linux/drivers/net/wireguard/allowedips.c

378 lines
10 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 "allowedips.h"
#include "peer.h"
static void swap_endian(u8 *dst, const u8 *src, u8 bits)
{
if (bits == 32) {
*(u32 *)dst = be32_to_cpu(*(const __be32 *)src);
} else if (bits == 128) {
((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]);
((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]);
}
}
static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
u8 cidr, u8 bits)
{
node->cidr = cidr;
node->bit_at_a = cidr / 8U;
#ifdef __LITTLE_ENDIAN
node->bit_at_a ^= (bits / 8U - 1U) % 8U;
#endif
node->bit_at_b = 7U - (cidr % 8U);
node->bitlen = bits;
memcpy(node->bits, src, bits / 8U);
}
#define CHOOSE_NODE(parent, key) \
parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
static void push_rcu(struct allowedips_node **stack,
struct allowedips_node __rcu *p, unsigned int *len)
{
if (rcu_access_pointer(p)) {
WARN_ON(IS_ENABLED(DEBUG) && *len >= 128);
stack[(*len)++] = rcu_dereference_raw(p);
}
}
static void root_free_rcu(struct rcu_head *rcu)
{
struct allowedips_node *node, *stack[128] = {
container_of(rcu, struct allowedips_node, rcu) };
unsigned int len = 1;
while (len > 0 && (node = stack[--len])) {
push_rcu(stack, node->bit[0], &len);
push_rcu(stack, node->bit[1], &len);
kfree(node);
}
}
static void root_remove_peer_lists(struct allowedips_node *root)
{
struct allowedips_node *node, *stack[128] = { root };
unsigned int len = 1;
while (len > 0 && (node = stack[--len])) {
push_rcu(stack, node->bit[0], &len);
push_rcu(stack, node->bit[1], &len);
if (rcu_access_pointer(node->peer))
list_del(&node->peer_list);
}
}
static void walk_remove_by_peer(struct allowedips_node __rcu **top,
struct wg_peer *peer, struct mutex *lock)
{
#define REF(p) rcu_access_pointer(p)
#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
#define PUSH(p) ({ \
WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \
stack[len++] = p; \
})
struct allowedips_node __rcu **stack[128], **nptr;
struct allowedips_node *node, *prev;
unsigned int len;
if (unlikely(!peer || !REF(*top)))
return;
for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
nptr = stack[len - 1];
node = DEREF(nptr);
if (!node) {
--len;
continue;
}
if (!prev || REF(prev->bit[0]) == node ||
REF(prev->bit[1]) == node) {
if (REF(node->bit[0]))
PUSH(&node->bit[0]);
else if (REF(node->bit[1]))
PUSH(&node->bit[1]);
} else if (REF(node->bit[0]) == prev) {
if (REF(node->bit[1]))
PUSH(&node->bit[1]);
} else {
if (rcu_dereference_protected(node->peer,
lockdep_is_held(lock)) == peer) {
RCU_INIT_POINTER(node->peer, NULL);
list_del_init(&node->peer_list);
if (!node->bit[0] || !node->bit[1]) {
rcu_assign_pointer(*nptr, DEREF(
&node->bit[!REF(node->bit[0])]));
kfree_rcu(node, rcu);
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
node = DEREF(nptr);
}
}
--len;
}
}
#undef REF
#undef DEREF
#undef PUSH
}
static unsigned int fls128(u64 a, u64 b)
{
return a ? fls64(a) + 64U : fls64(b);
}
static u8 common_bits(const struct allowedips_node *node, const u8 *key,
u8 bits)
{
if (bits == 32)
return 32U - fls(*(const u32 *)node->bits ^ *(const u32 *)key);
else if (bits == 128)
return 128U - fls128(
*(const u64 *)&node->bits[0] ^ *(const u64 *)&key[0],
*(const u64 *)&node->bits[8] ^ *(const u64 *)&key[8]);
return 0;
}
static bool prefix_matches(const struct allowedips_node *node, const u8 *key,
u8 bits)
{
/* This could be much faster if it actually just compared the common
* bits properly, by precomputing a mask bswap(~0 << (32 - cidr)), and
* the rest, but it turns out that common_bits is already super fast on
* modern processors, even taking into account the unfortunate bswap.
* So, we just inline it like this instead.
