Re: [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget

2024-05-15 Thread Tvrtko Ursulin
On 15/05/2024 15:31, Christian König wrote: Am 15.05.24 um 12:59 schrieb Tvrtko Ursulin: On 15/05/2024 08:20, Christian König wrote: Am 08.05.24 um 20:09 schrieb Tvrtko Ursulin: From: Tvrtko Ursulin Current code appears to live in a misconception that playing with buffer allowed and

Re: [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget

2024-05-15 Thread Christian König
Am 15.05.24 um 12:59 schrieb Tvrtko Ursulin: On 15/05/2024 08:20, Christian König wrote: Am 08.05.24 um 20:09 schrieb Tvrtko Ursulin: From: Tvrtko Ursulin Current code appears to live in a misconception that playing with buffer allowed and preferred placements can control the decision on

Re: [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget

2024-05-15 Thread Tvrtko Ursulin
On 15/05/2024 08:20, Christian König wrote: Am 08.05.24 um 20:09 schrieb Tvrtko Ursulin: From: Tvrtko Ursulin Current code appears to live in a misconception that playing with buffer allowed and preferred placements can control the decision on whether backing store migration will be

Re: [RFC 2/5] drm/amdgpu: Actually respect buffer migration budget

2024-05-15 Thread Christian König
Am 08.05.24 um 20:09 schrieb Tvrtko Ursulin: From: Tvrtko Ursulin Current code appears to live in a misconception that playing with buffer allowed and preferred placements can control the decision on whether backing store migration will be attempted or not. Both from code inspection and from

[RFC 2/5] drm/amdgpu: Actually respect buffer migration budget

2024-05-08 Thread Tvrtko Ursulin
From: Tvrtko Ursulin Current code appears to live in a misconception that playing with buffer allowed and preferred placements can control the decision on whether backing store migration will be attempted or not. Both from code inspection and from empirical experiments I see that not being