Re: [PATCH v3 01/12] drm: Add dummy page per device or GEM object

[Daniel Vetter <daniel@ffwll.ch>]

On Mon, Jan 11, 2021 at 03:45:10PM -0500, Andrey Grodzovsky wrote:
> 
> On 1/11/21 11:15 AM, Daniel Vetter wrote:
> > On Mon, Jan 11, 2021 at 05:13:56PM +0100, Daniel Vetter wrote:
> > > On Fri, Jan 08, 2021 at 04:49:55PM +0000, Grodzovsky, Andrey wrote:
> > > > Ok then, I guess I will proceed with the dummy pages list implementation then.
> > > > 
> > > > Andrey
> > > > 
> > > > ________________________________
> > > > From: Koenig, Christian <Christian.Koenig@amd.com>
> > > > Sent: 08 January 2021 09:52
> > > > To: Grodzovsky, Andrey <Andrey.Grodzovsky@amd.com>; Daniel Vetter <daniel@ffwll.ch>
> > > > Cc: amd-gfx@lists.freedesktop.org <amd-gfx@lists.freedesktop.org>; dri-devel@lists.freedesktop.org <dri-devel@lists.freedesktop.org>; daniel.vetter@ffwll.ch <daniel.vetter@ffwll.ch>; robh@kernel.org <robh@kernel.org>; l.stach@pengutronix.de <l.stach@pengutronix.de>; yuq825@gmail.com <yuq825@gmail.com>; eric@anholt.net <eric@anholt.net>; Deucher, Alexander <Alexander.Deucher@amd.com>; gregkh@linuxfoundation.org <gregkh@linuxfoundation.org>; ppaalanen@gmail.com <ppaalanen@gmail.com>; Wentland, Harry <Harry.Wentland@amd.com>
> > > > Subject: Re: [PATCH v3 01/12] drm: Add dummy page per device or GEM object
> > > > 
> > > > Mhm, I'm not aware of any let over pointer between TTM and GEM and we
> > > > worked quite hard on reducing the size of the amdgpu_bo, so another
> > > > extra pointer just for that corner case would suck quite a bit.
> > > We have a ton of other pointers in struct amdgpu_bo (or any of it's lower
> > > things) which are fairly single-use, so I'm really not much seeing the
> > > point in making this a special case. It also means the lifetime management
> > > becomes a bit iffy, since we can't throw away the dummy page then the last
> > > reference to the bo is released (since we don't track it there), but only
> > > when the last pointer to the device is released. Potentially this means a
> > > pile of dangling pages hanging around for too long.
> > Also if you really, really, really want to have this list, please don't
> > reinvent it since we have it already. drmm_ is exactly meant for resources
> > that should be freed when the final drm_device reference disappears.
> > -Daniel
> 
> 
> I maybe was eager to early, see i need to explicitly allocate the dummy page
> using page_alloc so
> i cannot use drmm_kmalloc for this, so once again like with the list i need
> to wrap it with a container struct
> which i can then allocate using drmm_kmalloc and inside there will be page
> pointer. But then
> on release it needs to free the page and so i supposedly need to use drmm_add_action
> to free the page before the container struct is released but drmm_kmalloc
> doesn't allow to set
> release action on struct allocation. So I created a new
> drmm_kmalloc_with_action API function
> but then you also need to supply the optional data pointer for the release
> action (the struct page in this case)
> and so this all becomes a bit overcomplicated (but doable). Is this extra
> API worth adding ? Maybe it can
> be useful in general.

drm_add_action_or_reset (for better control flow) has both a void * data
and a cleanup function (and it internally allocates the tracking structure
for that for you). So should work as-is? Allocating a tracking structure
for our tracking structure for a page would definitely be a bit too much.

