linux-kernel - Re: [PATCH v3 02/10] swiotlb: Factor out slot allocation and free

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:   Mon, 6 May 2019 09:54:30 +0800
From:   Lu Baolu <baolu.lu@...ux.intel.com>
To:     Christoph Hellwig <hch@....de>, Robin Murphy <robin.murphy@....com>
Cc:     baolu.lu@...ux.intel.com, David Woodhouse <dwmw2@...radead.org>,
        Joerg Roedel <joro@...tes.org>, ashok.raj@...el.com,
        jacob.jun.pan@...el.com, alan.cox@...el.com, kevin.tian@...el.com,
        mika.westerberg@...ux.intel.com, pengfei.xu@...el.com,
        Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
        Marek Szyprowski <m.szyprowski@...sung.com>,
        iommu@...ts.linux-foundation.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 02/10] swiotlb: Factor out slot allocation and free

Hi Christoph,

On 4/29/19 7:44 PM, Christoph Hellwig wrote:
> On Mon, Apr 29, 2019 at 12:06:52PM +0100, Robin Murphy wrote:
>>
>>  From the reply up-thread I guess you're trying to include an optimisation
>> to only copy the head and tail of the buffer if it spans multiple pages,
>> and directly map the ones in the middle, but AFAICS that's going to tie you
>> to also using strict mode for TLB maintenance, which may not be a win
>> overall depending on the balance between invalidation bandwidth vs. memcpy
>> bandwidth. At least if we use standard SWIOTLB logic to always copy the
>> whole thing, we should be able to release the bounce pages via the flush
>> queue to allow 'safe' lazy unmaps.
> 
> Oh.  The head and tail optimization is what I missed.  Yes, for that
> we'd need the offset.

Yes.

> 
>> Either way I think it would be worth just implementing the straightforward
>> version first, then coming back to consider optimisations later.
> 
> Agreed, let's start simple.  Especially as large DMA mappings or
> allocations should usually be properly aligned anyway, and if not we
> should fix that for multiple reasons.
> 

Agreed. I will prepare the next version simply without the optimization, 
so the offset is not required.

For your changes in swiotlb, will you formalize them in patches or want
me to do this?

Best regards,
Lu Baolu