tcp/udp: Make early_demux back namespacified.

commit 11052589cf5c0bab3b4884d423d5f60c38fcf25d upstream.

Commit e21145a987 ("ipv4: namespacify ip_early_demux sysctl knob") made
it possible to enable/disable early_demux on a per-netns basis.  Then, we
introduced two knobs, tcp_early_demux and udp_early_demux, to switch it for
TCP/UDP in commit dddb64bcb3 ("net: Add sysctl to toggle early demux for
tcp and udp").  However, the .proc_handler() was wrong and actually
disabled us from changing the behaviour in each netns.

We can execute early_demux if net.ipv4.ip_early_demux is on and each proto
.early_demux() handler is not NULL.  When we toggle (tcp|udp)_early_demux,
the change itself is saved in each netns variable, but the .early_demux()
handler is a global variable, so the handler is switched based on the
init_net's sysctl variable.  Thus, netns (tcp|udp)_early_demux knobs have
nothing to do with the logic.  Whether we CAN execute proto .early_demux()
is always decided by init_net's sysctl knob, and whether we DO it or not is
by each netns ip_early_demux knob.

This patch namespacifies (tcp|udp)_early_demux again.  For now, the users
of the .early_demux() handler are TCP and UDP only, and they are called
directly to avoid retpoline.  So, we can remove the .early_demux() handler
from inet6?_protos and need not dereference them in ip6?_rcv_finish_core().
If another proto needs .early_demux(), we can restore it at that time.

Fixes: dddb64bcb3 ("net: Add sysctl to toggle early demux for tcp and udp")
Signed-off-by: Kuniyuki Iwashima <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
This commit is contained in:
Kuniyuki Iwashima 2022-07-13 10:52:07 -07:00 • committed by Greg Kroah-Hartman
commit fe3da74428
9 changed files with 48 additions and 113 deletions

View file

@ -44,21 +44,25 @@
#include <net/inet_ecn.h>
#include <net/dst_metadata.h>
INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
void udp_v6_early_demux(struct sk_buff *);
void tcp_v6_early_demux(struct sk_buff *);
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
void (*edemux)(struct sk_buff *skb);
if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
const struct inet6_protocol *ipprot;
ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
udp_v6_early_demux, skb);
if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
!skb_dst(skb) && !skb->sk) {
switch (ipv6_hdr(skb)->nexthdr) {
case IPPROTO_TCP:
if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
tcp_v6_early_demux(skb);
break;
case IPPROTO_UDP:
if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
udp_v6_early_demux(skb);
break;
}
}
if (!skb_valid_dst(skb))
ip6_route_input(skb);
}

View file

@ -1729,7 +1729,7 @@ do_time_wait:
goto discard_it;
}
INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
@ -2084,12 +2084,7 @@ struct proto tcpv6_prot = {
.diag_destroy = tcp_abort,
};
/* thinking of making this const? Don't.
* early_demux can change based on sysctl.
*/
static struct inet6_protocol tcpv6_protocol = {
.early_demux = tcp_v6_early_demux,
.early_demux_handler = tcp_v6_early_demux,
static const struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,

View file

@ -973,7 +973,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
return NULL;
}
INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
void udp_v6_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
const struct udphdr *uh;
@ -1603,12 +1603,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
}
#endif
/* thinking of making this const? Don't.
* early_demux can change based on sysctl.
*/
static struct inet6_protocol udpv6_protocol = {
.early_demux = udp_v6_early_demux,
.early_demux_handler = udp_v6_early_demux,
static const struct inet6_protocol udpv6_protocol = {
.handler = udpv6_rcv,
.err_handler = udpv6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,