diff options
author | Kuniyuki Iwashima <kuniyu@amazon.com> | 2022-07-13 20:52:07 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-07-16 04:50:35 +0300 |
commit | 11052589cf5c0bab3b4884d423d5f60c38fcf25d (patch) | |
tree | 80de70b884d5defb7e23909e9ed7c5973bf5042a /net/ipv4/sysctl_net_ipv4.c | |
parent | df254d4508f96f298be8aff08da4d7e33d8584a0 (diff) | |
download | linux-11052589cf5c0bab3b4884d423d5f60c38fcf25d.tar.xz |
tcp/udp: Make early_demux back namespacified.
Commit e21145a9871a ("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 dddb64bcb346 ("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: dddb64bcb346 ("net: Add sysctl to toggle early demux for tcp and udp")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20220713175207.7727-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv4/sysctl_net_ipv4.c')
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 59 |
1 files changed, 2 insertions, 57 deletions
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 108fd86f2718..130e9c130311 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -350,61 +350,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -707,14 +652,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", |