linux-kernel - Re: [PATCH] driver core: Add branch prediction hints in really

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

Message-ID: <20181106202658.GA26208@kroah.com>
Date:   Tue, 6 Nov 2018 21:26:58 +0100
From:   Greg KH <gregkh@...uxfoundation.org>
To:     Muchun Song <smuchun@...il.com>
Cc:     rafael@...nel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] driver core: Add branch prediction hints in
 really_probe()

On Tue, Nov 06, 2018 at 09:46:30PM +0800, Muchun Song wrote:
> If condition is false in most cases. So, add an unlikely() to the if
> condition, so that the optimizer assumes that the condition is false.
> 
> Signed-off-by: Muchun Song <smuchun@...il.com>

As Rafael said, don't do stuff like this unless you can actually measure
the difference.  Last time we tested the kernel for this a few years
ago, about 75% of the unlikely/likely additions were incorrect, removing
them made the kernel faster.  Turns out the compiler and cpu know better
than developers do :)

Also, the probe() path is never a hot-path to worry about stuff like
this.

thanks,

greg k-h