linux-kernel - Re: [PATCH v6 02/22] drm/gem: Move mapping of imported dma-bufs to drm_gem_mmap

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:   Wed, 29 Jun 2022 10:43:45 +0200
From:   Thomas Hellström (Intel) 
        <thomas_os@...pmail.org>
To:     Dmitry Osipenko <dmitry.osipenko@...labora.com>
Cc:     intel-gfx@...ts.freedesktop.org, linux-kernel@...r.kernel.org,
        dri-devel@...ts.freedesktop.org,
        virtualization@...ts.linux-foundation.org,
        linaro-mm-sig@...ts.linaro.org, amd-gfx@...ts.freedesktop.org,
        linux-tegra@...r.kernel.org, Dmitry Osipenko <digetx@...il.com>,
        kernel@...labora.com, linux-media@...r.kernel.org,
        David Airlie <airlied@...ux.ie>,
        Gerd Hoffmann <kraxel@...hat.com>,
        Gurchetan Singh <gurchetansingh@...omium.org>,
        Chia-I Wu <olvaffe@...il.com>, Daniel Vetter <daniel@...ll.ch>,
        Daniel Almeida <daniel.almeida@...labora.com>,
        Gert Wollny <gert.wollny@...labora.com>,
        Gustavo Padovan <gustavo.padovan@...labora.com>,
        Daniel Stone <daniel@...ishbar.org>,
        Tomeu Vizoso <tomeu.vizoso@...labora.com>,
        Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
        Maxime Ripard <mripard@...nel.org>,
        Thomas Zimmermann <tzimmermann@...e.de>,
        Rob Herring <robh@...nel.org>,
        Steven Price <steven.price@....com>,
        Alyssa Rosenzweig <alyssa.rosenzweig@...labora.com>,
        Rob Clark <robdclark@...il.com>,
        Emil Velikov <emil.l.velikov@...il.com>,
        Robin Murphy <robin.murphy@....com>,
        Qiang Yu <yuq825@...il.com>,
        Sumit Semwal <sumit.semwal@...aro.org>,
        Christian König <christian.koenig@....com>,
        "Pan, Xinhui" <Xinhui.Pan@....com>,
        Thierry Reding <thierry.reding@...il.com>,
        Tomasz Figa <tfiga@...omium.org>,
        Marek Szyprowski <m.szyprowski@...sung.com>,
        Mauro Carvalho Chehab <mchehab@...nel.org>,
        Alex Deucher <alexander.deucher@....com>,
        Jani Nikula <jani.nikula@...ux.intel.com>,
        Joonas Lahtinen <joonas.lahtinen@...ux.intel.com>,
        Rodrigo Vivi <rodrigo.vivi@...el.com>,
        Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>
Subject: Re: [PATCH v6 02/22] drm/gem: Move mapping of imported dma-bufs to
 drm_gem_mmap_obj()


On 6/29/22 10:22, Dmitry Osipenko wrote:
> On 6/29/22 09:40, Thomas Hellström (Intel) wrote:
>> On 5/27/22 01:50, Dmitry Osipenko wrote:
>>> Drivers that use drm_gem_mmap() and drm_gem_mmap_obj() helpers don't
>>> handle imported dma-bufs properly, which results in mapping of something
>>> else than the imported dma-buf. For example, on NVIDIA Tegra we get a
>>> hard
>>> lockup when userspace writes to the memory mapping of a dma-buf that was
>>> imported into Tegra's DRM GEM.
>>>
>>> To fix this bug, move mapping of imported dma-bufs to drm_gem_mmap_obj().
>>> Now mmaping of imported dma-bufs works properly for all DRM drivers.
>> Same comment about Fixes: as in patch 1,
>>> Cc: stable@...r.kernel.org
>>> Signed-off-by: Dmitry Osipenko <dmitry.osipenko@...labora.com>
>>> ---
>>>    drivers/gpu/drm/drm_gem.c              | 3 +++
>>>    drivers/gpu/drm/drm_gem_shmem_helper.c | 9 ---------
>>>    drivers/gpu/drm/tegra/gem.c            | 4 ++++
>>>    3 files changed, 7 insertions(+), 9 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
>>> index 86d670c71286..7c0b025508e4 100644
>>> --- a/drivers/gpu/drm/drm_gem.c
>>> +++ b/drivers/gpu/drm/drm_gem.c
>>> @@ -1038,6 +1038,9 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj,
>>> unsigned long obj_size,
>>>        if (obj_size < vma->vm_end - vma->vm_start)
>>>            return -EINVAL;
>>>    +    if (obj->import_attach)
>>> +        return dma_buf_mmap(obj->dma_buf, vma, 0);
>> If we start enabling mmaping of imported dma-bufs on a majority of
>> drivers in this way, how do we ensure that user-space is not blindly
>> using the object mmap without calling the needed DMA_BUF_IOCTL_SYNC
>> which is needed before and after cpu access of mmap'ed dma-bufs?
>>
>> I was under the impression (admittedly without looking) that the few
>> drivers that actually called into dma_buf_mmap() had some private
>> user-mode driver code in place that ensured this happened.
> Since it's a userspace who does the mapping, then it should be a
> responsibility of userspace to do all the necessary syncing.

Sure, but nothing prohibits user-space to ignore the syncing thinking 
"It works anyway", testing those drivers where the syncing is a NOP. And 
when a driver that finally needs syncing is tested it's too late to fix 
all broken user-space.

>   I'm not
> sure whether anyone in userspace really needs to map imported dma-bufs
> in practice. Nevertheless, this use-case is broken and should be fixed
> by either allowing to do the mapping or prohibiting it.
>
Then I'd vote for prohibiting it, at least for now. And for the future 
moving forward we could perhaps revisit the dma-buf need for syncing, 
requiring those drivers that actually need it to implement emulated 
coherent memory which can be done not too inefficiently (vmwgfx being 
one example).

/Thomas