Essentiall drmm_add_action is your kcalloc_with_action function you want,
as long as all you need is a single void * pointer (we could do the
kzalloc_with_action though, there's enough space, just no need yet for any
of the current users).
-Daniel

> 
> Andrey
> 
> 
> 
> > > If you need some ideas for redundant pointers:
> > > - destroy callback (kinda not cool to not have this const anyway), we
> > >    could refcount it all with the overall gem bo. Quite a bit of work.
> > > - bdev pointer, if we move the device ttm stuff into struct drm_device, or
> > >    create a common struct ttm_device, we can ditch that
> > > - We could probably merge a few of the fields and find 8 bytes somewhere
> > > - we still have 2 krefs, would probably need to fix that before we can
> > >    merge the destroy callbacks
> > > 
> > > So there's plenty of room still, if the size of a bo struct is really that
> > > critical. Imo it's not.
> > > 
> > > 
> > > > Christian.
> > > > 
> > > > Am 08.01.21 um 15:46 schrieb Andrey Grodzovsky:
> > > > > Daniel had some objections to this (see bellow) and so I guess I need
> > > > > you both to agree on the approach before I proceed.
> > > > > 
> > > > > Andrey
> > > > > 
> > > > > On 1/8/21 9:33 AM, Christian König wrote:
> > > > > > Am 08.01.21 um 15:26 schrieb Andrey Grodzovsky:
> > > > > > > Hey Christian, just a ping.
> > > > > > Was there any question for me here?
> > > > > > 
> > > > > > As far as I can see the best approach would still be to fill the VMA
> > > > > > with a single dummy page and avoid pointers in the GEM object.
> > > > > > 
> > > > > > Christian.
> > > > > > 
> > > > > > > Andrey
> > > > > > > 
> > > > > > > On 1/7/21 11:37 AM, Andrey Grodzovsky wrote:
> > > > > > > > On 1/7/21 11:30 AM, Daniel Vetter wrote:
> > > > > > > > > On Thu, Jan 07, 2021 at 11:26:52AM -0500, Andrey Grodzovsky wrote:
> > > > > > > > > > On 1/7/21 11:21 AM, Daniel Vetter wrote:
> > > > > > > > > > > On Tue, Jan 05, 2021 at 04:04:16PM -0500, Andrey Grodzovsky wrote:
> > > > > > > > > > > > On 11/23/20 3:01 AM, Christian König wrote:
> > > > > > > > > > > > > Am 23.11.20 um 05:54 schrieb Andrey Grodzovsky:
> > > > > > > > > > > > > > On 11/21/20 9:15 AM, Christian König wrote:
> > > > > > > > > > > > > > > Am 21.11.20 um 06:21 schrieb Andrey Grodzovsky:
> > > > > > > > > > > > > > > > Will be used to reroute CPU mapped BO's page faults once
> > > > > > > > > > > > > > > > device is removed.
> > > > > > > > > > > > > > > Uff, one page for each exported DMA-buf? That's not
> > > > > > > > > > > > > > > something we can do.
> > > > > > > > > > > > > > > 
> > > > > > > > > > > > > > > We need to find a different approach here.
> > > > > > > > > > > > > > > 
> > > > > > > > > > > > > > > Can't we call alloc_page() on each fault and link them together
> > > > > > > > > > > > > > > so they are freed when the device is finally reaped?
> > > > > > > > > > > > > > For sure better to optimize and allocate on demand when we reach
> > > > > > > > > > > > > > this corner case, but why the linking ?
> > > > > > > > > > > > > > Shouldn't drm_prime_gem_destroy be good enough place to free ?
> > > > > > > > > > > > > I want to avoid keeping the page in the GEM object.
> > > > > > > > > > > > > 
> > > > > > > > > > > > > What we can do is to allocate a page on demand for each fault
> > > > > > > > > > > > > and link
> > > > > > > > > > > > > the together in the bdev instead.
> > > > > > > > > > > > > 
> > > > > > > > > > > > > And when the bdev is then finally destroyed after the last
> > > > > > > > > > > > > application
> > > > > > > > > > > > > closed we can finally release all of them.
> > > > > > > > > > > > > 
> > > > > > > > > > > > > Christian.
> > > > > > > > > > > > Hey, started to implement this and then realized that by
> > > > > > > > > > > > allocating a page
> > > > > > > > > > > > for each fault indiscriminately
