From: Menglong Dong <[email protected]>
The mptcp socket and its subflow sockets in accept queue can't be
released after the process exit.
While the release of a mptcp socket in listening state, the
corresponding tcp socket will be released too. Meanwhile, the tcp
socket in the unaccept queue will be released too. However, only init
subflow is in the unaccept queue, and the joined subflow is not in the
unaccept queue, which makes the joined subflow won't be released, and
therefore the corresponding unaccepted mptcp socket will not be released
to.
This can be reproduced easily with following steps:
1. create 2 namespace and veth:
$ ip netns add mptcp-client
$ ip netns add mptcp-server
$ sysctl -w net.ipv4.conf.all.rp_filter=0
$ ip netns exec mptcp-client sysctl -w net.mptcp.enabled=1
$ ip netns exec mptcp-server sysctl -w net.mptcp.enabled=1
$ ip link add red-client netns mptcp-client type veth peer red-server \
netns mptcp-server
$ ip -n mptcp-server address add 10.0.0.1/24 dev red-server
$ ip -n mptcp-server address add 192.168.0.1/24 dev red-server
$ ip -n mptcp-client address add 10.0.0.2/24 dev red-client
$ ip -n mptcp-client address add 192.168.0.2/24 dev red-client
$ ip -n mptcp-server link set red-server up
$ ip -n mptcp-client link set red-client up
2. configure the endpoint and limit for client and server:
$ ip -n mptcp-server mptcp endpoint flush
$ ip -n mptcp-server mptcp limits set subflow 2 add_addr_accepted 2
$ ip -n mptcp-client mptcp endpoint flush
$ ip -n mptcp-client mptcp limits set subflow 2 add_addr_accepted 2
$ ip -n mptcp-client mptcp endpoint add 192.168.0.2 dev red-client id \
1 subflow
3. listen and accept on a port, such as 9999. The nc command we used
here is modified, which makes it use mptcp protocol by default.
$ ip netns exec mptcp-server nc -l -k -p 9999
4. open another *two* terminal and use each of them to connect to the
server with the following command:
$ ip netns exec mptcp-client nc 10.0.0.1 9999
Input something after connect to triger the connection of the second
subflow. So that there are two established mptcp connections, with the
second one still unaccepted.
5. exit all the nc command, and check the tcp socket in server namespace.
And you will find that there is one tcp socket in CLOSE_WAIT state
and can't release forever.
Fix this by closing all of the unaccepted mptcp socket in
mptcp_subflow_queue_clean() with mptcp_close_nolock().
Now, we can ensure that all unaccepted mptcp sockets will be cleaned by
mptcp_close() before they are released, so mptcp_sock_destruct(), which is
used to clean the unaccepted mptcp socket, is not needed anymore.
Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Reviewed-by: Jiang Biao <[email protected]>
Reviewed-by: Mengen Sun <[email protected]>
Signed-off-by: Menglong Dong <[email protected]>
---
net/mptcp/protocol.c | 13 +++++++++----
net/mptcp/subflow.c | 33 ++++++++-------------------------
2 files changed, 17 insertions(+), 29 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d398f3810662..fe6b7fbb145c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2796,13 +2796,12 @@ static void __mptcp_destroy_sock(struct sock *sk)
sock_put(sk);
}
-static void mptcp_close(struct sock *sk, long timeout)
+void mptcp_close_nolock(struct sock *sk, long timeout)
{
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
bool do_cancel_work = false;
- lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
@@ -2833,7 +2832,6 @@ static void mptcp_close(struct sock *sk, long timeout)
}
sock_orphan(sk);
- sock_hold(sk);
pr_debug("msk=%p state=%d", sk, sk->sk_state);
if (mptcp_sk(sk)->token)
mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
@@ -2844,10 +2842,17 @@ static void mptcp_close(struct sock *sk, long timeout)
} else {
mptcp_reset_timeout(msk, 0);
}
- release_sock(sk);
+
if (do_cancel_work)
mptcp_cancel_work(sk);
+}
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ sock_hold(sk);
+ lock_sock(sk);
+ mptcp_close_nolock(sk, timeout);
+ release_sock(sk);
sock_put(sk);
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c7d49fb6e7bd..cebabf2bb222 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -602,30 +602,6 @@ static bool subflow_hmac_valid(const struct request_sock *req,
return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
}
-static void mptcp_sock_destruct(struct sock *sk)
-{
- /* if new mptcp socket isn't accepted, it is free'd
- * from the tcp listener sockets request queue, linked
- * from req->sk. The tcp socket is released.
- * This calls the ULP release function which will
- * also remove the mptcp socket, via
- * sock_put(ctx->conn).
- *
- * Problem is that the mptcp socket will be in
- * ESTABLISHED state and will not have the SOCK_DEAD flag.
