linux-kernel - Re: [PATCH 2/5] x86/kernel: Skip TSC test and error messages if already unstable

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: <alpine.DEB.2.20.1710121314440.1930@nanos>
Date:   Thu, 12 Oct 2017 13:17:12 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     mike.travis@....com
cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>,
        Bin Gao <bin.gao@...ux.intel.com>,
        Prarit Bhargava <prarit@...hat.com>,
        Dimitri Sivanich <dimitri.sivanich@....com>,
        Andrew Banman <andrew.banman@....com>,
        Russ Anderson <russ.anderson@....com>,
        linux-kernel@...r.kernel.org, x86@...nel.org
Subject: Re: [PATCH 2/5] x86/kernel: Skip TSC test and error messages if
 already unstable

On Thu, 5 Oct 2017, mike.travis@....com wrote:

> If the TSC has already been determined to be unstable, then checking
> TSC ADJUST values is a waste of time and generates unnecessary error
> messages.
> 
> Signed-off-by: Mike Travis <mike.travis@....com>
> Reviewed-by: Dimitri Sivanich <dimitri.sivanich@....com>
> Reviewed-by: Russ Anderson <russ.anderson@....com>
> Reviewed-by: Peter Zijlstra <peterz@...radead.org>
> ---
>  arch/x86/kernel/tsc_sync.c |    8 ++++++++
>  1 file changed, 8 insertions(+)
> 
> --- linux.orig/arch/x86/kernel/tsc_sync.c
> +++ linux/arch/x86/kernel/tsc_sync.c
> @@ -38,6 +38,10 @@ void tsc_verify_tsc_adjust(bool resume)
>  	if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
>  		return;
>  
> +	/* Skip unnecessary error messages if TSC already unstable */
> +	if (check_tsc_unstable())
> +		return;
> +
>  	/* Rate limit the MSR check */
>  	if (!resume && time_before(jiffies, adj->nextcheck))
>  		return;
> @@ -89,6 +93,10 @@ bool tsc_store_and_check_tsc_adjust(bool
>  	if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
>  		return false;
>  
> +	/* Skip unnecessary error messages if TSC already unstable */
> +	if (check_tsc_unstable())
> +		return false;
> +
>  	rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
>  	cur->bootval = bootval;
>  	cur->adjusted = bootval;

This hunk rejects and I really can't figure out against which tree that
would apply.

Btw, there are two incarnations of tsc_store_and_check_tsc_adjust().
Shouldn't the !SMP variant get the same treatment?

Thanks,

	tglx