linux-kernel - Re: [PATCH v15 11/11] RFC: fw

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: <CAMxuvaw-v3BagJ6-50sxW24X3c=S-4Xfd5e1Unq8ScNbxKvkSQ@mail.gmail.com>
Date:   Wed, 28 Feb 2018 17:00:58 +0100
From:   Marc-André Lureau <marcandre.lureau@...hat.com>
To:     "Michael S. Tsirkin" <mst@...hat.com>
Cc:     Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Sergio Lopez Pascual <slp@...hat.com>,
        Baoquan He <bhe@...hat.com>, "Somlo, Gabriel" <somlo@....edu>,
        xiaolong.ye@...el.com
Subject: Re: [PATCH v15 11/11] RFC: fw_cfg: do DMA read operation

Hi

On Wed, Feb 28, 2018 at 4:48 PM, Michael S. Tsirkin <mst@...hat.com> wrote:
> On Wed, Feb 28, 2018 at 04:41:51PM +0100, Marc-André Lureau wrote:
>> I don't know if it's always safe to enable dma in read_raw(), how
>> could we know? Is there a check we could use to choose one or ther
>> other (and thus avoiding explicit dma/readfn argument)?
>
> I'm not sure - but does it really matter? Is anyone reading large files
> like this in production where speed matters?
> Why even bother with DMA?

The difference is quite significante for not so small files, as shown above.

And if they access the fw_cfg entries at boot time, or when starting
things etc, this may speed things up.