Re: [PATCH 18/19] iommu/arm-smmu: add a way for implementations to influence SCTLR

2020-09-01 Thread Bjorn Andersson
On Thu 13 Aug 21:41 CDT 2020, Rob Clark wrote: > From: Rob Clark > > For the Adreno GPU's SMMU, we want SCTLR.HUPCF set to ensure that > pending translations are not terminated on iova fault. Otherwise > a terminated CP read could hang the GPU by returning invalid > command-stream data. >

[PATCH 18/19] iommu/arm-smmu: add a way for implementations to influence SCTLR

2020-08-13 Thread Rob Clark
From: Rob Clark For the Adreno GPU's SMMU, we want SCTLR.HUPCF set to ensure that pending translations are not terminated on iova fault. Otherwise a terminated CP read could hang the GPU by returning invalid command-stream data. Signed-off-by: Rob Clark ---