linux-kernel - Re: [PATCH] MM: Support more pagesizes for MAP_HUGETLB/SHM

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, 13 Jun 2012 16:38:15 -0400
From:	Rik van Riel <riel@...hat.com>
To:	Andi Kleen <andi@...stfloor.org>
CC:	linux-mm@...ck.org, linux-kernel@...r.kernel.org,
	Andi Kleen <ak@...ux.intel.com>
Subject: Re: [PATCH] MM: Support more pagesizes for MAP_HUGETLB/SHM_HUGETLB
 v2

On 06/13/2012 04:31 PM, Andi Kleen wrote:
> On Wed, Jun 13, 2012 at 04:24:47PM -0400, Rik van Riel wrote:
>> This would also be useful for emulators such as qemu-kvm,
>> which want the guest memory to be 2MB aligned.
>
> hugetlbfs does implicit align, so right now I mash
> the two together and use up many of the remaining bits
>
> If you want align different than page sizes you may need
> to go 64bits with the flags.

All alignment is a power of two, so six bits should
be enough for up to 2^64 pages :)

> Is there a use case for alignment independent of page sizes?

No, but page size differs per architecture and it
would be nice if we could share arch_get_unmapped_area
and related code in mm/, instead of every architecture
having its own.

In fact, that is what I am working on right now, and
my current road block is the page colouring code :)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/