linux-kernel - Re: [PATCH] perf/x86/intel/pt: Use boot_cpu

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: <20160406165738.GK12070@pd.tnic>
Date:	Wed, 6 Apr 2016 18:57:38 +0200
From:	Borislav Petkov <bp@...en8.de>
To:	Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Cc:	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
	vince@...ter.net, eranian@...gle.com,
	Arnaldo Carvalho de Melo <acme@...radead.org>
Subject: Re: [PATCH] perf/x86/intel/pt: Use boot_cpu_has() because it's there

On Wed, Apr 06, 2016 at 05:35:07PM +0300, Alexander Shishkin wrote:
> At the moment, initialization path is using test_cpu_cap(&boot_cpu_data),
> to detect PT, which is just open coding boot_cpu_has(). Use the latter
> instead.
> 
> Signed-off-by: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
> ---
>  arch/x86/events/intel/pt.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
> index 32b613e863..7c7f09a8fe 100644
> --- a/arch/x86/events/intel/pt.c
> +++ b/arch/x86/events/intel/pt.c
> @@ -1159,7 +1159,7 @@ static __init int pt_init(void)
>  
>  	BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE);
>  
> -	if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT))
> +	if (!boot_cpu_has(X86_FEATURE_INTEL_PT))
>  		return -ENODEV;
>  
>  	get_online_cpus();
> -- 

Acked-by: Borislav Petkov <bp@...e.de>

Btw, there's another wonderful gem in the tree:

arch/x86/kernel/cpu/cyrix.c:201:        if (test_cpu_cap(c, 1*32+24)) {

Jeez, and a naked number at that which is not even a define in
arch/x86/include/asm/cpufeatures.h

Ah, I need to look at the whole thing:

        /* Cyrix used bit 24 in extended (AMD) CPUID for Cyrix MMX extensions */
        if (test_cpu_cap(c, 1*32+24)) {
                clear_cpu_cap(c, 1*32+24);
                set_cpu_cap(c, X86_FEATURE_CXMMX);
        }

So it is actually a correction for "smart" hw.

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.