ipv4: tcp: give socket pointer to control skbs

ip_send_unicast_reply() send orphaned 'control packets'.

These are RST packets and also ACK packets sent from TIME_WAIT.

Some eBPF programs would prefer to have a meaningful skb->sk
pointer as much as possible.

This means that TCP can now attach TIME_WAIT sockets to outgoing
skbs.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Brian Vazquez <brianvv@google.com>
Link: https://patch.msgid.link/20241010174817.1543642-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/ip.h b/include/net/ip.h
index bab084df15677543b7400bb2832c0e83988884cb..4be0a6a603b2b5d5cfddc045a7d49d0d77be9570 100644 (file)
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -288,7 +288,8 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
        return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
+                          struct sk_buff *skb,
                           const struct ip_options *sopt,
                           __be32 daddr, __be32 saddr,
                           const struct ip_reply_arg *arg,

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e5c55a95063dd8340f9a014102408e859b4eb755..0065b1996c947078bea210c9abe5c80fa0e0ab4f 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1596,7 +1596,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
  *     Generic function to send a packet as reply to another packet.
  *     Used to send some TCP resets/acks so far.
  */
-void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
+                          struct sk_buff *skb,
                           const struct ip_options *sopt,
                           __be32 daddr, __be32 saddr,
                           const struct ip_reply_arg *arg,
@@ -1662,6 +1663,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
                          arg->csumoffset) = csum_fold(csum_add(nskb->csum,
                                                                arg->csum));
                nskb->ip_summed = CHECKSUM_NONE;
+               if (orig_sk)
+                       skb_set_owner_edemux(nskb, (struct sock *)orig_sk);
                if (transmit_time)
                        nskb->tstamp_type = SKB_CLOCK_MONOTONIC;
                if (txhash)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 985028434f644c399e51d12ba8d9c2c5740dc6e1..9d3dd101ea713b14e13afe662baa49d21b3b716c 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -907,7 +907,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
                ctl_sk->sk_mark = 0;
                ctl_sk->sk_priority = 0;
        }
-       ip_send_unicast_reply(ctl_sk,
+       ip_send_unicast_reply(ctl_sk, sk,
                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                              ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                              &arg, arg.iov[0].iov_len,
@@ -1021,7 +1021,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
        ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
                           inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
        transmit_time = tcp_transmit_time(sk);
-       ip_send_unicast_reply(ctl_sk,
+       ip_send_unicast_reply(ctl_sk, sk,
                              skb, &TCP_SKB_CB(skb)->header.h4.opt,
                              ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
                              &arg, arg.iov[0].iov_len,