If the bo is idle when calling ttm_bo_pipeline_gutting(), we unnecessarily
create a ghost object and push it out to delayed destroy.
Fix this by adding a path for idle, and document the function.
Also avoid having the bo end up in a bad state vulnerable to user-space
triggered kernel BUGs if the call to ttm_tt_create() fails.
Finally reuse ttm_bo_pipeline_gutting() in ttm_bo_evict().
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20210602083818.241793-7-thomas.hellstrom@linux.intel.com
The internal ttm_bo_util memcpy uses ioremap functionality, and while it
probably might be possible to use it for copying in- and out of
sglist represented io memory, using io_mem_reserve() / io_mem_free()
callbacks, that would cause problems with fault().
Instead, implement a method mapping page-by-page using kmap_local()
semantics. As an additional benefit we then avoid the occasional global
TLB flushes of ioremap() and consuming ioremap space, elimination of a
critical point of failure and with a slight change of semantics we could
also push the memcpy out async for testing and async driver development
purposes.
A special linear iomem iterator is introduced internally to mimic the
old ioremap behaviour for code-paths that can't immediately be ported
over. This adds to the code size and should be considered a temporary
solution.
Looking at the code we have a lot of checks for iomap tagged pointers.
Ideally we should extend the core memremap functions to also accept
uncached memory and kmap_local functionality. Then we could strip a
lot of code.
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20210602083818.241793-4-thomas.hellstrom@linux.intel.com
Instead of both driver and TTM allocating memory finalize embedding the
ttm_resource object as base into the driver backends.
v2: fix typo in vmwgfx grid mgr and double init in amdgpu_vram_mgr.c
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210602100914.46246-10-christian.koenig@amd.com
When we want to decouble resource management from buffer management we need to
be able to handle resources separately.
Add a resource pointer and rename bo->mem so that all code needs to
change to access the pointer instead.
No functional change.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210430092508.60710-4-christian.koenig@amd.com
On device removal reroute all CPU mappings to dummy page.
v3:
Remove loop to find DRM file and instead access it
by vma->vm_file->private_data. Move dummy page installation
into a separate function.
v4:
Map the entire BOs VA space into on demand allocated dummy page
on the first fault for that BO.
v5: Remove duplicate return.
v6: Polish ttm_bo_vm_dummy_page, remove superfluous code.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210512142648.666476-2-andrey.grodzovsky@amd.com
msm-next pull request has a baseline with stuff from -fixes, roll
forward first.
Some simple conflicts in amdgpu, ttm and one in i915 where git gets
confused and tries to add the same function twice.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The shrinker based approach still has some flaws. Especially that we need
temporary pages to free up the pages allocated to the driver is problematic
in a shrinker.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324134845.2338-1-christian.koenig@amd.com
Instead of having a global lock for potentially less contention.
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/424010/
Instead evict round robin from each devices SYSTEM and TT domain.
v2: reorder num_pages access reported by Dan's script
v3: fix rebase fallout, num_pages should be 32bit
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/424009/
Move the iteration of the global lru into the new function
ttm_global_swapout() and use that instead in drivers.
v2: consistently return int
v3: fix build fail
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/424008/
This is just another feature which is only used by VMWGFX, so move
it into the driver instead.
I've tried to add the accounting sysfs file to the kobject of the drm
minor, but I'm not 100% sure if this works as expected.
v2: fix typo in KFD and avoid 64bit divide
v3: fix init order in VMWGFX
v4: use pdev sysfs reference instead of drm
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Zack Rusin <zackr@vmware.com> (v3)
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210208133226.36955-2-christian.koenig@amd.com
TTM implements a rather extensive accounting of allocated memory.
There are two reasons for this:
1. It tries to block userspace allocating a huge number of very small
BOs without accounting for the kmalloced memory.
2. Make sure we don't over allocate and run into an OOM situation
during swapout while trying to handle the memory shortage.
This is only partially a good idea. First of all it is perfectly
valid for an application to use all of system memory, limiting it to
50% is not really acceptable.
