[v5,0/4] rework bo mem stats tracking

Message

Yunxiang Li Oct. 18, 2024, 1:33 p.m. UTC

Right now every time the fdinfo is read, we go through the vm lists and
lock all the BOs to calcuate the statistics. This causes a lot of lock
contention when the VM is actively used. It gets worse if there is a lot
of shared BOs or if there's a lot of submissions. We have seen
submissions lock-up for seconds due to fdinfo for some workload.
Therefore, rework the implementation to track the BOs as they get moved
around.

Also the visible memory stat is removed to simplify implementation, it's
unclear how useful this stat is since kernel map/unmap BOs whenever it
wants to and on a modern system all of VRAM can be mapped if needed.

v5: rebase on top of the drm_print_memory_stats refactor

Yunxiang Li (4):
  drm/amdgpu: remove unused function parameter
  drm/amdgpu: make drm-memory-* report resident memory
  drm/amdgpu: stop tracking visible memory stats
  drm/amdgpu: track bo memory stats at runtime

 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c      |   4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c |  16 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c  |  24 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c     |   3 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c  |  94 +--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h  |  14 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c      | 208 +++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h      |  27 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c   |   1 +
 drivers/gpu/drm/drm_file.c                  |   8 +
 include/drm/drm_file.h                      |   1 +
 11 files changed, 241 insertions(+), 159 deletions(-)