linux-kernel - Re: RFC: Petition Intel/AMD to add POPF

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]

Date:	Wed, 17 Aug 2016 20:41:34 +0200
From:	Denys Vlasenko <dvlasenk@...hat.com>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	Ingo Molnar <mingo@...nel.org>, Andy Lutomirski <luto@...nel.org>,
	Dan Williams <dan.j.williams@...el.com>,
	Alex Deucher <alexander.deucher@....com>,
	"Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
	Christian König <christian.koenig@....com>,
	Vinod Koul <vinod.koul@...el.com>,
	Johannes Berg <johannes.berg@...el.com>,
	Sara Sharon <sara.sharon@...el.com>,
	Adrian Hunter <adrian.hunter@...el.com>,
	the arch/x86 maintainers <x86@...nel.org>,
	LKML <linux-kernel@...r.kernel.org>
Subject: Re: RFC: Petition Intel/AMD to add POPF_IF insn

On 08/17/2016 07:32 PM, Linus Torvalds wrote:
> On Wed, Aug 17, 2016 at 10:20 AM, Denys Vlasenko <dvlasenk@...hat.com> wrote:
>> Last year, a proposal was floated to avoid costly POPF.
>> In particular, each spin_unlock_irqrestore() does it,
>> a rather common operation.
>
> Quiet frankly, it takes so long for hw features that I don't think
> it's worth it for something like this.

True, it will take some ~5 years for new hardware to become
widely used.

OTOH 5 years will inevitably pass. Just like now 32-bit Linux userspace
is commonly compiled to "i686" instruction set, because
inevitably enough time has passed that you can safely assume
most people run at least Pentium Pro-level CPU, with CMOV, CMPXCHG,
etc.

If the new instruction will be implemented with "REPZ POPF" encoding,
no recompilation or alternatives will be needed for the new kernel
to run on an old CPU. On an old CPU, entire EFLAGS will be restored.
On a new one, only EFLAGS.IF.