ipv6: tcp: send consistent autoflowlabel in SYN_RECV state
Subsystems (3)
PATCH 1/1 ipv6: tcp: send consistent autoflowlabel in SYN_RECV state
From: Eric Dumazet <[email protected]>
This is a followup of commit c67b85558ff2 ("ipv6: tcp: send consistent autoflowlabel in TIME_WAIT state"), but for SYN_RECV state.
In some cases, TCP sends a challenge ACK on behalf of a SYN_RECV request. WHen this happens, we want to use the flow label that was used when the prior SYNACK packet was sent, instead of another one.
After his patch, following packetdrill passes:
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+.2 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+0 > (flowlabel 0x11) S. 0:0(0) ack 1 <...>
// Test if a challenge ack is properly sent (same flowlabel than prior SYNACK)
+.01 < . 4000000000:4000000000(0) ack 1 win 320
+0 > (flowlabel 0x11) . 1:1(0) ack 1
--- net/ipv6/tcp_ipv6.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-)
net/ipv6/tcp_ipv6.c +14 -12
@@ -858,7 +858,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {static void tcp_v6_send_response (const struct sock *sk,struct sk_buff *skb,u32 seq,u32 ack,u32 win,u32 tsval,u32 tsecr,int oif,struct tcp_md5sig_key *key,int rst, -u8 tclass,__be32 label,u32 priority) +u8 tclass,__be32 label,u32 priority,u32 txhash) {const struct tcphdr *th =tcp_hdr (skb);struct tcphdr *t1;
@@ -949,16 +949,16 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 }if (sk) { -if (sk->sk_state ==TCP_TIME_WAIT ) { +if (sk->sk_state ==TCP_TIME_WAIT ) mark =inet_twsk (sk)->tw_mark; -/* autoflowlabel relies on buff->hash */ -skb_set_hash (buff,inet_twsk (sk)->tw_txhash, -PKT_HASH_TYPE_L4 ); - }else { +else mark = sk->sk_mark; - }skb_set_delivery_time (buff,tcp_transmit_time (sk), true); } +if (txhash) { +/* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ +skb_set_hash (buff, txhash,PKT_HASH_TYPE_L4 ); + } fl6.flowi6_mark =IP6_REPLY_MARK (net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source;
@@ -1085,7 +1085,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) }tcp_v6_send_response (sk, skb, seq, ack_seq,0 ,0 ,0 , oif, key,1 , -ipv6_get_dsfield (ipv6h), label, priority); +ipv6_get_dsfield (ipv6h), label, priority,0 );#ifdef CONFIG_TCP_MD5SIG out:
@@ -1096,10 +1096,10 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)static void tcp_v6_send_ack (const struct sock *sk,struct sk_buff *skb,u32 seq,u32 ack,u32 win,u32 tsval,u32 tsecr,int oif,struct tcp_md5sig_key *key,u8 tclass, -__be32 label,u32 priority) +__be32 label,u32 priority,u32 txhash) {tcp_v6_send_response (sk, skb, seq, ack, win, tsval, tsecr, oif, key,0 , - tclass, label, priority); + tclass, label, priority, txhash); }static void tcp_v6_timewait_ack (struct sock *sk,struct sk_buff *skb)
@@ -1111,7 +1111,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,tcp_time_stamp_raw () + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if,tcp_twsk_md5_key (tcptw), - tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority); + tw->tw_tclass,cpu_to_be32 (tw->tw_flowlabel), tw->tw_priority, + tw->tw_txhash);inet_twsk_put (tw); }
@@ -1138,7 +1139,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,tcp_time_stamp_raw () +tcp_rsk (req)->ts_off, req->ts_recent, sk->sk_bound_dev_if,tcp_v6_md5_do_lookup (sk, &ipv6_hdr (skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority); +ipv6_get_dsfield (ipv6_hdr (skb)),0 , sk->sk_priority, + tcp_rsk(req)->txhash); }
Signature · 1 line
2.37.2.672.g94769d06f0-goog
This patch was applied to netdev/net-next.git (master) by Jakub Kicinski <[email protected]>:
Hello:
This patch was applied to netdev/net-next.git (master) by Jakub Kicinski <[email protected]>:
Quoted 10 lines · On Wed, 31 Aug 2022 13:37:29 -0700 you wrote:
From: Eric Dumazet <[email protected]>
This is a followup of commit
c67b85558ff2("ipv6: tcp: send consistent autoflowlabel inTIME_WAITstate"), but forSYN_RECVstate.In some cases, TCP sends a challenge ACK on behalf of a
SYN_RECVrequest. WHen this happens, we want to use the flow label that was used when the prior SYNACK packet was sent, instead of another one.[...]
Here is the summary with links:
- [net-next] ipv6: tcp: send consistent autoflowlabel in SYN_RECV state
https://git.kernel.org/netdev/net-next/c/aa51b80e1af4
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html