mptcp: add a new sysctl for make after break timeout

The MPTCP protocol allows sockets with no alive subflows to stay
in ESTABLISHED status for and user-defined timeout, to allow for
later subflows creation.

Currently such timeout is constant - TCP_TIMEWAIT_LEN. Let the
user-space configure them via a newly added sysctl, to better cope
with busy servers and simplify (make them faster) the relevant
pktdrill tests.

Note that the new know does not apply to orphaned MPTCP socket
waiting for the data_fin handshake completion: they always wait
TCP_TIMEWAIT_LEN.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-2-v1-1-9dc60939d371@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 15f1919d640c092c1c919264e72d218be5d413fd..69975ce25a029400e4e55779ee8220a322b930f9 100644 (file)
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -25,6 +25,17 @@ add_addr_timeout - INTEGER (seconds)
 
        Default: 120
 
+close_timeout - INTEGER (seconds)
+       Set the make-after-break timeout: in absence of any close or
+       shutdown syscall, MPTCP sockets will maintain the status
+       unchanged for such time, after the last subflow removal, before
+       moving to TCP_CLOSE.
+
+       The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace
+       sysctl.
+
+       Default: 60
+
 checksum_enabled - BOOLEAN
        Control whether DSS checksum can be enabled.
 

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index e72b518c5d0266f091b61703f371c846b24dae33..13fe0748dde83804daa160af50827dfc899fc426 100644 (file)
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -27,6 +27,7 @@ struct mptcp_pernet {
 #endif
 
        unsigned int add_addr_timeout;
+       unsigned int close_timeout;
        unsigned int stale_loss_cnt;
        u8 mptcp_enabled;
        u8 checksum_enabled;
@@ -65,6 +66,13 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net)
        return mptcp_get_pernet(net)->stale_loss_cnt;
 }
 
+unsigned int mptcp_close_timeout(const struct sock *sk)
+{
+       if (sock_flag(sk, SOCK_DEAD))
+               return TCP_TIMEWAIT_LEN;
+       return mptcp_get_pernet(sock_net(sk))->close_timeout;
+}
+
 int mptcp_get_pm_type(const struct net *net)
 {
        return mptcp_get_pernet(net)->pm_type;
@@ -79,6 +87,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
        pernet->mptcp_enabled = 1;
        pernet->add_addr_timeout = TCP_RTO_MAX;
+       pernet->close_timeout = TCP_TIMEWAIT_LEN;
        pernet->checksum_enabled = 0;
        pernet->allow_join_initial_addr_port = 1;
        pernet->stale_loss_cnt = 4;
@@ -141,6 +150,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
                .mode = 0644,
                .proc_handler = proc_dostring,
        },
+       {
+               .procname = "close_timeout",
+               .maxlen = sizeof(unsigned int),
+               .mode = 0644,
+               .proc_handler = proc_dointvec_jiffies,
+       },
        {}
 };
 
@@ -163,6 +178,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
        table[4].data = &pernet->stale_loss_cnt;
        table[5].data = &pernet->pm_type;
        table[6].data = &pernet->scheduler;
+       table[7].data = &pernet->close_timeout;
 
        hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
                                     ARRAY_SIZE(mptcp_sysctl_table));

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 886ab689a8aea920a1b3c4b22b64c3b3b7268f26..a21f8ed263436e1c0c3be868aca170888a1cced6 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2391,8 +2391,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
        if (msk->in_accept_queue && msk->first == ssk &&
            (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) {
                /* ensure later check in mptcp_worker() will dispose the msk */
-               mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1));
                sock_set_flag(sk, SOCK_DEAD);
+               mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1));
                lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
                mptcp_subflow_drop_ctx(ssk);
                goto out_release;
@@ -2516,7 +2516,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk)
                return false;
 
        return time_after32(tcp_jiffies32,
-                 inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN);
+                 inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk));
 }
 
 static void mptcp_check_fastclose(struct mptcp_sock *msk)
@@ -2659,7 +2659,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout)
                return;
 
        close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies +
-                       TCP_TIMEWAIT_LEN;
+                       mptcp_close_timeout(sk);
 
        /* the close timeout takes precedence on the fail one, and here at least one of
         * them is active

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c4c05afdc48cabc881fb26e707e9b8873d033ccc..40228b55e3e92f8035b067fd101afe4c23261e9f 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -615,6 +615,7 @@ unsigned int mptcp_get_add_addr_timeout(const struct net *net);
 int mptcp_is_checksum_enabled(const struct net *net);
 int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
+unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,