mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:05:18 +07:00
e7096c131e
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>
222 lines
6.3 KiB
C
222 lines
6.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
|
|
*/
|
|
|
|
#include "peerlookup.h"
|
|
#include "peer.h"
|
|
#include "noise.h"
|
|
|
|
static struct hlist_head *pubkey_bucket(struct pubkey_hashtable *table,
|
|
const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
|
|
{
|
|
/* siphash gives us a secure 64bit number based on a random key. Since
|
|
* the bits are uniformly distributed, we can then mask off to get the
|
|
* bits we need.
|
|
*/
|
|
const u64 hash = siphash(pubkey, NOISE_PUBLIC_KEY_LEN, &table->key);
|
|
|
|
return &table->hashtable[hash & (HASH_SIZE(table->hashtable) - 1)];
|
|
}
|
|
|
|
struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void)
|
|
{
|
|
struct pubkey_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
|
|
|
|
if (!table)
|
|
return NULL;
|
|
|
|
get_random_bytes(&table->key, sizeof(table->key));
|
|
hash_init(table->hashtable);
|
|
mutex_init(&table->lock);
|
|
return table;
|
|
}
|
|
|
|
void wg_pubkey_hashtable_add(struct pubkey_hashtable *table,
|
|
struct wg_peer *peer)
|
|
{
|
|
mutex_lock(&table->lock);
|
|
hlist_add_head_rcu(&peer->pubkey_hash,
|
|
pubkey_bucket(table, peer->handshake.remote_static));
|
|
mutex_unlock(&table->lock);
|
|
}
|
|
|
|
void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table,
|
|
struct wg_peer *peer)
|
|
{
|
|
mutex_lock(&table->lock);
|
|
hlist_del_init_rcu(&peer->pubkey_hash);
|
|
mutex_unlock(&table->lock);
|
|
}
|
|
|
|
/* Returns a strong reference to a peer */
|
|
struct wg_peer *
|
|
wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table,
|
|
const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
|
|
{
|
|
struct wg_peer *iter_peer, *peer = NULL;
|
|
|
|
rcu_read_lock_bh();
|
|
hlist_for_each_entry_rcu_bh(iter_peer, pubkey_bucket(table, pubkey),
|
|
pubkey_hash) {
|
|
if (!memcmp(pubkey, iter_peer->handshake.remote_static,
|
|
NOISE_PUBLIC_KEY_LEN)) {
|
|
peer = iter_peer;
|
|
break;
|
|
}
|
|
}
|
|
peer = wg_peer_get_maybe_zero(peer);
|
|
rcu_read_unlock_bh();
|
|
return peer;
|
|
}
|
|
|
|
static struct hlist_head *index_bucket(struct index_hashtable *table,
|
|
const __le32 index)
|
|
{
|
|
/* Since the indices are random and thus all bits are uniformly
|
|
* distributed, we can find its bucket simply by masking.
|
|
*/
|
|
return &table->hashtable[(__force u32)index &
|
|
(HASH_SIZE(table->hashtable) - 1)];
|
|
}
|
|
|
|
struct index_hashtable *wg_index_hashtable_alloc(void)
|
|
{
|
|
struct index_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
|
|
|
|
if (!table)
|
|
return NULL;
|
|
|
|
hash_init(table->hashtable);
|
|
spin_lock_init(&table->lock);
|
|
return table;
|
|
}
|
|
|
|
/* At the moment, we limit ourselves to 2^20 total peers, which generally might
|
|
* amount to 2^20*3 items in this hashtable. The algorithm below works by
|
|
* picking a random number and testing it. We can see that these limits mean we
|
|
* usually succeed pretty quickly:
|
|
*
|
|
* >>> def calculation(tries, size):
|
|
* ... return (size / 2**32)**(tries - 1) * (1 - (size / 2**32))
|
|
* ...
|
|
* >>> calculation(1, 2**20 * 3)
|
|
* 0.999267578125
|
|
* >>> calculation(2, 2**20 * 3)
|
|
* 0.0007318854331970215
|
|
* >>> calculation(3, 2**20 * 3)
|
|
* 5.360489012673497e-07
|
|
* >>> calculation(4, 2**20 * 3)
|
|
* 3.9261394135792216e-10
|
|
*
|
|
* At the moment, we don't do any masking, so this algorithm isn't exactly
|
|
* constant time in either the random guessing or in the hash list lookup. We
|
|
* could require a minimum of 3 tries, which would successfully mask the
|
|
* guessing. this would not, however, help with the growing hash lengths, which
|
|
* is another thing to consider moving forward.
