linux-kernel - Optimization in pick_next

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]

Message-ID: <9af14b44-81c7-cdb1-ed4f-2f684f9fdbb3@rasmusvillemoes.dk>
Date:   Thu, 28 Nov 2019 08:46:35 +0100
From:   Rasmus Villemoes <linux@...musvillemoes.dk>
To:     LKML <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>
Subject: Optimization in pick_next_task

In kernel/sched/core.c, we have

        /*
         * Optimization: we know that if all tasks are in the fair class
we can
         * call that function directly,

But then the code goes on to do

                p = fair_sched_class.pick_next_task(rq, prev, rf);
                ...
                if (unlikely(!p))
                        p = idle_sched_class.pick_next_task(rq, prev, rf);

which still loads a function pointer and calls
pick_next_task_{fair,idle} through that. Should those be made extern and
used here, or am I misinterpreting what "directly" refers to?

Rasmus