linux-kernel - Re: [PATCH v4 5/7] dma-buf: system_heap: Allocate higher order pages if available

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <CALAqxLU1=vScNWfxc-Ji9F_cY311z8GuFLiFT0q0PrDyJVxViA@mail.gmail.com>
Date:   Thu, 29 Oct 2020 20:30:04 -0700
From:   John Stultz <john.stultz@...aro.org>
To:     Hillf Danton <hdanton@...a.com>
Cc:     lkml <linux-kernel@...r.kernel.org>,
        Sumit Semwal <sumit.semwal@...aro.org>,
        Liam Mark <lmark@...eaurora.org>,
        Robin Murphy <robin.murphy@....com>,
        Ezequiel Garcia <ezequiel@...labora.com>,
        Simon Ser <contact@...rsion.fr>,
        James Jones <jajones@...dia.com>,
        linux-media <linux-media@...r.kernel.org>,
        dri-devel <dri-devel@...ts.freedesktop.org>
Subject: Re: [PATCH v4 5/7] dma-buf: system_heap: Allocate higher order pages
 if available

On Thu, Oct 29, 2020 at 7:34 PM Hillf Danton <hdanton@...a.com> wrote:
> On Thu, 29 Oct 2020 12:34:51 -0700 John Stultz wrote:
> > As for your comment on HPAGE_PMD_ORDER (9 on arm64/arm) and
> > PAGE_ALLOC_COSTLY_ORDER(3), I'm not totally sure I understand your
> > question? Are you suggesting those values would be more natural orders
> > to choose from?
>
> The numbers, 9 and 3, are not magic themselves but under the mm diretory
> they draw more attentions than others do. Sometimes it would take two
> minutes for me to work out that HPAGE_PMD_ORDER does not mean 1MiB, on
> platforms like arm64 or not.

Yes, I can say it took me longer than two minutes to dig around and
work out HPAGE_PMD_ORDER for my last reply.  :)

Though I'm still a bit unsure if you are proposing something more than
just a comment to explain why order 8 and order 4 allocations are used
in my patch? Please let me know if so.

thanks
-john