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  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]
Date:   Mon, 4 Mar 2019 14:13:18 +0100
From:   Paolo Bonzini <>
To:     Peter Zijlstra <>
Cc:     Fenghua Yu <>,
        Thomas Gleixner <>,
        Ingo Molnar <>, Borislav Petkov <>,
        H Peter Anvin <>,
        Dave Hansen <>,
        Ashok Raj <>,
        Ravi V Shankar <>,
        Xiaoyao Li <>,
        linux-kernel <>,
        x86 <>,
Subject: Re: [PATCH v4 01/17] x86/common: Align cpu_caps_cleared and
 cpu_caps_set to unsigned long

On 04/03/19 13:44, Peter Zijlstra wrote:
> On Mon, Mar 04, 2019 at 11:48:18AM +0100, Paolo Bonzini wrote:
>> True that.  On the other hand btsl/btrl is also one byte smaller if no 
>> operand is %r8-%r15.
> Because then we loose the REX prefix, right. Now _that_ might actually
> be a reason to do that :-)

I knew that would be the right way to put it for you. :)

>> In any case, /me wonders if we should have a macro like
>> #define DECLARE_LE_BITMAP(name,bits) \
>>         u32 name[DIV_ROUND_UP(bits, 32)] __aligned(sizeof(unsigned long))
>  s/u32/__le32/
> To go in bitops/le.h, sure, if there's enough users.

Hmm... actually that should be "BITS_TO_LONGS(bits) * sizeof(unsigned
long) / 4" because bitmap functions may access (or even clear) the last
word as 64 bits.


Powered by blists - more mailing lists