From 8e069fd3fd396b89af417e50b359bc9892dd41cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Nov 2026 08:54:41 +0100 Subject: [PATCH] tcp: ipv6: do not read ireq->pktopts from tcp_v6_send_synack() When IPV6_FL_F_REFLECT is set on a listener, or the net.ipv6.flowlabel_reflect sysctl has FLOWLABEL_REFLECT_ESTABLISHED, tcp_v6_send_synack() reflects the flowlabel of the SYN packet, reading it from the skb stored in ireq->pktopts. Since commit 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table"), request sockets are processed without holding the listener lock. A cpu can then process a retransmitted SYN for a request socket, and send a SYNACK from tcp_check_req(), while another cpu receives the ACK completing the 3WHS. tcp_v6_syn_recv_sock() consumes ireq->pktopts when it wins the hashdance, and the first cpu reads a freed skb: BUG: KASAN: slab-use-after-free in tcp_v6_send_synack (include/linux/skbuff.h:3152 include/linux/ipv6.h:110 net/ipv6/tcp_ipv6.c:582) Read of size 8 at addr ffff88802b08b608 by task poc-ipv6-pktopt/5076 Call Trace: tcp_v6_send_synack (include/linux/skbuff.h:3152 include/linux/ipv6.h:110 net/ipv6/tcp_ipv6.c:582) tcp_rtx_synack (net/ipv4/tcp_output.c:4719) tcp_check_req (net/ipv4/tcp_minisocks.c:762) tcp_v6_rcv (net/ipv6/tcp_ipv6.c:1826) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:479) ip6_input_finish (net/ipv6/ip6_input.c:534) ip6_input (include/linux/netfilter.h:325 include/linux/netfilter.h:319 net/ipv6/ip6_input.c:545) ipv6_rcv (include/net/dst.h:481 net/ipv6/ip6_input.c:119 include/linux/netfilter.h:325 include/linux/netfilter.h:319 net/ipv6/ip6_input.c:351) Freed by task 5074 on cpu 0 at 15.412249s: kmem_cache_free (include/linux/kasan.h:235 mm/slub.c:2780 mm/slub.c:6630 mm/slub.c:6757) tcp_v6_syn_recv_sock (net/ipv6/tcp_ipv6.c:1528) tcp_check_req (net/ipv4/tcp_minisocks.c:934) tcp_v6_rcv (net/ipv6/tcp_ipv6.c:1826) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:479) ip6_input_finish (net/ipv6/ip6_input.c:534) Request socket migration has the same issue: reqsk_migrate_reset() transfers ireq->pktopts to the clone, which can be freed while another cpu holding a reference on the old request socket is still sending a SYNACK. The SYNACK timer itself is not an issue, because inet_csk_reqsk_queue_drop() calls timer_delete_sync(). Save the flowlabel of the SYN in the request socket instead, so that tcp_v6_send_synack() no longer needs ireq->pktopts. As a side effect, the flowlabel is also reflected for SYN packets reusing a TIME_WAIT socket, as ireq->pktopts is not set in this case. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Fixes: c905dee62232 ("tcp: Migrate TCP_NEW_SYN_RECV requests at retransmitting SYN+ACKs.") Reported-by: Anvik Loitongbam Reported-by: Yingjie Wang Closes: https://lore.kernel.org/netdev/82c31e4d5043f3dbd11b44177cfba779d335aae3.1793599929.git.x-professor@outlook.com/ Signed-off-by: Eric Dumazet Reviewed-by: Jiayuan Chen Reviewed-by: Neal Cardwell Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20261102075441.3771550-1-edumazet@kernel.org Signed-off-by: Paolo Abeni --- include/linux/tcp.h | 3 +++ net/ipv6/tcp_ipv6.c | 5 +++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d18f7bc1e5d0..5a4c61fc240e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -179,6 +179,9 @@ struct tcp_request_sock { u8 ao_rcv_next; bool used_tcp_ao; #endif +#if IS_ENABLED(CONFIG_IPV6) + __be32 syn_flowlabel; +#endif }; #define tcp_rsk(ptr) container_of_const(ptr, struct tcp_request_sock, req.req) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e006a30360ea..d406cd3c8cea 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -578,8 +578,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; - if (inet6_test_bit(REPFLOW, sk) && ireq->pktopts) - fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + if (inet6_test_bit(REPFLOW, sk)) + fl6->flowlabel = tcp_rsk(req)->syn_flowlabel; tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | @@ -789,6 +789,7 @@ static void tcp_v6_init_req(struct request_sock *req, ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ir_rmt_addr = LOOPBACK4_IPV6; ireq->ir_loc_addr = LOOPBACK4_IPV6; + tcp_rsk(req)->syn_flowlabel = ip6_flowlabel(ipv6_hdr(skb)); /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) &&