| 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: <20250117-net-next-mptcp-syn_retrans_before_tcp_fallback-v1-1-ab4b187099b0@kernel.org>
Date: Fri, 17 Jan 2025 18:40:31 +0100
From: "Matthieu Baerts (NGI0)" <matttbe@...nel.org>
To: mptcp@...ts.linux.dev, Mat Martineau <martineau@...nel.org>,
Geliang Tang <geliang@...nel.org>, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>,
Jonathan Corbet <corbet@....net>
Cc: netdev@...r.kernel.org, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, "Matthieu Baerts (NGI0)" <matttbe@...nel.org>
Subject: [PATCH net-next] mptcp: sysctl: add
syn_retrans_before_tcp_fallback
The number of SYN + MPC retransmissions before falling back to TCP was
fixed to 2. This is certainly a good default value, but having a fixed
number can be a problem in some environments.
The current behaviour means that if all packets are dropped, there will
be:
- The initial SYN + MPC
- 2 retransmissions with MPC
- The next ones will be without MPTCP.
So typically ~3 seconds before falling back to TCP. In some networks
where some temporally blackholes are unfortunately frequent, or when a
client tries to initiate connections while the network is not ready yet,
this can cause new connections not to have MPTCP connections.
In such environments, it is now possible to increase the number of SYN
retransmissions with MPTCP options to make sure MPTCP is used.
Interesting values are:
- 0: the first retransmission will be done without MPTCP options: quite
aggressive, but also a higher risk of detecting false-positive
MPTCP blackholes.
- >= 128: all SYN retransmissions will keep the MPTCP options: back to
the < 6.12 behaviour.
The default behaviour is not changed here.
Reviewed-by: Mat Martineau <martineau@...nel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@...nel.org>
---
Documentation/networking/mptcp-sysctl.rst | 16 ++++++++++++++++
net/mptcp/ctrl.c | 21 +++++++++++++++++----
2 files changed, 33 insertions(+), 4 deletions(-)
diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 95598c21fc8e8782533bbc6a36de63bb465c297c..dc45c02113537b98dff76a6ed431c0449b5217f8 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -108,3 +108,19 @@ stale_loss_cnt - INTEGER
This is a per-namespace sysctl.
Default: 4
+
+syn_retrans_before_tcp_fallback - INTEGER
+ The number of SYN + MP_CAPABLE retransmissions before falling back to
+ TCP, i.e. dropping the MPTCP options. In other words, if all the packets
+ are dropped on the way, there will be:
+
+ * The initial SYN with MPTCP support
+ * This number of SYN retransmitted with MPTCP support
+ * The next SYN retransmissions will be without MPTCP support
+
+ 0 means the first retransmission will be done without MPTCP options.
+ >= 128 means that all SYN retransmissions will keep the MPTCP options. A
+ lower number might increase false-positive MPTCP blackholes detections.
+ This is a per-namespace sysctl.
+
+ Default: 2
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index b0dd008e2114bce65ee3906bbdc19a5a4316cefa..3999e0ba2c35b50c36ce32277e0b8bfb24197946 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -32,6 +32,7 @@ struct mptcp_pernet {
unsigned int close_timeout;
unsigned int stale_loss_cnt;
atomic_t active_disable_times;
+ u8 syn_retrans_before_tcp_fallback;
unsigned long active_disable_stamp;
u8 mptcp_enabled;
u8 checksum_enabled;
@@ -92,6 +93,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
pernet->mptcp_enabled = 1;
pernet->add_addr_timeout = TCP_RTO_MAX;
pernet->blackhole_timeout = 3600;
+ pernet->syn_retrans_before_tcp_fallback = 2;
atomic_set(&pernet->active_disable_times, 0);
pernet->close_timeout = TCP_TIMEWAIT_LEN;
pernet->checksum_enabled = 0;
@@ -245,6 +247,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
.proc_handler = proc_blackhole_detect_timeout,
.extra1 = SYSCTL_ZERO,
},
+ {
+ .procname = "syn_retrans_before_tcp_fallback",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ },
};
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -269,6 +277,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
/* table[7] is for available_schedulers which is read-only info */
table[8].data = &pernet->close_timeout;
table[9].data = &pernet->blackhole_timeout;
+ table[10].data = &pernet->syn_retrans_before_tcp_fallback;
hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
ARRAY_SIZE(mptcp_sysctl_table));
@@ -392,17 +401,21 @@ void mptcp_active_enable(struct sock *sk)
void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
{
struct mptcp_subflow_context *subflow;
- u32 timeouts;
if (!sk_is_mptcp(ssk))
return;
- timeouts = inet_csk(ssk)->icsk_retransmits;
subflow = mptcp_subflow_ctx(ssk);
if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) {
- if (timeouts == 2 || (timeouts < 2 && expired)) {
- MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP);
+ struct net *net = sock_net(ssk);
+ u8 timeouts, to_max;
+
+ timeouts = inet_csk(ssk)->icsk_retransmits;
+ to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
+
+ if (timeouts == to_max || (timeouts < to_max && expired)) {
+ MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
subflow->mpc_drop = 1;
mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
} else {
---
base-commit: 7d2eba0f83a59d360ed1e77ed2778101a6e3c4a1
change-id: 20250117-net-next-mptcp-syn_retrans_before_tcp_fallback-5f41bbc8482e
Best regards,
--
Matthieu Baerts (NGI0) <matttbe@...nel.org>
Powered by blists - more mailing lists