- * Both result in warnings from inet_sock_destruct.
- */
- if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
- sk->sk_state = TCP_CLOSE;
- WARN_ON_ONCE(sk->sk_socket);
- sock_orphan(sk);
- }
-
- /* We don't need to clear msk->subflow, as it's still NULL at this point */
- mptcp_destroy_common(mptcp_sk(sk), 0);
- inet_sock_destruct(sk);
-}
-
static void mptcp_force_close(struct sock *sk)
{
/* the msk is not yet exposed to user-space */
@@ -768,7 +744,6 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
/* new mpc subflow takes ownership of the newly
* created mptcp socket
*/
- new_msk->sk_destruct = mptcp_sock_destruct;
mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
@@ -1765,11 +1740,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
struct sock *sk = (struct sock *)msk;
bool slow;
+ sock_hold(sk);
slow = lock_sock_fast_nested(sk);
next = msk->dl_next;
msk->first = NULL;
msk->dl_next = NULL;
+
+ /* mptcp_close_nolock() will put a extra reference on sk,
+ * so we hold one here.
+ */
+ sock_hold(sk);
+ mptcp_close_nolock(sk, 0);
unlock_sock_fast(sk, slow);
+ sock_put(sk);
}
/* we are still under the listener msk socket lock */
--
2.37.2
On Wed, Sep 7, 2022 at 4:51 PM Matthieu Baerts
<[email protected]> wrote:
>
> Hi Menglong,
>
> On 07/09/2022 10:33, [email protected] wrote:
> > From: Menglong Dong <[email protected]>
> >
> > The mptcp socket and its subflow sockets in accept queue can't be
> > released after the process exit.
> >
> > While the release of a mptcp socket in listening state, the
> > corresponding tcp socket will be released too. Meanwhile, the tcp
> > socket in the unaccept queue will be released too. However, only init
> > subflow is in the unaccept queue, and the joined subflow is not in the
> > unaccept queue, which makes the joined subflow won't be released, and
> > therefore the corresponding unaccepted mptcp socket will not be released
> > to.
>
> Thank you for the patch!
>
> (...)
>
> > ---
> > net/mptcp/protocol.c | 13 +++++++++----
> > net/mptcp/subflow.c | 33 ++++++++-------------------------
> > 2 files changed, 17 insertions(+), 29 deletions(-)
> >
> > diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> > index d398f3810662..fe6b7fbb145c 100644
> > --- a/net/mptcp/protocol.c
> > +++ b/net/mptcp/protocol.c
> > @@ -2796,13 +2796,12 @@ static void __mptcp_destroy_sock(struct sock *sk)
> > sock_put(sk);
> > }
> >
> > -static void mptcp_close(struct sock *sk, long timeout)
> > +void mptcp_close_nolock(struct sock *sk, long timeout)
>
> I didn't look at it into details but like the previous previous, I don't
> think this one compiles without errors: you define this (non static)
> function here in protocol.c but you don't "expose" it in protocol.h ...
> (see below)
>
Oops...I forgot to commit the protocol.h :)
> > diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
> > index c7d49fb6e7bd..cebabf2bb222 100644
> > --- a/net/mptcp/subflow.c
> > +++ b/net/mptcp/subflow.c
>
> (...)
>
> > @@ -1765,11 +1740,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
> > struct sock *sk = (struct sock *)msk;
> > bool slow;
> >
> > + sock_hold(sk);
> > slow = lock_sock_fast_nested(sk);
> > next = msk->dl_next;
> > msk->first = NULL;
> > msk->dl_next = NULL;
> > +
> > + /* mptcp_close_nolock() will put a extra reference on sk,
> > + * so we hold one here.
> > + */
> > + sock_hold(sk);
> > + mptcp_close_nolock(sk, 0);
>
> ... I guess the compiler will complain if you try to use it here from
> subflow.c, no?
>
Hmm...The compiler didn't, as I modified protocol.h locally. That
's why I didn't find this mistake :)
> Also, did you have the opportunity to run the different MPTCP selftests
> with this patch?
>
Not yet. I'll do it before the next version.
Thanks!
Menglong Dong
> Cheers,
> Matt
> --
> Tessares | Belgium | Hybrid Access Solutions
> http://www.tessares.net
Hi Menglong,
On 07/09/2022 10:33, [email protected] wrote:
> From: Menglong Dong <[email protected]>
>
> The mptcp socket and its subflow sockets in accept queue can't be
> released after the process exit.
>
> While the release of a mptcp socket in listening state, the
> corresponding tcp socket will be released too. Meanwhile, the tcp
> socket in the unaccept queue will be released too. However, only init
> subflow is in the unaccept queue, and the joined subflow is not in the
> unaccept queue, which makes the joined subflow won't be released, and
> therefore the corresponding unaccepted mptcp socket will not be released
> to.
