netdev - tcp_update_metrics() fail fast before declaring variables

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Date:	Fri, 7 Aug 2015 22:49:48 +0300
From:	Donatas Abraitis <donatas.abraitis@...il.com>
To:	netdev@...r.kernel.org
Subject: tcp_update_metrics() fail fast before declaring variables

Hi folks,

one short question regarding net.ipv4.tcp_no_metrics_save sysctl
parameter. Code snippet is actually the following:

void tcp_update_metrics(struct sock *sk)
{
  struct tcp_sock *tp = tcp_sk(sk);
  struct dst_entry *dst = __sk_dst_get(sk);

  if (sysctl_tcp_nometrics_save)
    return;

Why this 'if' statement can't be moved before variables? I think fail
fast could save some instructions in this place. Any thoughts?

Here is the performance benchmarking results:

Test #1 (sysctl -w net.ipv4.tcp_no_metrics_save=0)
sum: 79726, avg: 1295ns
min: 453ns, max: 16487ns

Test #2 (sysctl -w net.ipv4.tcp_no_metrics_save=1)
sum: 77515, avg: 1181ns
min: 431ns, max: 15989ns

Benchmarked with Systemtap:

global c;
probe kernel.function("tcp_update_metrics").return
{
        c <<< (gettimeofday_ns() - @entry(gettimeofday_ns()));
}
probe timer.s(60)
{
        printf("sum: %d, avg: %dns\n", @count(c), @avg(c));
        printf("min: %dns, max: %dns\n", @min(c), @max(c));
        delete c;
        exit();
}
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html