[PATCH 5.15.y 4/4] tcp: clamp route advmss to TCP_MIN_MSS

[Sasha Levin <sashal@kernel.org>]

From: Yong Wang <edragain@163.com>

[ Upstream commit 870a9e42ecc6fe1b8c25d87af043cb0d9c178fe1 ]

tcp_select_initial_window() assumes that callers never pass an MSS
smaller than 1, but route-derived advmss values can violate that
assumption.

A too-small explicit RTAX_ADVMSS is one way to get there, but it is not
the only one. The same divide-by-zero can also be reached through the
"default advmss" path when RTAX_ADVMSS is left at 0 and the effective
advmss is later driven down by route MTU and min_adv_mss.

Introduce a tcp_dst_advmss() helper that clamps route advmss to
TCP_MIN_MSS before TCP consumes it, and use it in the TCP paths that
derive advmss from dst metrics. This keeps the effective MSS from
dropping to zero before tcp_select_initial_window() rounds the receive
window.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Reported-by: Vega <vega@nebusec.ai>
Signed-off-by: Yong Wang <edragain@163.com>
Signed-off-by: Ren Wei <weir@nebusec.ai>
Link: https://patch.msgid.link/251eaf8277fa7c66364c9815c5da01662d269181.1787074852.git.edragain@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[ discarded upstream ssthresh refactor context and kept existing WRITE_ONCE-free window_clamp assignment style, replacing dst_metric_advmss() with tcp_dst_advmss() ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/tcp.h        | 5 +++++
 net/ipv4/tcp_ipv4.c      | 2 +-
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv4/tcp_output.c    | 6 +++---
 net/ipv6/tcp_ipv6.c      | 2 +-
 5 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index be91d81d66ab3..48e0a1d363e84 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1436,6 +1436,11 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+static inline u32 tcp_dst_advmss(const struct dst_entry *dst)
+{
+	return max_t(u32, dst_metric_advmss(dst), TCP_MIN_MSS);
+}
+
 void tcp_cleanup_rbuf(struct sock *sk, int copied);
 
 /* We provision sk_rcvbuf around 200% of sk_rcvlowat.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6f97dfbc5343d..dac9c151f671b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1614,7 +1614,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 061225d645e6b..e36c466b4b65a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -369,7 +369,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	u32 rcv_wnd;
 	int mss;
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a2d5e9f1fe241..462c704cc18a9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -125,7 +125,7 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 	int mss = tp->advmss;
 
 	if (dst) {
-		unsigned int metric = dst_metric_advmss(dst);
+		unsigned int metric = tcp_dst_advmss(dst);
 
 		if (metric < mss) {
 			mss = metric;
@@ -3597,7 +3597,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	}
 	skb_dst_set(skb, dst);
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 	now = tcp_clock_ns();
@@ -3713,7 +3713,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
-	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	tp->advmss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5c6b0d98730d9..7dc0d53c3c249 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1396,7 +1396,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst6_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
-- 
2.53.0