Thank you for the patch!
(...)
> ---
> net/mptcp/protocol.c | 13 +++++++++----
> net/mptcp/subflow.c | 33 ++++++++-------------------------
> 2 files changed, 17 insertions(+), 29 deletions(-)
>
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index d398f3810662..fe6b7fbb145c 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -2796,13 +2796,12 @@ static void __mptcp_destroy_sock(struct sock *sk)
> sock_put(sk);
> }
>
> -static void mptcp_close(struct sock *sk, long timeout)
> +void mptcp_close_nolock(struct sock *sk, long timeout)
I didn't look at it into details but like the previous previous, I don't
think this one compiles without errors: you define this (non static)
function here in protocol.c but you don't "expose" it in protocol.h ...
(see below)
> diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
> index c7d49fb6e7bd..cebabf2bb222 100644
> --- a/net/mptcp/subflow.c
> +++ b/net/mptcp/subflow.c
(...)
> @@ -1765,11 +1740,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
> struct sock *sk = (struct sock *)msk;
> bool slow;
>
> + sock_hold(sk);
> slow = lock_sock_fast_nested(sk);
> next = msk->dl_next;
> msk->first = NULL;
> msk->dl_next = NULL;
> +
> + /* mptcp_close_nolock() will put a extra reference on sk,
> + * so we hold one here.
> + */
> + sock_hold(sk);
> + mptcp_close_nolock(sk, 0);
... I guess the compiler will complain if you try to use it here from
subflow.c, no?
Also, did you have the opportunity to run the different MPTCP selftests
with this patch?
Cheers,
Matt
--
Tessares | Belgium | Hybrid Access Solutions
http://www.tessares.net
Hi,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net/master]
url: https://github.com/intel-lab-lkp/linux/commits/menglong8-dong-gmail-com/net-mptcp-fix-unreleased-socket-in-accept-queue/20220907-163559
base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git e1091e226a2bab4ded1fe26efba2aee1aab06450
config: parisc-allyesconfig (https://download.01.org/0day-ci/archive/20220907/[email protected]/config)
compiler: hppa-linux-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/d238db12dcac26bfb2197e0aae24fadf6bbfdcb6
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review menglong8-dong-gmail-com/net-mptcp-fix-unreleased-socket-in-accept-queue/20220907-163559
git checkout d238db12dcac26bfb2197e0aae24fadf6bbfdcb6
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=parisc SHELL=/bin/bash net/
If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <[email protected]>
All warnings (new ones prefixed by >>):
>> net/mptcp/protocol.c:2799:6: warning: no previous prototype for 'mptcp_close_nolock' [-Wmissing-prototypes]
2799 | void mptcp_close_nolock(struct sock *sk, long timeout)
| ^~~~~~~~~~~~~~~~~~
vim +/mptcp_close_nolock +2799 net/mptcp/protocol.c
2798
> 2799 void mptcp_close_nolock(struct sock *sk, long timeout)
2800 {
2801 struct mptcp_subflow_context *subflow;
2802 struct mptcp_sock *msk = mptcp_sk(sk);
2803 bool do_cancel_work = false;
2804
2805 sk->sk_shutdown = SHUTDOWN_MASK;
2806
2807 if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
2808 inet_sk_state_store(sk, TCP_CLOSE);
2809 goto cleanup;
2810 }
2811
2812 if (mptcp_close_state(sk))
2813 __mptcp_wr_shutdown(sk);
2814
2815 sk_stream_wait_close(sk, timeout);
2816
2817 cleanup:
2818 /* orphan all the subflows */
2819 inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
2820 mptcp_for_each_subflow(msk, subflow) {
2821 struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
2822 bool slow = lock_sock_fast_nested(ssk);
2823
2824 /* since the close timeout takes precedence on the fail one,
2825 * cancel the latter
2826 */
2827 if (ssk == msk->first)
2828 subflow->fail_tout = 0;
2829
2830 sock_orphan(ssk);
2831 unlock_sock_fast(ssk, slow);
2832 }
2833 sock_orphan(sk);
2834
2835 pr_debug("msk=%p state=%d", sk, sk->sk_state);
2836 if (mptcp_sk(sk)->token)
2837 mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
2838
2839 if (sk->sk_state == TCP_CLOSE) {
2840 __mptcp_destroy_sock(sk);
2841 do_cancel_work = true;
2842 } else {
2843 mptcp_reset_timeout(msk, 0);
2844 }
2845
2846 if (do_cancel_work)
2847 mptcp_cancel_work(sk);
2848 }
2849
--
0-DAY CI Kernel Test Service
https://01.org/lkp