OpenCloudOS-Kernel/drivers/net/wireguard/noise.c

833 lines
26 KiB
C
Raw Normal View History

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>
2019-12-09 07:27:34 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*/
#include "noise.h"
#include "device.h"
#include "peer.h"
#include "messages.h"
#include "queueing.h"
#include "peerlookup.h"
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
#include <linux/scatterlist.h>
#include <linux/highmem.h>
#include <crypto/algapi.h>
/* This implements Noise_IKpsk2:
*
* <- s
* ******
* -> e, es, s, ss, {t}
* <- e, ee, se, psk, {}
*/
static const u8 handshake_name[37] = "Noise_IKpsk2_25519_ChaChaPoly_BLAKE2s";
static const u8 identifier_name[34] = "WireGuard v1 zx2c4 Jason@zx2c4.com";
static u8 handshake_init_hash[NOISE_HASH_LEN] __ro_after_init;
static u8 handshake_init_chaining_key[NOISE_HASH_LEN] __ro_after_init;
static atomic64_t keypair_counter = ATOMIC64_INIT(0);
void __init wg_noise_init(void)
{
struct blake2s_state blake;
blake2s(handshake_init_chaining_key, handshake_name, NULL,
NOISE_HASH_LEN, sizeof(handshake_name), 0);
blake2s_init(&blake, NOISE_HASH_LEN);
blake2s_update(&blake, handshake_init_chaining_key, NOISE_HASH_LEN);
blake2s_update(&blake, identifier_name, sizeof(identifier_name));
blake2s_final(&blake, handshake_init_hash);
}
/* Must hold peer->handshake.static_identity->lock */
bool wg_noise_precompute_static_static(struct wg_peer *peer)
{
wireguard: noise: reject peers with low order public keys Our static-static calculation returns a failure if the public key is of low order. We check for this when peers are added, and don't allow them to be added if they're low order, except in the case where we haven't yet been given a private key. In that case, we would defer the removal of the peer until we're given a private key, since at that point we're doing new static-static calculations which incur failures we can act on. This meant, however, that we wound up removing peers rather late in the configuration flow. Syzkaller points out that peer_remove calls flush_workqueue, which in turn might then wait for sending a handshake initiation to complete. Since handshake initiation needs the static identity lock, holding the static identity lock while calling peer_remove can result in a rare deadlock. We have precisely this case in this situation of late-stage peer removal based on an invalid public key. We can't drop the lock when removing, because then incoming handshakes might interact with a bogus static-static calculation. While the band-aid patch for this would involve breaking up the peer removal into two steps like wg_peer_remove_all does, in order to solve the locking issue, there's actually a much more elegant way of fixing this: If the static-static calculation succeeds with one private key, it *must* succeed with all others, because all 32-byte strings map to valid private keys, thanks to clamping. That means we can get rid of this silly dance and locking headaches of removing peers late in the configuration flow, and instead just reject them early on, regardless of whether the device has yet been assigned a private key. For the case where the device doesn't yet have a private key, we safely use zeros just for the purposes of checking for low order points by way of checking the output of the calculation. The following PoC will trigger the deadlock: ip link add wg0 type wireguard ip addr add 10.0.0.1/24 dev wg0 ip link set wg0 up ping -f 10.0.0.2 & while true; do wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234 wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=) done [ 0.949105] ====================================================== [ 0.949550] WARNING: possible circular locking dependency detected [ 0.950143] 5.5.0-debug+ #18 Not tainted [ 0.950431] ------------------------------------------------------ [ 0.950959] wg/89 is trying to acquire lock: [ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0 [ 0.951865] [ 0.951865] but task is already holding lock: [ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.953011] [ 0.953011] which lock already depends on the new lock. [ 0.953011] [ 0.953651] [ 0.953651] the existing dependency chain (in reverse order) is: [ 0.954292] [ 0.954292] -> #2 (&wg->static_identity.lock){++++}: [ 0.954804] lock_acquire+0x127/0x350 [ 0.955133] down_read+0x83/0x410 [ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700 [ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280 [ 0.956401] wg_packet_handshake_send_worker+0x10/0x20 [ 0.956841] process_one_work+0x806/0x1500 [ 0.957167] worker_thread+0x8c/0xcb0 [ 0.957549] kthread+0x2ee/0x3b0 [ 0.957792] ret_from_fork+0x24/0x30 [ 0.958234] [ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}: [ 0.958808] lock_acquire+0x127/0x350 [ 0.959075] process_one_work+0x7ab/0x1500 [ 0.959369] worker_thread+0x8c/0xcb0 [ 0.959639] kthread+0x2ee/0x3b0 [ 0.959896] ret_from_fork+0x24/0x30 [ 0.960346] [ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}: [ 0.960945] check_prev_add+0x167/0x1e20 [ 0.961351] __lock_acquire+0x2012/0x3170 [ 0.961725] lock_acquire+0x127/0x350 [ 0.961990] flush_workqueue+0x106/0x12f0 [ 0.962280] peer_remove_after_dead+0x160/0x220 [ 0.962600] wg_set_device+0xa24/0xcc0 [ 0.962994] genl_rcv_msg+0x52f/0xe90 [ 0.963298] netlink_rcv_skb+0x111/0x320 [ 0.963618] genl_rcv+0x1f/0x30 [ 0.963853] netlink_unicast+0x3f6/0x610 [ 0.964245] netlink_sendmsg+0x700/0xb80 [ 0.964586] __sys_sendto+0x1dd/0x2c0 [ 0.964854] __x64_sys_sendto+0xd8/0x1b0 [ 0.965141] do_syscall_64+0x90/0xd9a [ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.965769] [ 0.965769] other info that might help us debug this: [ 0.965769] [ 0.966337] Chain exists of: [ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock [ 0.966337] [ 0.967417] Possible unsafe locking scenario: [ 0.967417] [ 0.967836] CPU0 CPU1 [ 0.968155] ---- ---- [ 0.968497] lock(&wg->static_identity.lock); [ 0.968779] lock((work_completion)(&peer->transmit_handshake_work)); [ 0.969345] lock(&wg->static_identity.lock); [ 0.969809] lock((wq_completion)wg-kex-wg0); [ 0.970146] [ 0.970146] *** DEADLOCK *** [ 0.970146] [ 0.970531] 5 locks held by wg/89: [ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30 [ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90 [ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0 [ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0 [ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.973653] [ 0.973653] stack backtrace: [ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18 [ 0.974476] Call Trace: [ 0.974638] dump_stack+0x97/0xe0 [ 0.974869] check_noncircular+0x312/0x3e0 [ 0.975132] ? print_circular_bug+0x1f0/0x1f0 [ 0.975410] ? __kernel_text_address+0x9/0x30 [ 0.975727] ? unwind_get_return_address+0x51/0x90 [ 0.976024] check_prev_add+0x167/0x1e20 [ 0.976367] ? graph_lock+0x70/0x160 [ 0.976682] __lock_acquire+0x2012/0x3170 [ 0.976998] ? register_lock_class+0x1140/0x1140 [ 0.977323] lock_acquire+0x127/0x350 [ 0.977627] ? flush_workqueue+0xe3/0x12f0 [ 0.977890] flush_workqueue+0x106/0x12f0 [ 0.978147] ? flush_workqueue+0xe3/0x12f0 [ 0.978410] ? find_held_lock+0x2c/0x110 [ 0.978662] ? lock_downgrade+0x6e0/0x6e0 [ 0.978919] ? queue_rcu_work+0x60/0x60 [ 0.979166] ? netif_napi_del+0x151/0x3b0 [ 0.979501] ? peer_remove_after_dead+0x160/0x220 [ 0.979871] peer_remove_after_dead+0x160/0x220 [ 0.980232] wg_set_device+0xa24/0xcc0 [ 0.980516] ? deref_stack_reg+0x8e/0xc0 [ 0.980801] ? set_peer+0xe10/0xe10 [ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150 [ 0.981430] ? __nla_validate_parse+0x163/0x270 [ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310 [ 0.982078] genl_rcv_msg+0x52f/0xe90 [ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.982690] ? register_lock_class+0x1140/0x1140 [ 0.983049] netlink_rcv_skb+0x111/0x320 [ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.983645] ? netlink_ack+0x880/0x880 [ 0.983888] genl_rcv+0x1f/0x30 [ 0.984168] netlink_unicast+0x3f6/0x610 [ 0.984443] ? netlink_detachskb+0x60/0x60 [ 0.984729] ? find_held_lock+0x2c/0x110 [ 0.984976] netlink_sendmsg+0x700/0xb80 [ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60 [ 0.985533] __sys_sendto+0x1dd/0x2c0 [ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0 [ 0.986039] ? sockfd_lookup_light+0x17/0x160 [ 0.986397] ? __sys_recvmsg+0x8c/0xf0 [ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0 [ 0.987018] __x64_sys_sendto+0xd8/0x1b0 [ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0 [ 0.987666] do_syscall_64+0x90/0xd9a [ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.988223] RIP: 0033:0x7fe77c12003e [ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4 [ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e [ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004 [ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c [ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c [ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001 Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-05 05:17:26 +08:00
bool ret;
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>
2019-12-09 07:27:34 +08:00
down_write(&peer->handshake.lock);
wireguard: noise: reject peers with low order public keys Our static-static calculation returns a failure if the public key is of low order. We check for this when peers are added, and don't allow them to be added if they're low order, except in the case where we haven't yet been given a private key. In that case, we would defer the removal of the peer until we're given a private key, since at that point we're doing new static-static calculations which incur failures we can act on. This meant, however, that we wound up removing peers rather late in the configuration flow. Syzkaller points out that peer_remove calls flush_workqueue, which in turn might then wait for sending a handshake initiation to complete. Since handshake initiation needs the static identity lock, holding the static identity lock while calling peer_remove can result in a rare deadlock. We have precisely this case in this situation of late-stage peer removal based on an invalid public key. We can't drop the lock when removing, because then incoming handshakes might interact with a bogus static-static calculation. While the band-aid patch for this would involve breaking up the peer removal into two steps like wg_peer_remove_all does, in order to solve the locking issue, there's actually a much more elegant way of fixing this: If the static-static calculation succeeds with one private key, it *must* succeed with all others, because all 32-byte strings map to valid private keys, thanks to clamping. That means we can get rid of this silly dance and locking headaches of removing peers late in the configuration flow, and instead just reject them early on, regardless of whether the device has yet been assigned a private key. For the case where the device doesn't yet have a private key, we safely use zeros just for the purposes of checking for low order points by way of checking the output of the calculation. The following PoC will trigger the deadlock: ip link add wg0 type wireguard ip addr add 10.0.0.1/24 dev wg0 ip link set wg0 up ping -f 10.0.0.2 & while true; do wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234 wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=) done [ 0.949105] ====================================================== [ 0.949550] WARNING: possible circular locking dependency detected [ 0.950143] 5.5.0-debug+ #18 Not tainted [ 0.950431] ------------------------------------------------------ [ 0.950959] wg/89 is trying to acquire lock: [ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0 [ 0.951865] [ 0.951865] but task is already holding lock: [ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.953011] [ 0.953011] which lock already depends on the new lock. [ 0.953011] [ 0.953651] [ 0.953651] the existing dependency chain (in reverse order) is: [ 0.954292] [ 0.954292] -> #2 (&wg->static_identity.lock){++++}: [ 0.954804] lock_acquire+0x127/0x350 [ 0.955133] down_read+0x83/0x410 [ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700 [ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280 [ 0.956401] wg_packet_handshake_send_worker+0x10/0x20 [ 0.956841] process_one_work+0x806/0x1500 [ 0.957167] worker_thread+0x8c/0xcb0 [ 0.957549] kthread+0x2ee/0x3b0 [ 0.957792] ret_from_fork+0x24/0x30 [ 0.958234] [ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}: [ 0.958808] lock_acquire+0x127/0x350 [ 0.959075] process_one_work+0x7ab/0x1500 [ 0.959369] worker_thread+0x8c/0xcb0 [ 0.959639] kthread+0x2ee/0x3b0 [ 0.959896] ret_from_fork+0x24/0x30 [ 0.960346] [ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}: [ 0.960945] check_prev_add+0x167/0x1e20 [ 0.961351] __lock_acquire+0x2012/0x3170 [ 0.961725] lock_acquire+0x127/0x350 [ 0.961990] flush_workqueue+0x106/0x12f0 [ 0.962280] peer_remove_after_dead+0x160/0x220 [ 0.962600] wg_set_device+0xa24/0xcc0 [ 0.962994] genl_rcv_msg+0x52f/0xe90 [ 0.963298] netlink_rcv_skb+0x111/0x320 [ 0.963618] genl_rcv+0x1f/0x30 [ 0.963853] netlink_unicast+0x3f6/0x610 [ 0.964245] netlink_sendmsg+0x700/0xb80 [ 0.964586] __sys_sendto+0x1dd/0x2c0 [ 0.964854] __x64_sys_sendto+0xd8/0x1b0 [ 0.965141] do_syscall_64+0x90/0xd9a [ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.965769] [ 0.965769] other info that might help us debug this: [ 0.965769] [ 0.966337] Chain exists of: [ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock [ 0.966337] [ 0.967417] Possible unsafe locking scenario: [ 0.967417] [ 0.967836] CPU0 CPU1 [ 0.968155] ---- ---- [ 0.968497] lock(&wg->static_identity.lock); [ 0.968779] lock((work_completion)(&peer->transmit_handshake_work)); [ 0.969345] lock(&wg->static_identity.lock); [ 0.969809] lock((wq_completion)wg-kex-wg0); [ 0.970146] [ 0.970146] *** DEADLOCK *** [ 0.970146] [ 0.970531] 5 locks held by wg/89: [ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30 [ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90 [ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0 [ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0 [ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.973653] [ 0.973653] stack backtrace: [ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18 [ 0.974476] Call Trace: [ 