*/
return common_bits(node, key, bits) >= node->cidr;
}
static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
const u8 *key)
{
struct allowedips_node *node = trie, *found = NULL;
while (node && prefix_matches(node, key, bits)) {
if (rcu_access_pointer(node->peer))
found = node;
if (node->cidr == bits)
break;
node = rcu_dereference_bh(CHOOSE_NODE(node, key));
}
return found;
}
/* Returns a strong reference to a peer */
static struct wg_peer *lookup(struct allowedips_node __rcu *root, u8 bits,
const void *be_ip)
{
/* Aligned so it can be passed to fls/fls64 */
u8 ip[16] __aligned(__alignof(u64));
struct allowedips_node *node;
struct wg_peer *peer = NULL;
swap_endian(ip, be_ip, bits);
rcu_read_lock_bh();
retry:
node = find_node(rcu_dereference_bh(root), bits, ip);
if (node) {
peer = wg_peer_get_maybe_zero(rcu_dereference_bh(node->peer));
if (!peer)
goto retry;
}
rcu_read_unlock_bh();
return peer;
}
static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
u8 cidr, u8 bits, struct allowedips_node **rnode,
struct mutex *lock)
{
struct allowedips_node *node = rcu_dereference_protected(trie,
lockdep_is_held(lock));
struct allowedips_node *parent = NULL;
bool exact = false;
while (node && node->cidr <= cidr && prefix_matches(node, key, bits)) {
parent = node;
if (parent->cidr == cidr) {
exact = true;
break;
}
node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
lockdep_is_held(lock));
}
*rnode = parent;
return exact;
}
static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
u8 cidr, struct wg_peer *peer, struct mutex *lock)
{
struct allowedips_node *node, *parent, *down, *newnode;
if (unlikely(cidr > bits || !peer))
return -EINVAL;
if (!rcu_access_pointer(*trie)) {
node = kzalloc(sizeof(*node), GFP_KERNEL);
if (unlikely(!node))
return -ENOMEM;
RCU_INIT_POINTER(node->peer, peer);
list_add_tail(&node->peer_list, &peer->allowedips_list);
copy_and_assign_cidr(node, key, cidr, bits);
rcu_assign_pointer(*trie, node);
return 0;
}
if (node_placement(*trie, key, cidr, bits, &node, lock)) {
rcu_assign_pointer(node->peer, peer);
list_move_tail(&node->peer_list, &peer->allowedips_list);
return 0;
}
newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
if (unlikely(!newnode))
return -ENOMEM;
RCU_INIT_POINTER(newnode->peer, peer);
list_add_tail(&newnode->peer_list, &peer->allowedips_list);
copy_and_assign_cidr(newnode, key, cidr, bits);
if (!node) {
down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
} else {
down = rcu_dereference_protected(CHOOSE_NODE(node, key),
lockdep_is_held(lock));
if (!down) {
rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
return 0;
}
}
cidr = min(cidr, common_bits(down, key, bits));
parent = node;
if (newnode->cidr == cidr) {
rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
if (!parent)
rcu_assign_pointer(*trie, newnode);
else
rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
newnode);
} else {
node = kzalloc(sizeof(*node), GFP_KERNEL);
if (unlikely(!node)) {
wireguard: allowedips: fix use-after-free in root_remove_peer_lists In the unlikely case a new node could not be allocated, we need to remove @newnode from @peer->allowedips_list before freeing it. syzbot reported: BUG: KASAN: use-after-free in __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54 Read of size 8 at addr ffff88809881a538 by task syz-executor.4/30133 CPU: 0 PID: 30133 Comm: syz-executor.4 Not tainted 5.5.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:639 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135 __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54 __list_del_entry include/linux/list.h:132 [inline] list_del include/linux/list.h:146 [inline] root_remove_peer_lists+0x24f/0x4b0 drivers/net/wireguard/allowedips.c:65 wg_allowedips_free+0x232/0x390 drivers/net/wireguard/allowedips.c:300 wg_peer_remove_all+0xd5/0x620 drivers/net/wireguard/peer.c:187 wg_set_device+0xd01/0x1350 drivers/net/wireguard/netlink.c:542 genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:672 ____sys_sendmsg+0x753/0x880 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 __do_sys_sendmsg net/socket.c:2439 [inline] __se_sys_sendmsg net/socket.c:2437 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45b399 Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f99a9bcdc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f99a9bce6d4 RCX: 000000000045b399 RDX: 0000000000000000 RSI: 0000000020001340 RDI: 0000000000000003 RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004 R13: 00000000000009ba R14: 00000000004cb2b8 R15: 0000000000000009 Allocated by task 30103: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] __kasan_kmalloc mm/kasan/common.c:513 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527 kmem_cache_alloc_trace+0x158/0x790 mm/slab.c:3551 kmalloc include/linux/slab.h:556 [inline] kzalloc include/linux/slab.h:670 [inline] add+0x70a/0x1970 drivers/net/wireguard/allowedips.c:236 wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320 set_allowedip drivers/net/wireguard/netlink.c:343 [inline] set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468 wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591 genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:672 ____sys_sendmsg+0x753/0x880 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 __do_sys_sendmsg net/socket.c:2439 [inline] __se_sys_sendmsg net/socket.c:2437 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 30103: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] kasan_set_free_info mm/kasan/common.c:335 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483 __cache_free mm/slab.c:3426 [inline] kfree+0x10a/0x2c0 mm/slab.c:3757 add+0x12d2/0x1970 drivers/net/wireguard/allowedips.c:266 wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320 set_allowedip drivers/net/wireguard/netlink.c:343 [inline] set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468 wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591 genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:672 ____sys_sendmsg+0x753/0x880 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 __do_sys_sendmsg net/socket.c:2439 [inline] __se_sys_sendmsg net/socket.c:2437 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88809881a500 which belongs to the cache kmalloc-64 of size 64 The buggy address is located 56 bytes inside of 64-byte region [ffff88809881a500, ffff88809881a540) The buggy address belongs to the page: page:ffffea0002620680 refcount:1 mapcount:0 mapping:ffff8880aa400380 index:0x0 raw: 00fffe0000000200 ffffea000250b748 ffffea000254bac8 ffff8880aa400380 raw: 0000000000000000 ffff88809881a000 0000000100000020 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88809881a400: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88809881a480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc >ffff88809881a500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ^ ffff88809881a580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88809881a600: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jason A. Donenfeld <Jason@zx2c4.com> Cc: wireguard@lists.zx2c4.com Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-05 05:17:25 +08:00
list_del(&newnode->peer_list);
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
kfree(newnode);
return -ENOMEM;
}
INIT_LIST_HEAD(&node->peer_list);
copy_and_assign_cidr(node, newnode->bits, cidr, bits);
rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
if (!parent)
rcu_assign_pointer(*trie, node);
else
rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
node);
}
return 0;
}
void wg_allowedips_init(struct allowedips *table)
{
table->root4 = table->root6 = NULL;
table->seq = 1;
}
void wg_allowedips_free(struct allowedips *table, struct mutex *lock)
{
struct allowedips_node __rcu *old4 = table->root4, *old6 = table->root6;
++table->seq;
RCU_INIT_POINTER(table->root4, NULL);
RCU_INIT_POINTER(table->root6, NULL);
if (rcu_access_pointer(old4)) {
struct allowedips_node *node = rcu_dereference_protected(old4,
lockdep_is_held(lock));
root_remove_peer_lists(node);
call_rcu(&node->rcu, root_free_rcu);
}
if (rcu_access_pointer(old6)) {
struct allowedips_node *node = rcu_dereference_protected(old6,
lockdep_is_held(lock));
root_remove_peer_lists(node);
call_rcu(&node->rcu, root_free_rcu);
}
}
int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
u8 cidr, struct wg_peer *peer, struct mutex *lock)
{
/* Aligned so it can be passed to fls */
u8 key[4] __aligned(__alignof(u32));
++table->seq;
swap_endian(key, (const u8 *)ip, 32);
return add(&table->root4, 32, key, cidr, peer, lock);
}
int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
u8 cidr, struct wg_peer *peer, struct mutex *lock)
{
/* Aligned so it can be passed to fls64 */
u8 key[16] __aligned(__alignof(u64));
++table->seq;
swap_endian(key, (const u8 *)ip, 128);
return add(&table->root6, 128, key, cidr, peer, lock);
}
void wg_allowedips_remove_by_peer(struct allowedips *table,
struct wg_peer *peer, struct mutex *lock)
{
++table->seq;
walk_remove_by_peer(&table->root4, peer, lock);
walk_remove_by_peer(&table->root6, peer, lock);
}
int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
{
const unsigned int cidr_bytes = DIV_ROUND_UP(node->cidr, 8U);
swap_endian(ip, node->bits, node->bitlen);
memset(ip + cidr_bytes, 0, node->bitlen / 8U - cidr_bytes);
if (node->cidr)
ip[cidr_bytes - 1U] &= ~0U << (-node->cidr % 8U);
*cidr = node->cidr;
return node->bitlen == 32 ? AF_INET : AF_INET6;
}
/* Returns a strong reference to a peer */
struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return lookup(table->root4, 32, &ip_hdr(skb)->daddr);
else if (skb->protocol == htons(ETH_P_IPV6))
return lookup(table->root6, 128, &ipv6_hdr(skb)->daddr);
return NULL;
}
/* Returns a strong reference to a peer */
struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return lookup(table->root4, 32, &ip_hdr(skb)->saddr);
else if (skb->protocol == htons(ETH_P_IPV6))
return lookup(table->root6, 128, &ipv6_hdr(skb)->saddr);
return NULL;
}
#include "selftest/allowedips.c"