[PATCH v2 0/7] Pagefault refactor

[Matthew Brost <matthew.brost@intel.com>]

We likely need multiple page fault producers feeding into a common
consumer backend. Additionally, our current page fault work queue
design—being per-GT rather than per-device—makes little sense. Clean up
pagefault handling with clear layers.

Matt

Matthew Brost (7):
  drm/xe: Stub out new pagefault layer
  drm/xe: Implement xe_pagefault_init
  drm/xe: Implement xe_pagefault_reset
  drm/xe: Implement xe_pagefault_handler
  drm/xe: Implement xe_pagefault_queue_work
  drm/xe: Add xe_guc_pagefault layer
  drm/xe: Remove unused GT page fault code

 drivers/gpu/drm/xe/Makefile             |   3 +-
 drivers/gpu/drm/xe/xe_device.c          |   5 +
 drivers/gpu/drm/xe/xe_device_types.h    |  11 +
 drivers/gpu/drm/xe/xe_gt.c              |   8 +-
 drivers/gpu/drm/xe/xe_gt_pagefault.c    | 679 ------------------------
 drivers/gpu/drm/xe/xe_gt_pagefault.h    |  19 -
 drivers/gpu/drm/xe/xe_gt_types.h        |  65 ---
 drivers/gpu/drm/xe/xe_guc_ct.c          |   6 +-
 drivers/gpu/drm/xe/xe_guc_pagefault.c   |  95 ++++
 drivers/gpu/drm/xe/xe_guc_pagefault.h   |  15 +
 drivers/gpu/drm/xe/xe_pagefault.c       | 436 +++++++++++++++
 drivers/gpu/drm/xe/xe_pagefault.h       |  19 +
 drivers/gpu/drm/xe/xe_pagefault_types.h | 136 +++++
 drivers/gpu/drm/xe/xe_svm.c             |   3 +-
 drivers/gpu/drm/xe/xe_vm.c              |   1 -
 15 files changed, 723 insertions(+), 778 deletions(-)
 delete mode 100644 drivers/gpu/drm/xe/xe_gt_pagefault.c
 delete mode 100644 drivers/gpu/drm/xe/xe_gt_pagefault.h
 create mode 100644 drivers/gpu/drm/xe/xe_guc_pagefault.c
 create mode 100644 drivers/gpu/drm/xe/xe_guc_pagefault.h
 create mode 100644 drivers/gpu/drm/xe/xe_pagefault.c
 create mode 100644 drivers/gpu/drm/xe/xe_pagefault.h
 create mode 100644 drivers/gpu/drm/xe/xe_pagefault_types.h

-- 
2.34.1