Re: [Freedreno] [PATCH 00/11] drm/msm: A5XX preemption

2017-02-06 Thread Alex Deucher
On Mon, Feb 6, 2017 at 12:59 PM, Daniel Vetter  wrote:
> On Mon, Feb 06, 2017 at 10:39:28AM -0700, Jordan Crouse wrote:
>> This series of patches implements multiple ringbuffers and preemption for 
>> Adreno
>> A5XX targets. Preemption allows a command to be interrupted at specific
>> preemption points and execution switched to a different ringbuffer.
>>
>> The software alogrithm uses preemption to enforce quality of service for
>> priority levels - commands to a certain ring preempt the rings of lower
>> priority. Note that priority is a software construct; the driver chooses a 
>> ring
>> to switch to and the hardware executes. This is important because it shows 
>> that
>> preemption can be used for things other than priority (timeslices for 
>> quality of
>> service for example).
>>
>> This initial series implements 4 ringbuffers to give sufficient coverage for 
>> the
>> range of priority levels requested by the GLES and compute extensions. The
>> targeted ringbuffer is specified in the command submission flags. The default
>> ring is 0 (lowest priority).
>
> Link to userspace part that implements these extensions? Also which
> gles/compute extensions are you talking about? Asking not just because of
> the open source userspace requirement, but also because we want to
> upstream a scheduler on the i915 side. Getting alignment on that across
> drm drivers would be sweet.

FWIW, we have had a GPU scheduler in amdgpu for several years now.  We
purposely tried to keep it largely separate from our driver so others
could leverage it if they wanted to.  See
drivers/gpu/drm/amd/scheduler in the kernel.

Alex

>
> Adding intel-gfx, I'll poke the folks working on this too.
> -Daniel
>
>>
>> Jordan
>>
>> Jordan Crouse (11):
>>   drm/msm: Make sure to detach the MMU during GPU cleanup
>>   drm/msm: Improve the zap shader
>>   drm/msm: Add hint to DRM_IOCTL_MSM_GEM_INFO to return an object IOVA
>>   drm/msm: Remove idle function hook
>>   drm/msm: get an iova from the address space instead of an id
>>   drm/msm: Add a struct to pass configuration to msm_gpu_init()
>>   drm/msm: Remove memptrs->wptr
>>   drm/msm: Support multiple ringbuffers
>>   drm/msm: Shadow current pointer in the ring until command is complete
>>   drm/msm: Make the value of RB_CNTL (almost) generic
>>   drm/msm: Implement preemption for A5XX targets
>>
>>  drivers/gpu/drm/msm/Makefile  |   1 +
>>  drivers/gpu/drm/msm/adreno/a3xx_gpu.c |  13 +-
>>  drivers/gpu/drm/msm/adreno/a4xx_gpu.c |  13 +-
>>  drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 278 +-
>>  drivers/gpu/drm/msm/adreno/a5xx_gpu.h | 106 +
>>  drivers/gpu/drm/msm/adreno/a5xx_power.c   |  11 +-
>>  drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 367 
>> ++
>>  drivers/gpu/drm/msm/adreno/adreno_gpu.c   | 215 +++--
>>  drivers/gpu/drm/msm/adreno/adreno_gpu.h   |  42 ++--
>>  drivers/gpu/drm/msm/dsi/dsi_host.c|  15 +-
>>  drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c  |   8 +-
>>  drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c   |  18 +-
>>  drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h   |   3 -
>>  drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c |  13 +-
>>  drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c  |   5 +-
>>  drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c   |  11 +-
>>  drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h   |   4 -
>>  drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c |  13 +-
>>  drivers/gpu/drm/msm/msm_drv.c |  43 ++--
>>  drivers/gpu/drm/msm/msm_drv.h |  27 ++-
>>  drivers/gpu/drm/msm/msm_fb.c  |  15 +-
>>  drivers/gpu/drm/msm/msm_fbdev.c   |  10 +-
>>  drivers/gpu/drm/msm/msm_fence.c   |  85 +--
>>  drivers/gpu/drm/msm/msm_fence.h   |  13 +-
>>  drivers/gpu/drm/msm/msm_gem.c | 124 +++---
>>  drivers/gpu/drm/msm/msm_gem.h |   5 +-
>>  drivers/gpu/drm/msm/msm_gem_submit.c  |  14 +-
>>  drivers/gpu/drm/msm/msm_gpu.c | 140 +++-
>>  drivers/gpu/drm/msm/msm_gpu.h |  54 -
>>  drivers/gpu/drm/msm/msm_kms.h |   3 +
>>  drivers/gpu/drm/msm/msm_ringbuffer.c  |  14 +-
>>  drivers/gpu/drm/msm/msm_ringbuffer.h  |  21 +-
>>  include/uapi/drm/msm_drm.h|   9 +-
>>  33 files changed, 1324 insertions(+), 389 deletions(-)
>>  create mode 100644 drivers/gpu/drm/msm/adreno/a5xx_preempt.c
>>
>> --
>> 1.9.1
>>
>> ___
>> dri-devel mailing list
>> dri-de...@lists.freedesktop.org
>> https://lists.freedesktop.org/mailman/listinfo/dri-devel
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch
> ___
> dri-devel mailing list
> dri-de...@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
___
Freedreno mailing list
Freedreno@lists.freedesktop.org

Re: [Freedreno] [PATCH 00/11] drm/msm: A5XX preemption

2017-02-06 Thread Daniel Stone
Hi,

On 6 February 2017 at 17:59, Daniel Vetter  wrote:
> On Mon, Feb 06, 2017 at 10:39:28AM -0700, Jordan Crouse wrote:
>> This initial series implements 4 ringbuffers to give sufficient coverage for 
>> the
>> range of priority levels requested by the GLES and compute extensions. The
>> targeted ringbuffer is specified in the command submission flags. The default
>> ring is 0 (lowest priority).
>
> Link to userspace part that implements these extensions? Also which
> gles/compute extensions are you talking about? Asking not just because of
> the open source userspace requirement, but also because we want to
> upstream a scheduler on the i915 side. Getting alignment on that across
> drm drivers would be sweet.

Assuming he meant EGL rather than GLES, this is the usual one:
https://www.khronos.org/registry/EGL/extensions/IMG/EGL_IMG_context_priority.txt

Cheers,
Daniel
___
Freedreno mailing list
Freedreno@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/freedreno