tcp_v6_connect, ip6_datagram_dst_update and ip6_sk_dst_lookup_flow obtain a dst and sample its validation cookie afterwards. If a matching xfrm policy is inserted between lookup and cookie sampling, the plain route can be cached with a post-insertion serial. Subsequent packets then pass dst validation and bypass the new policy until another relevant FIB change. Store the cookie returned by ip6_dst_lookup_flow_cookie in these paths instead. Add ip6_dst_store_cookie to accept the supplied cookie, retaining ip6_dst_store for unconverted callers. This is a partial conversion. Established TCP route refills, header rebuilds and accepted-socket setup still use late cookie sampling. Those paths and other persistent caches, including SCTP and dst_cache users, are left for follow-up conversions. This race was found while investigating how mutable socket routing properties affect the dst cache in ovpn's UDP TX path. The socket-cache case was then reproduced in a VM by adding a debug-only kernel delay after the route and policy lookup, then inserting a matching xfrm policy before cookie sampling. TCP connect and connected UDP sockets continued sending plaintext after the policy insertion. With lookup cookies, the stale cached route was rejected on reuse. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ralf Lici --- Changes since v2 https://lore.kernel.org/all/43917b9119e13e54dcde0e2941d3f4a1fe255df7.1794384146.git.ralf@mandelbit.com/ - Add a Fixes tag referencing the initial git import. (Sashiko) - Clearly state that this is only a partial conversion to the new API. No changes since v1 https://lore.kernel.org/netdev/832892eaa7d2371f20459c3134c72914e42970b0.1793806941.git.ralf@mandelbit.com/ include/net/ip6_route.h | 18 +++++++++++++----- net/ipv6/datagram.c | 6 ++++-- net/ipv6/ip6_output.c | 6 ++++-- net/ipv6/route.c | 12 ++++++------ net/ipv6/tcp_ipv6.c | 5 +++-- 5 files changed, 30 insertions(+), 17 deletions(-) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 95f936be32c6..2684f6069a5e 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -252,13 +252,13 @@ static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) /* * Store a destination cache entry in a socket */ -static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, - bool daddr_set, - bool saddr_set) +static inline void ip6_dst_store_cookie(struct sock *sk, struct dst_entry *dst, + u32 cookie, bool daddr_set, + bool saddr_set) { struct ipv6_pinfo *np = inet6_sk(sk); - np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); + np->dst_cookie = cookie; sk_setup_caps(sk, dst); np->daddr_cache = daddr_set; #ifdef CONFIG_IPV6_SUBTREES @@ -266,8 +266,16 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, #endif } +static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, + bool daddr_set, + bool saddr_set) +{ + ip6_dst_store_cookie(sk, dst, rt6_get_cookie(dst_rt6_info(dst)), + daddr_set, saddr_set); +} + void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, - const struct flowi6 *fl6); + const struct flowi6 *fl6, u32 cookie); static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index ff7a7ffbf983..c18609bab366 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -78,6 +78,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) struct in6_addr *final_p; struct dst_entry *dst; struct flowi6 *fl6; + u32 cookie; int err = 0; if (inet6_test_bit(SNDFLOW, sk) && @@ -94,7 +95,8 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p = fl6_update_dst(fl6, opt, &np->final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); + dst = ip6_dst_lookup_flow_cookie(sock_net(sk), sk, fl6, final_p, + &cookie); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; @@ -112,7 +114,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) } } - ip6_sk_dst_store_flow(sk, dst, fl6); + ip6_sk_dst_store_flow(sk, dst, fl6, cookie); out: fl6_sock_release(flowlabel); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b87ccb5586cf..d51986d5ea4b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1370,6 +1370,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, bool connected) { struct dst_entry *dst; + u32 cookie; if (connected) { dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); @@ -1378,9 +1379,10 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, return dst; } - dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); + dst = ip6_dst_lookup_flow_cookie(sock_net(sk), sk, fl6, final_dst, + &cookie); if (connected && !IS_ERR(dst)) - ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); + ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6, cookie); return dst; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c54844b83828..b19bc0d0c78d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3048,19 +3048,19 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) } void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, - const struct flowi6 *fl6) + const struct flowi6 *fl6, u32 cookie) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr), + ip6_dst_store_cookie(sk, dst, cookie, + ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr), #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl6->saddr, &np->saddr) ? - true : + ipv6_addr_equal(&fl6->saddr, &np->saddr) ? + true : #endif - false); + false); } static bool ip6_redirect_nh_match(const struct fib6_result *res, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9e22ed61a6de..9dc031437b42 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -145,6 +145,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, struct dst_entry *dst; struct flowi6 *fl6; int addr_type; + u32 cookie; int err; if (addr_len < SIN6_LEN_RFC2133) @@ -288,7 +289,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, */ ip6_ecmp_set_mp_hash(net, fl6, sk->sk_txhash); - dst = ip6_dst_lookup_flow(net, sk, fl6, final_p); + dst = ip6_dst_lookup_flow_cookie(net, sk, fl6, final_p, &cookie); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -312,7 +313,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(sk, dst, false, false); + ip6_dst_store_cookie(sk, dst, cookie, false, false); icsk->icsk_ext_hdr_len = 0; if (opt) -- 2.56.0