diff mbox series

[net-next] ipv6: tcp: send consistent autoflowlabel in SYN_RECV state

Message ID 20220831203729.458000-1-eric.dumazet@gmail.com (mailing list archive)
State Accepted
Commit aa51b80e1af47b3781abb1fb1666445a7616f0cd
Delegated to: Netdev Maintainers
Headers show
Series [net-next] ipv6: tcp: send consistent autoflowlabel in SYN_RECV state | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Single patches do not need cover letters
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 2 this patch: 2
netdev/cc_maintainers warning 2 maintainers not CCed: yoshfuji@linux-ipv6.org dsahern@kernel.org
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 2 this patch: 2
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet Aug. 31, 2022, 8:37 p.m. UTC 
From: Eric Dumazet <edumazet@google.com>

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

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv6/tcp_ipv6.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

Comments

patchwork-bot+netdevbpf@kernel.org Sept. 2, 2022, 4:10 a.m. UTC | #1 
Hello:

This patch was applied to netdev/net-next.git (master)
by Jakub Kicinski <kuba@kernel.org>:

On Wed, 31 Aug 2022 13:37:29 -0700 you wrote:
> From: Eric Dumazet <edumazet@google.com>
> 
> 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.
> 
> [...]

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!
diff mbox series

Patch

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ff5c4fc135fcc165f92f3cbf3a89d5e7099eece6..35013497e4078c99c046cc6970e1a87768f08ff1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -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);
 }