0.974638] dump_stack+0x97/0xe0 [ 0.974869] check_noncircular+0x312/0x3e0 [ 0.975132] ? print_circular_bug+0x1f0/0x1f0 [ 0.975410] ? __kernel_text_address+0x9/0x30 [ 0.975727] ? unwind_get_return_address+0x51/0x90 [ 0.976024] check_prev_add+0x167/0x1e20 [ 0.976367] ? graph_lock+0x70/0x160 [ 0.976682] __lock_acquire+0x2012/0x3170 [ 0.976998] ? register_lock_class+0x1140/0x1140 [ 0.977323] lock_acquire+0x127/0x350 [ 0.977627] ? flush_workqueue+0xe3/0x12f0 [ 0.977890] flush_workqueue+0x106/0x12f0 [ 0.978147] ? flush_workqueue+0xe3/0x12f0 [ 0.978410] ? find_held_lock+0x2c/0x110 [ 0.978662] ? lock_downgrade+0x6e0/0x6e0 [ 0.978919] ? queue_rcu_work+0x60/0x60 [ 0.979166] ? netif_napi_del+0x151/0x3b0 [ 0.979501] ? peer_remove_after_dead+0x160/0x220 [ 0.979871] peer_remove_after_dead+0x160/0x220 [ 0.980232] wg_set_device+0xa24/0xcc0 [ 0.980516] ? deref_stack_reg+0x8e/0xc0 [ 0.980801] ? set_peer+0xe10/0xe10 [ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150 [ 0.981430] ? __nla_validate_parse+0x163/0x270 [ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310 [ 0.982078] genl_rcv_msg+0x52f/0xe90 [ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.982690] ? register_lock_class+0x1140/0x1140 [ 0.983049] netlink_rcv_skb+0x111/0x320 [ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.983645] ? netlink_ack+0x880/0x880 [ 0.983888] genl_rcv+0x1f/0x30 [ 0.984168] netlink_unicast+0x3f6/0x610 [ 0.984443] ? netlink_detachskb+0x60/0x60 [ 0.984729] ? find_held_lock+0x2c/0x110 [ 0.984976] netlink_sendmsg+0x700/0xb80 [ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60 [ 0.985533] __sys_sendto+0x1dd/0x2c0 [ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0 [ 0.986039] ? sockfd_lookup_light+0x17/0x160 [ 0.986397] ? __sys_recvmsg+0x8c/0xf0 [ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0 [ 0.987018] __x64_sys_sendto+0xd8/0x1b0 [ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0 [ 0.987666] do_syscall_64+0x90/0xd9a [ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.988223] RIP: 0033:0x7fe77c12003e [ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4 [ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e [ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004 [ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c [ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c [ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001 Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-05 05:17:26 +08:00
if (peer->handshake.static_identity->has_identity) {
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>
2019-12-09 07:27:34 +08:00
ret = curve25519(
peer->handshake.precomputed_static_static,
peer->handshake.static_identity->static_private,
peer->handshake.remote_static);
wireguard: noise: reject peers with low order public keys Our static-static calculation returns a failure if the public key is of low order. We check for this when peers are added, and don't allow them to be added if they're low order, except in the case where we haven't yet been given a private key. In that case, we would defer the removal of the peer until we're given a private key, since at that point we're doing new static-static calculations which incur failures we can act on. This meant, however, that we wound up removing peers rather late in the configuration flow. Syzkaller points out that peer_remove calls flush_workqueue, which in turn might then wait for sending a handshake initiation to complete. Since handshake initiation needs the static identity lock, holding the static identity lock while calling peer_remove can result in a rare deadlock. We have precisely this case in this situation of late-stage peer removal based on an invalid public key. We can't drop the lock when removing, because then incoming handshakes might interact with a bogus static-static calculation. While the band-aid patch for this would involve breaking up the peer removal into two steps like wg_peer_remove_all does, in order to solve the locking issue, there's actually a much more elegant way of fixing this: If the static-static calculation succeeds with one private key, it *must* succeed with all others, because all 32-byte strings map to valid private keys, thanks to clamping. That means we can get rid of this silly dance and locking headaches of removing peers late in the configuration flow, and instead just reject them early on, regardless of whether the device has yet been assigned a private key. For the case where the device doesn't yet have a private key, we safely use zeros just for the purposes of checking for low order points by way of checking the output of the calculation. The following PoC will trigger the deadlock: ip link add wg0 type wireguard ip addr add 10.0.0.1/24 dev wg0 ip link set wg0 up ping -f 10.0.0.2 & while true; do wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234 wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=) done [ 0.949105] ====================================================== [ 0.949550] WARNING: possible circular locking dependency detected [ 0.950143] 5.5.0-debug+ #18 Not tainted [ 0.950431] ------------------------------------------------------ [ 0.950959] wg/89 is trying to acquire lock: [ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0 [ 0.951865] [ 0.951865] but task is already holding lock: [ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.953011] [ 0.953011] which lock already depends on the new lock. [ 0.953011] [ 0.953651] [ 0.953651] the existing dependency chain (in reverse order) is: [ 0.954292] [ 0.954292] -> #2 (&wg->static_identity.lock){++++}: [ 0.954804] lock_acquire+0x127/0x350 [ 0.955133] down_read+0x83/0x410 [ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700 [ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280 [ 0.956401] wg_packet_handshake_send_worker+0x10/0x20 [ 0.956841] process_one_work+0x806/0x1500 [ 0.957167] worker_thread+0x8c/0xcb0 [ 0.957549] kthread+0x2ee/0x3b0 [ 0.957792] ret_from_fork+0x24/0x30 [ 0.958234] [ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}: [ 0.958808] lock_acquire+0x127/0x350 [ 0.959075] process_one_work+0x7ab/0x1500 [ 0.959369] worker_thread+0x8c/0xcb0 [ 0.959639] kthread+0x2ee/0x3b0 [ 0.959896] ret_from_fork+0x24/0x30 [ 0.960346] [ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}: [ 0.960945] check_prev_add+0x167/0x1e20 [ 0.961351] __lock_acquire+0x2012/0x3170 [ 0.961725] lock_acquire+0x127/0x350 [ 0.961990] flush_workqueue+0x106/0x12f0 [ 0.962280] peer_remove_after_dead+0x160/0x220 [ 0.962600] wg_set_device+0xa24/0xcc0 [ 0.962994] genl_rcv_msg+0x52f/0xe90 [ 0.963298] netlink_rcv_skb+0x111/0x320 [ 0.963618] genl_rcv+0x1f/0x30 [ 0.963853] netlink_unicast+0x3f6/0x610 [ 0.964245] netlink_sendmsg+0x700/0xb80 [ 0.964586] __sys_sendto+0x1dd/0x2c0 [ 0.964854] __x64_sys_sendto+0xd8/0x1b0 [ 0.965141] do_syscall_64+0x90/0xd9a [ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.965769] [ 0.965769] other info that might help us debug this: [ 0.965769] [ 0.966337] Chain exists of: [ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock [ 0.966337] [ 0.967417] Possible unsafe locking scenario: [ 0.967417] [ 0.967836] CPU0 CPU1 [ 