linux-kernel - Re: [PATCH resend] smp: avoid sending needless IPI in smp_call_function

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20170519110951.afpvoewwmszdnob5@hirez.programming.kicks-ass.net>
Date:   Fri, 19 May 2017 13:09:51 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Aaron Lu <aaron.lu@...el.com>
Cc:     linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Huang Ying <ying.huang@...el.com>
Subject: Re: [PATCH resend] smp: avoid sending needless IPI in
 smp_call_function_many()

On Fri, May 19, 2017 at 03:53:31PM +0800, Aaron Lu wrote:
> @@ -434,6 +442,7 @@ void smp_call_function_many(const struct cpumask *mask,
>  	if (unlikely(!cpumask_weight(cfd->cpumask)))
>  		return;

Another thing that occurred to me while staring at that function, is
that we could move:

	cpumask_and(cfd->cpumask, mask, cpu_online_mask);

to the very begin of that function, that would then obviate the need for
that cpumask_weight() test afaict.


I'm not sure its worth the trouble, but it would make the function
slightly easier to look at.