linux-kernel - Re: [Linaro-mm-sig] [PATCH v5 00/40] drm/msm: sparse / "VM

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: <CAF6AEGs1hNGMMBjZuXoGjxF+JA1AHY_wx=gmqK4z=zShYoR6=w@mail.gmail.com>
Date: Mon, 19 May 2025 14:51:20 -0700
From: Rob Clark <robdclark@...il.com>
To: Dave Airlie <airlied@...il.com>
Cc: dri-devel@...ts.freedesktop.org, freedreno@...ts.freedesktop.org, 
	linux-arm-msm@...r.kernel.org, Connor Abbott <cwabbott0@...il.com>, 
	Rob Clark <robdclark@...omium.org>, Abhinav Kumar <quic_abhinavk@...cinc.com>, 
	André Almeida <andrealmeid@...lia.com>, 
	Arnd Bergmann <arnd@...db.de>, Barnabás Czémán <barnabas.czeman@...nlining.org>, 
	Christopher Snowhill <chris@...e54.net>, Dmitry Baryshkov <dmitry.baryshkov@....qualcomm.com>, 
	Dmitry Baryshkov <lumag@...nel.org>, Eugene Lepshy <fekz115@...il.com>, 
	"open list:IOMMU SUBSYSTEM" <iommu@...ts.linux.dev>, Jason Gunthorpe <jgg@...pe.ca>, 
	Jessica Zhang <quic_jesszhan@...cinc.com>, Joao Martins <joao.m.martins@...cle.com>, 
	Jonathan Marek <jonathan@...ek.ca>, Jun Nie <jun.nie@...aro.org>, 
	Kevin Tian <kevin.tian@...el.com>, Konrad Dybcio <konradybcio@...nel.org>, 
	Krzysztof Kozlowski <krzysztof.kozlowski@...aro.org>, 
	"moderated list:DMA BUFFER SHARING FRAMEWORK:Keyword:bdma_?:buf|fence|resvb" <linaro-mm-sig@...ts.linaro.org>, 
	"m oderated list:ARM SMMU DRIVERS" <linux-arm-kernel@...ts.infradead.org>, 
	open list <linux-kernel@...r.kernel.org>, 
	"open list:DMA BUFFER SHARING FRAMEWORK:Keyword:bdma_?:buf|fence|resvb" <linux-media@...r.kernel.org>, 
	Marijn Suijten <marijn.suijten@...ainline.org>, Nicolin Chen <nicolinc@...dia.com>, 
	"Rob Herring (Arm)" <robh@...nel.org>, Robin Murphy <robin.murphy@....com>, Sean Paul <sean@...rly.run>, 
	Will Deacon <will@...nel.org>
Subject: Re: [Linaro-mm-sig] [PATCH v5 00/40] drm/msm: sparse / "VM_BIND" support

On Mon, May 19, 2025 at 2:45 PM Dave Airlie <airlied@...il.com> wrote:
>
> On Tue, 20 May 2025 at 07:25, Rob Clark <robdclark@...il.com> wrote:
> >
> > On Mon, May 19, 2025 at 2:15 PM Dave Airlie <airlied@...il.com> wrote:
> > >
> > > On Tue, 20 May 2025 at 03:54, Rob Clark <robdclark@...il.com> wrote:
> > > >
> > > > From: Rob Clark <robdclark@...omium.org>
> > > >
> > > > Conversion to DRM GPU VA Manager[1], and adding support for Vulkan Sparse
> > > > Memory[2] in the form of:
> > > >
> > > > 1. A new VM_BIND submitqueue type for executing VM MSM_SUBMIT_BO_OP_MAP/
> > > >    MAP_NULL/UNMAP commands
> > > >
> > > > 2. A new VM_BIND ioctl to allow submitting batches of one or more
> > > >    MAP/MAP_NULL/UNMAP commands to a VM_BIND submitqueue
> > > >
> > > > I did not implement support for synchronous VM_BIND commands.  Since
> > > > userspace could just immediately wait for the `SUBMIT` to complete, I don't
> > > > think we need this extra complexity in the kernel.  Synchronous/immediate
> > > > VM_BIND operations could be implemented with a 2nd VM_BIND submitqueue.
> > >
> > > This seems suboptimal for Vulkan userspaces. non-sparse binds are all
> > > synchronous, you are adding an extra ioctl to wait, or do you manage
> > > these via a different mechanism?
> >
> > Normally it's just an extra in-fence for the SUBMIT ioctl to ensure
> > the binds happen before cmd execution
> >
> > When it comes to UAPI, it's easier to add something later, than to
> > take something away, so I don't see a problem adding synchronous binds
> > later if that proves to be needed.  But I don't think it is.
>
> I'm not 100% sure that is conformant behaviour to the vulkan spec,
>
> Two questions come to mind:
> 1. where is this out fence stored? vulkan being explicit with no
> guarantee of threads doing things, seems like you'd need to use a lock
> in the vulkan driver to store it, esp if multiple threads bind memory.

turnip is protected dev->vm_bind_fence_fd with a u_rwlock

> 2. If it's fine to lazy bind on the hw side, do you also handle the
> case where something is bound and immediately freed, where does the
> fence go then, do you wait for the fence before destroying things?

right no turnip is just relying on the UNMAP/unbind going thru the
same queue.. but I guess it could also use vm_bind_fence_fd as an
in-fence.

BR,
-R