> > > > > > > > > > > > we will be allocating a new page for each faulting virtual
> > > > > > > > > > > > address within a
> > > > > > > > > > > > VA range belonging the same BO
> > > > > > > > > > > > and this is obviously too much and not the intention. Should I
> > > > > > > > > > > > instead use
> > > > > > > > > > > > let's say a hashtable with the hash
> > > > > > > > > > > > key being faulting BO address to actually keep allocating and
> > > > > > > > > > > > reusing same
> > > > > > > > > > > > dummy zero page per GEM BO
> > > > > > > > > > > > (or for that matter DRM file object address for non imported
> > > > > > > > > > > > BOs) ?
> > > > > > > > > > > Why do we need a hashtable? All the sw structures to track this
> > > > > > > > > > > should
> > > > > > > > > > > still be around:
> > > > > > > > > > > - if gem_bo->dma_buf is set the buffer is currently exported as
> > > > > > > > > > > a dma-buf,
> > > > > > > > > > >      so defensively allocate a per-bo page
> > > > > > > > > > > - otherwise allocate a per-file page
> > > > > > > > > > That exactly what we have in current implementation
> > > > > > > > > > 
> > > > > > > > > > 
> > > > > > > > > > > Or is the idea to save the struct page * pointer? That feels a
> > > > > > > > > > > bit like
> > > > > > > > > > > over-optimizing stuff. Better to have a simple implementation
> > > > > > > > > > > first and
> > > > > > > > > > > then tune it if (and only if) any part of it becomes a problem
> > > > > > > > > > > for normal
> > > > > > > > > > > usage.
> > > > > > > > > > Exactly - the idea is to avoid adding extra pointer to
> > > > > > > > > > drm_gem_object,
> > > > > > > > > > Christian suggested to instead keep a linked list of dummy pages
> > > > > > > > > > to be
> > > > > > > > > > allocated on demand once we hit a vm_fault. I will then also
> > > > > > > > > > prefault the entire
> > > > > > > > > > VA range from vma->vm_end - vma->vm_start to vma->vm_end and map
> > > > > > > > > > them
> > > > > > > > > > to that single dummy page.
> > > > > > > > > This strongly feels like premature optimization. If you're worried
> > > > > > > > > about
> > > > > > > > > the overhead on amdgpu, pay down the debt by removing one of the
> > > > > > > > > redundant
> > > > > > > > > pointers between gem and ttm bo structs (I think we still have
> > > > > > > > > some) :-)
> > > > > > > > > 
> > > > > > > > > Until we've nuked these easy&obvious ones we shouldn't play "avoid 1
> > > > > > > > > pointer just because" games with hashtables.
> > > > > > > > > -Daniel
> > > > > > > > 
> > > > > > > > Well, if you and Christian can agree on this approach and suggest
> > > > > > > > maybe what pointer is
> > > > > > > > redundant and can be removed from GEM struct so we can use the
> > > > > > > > 'credit' to add the dummy page
> > > > > > > > to GEM I will be happy to follow through.
> > > > > > > > 
> > > > > > > > P.S Hash table is off the table anyway and we are talking only
> > > > > > > > about linked list here since by prefaulting
> > > > > > > > the entire VA range for a vmf->vma i will be avoiding redundant
> > > > > > > > page faults to same VMA VA range and so
> > > > > > > > don't need to search and reuse an existing dummy page but simply
> > > > > > > > create a new one for each next fault.
> > > > > > > > 
> > > > > > > > Andrey
> > > -- 
> > > Daniel Vetter
> > > Software Engineer, Intel Corporation
> > > https://nam11.safelinks.protection.outlook.com/?url=http%3A%2F%2Fblog.ffwll.ch%2F&amp;data=04%7C01%7Candrey.grodzovsky%40amd.com%7C4b581c55df204ca3d07408d8b64c1db8%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637459785321798393%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=EvvAip8vs9fzVRS1rb0r5ODiBMngxPuI9GKR2%2F%2B2LzE%3D&amp;reserved=0

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx