diff options
| author | Eric Dumazet <edumazet@google.com> | 2024-10-10 17:48:17 +0000 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2024-10-14 17:39:37 -0700 |
| commit | 79636038d37e7bd4d078238f2a3f002cab4423bc (patch) | |
| tree | b6d28ee2b7994c49ec797f143840e22eabdbd45a | |
| parent | 507a96737d99686ca1714c7ba1f60ac323178189 (diff) | |
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>
| -rw-r--r-- | include/net/ip.h | 3 | ||||
| -rw-r--r-- | net/ipv4/ip_output.c | 5 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 4 |
3 files changed, 8 insertions, 4 deletions
diff --git a/include/net/ip.h b/include/net/ip.h index bab084df1567..4be0a6a603b2 100644 --- 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 e5c55a95063d..0065b1996c94 100644 --- 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 985028434f64..9d3dd101ea71 100644 --- 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, |