What we need to take care of is that the application is held
accountable for the memory it allocated. This is what control
mechanisms like memcg and the normal Linux page accounting already do.
Making sure that we don't run into an OOM situation while trying to
cope with a memory shortage is still a good idea, but this is also
not very well implemented since it means another opportunity of
recursion from the driver back into TTM.
So start to rework all of this by implementing a shrinker callback which
allows for TT object to be swapped out if necessary.
v2: Switch from limit to shrinker callback.
v3: fix gfp mask handling, use atomic for swapable_pages, add debugfs
v4: drop the extra gfp_mask checks
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210208133226.36955-1-christian.koenig@amd.com
Rename ttm_bo_device to ttm_device.
Rename ttm_bo_driver to ttm_device_funcs.
Rename ttm_bo_global to ttm_global.
Move global and device related functions to ttm_device.[ch].
No functional change.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/415222/
ttm_resource_manager->use_type is only used for runtime changes by
vmwgfx. I think ideally we'd push this functionality into drivers -
ttm itself does not provide any locking to guarantee this is safe, so
the only way this can work at runtime is if the driver does provide
additional guarantees. vwmgfx does that through the
vmw_private->reservation_sem. Therefore supporting this feature in
shared code feels a bit misplaced.
As a first step add a WARN_ON to make sure the resource manager is
empty. This is just to make sure I actually understand correctly what
vmwgfx is doing, and to make sure an eventual subsequent refactor
doesn't break anything.
This check should also be useful for other drivers, to make sure they
haven't leaked anything.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201211162942.3399050-3-daniel.vetter@ffwll.ch
We only completely delete the BO from the LRU on destruction.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Link: https://patchwork.freedesktop.org/patch/404618/
Based on an idea from Dave, but cleaned up a bit.
We had multiple fields for essentially the same thing.
Now bo->base.size is the original size of the BO in
arbitrary units, usually bytes.
bo->mem.num_pages is the size in number of pages in the
resource domain of bo->mem.mem_type.
v2: use the GEM object size instead of the BO size
v3: fix printks in some places
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com> (v1)
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/406831/
ttm_module.h deals with internals of TTM and should never
be include outside of it.
v2: also move the file around
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/404885/
Not technically a problem for ttm, but very likely a driver bug and
pretty big time confusing for reviewing code.
So warn about it, both at cleanup time (so we catch these for sure)
and at pin/unpin time (so we know who's the culprit).
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201028113120.3641237-1-daniel.vetter@ffwll.ch
Currently drivers get called to move a buffer, but if they have to
move it temporarily through another space (SYSTEM->VRAM via TT)
then they can end up with a lot of ttm->driver->ttm call stacks,
if the temprorary space moves requires eviction.
Instead of letting the driver do all the placement/space for the
temporary, allow it to report back (-EMULTIHOP) and a placement (hop)
to the move code, which will then do the temporary move, and the
correct placement move afterwards.
This removes a lot of code from drivers, at the expense of
adding some midlayering. I've some further ideas on how to turn
it inside out, but I think this is a good solution to the call
stack problems.
v2: separate out the driver patches, add WARN for getting
MULTHOP in paths we shouldn't (Daniel)
v3: use memset (Christian)
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: hristian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201109005432.861936-2-airlied@gmail.com
The new functions ttm_bo_{vmap,vunmap}() map and unmap a TTM BO in kernel
address space. The mapping's address is returned as struct dma_buf_map.
Each function is a simplified version of TTM's existing kmap code. Both
functions respect the memory's location ani/or writecombine flags.
