[PATCH net v3 1/1] tcp: bound SYN-ACK timers to reqsk timeout range

[PATCH net v3 1/1] tcp: bound SYN-ACK timers to reqsk timeout range

[Ren Wei]

From: Zhiling Zou <roxy520tt@gmail.com>

tcp_synack_retries supplies the SYN-ACK retry limit used by request
socket timers. The same effective limit can also come from TCP_SYNCNT
through icsk_syn_retries, while TCP_DEFER_ACCEPT can keep an ACKed
request alive until rskq_defer_accept is reached.

The request socket timeout counter is incremented before it is used to
compute the next timeout. tcp_reqsk_timeout() and the Fast Open SYN-ACK
timer shift req->timeout by req->num_timeout. Excessive retry or
defer-accept limits can therefore drive these timer paths into invalid
shift counts before the request expires.

Limit tcp_synack_retries to the request socket timer range, clamp the
effective retry and defer-accept limits in the regular request socket
timer path, clamp the Fast Open retry limit, and make the request
socket timeout helper saturate before shifting.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Reported-by: Yuan Tan <yuantan098@gmail.com>
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Reported-by: Xin Liu <bird@lzu.edu.cn>
Assisted-by: Codex:gpt-5.4
Signed-off-by: Zhiling Zou <roxy520tt@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
---
Changes in v3:
  - Order local variables in tcp_reqsk_timeout_sk() by reverse Christmas tree.
  - v2 Link: https://lore.kernel.org/all/20260630035009.55201-1-n05ec@lzu.edu.cn/

Changes in v2:
  - Keep the existing max_retries calculation in tcp_fastopen_synack_timer()
    and only add the clamp, avoiding code churn.
  - v1 Link: https://lore.kernel.org/all/02e24eb83639e9d7ecc623f000c60254bb5c40a5.1782643946.git.roxy520tt@gmail.com/

 include/net/tcp.h               | 19 +++++++++++++++----
 net/ipv4/inet_connection_sock.c |  6 +++++-
 net/ipv4/sysctl_net_ipv4.c      |  2 ++
 net/ipv4/tcp_timer.c            |  3 ++-
 4 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6d376ea4d1c0..ee78436b8964 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -183,6 +183,7 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
 #define MAX_TCP_KEEPINTVL	32767
 #define MAX_TCP_KEEPCNT		127
 #define MAX_TCP_SYNCNT		127
+#define MAX_TCP_SYNACK_RETRIES	63
 
 /* Ensure that TCP PAWS checks are relaxed after ~2147 seconds
  * to avoid overflows. This assumes a clock smaller than 1 Mhz.
@@ -882,12 +883,22 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 	return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
 }
 
-static inline unsigned long tcp_reqsk_timeout(struct request_sock *req)
+static inline unsigned long tcp_reqsk_timeout_sk(const struct sock *sk,
+						 struct request_sock *req)
 {
-	u64 timeout = (u64)req->timeout << req->num_timeout;
+	u32 rto_max = tcp_rto_max(sk);
+	u64 timeout = req->timeout;
+
+	if (req->num_timeout >= BITS_PER_TYPE(u64) ||
+	    timeout > U64_MAX >> req->num_timeout)
+		return rto_max;
+
+	return (unsigned long)min_t(u64, timeout << req->num_timeout, rto_max);
+}
 
-	return (unsigned long)min_t(u64, timeout,
-				    tcp_rto_max(req->rsk_listener));
+static inline unsigned long tcp_reqsk_timeout(struct request_sock *req)
+{
+	return tcp_reqsk_timeout_sk(req->rsk_listener, req);
 }
 
 u32 tcp_delack_max(const struct sock *sk);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 56902bba5483..b74212bae3dd 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1056,6 +1056,8 @@ static void reqsk_timer_handler(struct timer_list *t)
 	net = sock_net(sk_listener);
 	max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
 		READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
+	max_syn_ack_retries = min_t(int, max_syn_ack_retries,
+				    MAX_TCP_SYNACK_RETRIES);
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
 	 * If synack was not acknowledged for 1 second, it means
@@ -1086,7 +1088,9 @@ static void reqsk_timer_handler(struct timer_list *t)
 		}
 	}
 
-	syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept),
+	syn_ack_recalc(req, max_syn_ack_retries,
+		       min_t(u8, READ_ONCE(queue->rskq_defer_accept),
+			     MAX_TCP_SYNACK_RETRIES),
 		       &expire, &resend);
 	tcp_syn_ack_timeout(req);
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ca1180dba1de..f9d233b98bbc 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -35,6 +35,7 @@ static int ip_ttl_min = 1;
 static int ip_ttl_max = 255;
 static int tcp_syn_retries_min = 1;
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
+static int tcp_synack_retries_max = MAX_TCP_SYNACK_RETRIES;
 static int tcp_syn_linear_timeouts_max = MAX_TCP_SYNCNT;
 static unsigned long ip_ping_group_range_min[] = { 0, 0 };
 static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
@@ -1034,6 +1035,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra2		= &tcp_synack_retries_max
 	},
 #ifdef CONFIG_SYN_COOKIES
 	{
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index bf171b5e1eb3..bbedf2b9e1bc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -467,6 +467,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 	 */
 	max_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
 		READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
+	max_retries = min_t(int, max_retries, MAX_TCP_SYNACK_RETRIES);
 
 	if (req->num_timeout >= max_retries) {
 		tcp_write_err(sk);
@@ -488,7 +489,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 	if (!tp->retrans_stamp)
 		tp->retrans_stamp = tcp_time_stamp_ts(tp);
 	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-			  req->timeout << req->num_timeout, false);
+			     tcp_reqsk_timeout_sk(sk, req), false);
 }
 
 static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
-- 
2.43.0

Re: [PATCH net v3 1/1] tcp: bound SYN-ACK timers to reqsk timeout range

[Paolo Abeni]

On 7/2/26 11:52 AM, Ren Wei wrote:
> @@ -1034,6 +1035,7 @@ static struct ctl_table ipv4_net_table[] = {
>  		.maxlen		= sizeof(u8),
>  		.mode		= 0644,
>  		.proc_handler	= proc_dou8vec_minmax,
> +		.extra2		= &tcp_synack_retries_max

This new restriction, even if correct, may break existing scripts.

Since the rest of the patch enforces the upper bound at every
sysctl_tcp_synack_retries usage, what about dropping this chunk?

/P