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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _WG_MESSAGES_H
|
|
|
|
#define _WG_MESSAGES_H
|
|
|
|
|
|
|
|
#include <crypto/curve25519.h>
|
|
|
|
#include <crypto/chacha20poly1305.h>
|
|
|
|
#include <crypto/blake2s.h>
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/param.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
|
|
|
|
enum noise_lengths {
|
|
|
|
NOISE_PUBLIC_KEY_LEN = CURVE25519_KEY_SIZE,
|
|
|
|
NOISE_SYMMETRIC_KEY_LEN = CHACHA20POLY1305_KEY_SIZE,
|
|
|
|
NOISE_TIMESTAMP_LEN = sizeof(u64) + sizeof(u32),
|
|
|
|
NOISE_AUTHTAG_LEN = CHACHA20POLY1305_AUTHTAG_SIZE,
|
|
|
|
NOISE_HASH_LEN = BLAKE2S_HASH_SIZE
|
|
|
|
};
|
|
|
|
|
|
|
|
#define noise_encrypted_len(plain_len) ((plain_len) + NOISE_AUTHTAG_LEN)
|
|
|
|
|
|
|
|
enum cookie_values {
|
|
|
|
COOKIE_SECRET_MAX_AGE = 2 * 60,
|
|
|
|
COOKIE_SECRET_LATENCY = 5,
|
|
|
|
COOKIE_NONCE_LEN = XCHACHA20POLY1305_NONCE_SIZE,
|
|
|
|
COOKIE_LEN = 16
|
|
|
|
};
|
|
|
|
|
|
|
|
enum counter_values {
|
wireguard: queueing: preserve flow hash across packet scrubbing
It's important that we clear most header fields during encapsulation and
decapsulation, because the packet is substantially changed, and we don't
want any info leak or logic bug due to an accidental correlation. But,
for encapsulation, it's wrong to clear skb->hash, since it's used by
fq_codel and flow dissection in general. Without it, classification does
not proceed as usual. This change might make it easier to estimate the
number of innerflows by examining clustering of out of order packets,
but this shouldn't open up anything that can't already be inferred
otherwise (e.g. syn packet size inference), and fq_codel can be disabled
anyway.
Furthermore, it might be the case that the hash isn't used or queried at
all until after wireguard transmits the encrypted UDP packet, which
means skb->hash might still be zero at this point, and thus no hash
taken over the inner packet data. In order to address this situation, we
force a calculation of skb->hash before encrypting packet data.
Of course this means that fq_codel might transmit packets slightly more
out of order than usual. Toke did some testing on beefy machines with
high quantities of parallel flows and found that increasing the
reply-attack counter to 8192 takes care of the most pathological cases
pretty well.
Reported-by: Dave Taht <dave.taht@gmail.com>
Reviewed-and-tested-by: Toke Høiland-Jørgensen <toke@toke.dk>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-20 12:49:29 +08:00
|
|
|
COUNTER_BITS_TOTAL = 8192,
|
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
|
|
|
COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
|
|
|
|
COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
|
|
|
|
};
|
|
|
|
|
|
|
|
enum limits {
|
|
|
|
REKEY_AFTER_MESSAGES = 1ULL << 60,
|
|
|
|
REJECT_AFTER_MESSAGES = U64_MAX - COUNTER_WINDOW_SIZE - 1,
|
|
|
|
REKEY_TIMEOUT = 5,
|
|
|
|
REKEY_TIMEOUT_JITTER_MAX_JIFFIES = HZ / 3,
|
|
|
|
REKEY_AFTER_TIME = 120,
|
|
|
|
REJECT_AFTER_TIME = 180,
|
|
|
|
INITIATIONS_PER_SECOND = 50,
|
|
|
|
MAX_PEERS_PER_DEVICE = 1U << 20,
|
|
|
|
KEEPALIVE_TIMEOUT = 10,
|
|
|
|
MAX_TIMER_HANDSHAKES = 90 / REKEY_TIMEOUT,
|
|
|
|
MAX_QUEUED_INCOMING_HANDSHAKES = 4096, /* TODO: replace this with DQL */
|
|
|
|
MAX_STAGED_PACKETS = 128,
|
|
|
|
MAX_QUEUED_PACKETS = 1024 /* TODO: replace this with DQL */
|
|
|
|
};
|
|
|
|
|
|
|
|
enum message_type {
|
|
|
|
MESSAGE_INVALID = 0,
|
|
|
|
MESSAGE_HANDSHAKE_INITIATION = 1,
|
|
|
|
MESSAGE_HANDSHAKE_RESPONSE = 2,
|
|
|
|
MESSAGE_HANDSHAKE_COOKIE = 3,
|
|
|
|
MESSAGE_DATA = 4
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_header {
|
|
|
|
/* The actual layout of this that we want is:
|
|
|
|
* u8 type
|
|
|
|
* u8 reserved_zero[3]
|
|
|
|
*
|
|
|
|
* But it turns out that by encoding this as little endian,
|
|
|
|
* we achieve the same thing, and it makes checking faster.
|
|
|
|
*/
|
|
|
|
__le32 type;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_macs {
|
|
|
|
u8 mac1[COOKIE_LEN];
|
|
|
|
u8 mac2[COOKIE_LEN];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_handshake_initiation {
|
|
|
|
struct message_header header;
|
|
|
|
__le32 sender_index;
|
|
|
|
u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
|
|
|
|
u8 encrypted_static[noise_encrypted_len(NOISE_PUBLIC_KEY_LEN)];
|
|
|
|
u8 encrypted_timestamp[noise_encrypted_len(NOISE_TIMESTAMP_LEN)];
|
|
|
|
struct message_macs macs;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_handshake_response {
|
|
|
|
struct message_header header;
|
|
|
|
__le32 sender_index;
|
|
|
|
__le32 receiver_index;
|
|
|
|
u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
|
|
|
|
u8 encrypted_nothing[noise_encrypted_len(0)];
|
|
|
|
struct message_macs macs;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_handshake_cookie {
|
|
|
|
struct message_header header;
|
|
|
|
__le32 receiver_index;
|
|
|
|
u8 nonce[COOKIE_NONCE_LEN];
|
|
|
|
u8 encrypted_cookie[noise_encrypted_len(COOKIE_LEN)];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct message_data {
|
|
|
|
struct message_header header;
|
|
|
|
__le32 key_idx;
|
|
|
|
__le64 counter;
|
|
|
|
u8 encrypted_data[];
|
|
|
|
};
|
|
|
|
|
|
|
|
#define message_data_len(plain_len) \
|
|
|
|
(noise_encrypted_len(plain_len) + sizeof(struct message_data))
|
|
|
|
|
|
|
|
enum message_alignments {
|
|
|
|
MESSAGE_PADDING_MULTIPLE = 16,
|
|
|
|
MESSAGE_MINIMUM_LENGTH = message_data_len(0)
|
|
|
|
};
|
|
|
|
|
|
|
|
#define SKB_HEADER_LEN \
|
|
|
|
(max(sizeof(struct iphdr), sizeof(struct ipv6hdr)) + \
|
|
|
|
sizeof(struct udphdr) + NET_SKB_PAD)
|
|
|
|
#define DATA_PACKET_HEAD_ROOM \
|
|
|
|
ALIGN(sizeof(struct message_data) + SKB_HEADER_LEN, 4)
|
|
|
|
|
|
|
|
enum { HANDSHAKE_DSCP = 0x88 /* AF41, plus 00 ECN */ };
|
|
|
|
|
|
|
|
#endif /* _WG_MESSAGES_H */
|