On top TTM's functions, GEM TTM helpers got drm_gem_ttm_{vmap,vunmap}(),
two helpers that convert a GEM object into the TTM BO and forward the call
to TTM's vmap/vunmap. These helpers can be dropped into the rsp GEM object
callbacks.
v5:
* use size_t for storing mapping size (Christian)
* ignore premapped memory areas correctly in ttm_bo_vunmap()
* rebase onto latest TTM interfaces (Christian)
* remove BUG() from ttm_bo_vmap() (Christian)
v4:
* drop ttm_kmap_obj_to_dma_buf() in favor of vmap helpers (Daniel,
Christian)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20201103093015.1063-6-tzimmermann@suse.de
The ttm_operation_ctx structure has a mixture of flags and bools. Drop the
flags and replace them with bools as well.
v2: fix typos, improve comments
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/398686/
During eviction we do want to trigger the OOM killer.
Only while doing new allocations we should try to avoid that and
return -ENOMEM to the application.
v2: rename the flag to gfp_retry_mayfail.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/398685/
Not used any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@amd.com>
Tested-by: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.freedesktop.org/patch/397087/?series=83051&rev=1
Provide the necessary parameters by all drivers and use the new pool alloc
when no driver specific function is provided.
v2: fix the GEM VRAM helpers
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@amd.com>
Tested-by: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.freedesktop.org/patch/397081/?series=83051&rev=1
This replaces the spaghetti code in the two existing page pools.
First of all depending on the allocation size it is between 3 (1GiB) and
5 (1MiB) times faster than the old implementation.
It makes better use of buddy pages to allow for larger physical contiguous
allocations which should result in better TLB utilization at least for
amdgpu.
Instead of a completely braindead approach of filling the pool with one
CPU while another one is trying to shrink it we only give back freed
pages.
This also results in much less locking contention and a trylock free MM
shrinker callback, so we can guarantee that pages are given back to the
system when needed.
Downside of this is that it takes longer for many small allocations until
the pool is filled up. We could address this, but I couldn't find an use
case where this actually matters. We also don't bother freeing large
chunks of pages any more since the CPU overhead in that path isn't really
that important.
The sysfs files are replaced with a single module parameter, allowing
users to override how many pages should be globally pooled in TTM. This
unfortunately breaks the UAPI slightly, but as far as we know nobody ever
depended on this.
Zeroing memory coming from the pool was handled inconsistently. The
alloc_pages() based pool was zeroing it, the dma_alloc_attr() based one
wasn't. For now the new implementation isn't zeroing pages from the pool
either and only sets the __GFP_ZERO flag when necessary.
The implementation has only 768 lines of code compared to the over 2600
of the old one, and also allows for saving quite a bunch of code in the
drivers since we don't need specialized handling there any more based on
kernel config.
Additional to all of that there was a neat bug with IOMMU, coherent DMA
mappings and huge pages which is now fixed in the new code as well.
v2: make ttm_pool_apply_caching static as reported by the kernel bot, add
some more checks
v3: fix some more checkpatch.pl warnings
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@amd.com>
Tested-by: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.freedesktop.org/patch/397080/?series=83051&rev=1
It makes no difference to kmalloc if the structure
is 48 or 64 bytes in size.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/396950/
We can still allocate 16TiB with that.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/396946/
Neither page allocation backend nor the driver should mess with that.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@amd.com>
Link: https://patchwork.freedesktop.org/patch/396948/
The move notify callback is only used in one place, this should
be removed in the future, but for now just rename it to the use
case which is to notify the driver that the GPU memory is to be
deleted.
Drivers can be cleaned up after this separately.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201021044031.1752624-2-airlied@gmail.com
This moves the to system move into the drivers, and moves all
the unbinds in the move path under driver control
Note: radeon/nouveau already wait so don't duplicate it.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201020010319.1692445-4-airlied@gmail.com
Changing the caching on the fly never really worked
flawlessly.
So stop this completely and just let drivers specific the
desired caching in the tt or bus object.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/394256/
Instead of the placement flags use the caching of the bus
mapping or tt object for the page protection flags.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/394255/
And implement setting it up correctly in the drivers.
This allows getting rid of the placement flags for this.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/394254/
All drivers can determine the tt caching state at creation time,
no need to do this on the fly during every validation.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/394253/
Thomas Hellström