drm/panfrost: Remove commented out call to panfrost_core_dump

panfrost_core_dump() has never existed in mainline, so remove it and add
a TODO entry that core dump support is currently lacking.

Sign

drm/panfrost: Remove commented out call to panfrost_core_dump

panfrost_core_dump() has never existed in mainline, so remove it and add
a TODO entry that core dump support is currently lacking.

Signed-off-by: Steven Price <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/panfrost: Implement per FD address spaces

Up until now, a single shared GPU address space was used. This is not
ideal as there's no protection between processes and doesn't work for
supporting t

drm/panfrost: Implement per FD address spaces

Up until now, a single shared GPU address space was used. This is not
ideal as there's no protection between processes and doesn't work for
supporting the same GPU/CPU VA feature. Most importantly, this will
hopefully mitigate Alyssa's fear of WebGL, whatever that is.

Most of the changes here are moving struct drm_mm and struct
panfrost_mmu objects from the per device struct to the per FD struct.
The critical function is panfrost_mmu_as_get() which handles allocating
and switching the h/w address spaces.

There's 3 states an AS can be in: free, allocated, and in use. When a
job runs, it requests an address space and then marks it not in use when
job is complete(but stays assigned). The first time thru, we find a free
AS in the alloc_mask and assign the AS to the FD. Then the next time
thru, we most likely already have our AS and we just mark it in use with
a ref count. We need a ref count because we have multiple job slots. If
the job/FD doesn't have an AS assigned and there are no free ones, then
we pick an allocated one not in use from our LRU list and switch the AS
from the old FD to the new one.

Cc: Tomeu Vizoso <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Robin Murphy <[email protected]>
Cc: Steven Price <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Acked-by: Alyssa Rosenzweig <[email protected]>
Reviewed-by: Steven Price <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/panfrost: Add support for GPU heap allocations

The midgard/bifrost GPUs need to allocate GPU heap memory which is
allocated on GPU page faults and not pinned in memory. The vendor driver
calls t

drm/panfrost: Add support for GPU heap allocations

The midgard/bifrost GPUs need to allocate GPU heap memory which is
allocated on GPU page faults and not pinned in memory. The vendor driver
calls this functionality GROW_ON_GPF.

This implementation assumes that BOs allocated with the
PANFROST_BO_NOEXEC flag are never mmapped or exported. Both of those may
actually work, but I'm unsure if there's some interaction there. It
would cause the whole object to be pinned in memory which would defeat
the point of this.

On faults, we map in 2MB at a time in order to utilize huge pages (if
enabled). Currently, once we've mapped pages in, they are only unmapped
if the BO is freed. Once we add shrinker support, we can unmap pages
with the shrinker.

Cc: Tomeu Vizoso <[email protected]>
Cc: Boris Brezillon <[email protected]>
Cc: Robin Murphy <[email protected]>
Acked-by: Alyssa Rosenzweig <[email protected]>
Reviewed-by: Steven Price <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/panfrost: Add madvise and shrinker support

Add support for madvise and a shrinker similar to other drivers. This
allows userspace to mark BOs which can be freed when there is memory
pressure.

U

drm/panfrost: Add madvise and shrinker support

Add support for madvise and a shrinker similar to other drivers. This
allows userspace to mark BOs which can be freed when there is memory
pressure.

Unlike other implementations, we don't depend on struct_mutex. The
driver maintains a list of BOs which can be freed when the shrinker
is called. Access to the list is serialized with the shrinker_lock.

Cc: Tomeu Vizoso <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Daniel Vetter <[email protected]>
Acked-by: Alyssa Rosenzweig <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/panfrost: Remove completed features still in TODO

There's a few features the driver supports which we forgot to remove, so
remove them now.

Cc: Tomeu Vizoso <[email protected]>
Signed-

drm/panfrost: Remove completed features still in TODO

There's a few features the driver supports which we forgot to remove, so
remove them now.

Cc: Tomeu Vizoso <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Reviewed-by: Boris Brezillon <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/panfrost: Add initial panfrost driver

This adds the initial driver for panfrost which supports Arm Mali
Midgard and Bifrost family of GPUs. Currently, only the T860 and
T760 Midgard GPUs have be

drm/panfrost: Add initial panfrost driver

This adds the initial driver for panfrost which supports Arm Mali
Midgard and Bifrost family of GPUs. Currently, only the T860 and
T760 Midgard GPUs have been tested.

v2:
- Add GPU reset on job hangs (Tomeu)
- Add RuntimePM and devfreq support (Tomeu)
- Fix T760 support (Tomeu)
- Add a TODO file (Rob, Tomeu)
- Support multiple in fences (Tomeu)
- Drop support for shared fences (Tomeu)
- Fill in MMU de-init (Rob)
- Move register definitions back to single header (Rob)
- Clean-up hardcoded job submit todos (Rob)
- Implement feature setup based on features/issues (Rob)
- Add remaining Midgard DT compatible strings (Rob)

v3:
- Add support for reset lines (Neil)
- Add a MAINTAINERS entry (Rob)
- Call dma_set_mask_and_coherent (Rob)
- Do MMU invalidate on map and unmap. Restructure to do a single
operation per map/unmap call. (Rob)
- Add a missing explicit padding to struct drm_panfrost_create_bo (Rob)
- Fix 0-day error: "panfrost_devfreq.c:151:9-16: ERROR: PTR_ERR applied after initialization to constant on line 150"
- Drop HW_FEATURE_AARCH64_MMU conditional (Rob)
- s/DRM_PANFROST_PARAM_GPU_ID/DRM_PANFROST_PARAM_GPU_PROD_ID/ (Rob)
- Check drm_gem_shmem_prime_import_sg_table() error code (Rob)
- Re-order power on sequence (Rob)
- Move panfrost_acquire_object_fences() before scheduling job (Rob)
- Add NULL checks on array pointers in job clean-up (Rob)
- Rework devfreq (Tomeu)
- Fix devfreq init with no regulator (Rob)
- Various WS and comments clean-up (Rob)

Cc: Maarten Lankhorst <[email protected]>
Cc: Maxime Ripard <[email protected]>
Cc: Sean Paul <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Daniel Vetter <[email protected]>
Cc: Lyude Paul <[email protected]>
Reviewed-by: Alyssa Rosenzweig <[email protected]>
Reviewed-by: Eric Anholt <[email protected]>
Reviewed-by: Steven Price <[email protected]>
Signed-off-by: Marty E. Plummer <[email protected]>
Signed-off-by: Tomeu Vizoso <[email protected]>
Signed-off-by: Neil Armstrong <[email protected]>
Signed-off-by: Rob Herring <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...