linux-kernel - Re: [PATCH] mm: introduce MADV_CLR

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: <20170522081223.GD27382@rapoport-lnx>
Date:   Mon, 22 May 2017 11:12:25 +0300
From:   Mike Rapoport <rppt@...ux.vnet.ibm.com>
To:     Anshuman Khandual <khandual@...ux.vnet.ibm.com>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Arnd Bergmann <arnd@...db.de>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Andrea Arcangeli <aarcange@...hat.com>,
        linux-mm <linux-mm@...ck.org>,
        lkml <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] mm: introduce MADV_CLR_HUGEPAGE

On Mon, May 22, 2017 at 12:56:45PM +0530, Anshuman Khandual wrote:
> On 05/22/2017 11:42 AM, Mike Rapoport wrote:
> > Currently applications can explicitly enable or disable THP for a memory
> > region using MADV_HUGEPAGE or MADV_NOHUGEPAGE. However, once either of
> > these advises is used, the region will always have
> > VM_HUGEPAGE/VM_NOHUGEPAGE flag set in vma->vm_flags.
> > The MADV_CLR_HUGEPAGE resets both these flags and allows managing THP in
> > the region according to system-wide settings.
> 
> Invoking madvise() for the first time with either MADV_HUGEPAGE or
> MADV_NOHUGEPAGE on the buffer will unsubscribe it from the system
> wide behavior for good. I am not saying we should not have a way
> to put it back into system wide mode but are there no other functions
> through madvise() or any other interface which may have the same
> situation.

There are madvise() interfaces that set or clear some of the vma->vm_flags,
e.g MADV_*FORK or MADV_*DUMP. The difference with MADV_*HUGEPAGE is that
it is using two flags and with current madvise() interface either of them
has to be set, but there is no interface to clear them both.

--
Sincerely yours,
Mike.