[PATCH v4 00/10] AMDGPU usermode queues

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This patch series introduces AMDGPU usermode queues for gfx workloads.
Usermode queues is a method of GPU workload submission into the graphics
hardware without any interaction with kernel/DRM schedulers. In this
method, a userspace graphics application can create its own workqueue
and submit it directly in the GPU HW.

The general idea of how this is supposed to work:
- The application creates the following GPU objetcs:
  - A queue object to hold the workload packets.
  - A read pointer object.
  - A write pointer object.
  - A doorbell page.
  - Shadow bufffer pages.
- The application picks a 32-bit offset in the doorbell page for this
  queue.
- The application uses the usermode_queue_create IOCTL introduced in
  this patch, by passing the GPU addresses of these objects (read ptr,
  write ptr, queue base address and 32-bit doorbell offset from the
  doorbell page)
- The kernel creates the queue and maps it in the HW.
- The application can start submitting the data in the queue as soon as
  the kernel IOCTL returns.
- After filling the workload data in the queue, the app must write the
  number of dwords added in the queue into the doorbell offset, and the
  GPU will start fetching the data.

libDRM changes for this series and a sample DRM test program can be found
in the MESA merge request here:
https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/287

This patch series depends on the doorbell-manager changes, which are being
reviewed here:
https://patchwork.freedesktop.org/series/115802/

Alex Deucher (1):
  drm/amdgpu: UAPI for user queue management

Arvind Yadav (1):
  drm/amdgpu: set FW parameters in v11_struct

Shashank Sharma (8):
  drm/amdgpu: add usermode queue base code
  drm/amdgpu: add new IOCTL for usermode queue
  drm/amdgpu: create GFX-gen11 MQD for userqueue
  drm/amdgpu: create context space for usermode queue
  drm/amdgpu: map usermode queue into MES
  drm/amdgpu: map wptr BO into GART
  drm/amdgpu: generate doorbell index for userqueue
  drm/amdgpu: cleanup leftover queues

 drivers/gpu/drm/amd/amdgpu/Makefile           |   2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu.h           |  10 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c       |   2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c       |   6 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c | 333 ++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c        | 195 ++++++++++
 .../gpu/drm/amd/include/amdgpu_userqueue.h    |  66 ++++
 include/uapi/drm/amdgpu_drm.h                 |  95 +++++
 8 files changed, 708 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c
 create mode 100644 drivers/gpu/drm/amd/include/amdgpu_userqueue.h

-- 
2.40.0




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux