ipv6: save dontfrag in cork

When spanning datagram construction over multiple send calls using
MSG_MORE, per datagram settings are configured on the first send.

That is when ip(6)_setup_cork stores these settings for subsequent use
in __ip(6)_append_data and others.

The only flag that escaped this was dontfrag. As a result, a datagram
could be constructed with df=0 on the first sendmsg, but df=1 on a
next. Which is what cmsg_ip.sh does in an upcoming MSG_MORE test in
the "diff" scenario.

Changing datagram conditions in the middle of constructing an skb
makes this already complex code path even more convoluted. It is here
unintentional. Bring this flag in line with expected sockopt/cmsg
behavior.

And stop passing ipc6 to __ip6_append_data, to avoid such issues
in the future. This is already the case for __ip_append_data.

inet6_cork had a 6 byte hole, so the 1B flag has no impact.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250307033620.411611-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a6e2aadbb91bd3bc788b5df5e4df34c859352167..5aeeed22f35bfc8f7d2b927f539c37d765f7cc4d 100644 (file)
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -207,6 +207,7 @@ struct inet6_cork {
        struct ipv6_txoptions *opt;
        u8 hop_limit;
        u8 tclass;
+       u8 dontfrag:1;
 };
 
 /* struct ipv6_pinfo - ipv6 private area */

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d91da522c34e78f84cc662b5f557039e05f7b549..581bc62890818e121f125f295c46fcddc15cbc3a 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1386,6 +1386,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
        }
        v6_cork->hop_limit = ipc6->hlimit;
        v6_cork->tclass = ipc6->tclass;
+       v6_cork->dontfrag = ipc6->dontfrag;
        if (rt->dst.flags & DST_XFRM_TUNNEL)
                mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
                      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
@@ -1421,7 +1422,7 @@ static int __ip6_append_data(struct sock *sk,
                             int getfrag(void *from, char *to, int offset,
                                         int len, int odd, struct sk_buff *skb),
                             void *from, size_t length, int transhdrlen,
-                            unsigned int flags, struct ipcm6_cookie *ipc6)
+                            unsigned int flags)
 {
        struct sk_buff *skb, *skb_prev = NULL;
        struct inet_cork *cork = &cork_full->base;
@@ -1475,7 +1476,7 @@ static int __ip6_append_data(struct sock *sk,
        if (headersize + transhdrlen > mtu)
                goto emsgsize;
 
-       if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
+       if (cork->length + length > mtu - headersize && v6_cork->dontfrag &&
            (sk->sk_protocol == IPPROTO_UDP ||
             sk->sk_protocol == IPPROTO_ICMPV6 ||
             sk->sk_protocol == IPPROTO_RAW)) {
@@ -1855,7 +1856,7 @@ int ip6_append_data(struct sock *sk,
 
        return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
                                 &np->cork, sk_page_frag(sk), getfrag,
-                                from, length, transhdrlen, flags, ipc6);
+                                from, length, transhdrlen, flags);
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
@@ -2058,7 +2059,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
        err = __ip6_append_data(sk, &queue, cork, &v6_cork,
                                &current->task_frag, getfrag, from,
                                length + exthdrlen, transhdrlen + exthdrlen,
-                               flags, ipc6);
+                               flags);
        if (err) {
                __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
                return ERR_PTR(err);