| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230227-upstream-net-20230227-mptcp-fixes-v1-3-070e30ae4a8e@tessares.net>
Date: Mon, 27 Feb 2023 18:29:26 +0100
From: Matthieu Baerts <matthieu.baerts@...sares.net>
To: mptcp@...ts.linux.dev, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Menglong Dong <imagedong@...cent.com>,
Mengen Sun <mengensun@...cent.com>,
Shuah Khan <shuah@...nel.org>, Florian Westphal <fw@...len.de>,
Jiang Biao <benbjiang@...cent.com>
Cc: netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-kselftest@...r.kernel.org,
Matthieu Baerts <matthieu.baerts@...sares.net>,
stable@...r.kernel.org, Christoph Paasch <cpaasch@...le.com>
Subject: [PATCH net 3/7] mptcp: use the workqueue to destroy unaccepted
sockets
From: Paolo Abeni <pabeni@...hat.com>
Christoph reported a UaF at token lookup time after having
refactored the passive socket initialization part:
BUG: KASAN: use-after-free in __token_bucket_busy+0x253/0x260
Read of size 4 at addr ffff88810698d5b0 by task syz-executor653/3198
CPU: 1 PID: 3198 Comm: syz-executor653 Not tainted 6.2.0-rc59af4eaa31c1f6c00c8f1e448ed99a45c66340dd5 #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x6e/0x91
print_report+0x16a/0x46f
kasan_report+0xad/0x130
__token_bucket_busy+0x253/0x260
mptcp_token_new_connect+0x13d/0x490
mptcp_connect+0x4ed/0x860
__inet_stream_connect+0x80e/0xd90
tcp_sendmsg_fastopen+0x3ce/0x710
mptcp_sendmsg+0xff1/0x1a20
inet_sendmsg+0x11d/0x140
__sys_sendto+0x405/0x490
__x64_sys_sendto+0xdc/0x1b0
do_syscall_64+0x3b/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
We need to properly clean-up all the paired MPTCP-level
resources and be sure to release the msk last, even when
the unaccepted subflow is destroyed by the TCP internals
via inet_child_forget().
We can re-use the existing MPTCP_WORK_CLOSE_SUBFLOW infra,
explicitly checking that for the critical scenario: the
closed subflow is the MPC one, the msk is not accepted and
eventually going through full cleanup.
With such change, __mptcp_destroy_sock() is always called
on msk sockets, even on accepted ones. We don't need anymore
to transiently drop one sk reference at msk clone time.
Please note this commit depends on the parent one:
mptcp: refactor passive socket initialization
Fixes: 58b09919626b ("mptcp: create msk early")
Cc: stable@...r.kernel.org # v6.0+
Reported-and-tested-by: Christoph Paasch <cpaasch@...le.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/347
Signed-off-by: Paolo Abeni <pabeni@...hat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@...sares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@...sares.net>
---
net/mptcp/protocol.c | 26 +++++++++++++++++---------
net/mptcp/protocol.h | 3 ++-
net/mptcp/subflow.c | 11 +++++++++--
3 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 447641d34c2c..b7014f939236 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2398,9 +2398,10 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
return 0;
}
-static void __mptcp_close_subflow(struct mptcp_sock *msk)
+static void __mptcp_close_subflow(struct sock *sk)
{
struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_sock *msk = mptcp_sk(sk);
might_sleep();
@@ -2414,7 +2415,15 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
if (!skb_queue_empty_lockless(&ssk->sk_receive_queue))
continue;
- mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+ mptcp_close_ssk(sk, ssk, subflow);
+ }
+
+ /* if the MPC subflow has been closed before the msk is accepted,
+ * msk will never be accept-ed, close it now
+ */
+ if (!msk->first && msk->in_accept_queue) {
+ sock_set_flag(sk, SOCK_DEAD);
+ inet_sk_state_store(sk, TCP_CLOSE);
}
}
@@ -2623,6 +2632,9 @@ static void mptcp_worker(struct work_struct *work)
__mptcp_check_send_data_fin(sk);
mptcp_check_data_fin(sk);
+ if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+ __mptcp_close_subflow(sk);
+
/* There is no point in keeping around an orphaned sk timedout or
* closed, but we need the msk around to reply to incoming DATA_FIN,
* even if it is orphaned and in FIN_WAIT2 state
@@ -2638,9 +2650,6 @@ static void mptcp_worker(struct work_struct *work)
}
}
- if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
- __mptcp_close_subflow(msk);
-
if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
__mptcp_retrans(sk);
@@ -3078,6 +3087,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
msk->local_key = subflow_req->local_key;
msk->token = subflow_req->token;
msk->subflow = NULL;
+ msk->in_accept_queue = 1;
WRITE_ONCE(msk->fully_established, false);
if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
WRITE_ONCE(msk->csum_enabled, true);
@@ -3095,8 +3105,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
security_inet_csk_clone(nsk, req);
bh_unlock_sock(nsk);
- /* keep a single reference */
- __sock_put(nsk);
+ /* note: the newly allocated socket refcount is 2 now */
return nsk;
}
@@ -3152,8 +3161,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
goto out;
}
- /* acquire the 2nd reference for the owning socket */
- sock_hold(new_mptcp_sock);
newsk = new_mptcp_sock;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
} else {
@@ -3704,6 +3711,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
struct sock *newsk = newsock->sk;
set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+ msk->in_accept_queue = 0;
lock_sock(newsk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 61fd8eabfca2..901c9da8fe66 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -295,7 +295,8 @@ struct mptcp_sock {
u8 recvmsg_inq:1,
cork:1,
nodelay:1,
- fastopening:1;
+ fastopening:1,
+ in_accept_queue:1;
int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a631a5e6fc7b..9d5bf2a020ef 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -699,9 +699,10 @@ static bool subflow_hmac_valid(const struct request_sock *req,
static void mptcp_force_close(struct sock *sk)
{
- /* the msk is not yet exposed to user-space */
+ /* the msk is not yet exposed to user-space, and refcount is 2 */
inet_sk_state_store(sk, TCP_CLOSE);
sk_common_release(sk);
+ sock_put(sk);
}
static void subflow_ulp_fallback(struct sock *sk,
@@ -1866,7 +1867,6 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s
struct sock *sk = (struct sock *)msk;
bool do_cancel_work;
- sock_hold(sk);
lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
next = msk->dl_next;
msk->first = NULL;
@@ -1954,6 +1954,13 @@ static void subflow_ulp_release(struct sock *ssk)
* when the subflow is still unaccepted
*/
release = ctx->disposable || list_empty(&ctx->node);
+
+ /* inet_child_forget() does not call sk_state_change(),
+ * explicitly trigger the socket close machinery
+ */
+ if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW,
+ &mptcp_sk(sk)->flags))
+ mptcp_schedule_work(sk);
sock_put(sk);
}
--
2.38.1
Powered by blists - more mailing lists