0.968155] ---- ---- [ 0.968497] lock(&wg->static_identity.lock); [ 0.968779] lock((work_completion)(&peer->transmit_handshake_work)); [ 0.969345] lock(&wg->static_identity.lock); [ 0.969809] lock((wq_completion)wg-kex-wg0); [ 0.970146] [ 0.970146] *** DEADLOCK *** [ 0.970146] [ 0.970531] 5 locks held by wg/89: [ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30 [ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90 [ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0 [ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0 [ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.973653] [ 0.973653] stack backtrace: [ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18 [ 0.974476] Call Trace: [ 0.974638] dump_stack+0x97/0xe0 [ 0.974869] check_noncircular+0x312/0x3e0 [ 0.975132] ? print_circular_bug+0x1f0/0x1f0 [ 0.975410] ? __kernel_text_address+0x9/0x30 [ 0.975727] ? unwind_get_return_address+0x51/0x90 [ 0.976024] check_prev_add+0x167/0x1e20 [ 0.976367] ? graph_lock+0x70/0x160 [ 0.976682] __lock_acquire+0x2012/0x3170 [ 0.976998] ? register_lock_class+0x1140/0x1140 [ 0.977323] lock_acquire+0x127/0x350 [ 0.977627] ? flush_workqueue+0xe3/0x12f0 [ 0.977890] flush_workqueue+0x106/0x12f0 [ 0.978147] ? flush_workqueue+0xe3/0x12f0 [ 0.978410] ? find_held_lock+0x2c/0x110 [ 0.978662] ? lock_downgrade+0x6e0/0x6e0 [ 0.978919] ? queue_rcu_work+0x60/0x60 [ 0.979166] ? netif_napi_del+0x151/0x3b0 [ 0.979501] ? peer_remove_after_dead+0x160/0x220 [ 0.979871] peer_remove_after_dead+0x160/0x220 [ 0.980232] wg_set_device+0xa24/0xcc0 [ 0.980516] ? deref_stack_reg+0x8e/0xc0 [ 0.980801] ? set_peer+0xe10/0xe10 [ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150 [ 0.981430] ? __nla_validate_parse+0x163/0x270 [ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310 [ 0.982078] genl_rcv_msg+0x52f/0xe90 [ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.982690] ? register_lock_class+0x1140/0x1140 [ 0.983049] netlink_rcv_skb+0x111/0x320 [ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.983645] ? netlink_ack+0x880/0x880 [ 0.983888] genl_rcv+0x1f/0x30 [ 0.984168] netlink_unicast+0x3f6/0x610 [ 0.984443] ? netlink_detachskb+0x60/0x60 [ 0.984729] ? find_held_lock+0x2c/0x110 [ 0.984976] netlink_sendmsg+0x700/0xb80 [ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60 [ 0.985533] __sys_sendto+0x1dd/0x2c0 [ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0 [ 0.986039] ? sockfd_lookup_light+0x17/0x160 [ 0.986397] ? __sys_recvmsg+0x8c/0xf0 [ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0 [ 0.987018] __x64_sys_sendto+0xd8/0x1b0 [ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0 [ 0.987666] do_syscall_64+0x90/0xd9a [ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.988223] RIP: 0033:0x7fe77c12003e [ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4 [ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e [ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004 [ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c [ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c [ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001 Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-05 05:17:26 +08:00
} else {
u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 };
ret = curve25519(empty, empty, peer->handshake.remote_static);
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>
2019-12-09 07:27:34 +08:00
memset(peer->handshake.precomputed_static_static, 0,
NOISE_PUBLIC_KEY_LEN);
wireguard: noise: reject peers with low order public keys Our static-static calculation returns a failure if the public key is of low order. We check for this when peers are added, and don't allow them to be added if they're low order, except in the case where we haven't yet been given a private key. In that case, we would defer the removal of the peer until we're given a private key, since at that point we're doing new static-static calculations which incur failures we can act on. This meant, however, that we wound up removing peers rather late in the configuration flow. Syzkaller points out that peer_remove calls flush_workqueue, which in turn might then wait for sending a handshake initiation to complete. Since handshake initiation needs the static identity lock, holding the static identity lock while calling peer_remove can result in a rare deadlock. We have precisely this case in this situation of late-stage peer removal based on an invalid public key. We can't drop the lock when removing, because then incoming handshakes might interact with a bogus static-static calculation. While the band-aid patch for this would involve breaking up the peer removal into two steps like wg_peer_remove_all does, in order to solve the locking issue, there's actually a much more elegant way of fixing this: If the static-static calculation succeeds with one private key, it *must* succeed with all others, because all 32-byte strings map to valid private keys, thanks to clamping. That means we can get rid of this silly dance and locking headaches of removing peers late in the configuration flow, and instead just reject them early on, regardless of whether the device has yet been assigned a private key. For the case where the device doesn't yet have a private key, we safely use zeros just for the purposes of checking for low order points by way of checking the output of the calculation. The following PoC will trigger the deadlock: ip link add wg0 type wireguard ip addr add 10.0.0.1/24 dev wg0 ip link set wg0 up ping -f 10.0.0.2 & while true; do wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234 wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=) done [ 0.949105] ====================================================== [ 0.949550] WARNING: possible circular locking dependency detected [ 0.950143] 5.5.0-debug+ #18 Not tainted [ 0.950431] ------------------------------------------------------ [ 0.950959] wg/89 is trying to acquire lock: [ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0 [ 0.951865] [ 0.951865] but task is already holding lock: [ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.953011] [ 0.953011] which lock already depends on the new lock. [ 0.953011] [ 0.953651] [ 0.953651] the existing dependency chain (in reverse order) is: [ 0.954292] [ 0.954292] -> #2 (&wg->static_identity.lock){++++}: [ 0.954804] lock_acquire+0x127/0x350 [ 0.955133] down_read+0x83/0x410 [ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700 [ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280 [ 0.956401] wg_packet_handshake_send_worker+0x10/0x20 [ 0.956841] process_one_work+0x806/0x1500 [ 0.957167] worker_thread+0x8c/0xcb0 [ 0.957549] kthread+0x2ee/0x3b0 [ 0.957792] ret_from_fork+0x24/0x30 [ 0.958234] [ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}: [ 0.958808] lock_acquire+0x127/0x350 [ 0.959075] process_one_work+0x7ab/0x1500 [ 0.959369] worker_thread+0x8c/0xcb0 [ 0.959639] kthread+0x2ee/0x3b0 [ 0.959896] ret_from_fork+0x24/0x30 [ 0.960346] [ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}: [ 0.960945] check_prev_add+0x167/0x1e20 [ 0.961351] __lock_acquire+0x2012/0x3170 [ 0.961725] lock_acquire+0x127/0x350 [ 