Re: [PATCH] iommu/arm-smmu: avoid pathological RPM behaviour for unmaps

2019-11-01 Thread Will Deacon
On Thu, Oct 31, 2019 at 02:31:02PM -0700, Rob Clark wrote: > From: Rob Clark > > When games, browser, or anything using a lot of GPU buffers exits, there > can be many hundreds or thousands of buffers to unmap and free. If the > GPU is otherwise suspended, this can cause arm-smmu to

[PATCH] iommu/arm-smmu: avoid pathological RPM behaviour for unmaps

2019-10-31 Thread Rob Clark
From: Rob Clark When games, browser, or anything using a lot of GPU buffers exits, there can be many hundreds or thousands of buffers to unmap and free. If the GPU is otherwise suspended, this can cause arm-smmu to resume/suspend for each buffer, resulting 5-10 seconds worth of reprogramming