linux-kernel - Re: [PATCH v4 2/3] mm: Add support for kmem caches in DMA32 zone

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: <CANMq1KCnpSUKoz83LcEgAkhCi8QVPH715xtgdQD23r-tYusrPw@mail.gmail.com>
Date:   Wed, 5 Dec 2018 19:01:03 +0800
From:   Nicolas Boichat <drinkcat@...omium.org>
To:     mhocko@...nel.org
Cc:     Will Deacon <will.deacon@....com>,
        Robin Murphy <robin.murphy@....com>,
        Joerg Roedel <joro@...tes.org>,
        Christoph Lameter <cl@...ux.com>,
        Pekka Enberg <penberg@...nel.org>,
        David Rientjes <rientjes@...gle.com>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Levin Alexander <Alexander.Levin@...rosoft.com>,
        Huaisheng Ye <yehs1@...ovo.com>,
        Mike Rapoport <rppt@...ux.vnet.ibm.com>,
        linux-arm Mailing List <linux-arm-kernel@...ts.infradead.org>,
        iommu@...ts.linux-foundation.org,
        lkml <linux-kernel@...r.kernel.org>, linux-mm@...ck.org,
        Yong Wu <yong.wu@...iatek.com>,
        Matthias Brugger <matthias.bgg@...il.com>,
        Tomasz Figa <tfiga@...gle.com>, yingjoe.chen@...iatek.com,
        hch@...radead.org, Matthew Wilcox <willy@...radead.org>
Subject: Re: [PATCH v4 2/3] mm: Add support for kmem caches in DMA32 zone

On Wed, Dec 5, 2018 at 5:56 PM Michal Hocko <mhocko@...nel.org> wrote:
>
> On Wed 05-12-18 13:48:27, Nicolas Boichat wrote:
> > In some cases (e.g. IOMMU ARMv7s page allocator), we need to allocate
> > data structures smaller than a page with GFP_DMA32 flag.
> >
> > This change makes it possible to create a custom cache in DMA32 zone
> > using kmem_cache_create, then allocate memory using kmem_cache_alloc.
> >
> > We do not create a DMA32 kmalloc cache array, as there are currently
> > no users of kmalloc(..., GFP_DMA32). The new test in check_slab_flags
> > ensures that such calls still fail (as they do before this change).
>
> The changelog should be much more specific about decisions made here.
> First of all it would be nice to mention the usecase.

Ok, I'll copy most of the cover letter text here (i.e. the fact that
IOMMU wants physical memory <4GB for L2 page tables, why it's better
than genalloc/page_frag).

> Secondly, why do we need a new sysfs file? Who is going to consume it?

We have cache_dma, so it seems consistent to add cache_dma32.

I wasn't aware of tools/vm/slabinfo.c, so I can add support for
cache_dma32 in a follow-up patch. Any other user I should take care
of?

> Then why do we need SLAB_MERGE_SAME to cover GFP_DMA32 as well?

SLAB_MERGE_SAME tells us which flags _need_ to be the same for the
slabs to be merged. We don't want slab caches with GFP_DMA32 and
~GFP_DMA32 to be merged, so it should be in there.
(https://elixir.bootlin.com/linux/v4.19.6/source/mm/slab_common.c#L342).

> I
> thought the whole point is to use dedicated slab cache. Who is this
> going to merge with?

Well, if there was another SLAB cache requiring 1KB GFP_DMA32
elements, then I don't see why we would not merge the caches. This is
what happens with this IOMMU L2 tables cache pre-CONFIG_ZONE_DMA32 on
arm64 (output on some 3.18 kernel below), and what would happen on
arm32 since we still use GFP_DMA.

/sys/kernel/slab # ls -l | grep dt-0001024
drwxr-xr-x. 2 root root 0 Dec  5 02:25 :dt-0001024
lrwxrwxrwx. 1 root root 0 Dec  5 02:25 dma-kmalloc-1024 -> :dt-0001024
lrwxrwxrwx. 1 root root 0 Dec  5 02:25 io-pgtable_armv7s_l2 -> :dt-0001024

Thanks!

> --
> Michal Hocko
> SUSE Labs