0.961990] flush_workqueue+0x106/0x12f0 [ 0.962280] peer_remove_after_dead+0x160/0x220 [ 0.962600] wg_set_device+0xa24/0xcc0 [ 0.962994] genl_rcv_msg+0x52f/0xe90 [ 0.963298] netlink_rcv_skb+0x111/0x320 [ 0.963618] genl_rcv+0x1f/0x30 [ 0.963853] netlink_unicast+0x3f6/0x610 [ 0.964245] netlink_sendmsg+0x700/0xb80 [ 0.964586] __sys_sendto+0x1dd/0x2c0 [ 0.964854] __x64_sys_sendto+0xd8/0x1b0 [ 0.965141] do_syscall_64+0x90/0xd9a [ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.965769] [ 0.965769] other info that might help us debug this: [ 0.965769] [ 0.966337] Chain exists of: [ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock [ 0.966337] [ 0.967417] Possible unsafe locking scenario: [ 0.967417] [ 0.967836] CPU0 CPU1 [ 0.968155] ---- ---- [ 0.968497] lock(&wg->static_identity.lock); [ 0.968779] lock((work_completion)(&peer->transmit_handshake_work)); [ 0.969345] lock(&wg->static_identity.lock); [ 0.969809] lock((wq_completion)wg-kex-wg0); [ 0.970146] [ 0.970146] *** DEADLOCK *** [ 0.970146] [ 0.970531] 5 locks held by wg/89: [ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30 [ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90 [ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0 [ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0 [ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 [ 0.973653] [ 0.973653] stack backtrace: [ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18 [ 0.974476] Call Trace: [ 0.974638] dump_stack+0x97/0xe0 [ 0.974869] check_noncircular+0x312/0x3e0 [ 0.975132] ? print_circular_bug+0x1f0/0x1f0 [ 0.975410] ? __kernel_text_address+0x9/0x30 [ 0.975727] ? unwind_get_return_address+0x51/0x90 [ 0.976024] check_prev_add+0x167/0x1e20 [ 0.976367] ? graph_lock+0x70/0x160 [ 0.976682] __lock_acquire+0x2012/0x3170 [ 0.976998] ? register_lock_class+0x1140/0x1140 [ 0.977323] lock_acquire+0x127/0x350 [ 0.977627] ? flush_workqueue+0xe3/0x12f0 [ 0.977890] flush_workqueue+0x106/0x12f0 [ 0.978147] ? flush_workqueue+0xe3/0x12f0 [ 0.978410] ? find_held_lock+0x2c/0x110 [ 0.978662] ? lock_downgrade+0x6e0/0x6e0 [ 0.978919] ? queue_rcu_work+0x60/0x60 [ 0.979166] ? netif_napi_del+0x151/0x3b0 [ 0.979501] ? peer_remove_after_dead+0x160/0x220 [ 0.979871] peer_remove_after_dead+0x160/0x220 [ 0.980232] wg_set_device+0xa24/0xcc0 [ 0.980516] ? deref_stack_reg+0x8e/0xc0 [ 0.980801] ? set_peer+0xe10/0xe10 [ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150 [ 0.981430] ? __nla_validate_parse+0x163/0x270 [ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310 [ 0.982078] genl_rcv_msg+0x52f/0xe90 [ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.982690] ? register_lock_class+0x1140/0x1140 [ 0.983049] netlink_rcv_skb+0x111/0x320 [ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 [ 0.983645] ? netlink_ack+0x880/0x880 [ 0.983888] genl_rcv+0x1f/0x30 [ 0.984168] netlink_unicast+0x3f6/0x610 [ 0.984443] ? netlink_detachskb+0x60/0x60 [ 0.984729] ? find_held_lock+0x2c/0x110 [ 0.984976] netlink_sendmsg+0x700/0xb80 [ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60 [ 0.985533] __sys_sendto+0x1dd/0x2c0 [ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0 [ 0.986039] ? sockfd_lookup_light+0x17/0x160 [ 0.986397] ? __sys_recvmsg+0x8c/0xf0 [ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0 [ 0.987018] __x64_sys_sendto+0xd8/0x1b0 [ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0 [ 0.987666] do_syscall_64+0x90/0xd9a [ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 0.988223] RIP: 0033:0x7fe77c12003e [ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4 [ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e [ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004 [ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c [ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c [ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001 Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-05 05:17:26 +08:00
}
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>
2019-12-09 07:27:34 +08:00
up_write(&peer->handshake.lock);
return ret;
}
bool wg_noise_handshake_init(struct noise_handshake *handshake,
struct noise_static_identity *static_identity,
const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
struct wg_peer *peer)
{
memset(handshake, 0, sizeof(*handshake));
init_rwsem(&handshake->lock);
handshake->entry.type = INDEX_HASHTABLE_HANDSHAKE;
handshake->entry.peer = peer;
memcpy(handshake->remote_static, peer_public_key, NOISE_PUBLIC_KEY_LEN);
if (peer_preshared_key)
memcpy(handshake->preshared_key, peer_preshared_key,
NOISE_SYMMETRIC_KEY_LEN);
handshake->static_identity = static_identity;
handshake->state = HANDSHAKE_ZEROED;
return wg_noise_precompute_static_static(peer);
}
static void handshake_zero(struct noise_handshake *handshake)
{
memset(&handshake->ephemeral_private, 0, NOISE_PUBLIC_KEY_LEN);
memset(&handshake->remote_ephemeral, 0, NOISE_PUBLIC_KEY_LEN);
memset(&handshake->hash, 0, NOISE_HASH_LEN);
memset(&handshake->chaining_key, 0, NOISE_HASH_LEN);
handshake->remote_index = 0;
handshake->state = HANDSHAKE_ZEROED;
}
void wg_noise_handshake_clear(struct noise_handshake *handshake)
{
wg_index_hashtable_remove(
handshake->entry.peer->device->index_hashtable,
&handshake->entry);
down_write(&handshake->lock);
handshake_zero(handshake);
up_write(&handshake->lock);
wg_index_hashtable_remove(
handshake->entry.peer->device->index_hashtable,
&handshake->entry);
}
static struct noise_keypair *keypair_create(struct wg_peer *peer)
{
struct noise_keypair *keypair = kzalloc(sizeof(*keypair), GFP_KERNEL);
if (unlikely(!keypair))
return NULL;
keypair->internal_id = atomic64_inc_return(&keypair_counter);
keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
keypair->entry.peer = peer;
kref_init(&keypair->refcount);
return keypair;
}
static void keypair_free_rcu(struct rcu_head *rcu)
{
kzfree(container_of(rcu, struct noise_keypair, rcu));
}
static void keypair_free_kref(struct kref *kref)
{
struct noise_keypair *keypair =
container_of(kref, struct noise_keypair, refcount);
net_dbg_ratelimited("%s: Keypair %llu destroyed for peer %llu\n",
keypair->entry.peer->device->dev->name,
keypair->internal_id,
keypair->entry.peer->internal_id);
wg_index_hashtable_remove(keypair->entry.peer->device->index_hashtable,
&keypair->entry);
call_rcu(&keypair->rcu, keypair_free_rcu);
}
void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now)
{
if (unlikely(!keypair))
return;
if (unlikely(unreference_now))
wg_index_hashtable_remove(
keypair->entry.peer->device->index_hashtable,
&keypair->entry);
kref_put(&keypair->refcount, keypair_free_kref);
}
struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair)
{
RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(),
"Taking noise keypair reference without holding the RCU BH read lock");
if (unlikely(!keypair || !kref_get_unless_zero(&keypair->refcount)))
return NULL;
return keypair;
}
void wg_noise_keypairs_clear(struct noise_keypairs *keypairs)
{
struct noise_keypair *old;
spin_lock_bh(&keypairs->keypair_update_lock);
/* We zero the next_keypair before zeroing the others, so that
* wg_noise_received_with_keypair returns early before subsequent ones
* are zeroed.
