linux-kernel - Re: [patch V2 01/17] x86/vdso: Mark the TSC clocksource path likely

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]

Date:   Fri, 14 Feb 2020 12:00:04 +0000
From:   Vincenzo Frascino <vincenzo.frascino@....com>
To:     Thomas Gleixner <tglx@...utronix.de>,
        LKML <linux-kernel@...r.kernel.org>
Cc:     x86@...nel.org, John Stultz <john.stultz@...aro.org>,
        Andy Lutomirski <luto@...nel.org>,
        Christophe Leroy <christophe.leroy@....fr>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Juergen Gross <jgross@...e.com>,
        Michael Kelley <mikelley@...rosoft.com>,
        Sasha Levin <sashal@...nel.org>,
        Ralf Baechle <ralf@...ux-mips.org>,
        Paul Burton <paulburton@...nel.org>,
        James Hogan <jhogan@...nel.org>,
        Russell King <linux@...linux.org.uk>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Marc Zyngier <maz@...nel.org>, Andrei Vagin <avagin@...il.com>
Subject: Re: [patch V2 01/17] x86/vdso: Mark the TSC clocksource path likely

On 2/7/20 12:38 PM, Thomas Gleixner wrote:
> Jumping out of line for the TSC clcoksource read is creating awful
> code. TSC is likely to be the clocksource at least on bare metal and the PV
> interfaces are sufficiently more work that the jump over the TSC read is
> just in the noise.
>

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@....com>

> Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
> ---
>  arch/x86/include/asm/vdso/gettimeofday.h |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> --- a/arch/x86/include/asm/vdso/gettimeofday.h
> +++ b/arch/x86/include/asm/vdso/gettimeofday.h
> @@ -243,7 +243,7 @@ static u64 vread_hvclock(void)
>  
>  static inline u64 __arch_get_hw_counter(s32 clock_mode)
>  {
> -	if (clock_mode == VCLOCK_TSC)
> +	if (likely(clock_mode == VCLOCK_TSC))
>  		return (u64)rdtsc_ordered();
>  	/*
>  	 * For any memory-mapped vclock type, we need to make sure that gcc
> 

-- 
Regards,
Vincenzo