linux-kernel - Re: [PATCH v4 1/3] arm64: cpufeature: introduce helper cpu_has_hw

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: <20190918164925.GB41588@arrakis.emea.arm.com>
Date:   Wed, 18 Sep 2019 17:49:25 +0100
From:   Catalin Marinas <catalin.marinas@....com>
To:     Matthew Wilcox <willy@...radead.org>
Cc:     Jia He <justin.he@....com>, Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        James Morse <james.morse@....com>,
        Marc Zyngier <maz@...nel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, Suzuki Poulose <Suzuki.Poulose@....com>,
        Punit Agrawal <punitagrawal@...il.com>,
        Anshuman Khandual <anshuman.khandual@....com>,
        Jun Yao <yaojun8558363@...il.com>,
        Alex Van Brunt <avanbrunt@...dia.com>,
        Robin Murphy <robin.murphy@....com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Jérôme Glisse <jglisse@...hat.com>,
        Ralph Campbell <rcampbell@...dia.com>, hejianet@...il.com,
        Kaly Xin <Kaly.Xin@....com>
Subject: Re: [PATCH v4 1/3] arm64: cpufeature: introduce helper
 cpu_has_hw_af()

On Wed, Sep 18, 2019 at 07:20:17AM -0700, Matthew Wilcox wrote:
> On Wed, Sep 18, 2019 at 09:19:12PM +0800, Jia He wrote:
> > +/* Decouple AF from AFDBM. */
> > +bool cpu_has_hw_af(void)
> > +{
> > +	return (read_cpuid(ID_AA64MMFR1_EL1) & 0xf);
> > +}
> > +
> 
> Do you really want to call read_cpuid() every time?  I would have thought
> you'd want to use the static branch mechanism to do the right thing at
> boot time.  See Documentation/static-keys.txt.

We do have a static branch mechanism for other CPU features but mostly
because on some big.LITTLE systems, the CPUs may differ slightly so we
only advertise the common features.

I guess here the additional instructions for reading and checking the
CPUID here would be lost in the noise compared to the actual page
copying.

-- 
Catalin