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: <20241125134505.GC38837@noisy.programming.kicks-ass.net>
Date: Mon, 25 Nov 2024 14:45:05 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Patryk Wlazlyn <patryk.wlazlyn@...ux.intel.com>
Cc: x86@...nel.org, linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org,
	rafael.j.wysocki@...el.com, len.brown@...el.com,
	artem.bityutskiy@...ux.intel.com, dave.hansen@...ux.intel.com,
	tglx@...utronix.de, gautham.shenoy@....com
Subject: Re: [RFC PATCH v4 5/8] x86/smp native_play_dead: Prefer
 cpuidle_play_dead() over mwait_play_dead()

On Mon, Nov 25, 2024 at 02:20:25PM +0100, Patryk Wlazlyn wrote:
> The algorithm based on cpuid leaf 0x5 in the mwait_play_dead(),
> for looking up the mwait hint for the deepest cstate may calculate the
> wrong hint on recent Intel x86 platforms.
> 
> Prefer cpuidle_play_dead() over the generic mwait_play_dead() loop and
> only fallback to the later in case of missing appropriate enter_dead()
> handler.

So 7/8 should go first, such that picking cpuidle doesn't end up in some
weird state.

> 
> Signed-off-by: Patryk Wlazlyn <patryk.wlazlyn@...ux.intel.com>
> ---
>  arch/x86/kernel/smpboot.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index d0464c7a0af5..2627b56fb9bc 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -1413,9 +1413,10 @@ void native_play_dead(void)
>  	play_dead_common();
>  	tboot_shutdown(TB_SHUTDOWN_WFS);
>  
> +	/* The first successful play_dead() will not return */
> +	cpuidle_play_dead();
>  	mwait_play_dead();
> -	if (cpuidle_play_dead())
> -		hlt_play_dead();
> +	hlt_play_dead();
>  }
>  
>  #else /* ... !CONFIG_HOTPLUG_CPU */
> -- 
> 2.47.0
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