drm/ttm: moving the LRU into the resource

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

To: ray.huang@xxxxxxx, daniel@xxxxxxxx, thomas.hellstrom@xxxxxxxxxxxxxxx
Subject: drm/ttm: moving the LRU into the resource
From: "Christian König" <ckoenig.leichtzumerken@xxxxxxxxx>
Date: Wed, 9 Feb 2022 09:40:50 +0100
Cc: amd-gfx@xxxxxxxxxxxxxxxxxxxxx, dri-devel@xxxxxxxxxxxxxxxxxxxxx

Hi guys,

so hopefully the last round for this set.

It fixes both a long outstanding problem with TTM and resource
allocation as well as Bas's new performance problem with RADV.

Please review and comment.

Thanks,
Christian.

Follow-Ups:
- [PATCH 9/9] drm/ttm: rework bulk move handling v2
  - From: Christian König
- [PATCH 8/9] drm/ttm: allow bulk moves for all domains
  - From: Christian König
- [PATCH 7/9] drm/amdgpu: drop amdgpu_gtt_node v2
  - From: Christian König
- [PATCH 6/9] drm/amdgpu: remove VRAM accounting
  - From: Christian König
- [PATCH 4/9] drm/radeon: remove resource accounting
  - From: Christian König
- [PATCH 5/9] drm/amdgpu: remove GTT accounting
  - From: Christian König
- [PATCH 3/9] drm/ttm: add resource iterator v2
  - From: Christian König
- [PATCH 1/9] drm/ttm: add common accounting to the resource mgr v3
  - From: Christian König
- [PATCH 2/9] drm/ttm: move the LRU into resource handling v3
  - From: Christian König

Prev by Date: Re: [RFC v4 11/11] Revert 'drm/amdgpu: annotate a false positive recursive locking'
Next by Date: [PATCH 2/9] drm/ttm: move the LRU into resource handling v3
Previous by thread: [PATCH 01/11] drm/amdgpu: Optimize xxx_ras_late_init/xxx_ras_late_fini for each ras block
Next by thread: [PATCH 2/9] drm/ttm: move the LRU into resource handling v3
Index(es):
- Date
- Thread

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

Powered by Linux