linux-kernel - Re: [tip:x86/idle] x86, hotplug: Move WBINVD back outside the play

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

Message-ID: <AANLkTimCXZWVb7ajANPg15Zuo22nst=d5p-MjXhzu1NX@mail.gmail.com>
Date:	Fri, 17 Sep 2010 17:48:41 -0700
From:	Venkatesh Pallipadi <venki@...gle.com>
To:	mingo@...hat.com, hpa@...or.com, linux-kernel@...r.kernel.org,
	asit.k.mallick@...el.com, arjan@...ux.kernel.org,
	a.p.zijlstra@...llo.hl, lenb@...nel.org, tglx@...utronix.de,
	hpa@...ux.intel.com, venki@...gle.com
Cc:	linux-tip-commits@...r.kernel.org
Subject: Re: [tip:x86/idle] x86, hotplug: Move WBINVD back outside the
 play_dead loop

On Fri, Sep 17, 2010 at 5:13 PM, tip-bot for H. Peter Anvin
<hpa@...ux.intel.com> wrote:
> Commit-ID:  a68e5c94f7d3dd64fef34dd5d97e365cae4bb42a
> Gitweb:     http://git.kernel.org/tip/a68e5c94f7d3dd64fef34dd5d97e365cae4bb42a
> Author:     H. Peter Anvin <hpa@...ux.intel.com>
> AuthorDate: Fri, 17 Sep 2010 17:06:46 -0700
> Committer:  H. Peter Anvin <hpa@...ux.intel.com>
> CommitDate: Fri, 17 Sep 2010 17:10:23 -0700
>
> x86, hotplug: Move WBINVD back outside the play_dead loop
>
> On processors with hyperthreading, when only one thread is offlined
> the other thread can cause a spurious wakeup on the idled thread.  We
> do not want to re-WBINVD when that happens.
>
> Ideally, we should simply skip WBINVD unless we're the last thread on
> a particular core to shut down, but there might be similar issues
> elsewhere in the system.
>
> Thus, revert to previous behavior of only WBINVD outside the loop.
> Partly as a result, remove the mb()'s around it: they are not
> necessary since wbinvd() is a serializing instruction, but they were
> intended to make sure the compiler didn't do any funny loop
> optimizations.
>
> Reported-by: Asit Mallick <asit.k.mallick@...el.com>
> Signed-off-by: H. Peter Anvin <hpa@...ux.intel.com>
> Cc: Arjan van de Ven <arjan@...ux.kernel.org>
> Cc: Len Brown <lenb@...nel.org>
> Cc: Venkatesh Pallipadi <venki@...gle.com>
> Cc: Peter Zijlstra <a.p.zijlstra@...llo.hl>
> LKML-Reference: <tip-ea53069231f9317062910d6e772cca4ce93de8c8@....kernel.org>
> ---
>  arch/x86/kernel/smpboot.c |   11 +++++------
>  1 files changed, 5 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index 07bf423..55c80ffb 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -1422,9 +1422,9 @@ static inline void mwait_play_dead(void)
>                        (highest_subcstate - 1);
>        }
>
> +       wbinvd();
> +
>        while (1) {
> -               mb();
> -               wbinvd();
>                __monitor(&current_thread_info()->flags, 0, 0);
>                mb();


Just one observation. There are some CPUs with errata that need
clflush before monitor. So, if that CPU wakesup spuriously it may have
problem reentering idle. Not sure whether that will be a problem as
that errata also depended on read happening on the flag. May be its
better to do monitor (0, 0, 0).

Thanks,
Venki
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/