Commit 65e9f702 authored by Geliang Tang's avatar Geliang Tang Committed by Geliang Tang
Browse files

mptcp: add a new sysctl for make after break timeout

mainline inclusion
from mainline-v6.7-rc1
commit d866ae9aaa4325f1097e8b7a50f202348ca89b87
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I9VYQ9
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=d866ae9aaa4325f1097e8b7a50f202348ca89b87



--------------------------------

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: default avatarMat Martineau <martineau@kernel.org>
Signed-off-by: default avatarPaolo Abeni <pabeni@redhat.com>
Signed-off-by: default avatarMat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-2-v1-1-9dc60939d371@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
Reviewed-by: default avatarJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: default avatarGeliang Tang <tanggeliang@kylinos.cn>
parent 3f3e2f87
Loading
Loading
Loading
Loading
+11 −0
Original line number Diff line number Diff line
@@ -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.

+16 −0
Original line number Diff line number Diff line
@@ -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;
@@ -178,6 +187,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
		.mode = 0644,
		.proc_handler = proc_scheduler,
	},
	{
		.procname = "close_timeout",
		.maxlen = sizeof(unsigned int),
		.mode = 0644,
		.proc_handler = proc_dointvec_jiffies,
	},
	{}
};

@@ -200,6 +215,7 @@ 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));
+3 −3
Original line number Diff line number Diff line
@@ -2387,8 +2387,8 @@ 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;
@@ -2513,7 +2513,7 @@ 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)
@@ -2656,7 +2656,7 @@ 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
+1 −0
Original line number Diff line number Diff line
@@ -623,6 +623,7 @@ 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_sock *msk,