*/
old = rcu_dereference_protected(keypairs->next_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
RCU_INIT_POINTER(keypairs->next_keypair, NULL);
wg_noise_keypair_put(old, true);
old = rcu_dereference_protected(keypairs->previous_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
wg_noise_keypair_put(old, true);
old = rcu_dereference_protected(keypairs->current_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
RCU_INIT_POINTER(keypairs->current_keypair, NULL);
wg_noise_keypair_put(old, true);
spin_unlock_bh(&keypairs->keypair_update_lock);
}
void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer)
{
struct noise_keypair *keypair;
wg_noise_handshake_clear(&peer->handshake);
wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
spin_lock_bh(&peer->keypairs.keypair_update_lock);
keypair = rcu_dereference_protected(peer->keypairs.next_keypair,
lockdep_is_held(&peer->keypairs.keypair_update_lock));
if (keypair)
keypair->sending.is_valid = false;
keypair = rcu_dereference_protected(peer->keypairs.current_keypair,
lockdep_is_held(&peer->keypairs.keypair_update_lock));
if (keypair)
keypair->sending.is_valid = false;
spin_unlock_bh(&peer->keypairs.keypair_update_lock);
}
static void add_new_keypair(struct noise_keypairs *keypairs,
struct noise_keypair *new_keypair)
{
struct noise_keypair *previous_keypair, *next_keypair, *current_keypair;
spin_lock_bh(&keypairs->keypair_update_lock);
previous_keypair = rcu_dereference_protected(keypairs->previous_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
next_keypair = rcu_dereference_protected(keypairs->next_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
current_keypair = rcu_dereference_protected(keypairs->current_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
if (new_keypair->i_am_the_initiator) {
/* If we're the initiator, it means we've sent a handshake, and
* received a confirmation response, which means this new
* keypair can now be used.
*/
if (next_keypair) {
/* If there already was a next keypair pending, we
* demote it to be the previous keypair, and free the
* existing current. Note that this means KCI can result
* in this transition. It would perhaps be more sound to
* always just get rid of the unused next keypair
* instead of putting it in the previous slot, but this
* might be a bit less robust. Something to think about
* for the future.
*/
RCU_INIT_POINTER(keypairs->next_keypair, NULL);
rcu_assign_pointer(keypairs->previous_keypair,
next_keypair);
wg_noise_keypair_put(current_keypair, true);
} else /* If there wasn't an existing next keypair, we replace
* the previous with the current one.
*/
rcu_assign_pointer(keypairs->previous_keypair,
current_keypair);
/* At this point we can get rid of the old previous keypair, and
* set up the new keypair.
*/
wg_noise_keypair_put(previous_keypair, true);
rcu_assign_pointer(keypairs->current_keypair, new_keypair);
} else {
/* If we're the responder, it means we can't use the new keypair
* until we receive confirmation via the first data packet, so
* we get rid of the existing previous one, the possibly
* existing next one, and slide in the new next one.
*/
rcu_assign_pointer(keypairs->next_keypair, new_keypair);
wg_noise_keypair_put(next_keypair, true);
RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
wg_noise_keypair_put(previous_keypair, true);
}
spin_unlock_bh(&keypairs->keypair_update_lock);
}
bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs,
struct noise_keypair *received_keypair)
{
struct noise_keypair *old_keypair;
bool key_is_new;
/* We first check without taking the spinlock. */
key_is_new = received_keypair ==
rcu_access_pointer(keypairs->next_keypair);
if (likely(!key_is_new))
return false;
spin_lock_bh(&keypairs->keypair_update_lock);
/* After locking, we double check that things didn't change from
* beneath us.
*/
if (unlikely(received_keypair !=
rcu_dereference_protected(keypairs->next_keypair,
lockdep_is_held(&keypairs->keypair_update_lock)))) {
spin_unlock_bh(&keypairs->keypair_update_lock);
return false;
}
/* When we've finally received the confirmation, we slide the next
* into the current, the current into the previous, and get rid of
* the old previous.
*/
old_keypair = rcu_dereference_protected(keypairs->previous_keypair,
lockdep_is_held(&keypairs->keypair_update_lock));
rcu_assign_pointer(keypairs->previous_keypair,
rcu_dereference_protected(keypairs->current_keypair,
lockdep_is_held(&keypairs->keypair_update_lock)));
wg_noise_keypair_put(old_keypair, true);
rcu_assign_pointer(keypairs->current_keypair, received_keypair);
RCU_INIT_POINTER(keypairs->next_keypair, NULL);
spin_unlock_bh(&keypairs->keypair_update_lock);
return true;
}
/* Must hold static_identity->lock */
void wg_noise_set_static_identity_private_key(
struct noise_static_identity *static_identity,
const u8 private_key[NOISE_PUBLIC_KEY_LEN])
{
memcpy(static_identity->static_private, private_key,
NOISE_PUBLIC_KEY_LEN);
curve25519_clamp_secret(static_identity->static_private);
static_identity->has_identity = curve25519_generate_public(
static_identity->static_public, private_key);
}
/* This is Hugo Krawczyk's HKDF:
* - https://eprint.iacr.org/2010/264.pdf
* - https://tools.ietf.org/html/rfc5869
*/
static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
size_t first_len, size_t second_len, size_t third_len,
size_t data_len, const u8 chaining_key[NOISE_HASH_LEN])
{
u8 output[BLAKE2S_HASH_SIZE + 1];
u8 secret[BLAKE2S_HASH_SIZE];
WARN_ON(IS_ENABLED(DEBUG) &&
(first_len > BLAKE2S_HASH_SIZE ||
second_len > BLAKE2S_HASH_SIZE ||
third_len > BLAKE2S_HASH_SIZE ||
((second_len || second_dst || third_len || third_dst) &&
(!first_len || !first_dst)) ||
((third_len || third_dst) && (!second_len || !second_dst))));
/* Extract entropy from data into secret */
blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN);
if (!first_dst || !first_len)
goto out;
/* Expand first key: key = secret, data = 0x1 */
output[0] = 1;
blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE);
memcpy(first_dst, output, first_len);
if (!second_dst || !second_len)
goto out;
/* Expand second key: key = secret, data = first-key || 0x2 */
output[BLAKE2S_HASH_SIZE] = 2;
blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
BLAKE2S_HASH_SIZE);
memcpy(second_dst, output, second_len);
if (!third_dst || !third_len)
goto out;
/* Expand third key: key = secret, data = second-key || 0x3 */
output[BLAKE2S_HASH_SIZE] = 3;
blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
BLAKE2S_HASH_SIZE);
memcpy(third_dst, output, third_len);
out:
/* Clear sensitive data from stack */
memzero_explicit(secret, BLAKE2S_HASH_SIZE);
memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
}
static void symmetric_key_init(struct noise_symmetric_key *key)
{
spin_lock_init(&key->counter.receive.lock);
atomic64_set(&key->counter.counter, 0);
memset(key->counter.receive.backtrack, 0,
sizeof(key->counter.receive.backtrack));
key->birthdate = ktime_get_coarse_boottime_ns();
key->is_valid = true;
}
static void derive_keys(struct noise_symmetric_key *first_dst,
struct noise_symmetric_key *second_dst,
const u8 chaining_key[NOISE_HASH_LEN])
{
kdf(first_dst->key, second_dst->key, NULL, NULL,
NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
chaining_key);
symmetric_key_init(first_dst);
symmetric_key_init(second_dst);
}
static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
u8 key[NOISE_SYMMETRIC_KEY_LEN],
const u8 private[NOISE_PUBLIC_KEY_LEN],
const u8 public[NOISE_PUBLIC_KEY_LEN])
{
u8 dh_calculation[NOISE_PUBLIC_KEY_LEN];
if (unlikely(!curve25519(dh_calculation, private, public)))
