linux-kernel - Re: [PATCH 6/7] dma-iommu: implement ->alloc

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: <20210216084947.GA23897@lst.de>
Date:   Tue, 16 Feb 2021 09:49:47 +0100
From:   Christoph Hellwig <hch@....de>
To:     Tomasz Figa <tfiga@...omium.org>
Cc:     Christoph Hellwig <hch@....de>,
        Mauro Carvalho Chehab <mchehab@...nel.org>,
        Marek Szyprowski <m.szyprowski@...sung.com>,
        Ricardo Ribalda <ribalda@...omium.org>,
        Sergey Senozhatsky <senozhatsky@...gle.com>,
        "open list:IOMMU DRIVERS" <iommu@...ts.linux-foundation.org>,
        Robin Murphy <robin.murphy@....com>,
        Linux Doc Mailing List <linux-doc@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Linux Media Mailing List <linux-media@...r.kernel.org>
Subject: Re: [PATCH 6/7] dma-iommu: implement ->alloc_noncontiguous

On Tue, Feb 16, 2021 at 05:14:55PM +0900, Tomasz Figa wrote:
> When working on the videobuf2 integration with Sergey I noticed that
> we always pass 0 as DMA attrs here, which removes the ability for
> drivers to use DMA_ATTR_ALLOC_SINGLE_PAGES.
> 
> It's quite important from a system stability point of view, because by
> default the iommu_dma allocator would prefer big order allocations for
> TLB locality reasons. For many devices, though, it doesn't really
> affect the performance, because of random access patterns, so single
> pages are good enough and reduce the risk of allocation failures or
> latency due to fragmentation.
> 
> Do you think we could add the attrs parameter to the
> dma_alloc_noncontiguous() API?

Yes, we could probably do that.