netdev - [PATCH net-next 7/8] tcp: stronger sk

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250711114006.480026-8-edumazet@google.com>
Date: Fri, 11 Jul 2025 11:40:05 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, 
	Paolo Abeni <pabeni@...hat.com>, Neal Cardwell <ncardwell@...gle.com>
Cc: Simon Horman <horms@...nel.org>, Kuniyuki Iwashima <kuniyu@...gle.com>, 
	Willem de Bruijn <willemb@...gle.com>, netdev@...r.kernel.org, eric.dumazet@...il.com, 
	Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 7/8] tcp: stronger sk_rcvbuf checks

Currently, TCP stack accepts incoming packet if sizes of receive queues
are below sk->sk_rcvbuf limit.

This can cause memory overshoot if the packet is big, like an 1/2 MB
BIG TCP one.

Refine the check to take into account the incoming skb truesize.

Note that we still accept the packet if the receive queue is empty,
to not completely freeze TCP flows in pathological conditions.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
 net/ipv4/tcp_input.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 39de55ff898e6ec9c6e5bc9dc7b80ec9d235ca44..9c5baace4b7b24140ab5e0eafc397f124c8c64dd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4888,10 +4888,20 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
+/* Check if this incoming skb can be added to socket receive queues
+ * while satisfying sk->sk_rcvbuf limit.
+ */
+static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
+{
+	unsigned int new_mem = atomic_read(&sk->sk_rmem_alloc) + skb->truesize;
+
+	return new_mem <= sk->sk_rcvbuf;
+}
+
 static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
 				 unsigned int size)
 {
-	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
+	if (!tcp_can_ingest(sk, skb) ||
 	    !sk_rmem_schedule(sk, skb, size)) {
 
 		if (tcp_prune_queue(sk, skb) < 0)
@@ -5507,7 +5517,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb)
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE);
 		tp->ooo_last_skb = rb_to_skb(prev);
 		if (!prev || goal <= 0) {
-			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			if (tcp_can_ingest(sk, skb) &&
 			    !tcp_under_memory_pressure(sk))
 				break;
 			goal = sk->sk_rcvbuf >> 3;
@@ -5541,12 +5551,12 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED);
 
-	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+	if (!tcp_can_ingest(sk, in_skb))
 		tcp_clamp_window(sk);
 	else if (tcp_under_memory_pressure(sk))
 		tcp_adjust_rcv_ssthresh(sk);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	tcp_collapse_ofo_queue(sk);
@@ -5556,7 +5566,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 			     NULL,
 			     tp->copied_seq, tp->rcv_nxt);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* Collapsing did not help, destructive actions follow.
@@ -5564,7 +5574,7 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb)
 
 	tcp_prune_ofo_queue(sk, in_skb);
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+	if (tcp_can_ingest(sk, in_skb))
 		return 0;
 
 	/* If we are really being abused, tell the caller to silently
-- 
2.50.0.727.gbf7dc18ff4-goog