return false;
kdf(chaining_key, key, NULL, dh_calculation, NOISE_HASH_LEN,
NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key);
memzero_explicit(dh_calculation, NOISE_PUBLIC_KEY_LEN);
return true;
}
static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len)
{
struct blake2s_state blake;
blake2s_init(&blake, NOISE_HASH_LEN);
blake2s_update(&blake, hash, NOISE_HASH_LEN);
blake2s_update(&blake, src, src_len);
blake2s_final(&blake, hash);
}
static void mix_psk(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN],
u8 key[NOISE_SYMMETRIC_KEY_LEN],
const u8 psk[NOISE_SYMMETRIC_KEY_LEN])
{
u8 temp_hash[NOISE_HASH_LEN];
kdf(chaining_key, temp_hash, key, psk, NOISE_HASH_LEN, NOISE_HASH_LEN,
NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, chaining_key);
mix_hash(hash, temp_hash, NOISE_HASH_LEN);
memzero_explicit(temp_hash, NOISE_HASH_LEN);
}
static void handshake_init(u8 chaining_key[NOISE_HASH_LEN],
u8 hash[NOISE_HASH_LEN],
const u8 remote_static[NOISE_PUBLIC_KEY_LEN])
{
memcpy(hash, handshake_init_hash, NOISE_HASH_LEN);
memcpy(chaining_key, handshake_init_chaining_key, NOISE_HASH_LEN);
mix_hash(hash, remote_static, NOISE_PUBLIC_KEY_LEN);
}
static void message_encrypt(u8 *dst_ciphertext, const u8 *src_plaintext,
size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
u8 hash[NOISE_HASH_LEN])
{
chacha20poly1305_encrypt(dst_ciphertext, src_plaintext, src_len, hash,
NOISE_HASH_LEN,
0 /* Always zero for Noise_IK */, key);
mix_hash(hash, dst_ciphertext, noise_encrypted_len(src_len));
}
static bool message_decrypt(u8 *dst_plaintext, const u8 *src_ciphertext,
size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
u8 hash[NOISE_HASH_LEN])
{
if (!chacha20poly1305_decrypt(dst_plaintext, src_ciphertext, src_len,
hash, NOISE_HASH_LEN,
0 /* Always zero for Noise_IK */, key))
return false;
mix_hash(hash, src_ciphertext, src_len);
return true;
}
static void message_ephemeral(u8 ephemeral_dst[NOISE_PUBLIC_KEY_LEN],
const u8 ephemeral_src[NOISE_PUBLIC_KEY_LEN],
u8 chaining_key[NOISE_HASH_LEN],
u8 hash[NOISE_HASH_LEN])
{
if (ephemeral_dst != ephemeral_src)
memcpy(ephemeral_dst, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
mix_hash(hash, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
kdf(chaining_key, NULL, NULL, ephemeral_src, NOISE_HASH_LEN, 0, 0,
NOISE_PUBLIC_KEY_LEN, chaining_key);
}
static void tai64n_now(u8 output[NOISE_TIMESTAMP_LEN])
{
struct timespec64 now;
ktime_get_real_ts64(&now);
/* In order to prevent some sort of infoleak from precise timers, we
* round down the nanoseconds part to the closest rounded-down power of
* two to the maximum initiations per second allowed anyway by the
* implementation.
*/
now.tv_nsec = ALIGN_DOWN(now.tv_nsec,
rounddown_pow_of_two(NSEC_PER_SEC / INITIATIONS_PER_SECOND));
/* https://cr.yp.to/libtai/tai64.html */
*(__be64 *)output = cpu_to_be64(0x400000000000000aULL + now.tv_sec);
*(__be32 *)(output + sizeof(__be64)) = cpu_to_be32(now.tv_nsec);
}
bool
wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
struct noise_handshake *handshake)
{
u8 timestamp[NOISE_TIMESTAMP_LEN];
u8 key[NOISE_SYMMETRIC_KEY_LEN];
bool ret = false;
/* We need to wait for crng _before_ taking any locks, since
* curve25519_generate_secret uses get_random_bytes_wait.
*/
wait_for_random_bytes();
down_read(&handshake->static_identity->lock);
down_write(&handshake->lock);
if (unlikely(!handshake->static_identity->has_identity))
goto out;
dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION);
handshake_init(handshake->chaining_key, handshake->hash,
handshake->remote_static);
/* e */
curve25519_generate_secret(handshake->ephemeral_private);
if (!curve25519_generate_public(dst->unencrypted_ephemeral,
handshake->ephemeral_private))
goto out;
message_ephemeral(dst->unencrypted_ephemeral,
dst->unencrypted_ephemeral, handshake->chaining_key,
handshake->hash);
/* es */
if (!mix_dh(handshake->chaining_key, key, handshake->ephemeral_private,
handshake->remote_static))
goto out;
/* s */
message_encrypt(dst->encrypted_static,
handshake->static_identity->static_public,
NOISE_PUBLIC_KEY_LEN, key, handshake->hash);
/* ss */
kdf(handshake->chaining_key, key, NULL,
handshake->precomputed_static_static, NOISE_HASH_LEN,
NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
handshake->chaining_key);
/* {t} */
tai64n_now(timestamp);
message_encrypt(dst->encrypted_timestamp, timestamp,
NOISE_TIMESTAMP_LEN, key, handshake->hash);
dst->sender_index = wg_index_hashtable_insert(
handshake->entry.peer->device->index_hashtable,
&handshake->entry);
handshake->state = HANDSHAKE_CREATED_INITIATION;
ret = true;
out:
up_write(&handshake->lock);
up_read(&handshake->static_identity->lock);
memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
return ret;
}
struct wg_peer *
wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
struct wg_device *wg)
{
struct wg_peer *peer = NULL, *ret_peer = NULL;
struct noise_handshake *handshake;
bool replay_attack, flood_attack;
u8 key[NOISE_SYMMETRIC_KEY_LEN];
u8 chaining_key[NOISE_HASH_LEN];
u8 hash[NOISE_HASH_LEN];
u8 s[NOISE_PUBLIC_KEY_LEN];
u8 e[NOISE_PUBLIC_KEY_LEN];
u8 t[NOISE_TIMESTAMP_LEN];
u64 initiation_consumption;
down_read(&wg->static_identity.lock);
if (unlikely(!wg->static_identity.has_identity))
goto out;
handshake_init(chaining_key, hash, wg->static_identity.static_public);
/* e */
message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
/* es */
if (!mix_dh(chaining_key, key, wg->static_identity.static_private, e))
goto out;
/* s */
if (!message_decrypt(s, src->encrypted_static,
sizeof(src->encrypted_static), key, hash))
goto out;
/* Lookup which peer we're actually talking to */
peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, s);
if (!peer)
goto out;
handshake = &peer->handshake;
/* ss */
kdf(chaining_key, key, NULL, handshake->precomputed_static_static,
NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
chaining_key);
/* {t} */
if (!message_decrypt(t, src->encrypted_timestamp,
sizeof(src->encrypted_timestamp), key, hash))
goto out;
down_read(&handshake->lock);
replay_attack = memcmp(t, handshake->latest_timestamp,
NOISE_TIMESTAMP_LEN) <= 0;
flood_attack = (s64)handshake->last_initiation_consumption +
NSEC_PER_SEC / INITIATIONS_PER_SECOND >
(s64)ktime_get_coarse_boottime_ns();
up_read(&handshake->lock);
if (replay_attack || flood_attack)
goto out;
/* Success! Copy everything to peer */
down_write(&handshake->lock);
memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
if (memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) > 0)
memcpy(handshake->latest_timestamp, t, NOISE_TIMESTAMP_LEN);
memcpy(handshake->hash, hash, NOISE_HASH_LEN);
memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
handshake->remote_index = src->sender_index;
if ((s64)(handshake->last_initiation_consumption -
(initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
handshake->last_initiation_consumption = initiation_consumption;
handshake->state = HANDSHAKE_CONSUMED_INITIATION;
up_write(&handshake->lock);
ret_peer = peer;
out:
memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
memzero_explicit(hash, NOISE_HASH_LEN);
memzero_explicit(chaining_key, NOISE_HASH_LEN);
up_read(&wg->static_identity.lock);
if (!ret_peer)
wg_peer_put(peer);
return ret_peer;
}
bool wg_noise_handshake_create_response(struct message_handshake_response *dst,
struct noise_handshake *handshake)
{
u8 key[NOISE_SYMMETRIC_KEY_LEN];
bool ret = false;
/* We need to wait for crng _before_ taking any locks, since
* curve25519_generate_secret uses get_random_bytes_wait.
