netdev - [PATCH v2 net-next 1/5] net: add TIME_WAIT logic to sk_to_full

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: <20241006203224.1404384-2-edumazet@google.com>
Date: Sun,  6 Oct 2024 20:32:20 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, 
	Paolo Abeni <pabeni@...hat.com>, Martin KaFai Lau <martin.lau@...ux.dev>
Cc: netdev@...r.kernel.org, eric.dumazet@...il.com, 
	Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH v2 net-next 1/5] net: add TIME_WAIT logic to sk_to_full_sk()

TCP will soon attach TIME_WAIT sockets to some ACK and RST.

Make sure sk_to_full_sk() detects this and does not return
a non full socket.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
 include/linux/bpf-cgroup.h | 2 +-
 include/net/inet_sock.h    | 4 +++-
 net/core/filter.c          | 6 +-----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index ce91d9b2acb9f8991150ceead4475b130bead438..f0f219271daf4afea2666c4d09fd4d1a8091f844 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -209,7 +209,7 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) {		       \
 		typeof(sk) __sk = sk_to_full_sk(sk);			       \
-		if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) &&	       \
+		if (__sk && __sk == skb_to_full_sk(skb) &&	       \
 		    cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS))	       \
 			__ret = __cgroup_bpf_run_filter_skb(__sk, skb,	       \
 						      CGROUP_INET_EGRESS); \
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index f01dd273bea69d2eaf7a1d28274d7f980942b78a..39c5a93b353ad9ac3047031d1718190d749f0530 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -321,8 +321,10 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
 static inline struct sock *sk_to_full_sk(struct sock *sk)
 {
 #ifdef CONFIG_INET
-	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
+	if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV)
 		sk = inet_reqsk(sk)->rsk_listener;
+	if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT)
+		sk = NULL;
 #endif
 	return sk;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index bd0d08bf76bb8de39ca2ca89cda99a97c9b0a034..202c1d386e19599e9fc6e0a0d4a95986ba6d0ea8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6778,8 +6778,6 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		/* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
 		 * sock refcnt is decremented to prevent a request_sock leak.
 		 */
-		if (!sk_fullsock(sk2))
-			sk2 = NULL;
 		if (sk2 != sk) {
 			sock_gen_put(sk);
 			/* Ensure there is no need to bump sk2 refcnt */
@@ -6826,8 +6824,6 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		/* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
 		 * sock refcnt is decremented to prevent a request_sock leak.
 		 */
-		if (!sk_fullsock(sk2))
-			sk2 = NULL;
 		if (sk2 != sk) {
 			sock_gen_put(sk);
 			/* Ensure there is no need to bump sk2 refcnt */
@@ -7276,7 +7272,7 @@ BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk)
 {
 	sk = sk_to_full_sk(sk);
 
-	if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE))
+	if (sk && sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE))
 		return (unsigned long)sk;
 
 	return (unsigned long)NULL;
-- 
2.47.0.rc0.187.ge670bccf7e-goog