>> +static irqreturn_t nsmmu_context_fault_inst(int irq,
>> +struct arm_smmu_device *smmu,
>> +int idx, int inst);
>More of these signed integers that could be unsigned. Also why the need to
>predeclare this? Can you
>> +if (smmu->impl->global_fault)
>> +return smmu->impl->global_fault(irq, smmu);
>Can't we just register impl->global_fault (if set) instead of
>arm_smmu_global_fault as the handler when we first set up the IRQs in
>arm_smmu_device_probe()?
>Ideally we'd do the same for the cont
On 29/08/2019 23:47, Krishna Reddy wrote:
Add global/context fault hooks to allow Nvidia SMMU implementation
handle faults across multiple SMMUs.
Signed-off-by: Krishna Reddy
---
drivers/iommu/arm-smmu-nvidia.c | 127
drivers/iommu/arm-smmu.c|
On Thu, Aug 29, 2019 at 03:47:04PM -0700, Krishna Reddy wrote:
> Add global/context fault hooks to allow Nvidia SMMU implementation
> handle faults across multiple SMMUs.
>
> Signed-off-by: Krishna Reddy
> ---
> drivers/iommu/arm-smmu-nvidia.c | 127
>
>
Add global/context fault hooks to allow Nvidia SMMU implementation
handle faults across multiple SMMUs.
Signed-off-by: Krishna Reddy
---
drivers/iommu/arm-smmu-nvidia.c | 127
drivers/iommu/arm-smmu.c| 6 ++
drivers/iommu/arm-smmu.h| 4