linux-toradex.git/drivers/gpu/drm/msm/msm_gpu.h, branch v4.4.3

drm/msm: restart queued submits after hang

2015-06-11T17:11:06+00:00

Track the list of in-flight submits.  If the gpu hangs, retire up to an
including the offending submit, and then re-submit the remainder.  This
way, for concurrently running piglit tests (for example), one failing
test doesn't cause unrelated tests to fail simply because it's submit
was queued up after one that triggered a hang.

Signed-off-by: Rob Clark

drm/msm: adreno a306 support

2015-06-11T17:11:01+00:00

As found in apq8016 (used in DragonBoard 410c) and msm8916.

Note that numerically a306 is actually 307 (since a305c already claimed
306).  Nice and confusing.

Signed-off-by: Rob Clark

drm/msm: clarify downstream bus scaling

2015-06-11T17:11:01+00:00

A few spots in the driver have support for downstream android
CONFIG_MSM_BUS_SCALING.  This is mainly to simplify backporting the
driver for various devices which do not have sufficient upstream
kernel support.  But the intentionally dead code seems to cause
some confusion.  Rename the #define to make this more clear.

Signed-off-by: Rob Clark

drm/msm/adreno: move decision about what gpu to to load

2014-09-10T15:19:08+00:00

Move this into into adreno_device, and decide based on gpu revision
rather than just assuming a3xx.

Signed-off-by: Rob Clark

drm/msm/adreno: split adreno device out into it's own file

2014-09-10T15:19:08+00:00

We'd rather not duplicate these parts as support for additional gpu
generations is added.

Signed-off-by: Rob Clark

drm/msm: add perf logging debugfs

2014-06-02T11:36:21+00:00

Signed-off-by: Rob Clark

drm/msm: crank down gpu when inactive

2014-03-31T14:27:46+00:00

Shut down the clks when the gpu has nothing to do.  A short inactivity
timer is used to provide a low pass filter for power transitions.

Signed-off-by: Rob Clark

drm/msm: add support for non-IOMMU systems

2014-01-09T19:38:58+00:00

Add a VRAM carveout that is used for systems which do not have an IOMMU.

The VRAM carveout uses CMA.  The arch code must setup a CMA pool for the
device (preferrably in highmem.. a 256m-512m VRAM pool in lowmem is not
cool).  The user can configure the VRAM pool size using msm.vram module
param.

Technically, the abstraction of IOMMU behind msm_mmu is not strictly
needed, but it simplifies the GEM code a bit, and will be useful later
when I add support for a2xx devices with GPUMMU, so I decided to keep
this part.

It appears to be possible to configure the GPU to restrict access to
addresses within the VRAM pool, but this is not done yet.  So for now
the GPU will refuse to load if there is no sort of mmu.  Once address
based limits are supported and tested to confirm that we aren't giving
the GPU access to arbitrary memory, this restriction can be lifted

Signed-off-by: Rob Clark

drm/msm: fix bus scaling

2014-01-09T19:38:58+00:00

This got a bit broken with original patches when re-arranging things to
move dependencies on mach-msm inside #ifndef OF.

Signed-off-by: Rob Clark

drm/msm: add basic hangcheck/recovery mechanism

2013-08-24T18:57:19+00:00

A basic, no-frills recovery mechanism in case the gpu gets wedged.  We
could try to be a bit more fancy and restart the next submit after the
one that got wedged, but for now keep it simple.  This is enough to
recover things if, for example, the gpu hangs mid way through a piglit
run.

Signed-off-by: Rob Clark