdev_priv(dev);
+	int ret = -ENOMEM;
+
+	wg->creating_net = src_net;
+	init_rwsem(&wg->static_identity.lock);
+	mutex_init(&wg->socket_update_lock);
+	mutex_init(&wg->device_update_lock);
+	skb_queue_head_init(&wg->incoming_handshakes);
+	wg_allowedips_init(&wg->peer_allowedips);
+	wg_cookie_checker_init(&wg->cookie_checker, wg);
+	INIT_LIST_HEAD(&wg->peer_list);
+	wg->device_update_gen = 1;
+
+	wg->peer_hashtable = wg_pubkey_hashtable_alloc();
+	if (!wg->peer_hashtable)
+		return ret;
+
+	wg->index_hashtable = wg_index_hashtable_alloc();
+	if (!wg->index_hashtable)
+		goto err_free_peer_hashtable;
+
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		goto err_free_index_hashtable;
+
+	wg->incoming_handshakes_worker =
+		wg_packet_percpu_multicore_worker_alloc(
+				wg_packet_handshake_receive_worker, wg);
+	if (!wg->incoming_handshakes_worker)
+		goto err_free_tstats;
+
+	wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
+			WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
+	if (!wg->handshake_receive_wq)
+		goto err_free_incoming_handshakes;
+
+	wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
+			WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
+	if (!wg->handshake_send_wq)
+		goto err_destroy_handshake_receive;
+
+	wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s",
+			WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name);
+	if (!wg->packet_crypt_wq)
+		goto err_destroy_handshake_send;
+
+	ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
+				   true, MAX_QUEUED_PACKETS);
+	if (ret < 0)
+		goto err_destroy_packet_crypt;
+
+	ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
+				   true, MAX_QUEUED_PACKETS);
+	if (ret < 0)
+		goto err_free_encrypt_queue;
+
+	ret = wg_ratelimiter_init();
+	if (ret < 0)
+		goto err_free_decrypt_queue;
+
+	ret = register_netdevice(dev);
+	if (ret < 0)
+		goto err_uninit_ratelimiter;
+
+	list_add(&wg->device_list, &device_list);
+
+	/* We wait until the end to assign priv_destructor, so that
+	 * register_netdevice doesn't call it for us if it fails.
+	 */
+	dev->priv_destructor = wg_destruct;
+
+	pr_debug("%s: Interface created\n", dev->name);
+	return ret;
+
+err_uninit_ratelimiter:
+	wg_ratelimiter_uninit();
+err_free_decrypt_queue:
+	wg_packet_queue_free(&wg->decrypt_queue, true);
+err_free_encrypt_queue:
+	wg_packet_queue_free(&wg->encrypt_queue, true);
+err_destroy_packet_crypt:
+	destroy_workqueue(wg->packet_crypt_wq);
+err_destroy_handshake_send:
+	destroy_workqueue(wg->handshake_send_wq);
+err_destroy_handshake_receive:
+	destroy_workqueue(wg->handshake_receive_wq);
+err_free_incoming_handshakes:
+	free_percpu(wg->incoming_handshakes_worker);
+err_free_tstats:
+	free_percpu(dev->tstats);
+err_free_index_hashtable:
+	kvfree(wg->index_hashtable);
+err_free_peer_hashtable:
+	kvfree(wg->peer_hashtable);
+	return ret;
+}
+
+static struct rtnl_link_ops link_ops __read_mostly = {
+	.kind			= KBUILD_MODNAME,
+	.priv_size		= sizeof(struct wg_device),
+	.setup			= wg_setup,
+	.newlink		= wg_newlink,
+};
+
+static int wg_netdevice_notification(struct notifier_block *nb,
+				     unsigned long action, void *data)
+{
+	struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
+	struct wg_device *wg = netdev_priv(dev);
+
+	ASSERT_RTNL();
+
+	if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
+		return 0;
+
+	if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
+		put_net(wg->creating_net);
+		wg->have_creating_net_ref = false;
+	} else if (dev_net(dev) != wg->creating_net &&
+		   !wg->have_creating_net_ref) {
+		wg->have_creating_net_ref = true;
+		get_net(wg->creating_net);
+	}
+	return 0;
+}
+
+static struct notifier_block netdevice_notifier = {
+	.notifier_call = wg_netdevice_notification
+};
+
+int __init wg_device_init(void)
+{
+	int ret;
+
+#ifdef CONFIG_PM_SLEEP
+	ret = register_pm_notifier(&pm_notifier);
+	if (ret)
+		return ret;
+#endif
+
+	ret = register_netdevice_notifier(&netdevice_notifier);
+	if (ret)
+		goto error_pm;
+
+	ret = rtnl_link_register(&link_ops);
+	if (ret)
+		goto error_netdevice;
+
+	return 0;
+
+error_netdevice:
+	unregister_netdevice_notifier(&netdevice_notifier);
+error_pm:
+#ifdef CONFIG_PM_SLEEP
+	unregister_pm_notifier(&pm_notifier);
+#endif
+	return ret;
+}
+
+void wg_device_uninit(void)
+{
+	rtnl_link_unregister(&link_ops);
+	unregister_netdevice_notifier(&netdevice_notifier);
+#ifdef CONFIG_PM_SLEEP
+	unregister_pm_notifier(&pm_notifier);
+#endif
+	rcu_barrier();
+}