*/
wait_for_random_bytes();
down_read(&handshake->static_identity->lock);
down_write(&handshake->lock);
if (handshake->state != HANDSHAKE_CONSUMED_INITIATION)
goto out;
dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE);
dst->receiver_index = handshake->remote_index;
/* e */
curve25519_generate_secret(handshake->ephemeral_private);
if (!curve25519_generate_public(dst->unencrypted_ephemeral,
handshake->ephemeral_private))
goto out;
message_ephemeral(dst->unencrypted_ephemeral,
dst->unencrypted_ephemeral, handshake->chaining_key,
handshake->hash);
/* ee */
if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
handshake->remote_ephemeral))
goto out;
/* se */
if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
handshake->remote_static))
goto out;
/* psk */
mix_psk(handshake->chaining_key, handshake->hash, key,
handshake->preshared_key);
/* {} */
message_encrypt(dst->encrypted_nothing, NULL, 0, key, handshake->hash);
dst->sender_index = wg_index_hashtable_insert(
handshake->entry.peer->device->index_hashtable,
&handshake->entry);
handshake->state = HANDSHAKE_CREATED_RESPONSE;
ret = true;
out:
up_write(&handshake->lock);
up_read(&handshake->static_identity->lock);
memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
return ret;
}
struct wg_peer *
wg_noise_handshake_consume_response(struct message_handshake_response *src,
struct wg_device *wg)
{
enum noise_handshake_state state = HANDSHAKE_ZEROED;
struct wg_peer *peer = NULL, *ret_peer = NULL;
struct noise_handshake *handshake;
u8 key[NOISE_SYMMETRIC_KEY_LEN];
u8 hash[NOISE_HASH_LEN];
u8 chaining_key[NOISE_HASH_LEN];
u8 e[NOISE_PUBLIC_KEY_LEN];
u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
u8 static_private[NOISE_PUBLIC_KEY_LEN];
down_read(&wg->static_identity.lock);
if (unlikely(!wg->static_identity.has_identity))
goto out;
handshake = (struct noise_handshake *)wg_index_hashtable_lookup(
wg->index_hashtable, INDEX_HASHTABLE_HANDSHAKE,
src->receiver_index, &peer);
if (unlikely(!handshake))
goto out;
down_read(&handshake->lock);
state = handshake->state;
memcpy(hash, handshake->hash, NOISE_HASH_LEN);
memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
memcpy(ephemeral_private, handshake->ephemeral_private,
NOISE_PUBLIC_KEY_LEN);
up_read(&handshake->lock);
if (state != HANDSHAKE_CREATED_INITIATION)
goto fail;
/* e */
message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
/* ee */
if (!mix_dh(chaining_key, NULL, ephemeral_private, e))
goto fail;
/* se */
if (!mix_dh(chaining_key, NULL, wg->static_identity.static_private, e))
goto fail;
/* psk */
mix_psk(chaining_key, hash, key, handshake->preshared_key);
/* {} */
if (!message_decrypt(NULL, src->encrypted_nothing,
sizeof(src->encrypted_nothing), key, hash))
goto fail;
/* Success! Copy everything to peer */
down_write(&handshake->lock);
/* It's important to check that the state is still the same, while we
* have an exclusive lock.
*/
if (handshake->state != state) {
up_write(&handshake->lock);
goto fail;
}
memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
memcpy(handshake->hash, hash, NOISE_HASH_LEN);
memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
handshake->remote_index = src->sender_index;
handshake->state = HANDSHAKE_CONSUMED_RESPONSE;
up_write(&handshake->lock);
ret_peer = peer;
goto out;
fail:
wg_peer_put(peer);
out:
memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
memzero_explicit(hash, NOISE_HASH_LEN);
memzero_explicit(chaining_key, NOISE_HASH_LEN);
memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
up_read(&wg->static_identity.lock);
return ret_peer;
}
bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
struct noise_keypairs *keypairs)
{
struct noise_keypair *new_keypair;
bool ret = false;
down_write(&handshake->lock);
if (handshake->state != HANDSHAKE_CREATED_RESPONSE &&
handshake->state != HANDSHAKE_CONSUMED_RESPONSE)
goto out;
new_keypair = keypair_create(handshake->entry.peer);
if (!new_keypair)
goto out;
new_keypair->i_am_the_initiator = handshake->state ==
HANDSHAKE_CONSUMED_RESPONSE;
new_keypair->remote_index = handshake->remote_index;
if (new_keypair->i_am_the_initiator)
derive_keys(&new_keypair->sending, &new_keypair->receiving,
handshake->chaining_key);
else
derive_keys(&new_keypair->receiving, &new_keypair->sending,
handshake->chaining_key);
handshake_zero(handshake);
rcu_read_lock_bh();
if (likely(!READ_ONCE(container_of(handshake, struct wg_peer,
handshake)->is_dead))) {
add_new_keypair(keypairs, new_keypair);
net_dbg_ratelimited("%s: Keypair %llu created for peer %llu\n",
handshake->entry.peer->device->dev->name,
new_keypair->internal_id,
handshake->entry.peer->internal_id);
ret = wg_index_hashtable_replace(
handshake->entry.peer->device->index_hashtable,
&handshake->entry, &new_keypair->entry);
} else {
kzfree(new_keypair);
}
rcu_read_unlock_bh();
out:
up_write(&handshake->lock);
return ret;
}