|
|
*/
|
|
|
|
__le32 wg_index_hashtable_insert(struct index_hashtable *table,
|
|
struct index_hashtable_entry *entry)
|
|
{
|
|
struct index_hashtable_entry *existing_entry;
|
|
|
|
spin_lock_bh(&table->lock);
|
|
hlist_del_init_rcu(&entry->index_hash);
|
|
spin_unlock_bh(&table->lock);
|
|
|
|
rcu_read_lock_bh();
|
|
|
|
search_unused_slot:
|
|
/* First we try to find an unused slot, randomly, while unlocked. */
|
|
entry->index = (__force __le32)get_random_u32();
|
|
hlist_for_each_entry_rcu_bh(existing_entry,
|
|
index_bucket(table, entry->index),
|
|
index_hash) {
|
|
if (existing_entry->index == entry->index)
|
|
/* If it's already in use, we continue searching. */
|
|
goto search_unused_slot;
|
|
}
|
|
|
|
/* Once we've found an unused slot, we lock it, and then double-check
|
|
* that nobody else stole it from us.
|
|
*/
|
|
spin_lock_bh(&table->lock);
|
|
hlist_for_each_entry_rcu_bh(existing_entry,
|
|
index_bucket(table, entry->index),
|
|
index_hash) {
|
|
if (existing_entry->index == entry->index) {
|
|
spin_unlock_bh(&table->lock);
|
|
/* If it was stolen, we start over. */
|
|
goto search_unused_slot;
|
|
}
|
|
}
|
|
/* Otherwise, we know we have it exclusively (since we're locked),
|
|
* so we insert.
|
|
*/
|
|
hlist_add_head_rcu(&entry->index_hash,
|
|
index_bucket(table, entry->index));
|
|
spin_unlock_bh(&table->lock);
|
|
|
|
rcu_read_unlock_bh();
|
|
|
|
return entry->index;
|
|
}
|
|
|
|
bool wg_index_hashtable_replace(struct index_hashtable *table,
|
|
struct index_hashtable_entry *old,
|
|
struct index_hashtable_entry *new)
|
|
{
|
|
if (unlikely(hlist_unhashed(&old->index_hash)))
|
|
return false;
|
|
spin_lock_bh(&table->lock);
|
|
new->index = old->index;
|
|
hlist_replace_rcu(&old->index_hash, &new->index_hash);
|
|
|
|
/* Calling init here NULLs out index_hash, and in fact after this
|
|
* function returns, it's theoretically possible for this to get
|
|
* reinserted elsewhere. That means the RCU lookup below might either
|
|
* terminate early or jump between buckets, in which case the packet
|
|
* simply gets dropped, which isn't terrible.
|
|
*/
|
|
INIT_HLIST_NODE(&old->index_hash);
|
|
spin_unlock_bh(&table->lock);
|
|
return true;
|
|
}
|
|
|
|
void wg_index_hashtable_remove(struct index_hashtable *table,
|
|
struct index_hashtable_entry *entry)
|
|
{
|
|
spin_lock_bh(&table->lock);
|
|
hlist_del_init_rcu(&entry->index_hash);
|
|
spin_unlock_bh(&table->lock);
|
|
}
|
|
|
|
/* Returns a strong reference to a entry->peer */
|
|
struct index_hashtable_entry *
|
|
wg_index_hashtable_lookup(struct index_hashtable *table,
|
|
const enum index_hashtable_type type_mask,
|
|
const __le32 index, struct wg_peer **peer)
|
|
{
|
|
struct index_hashtable_entry *iter_entry, *entry = NULL;
|
|
|
|
rcu_read_lock_bh();
|
|
hlist_for_each_entry_rcu_bh(iter_entry, index_bucket(table, index),
|
|
index_hash) {
|
|
if (iter_entry->index == index) {
|
|
if (likely(iter_entry->type & type_mask))
|
|
entry = iter_entry;
|
|
break;
|
|
}
|
|
}
|
|
if (likely(entry)) {
|
|
entry->peer = wg_peer_get_maybe_zero(entry->peer);
|
|
if (likely(entry->peer))
|
|
*peer = entry->peer;
|
|
else
|
|
entry = NULL;
|
|
}
|
|
rcu_read_unlock_bh();
|
|
return entry;
|
|
}
|