On 2018/8/9 19:06, Robin Murphy wrote:
> On 06/08/18 13:27, Zhen Lei wrote:
>> Dynamically choose strict or non-strict mode for page table config based
>> on the iommu domain type.
>>
>> Signed-off-by: Zhen Lei <thunder.leiz...@huawei.com>
>> ---
>> drivers/iommu/arm-smmu-v3.c | 7 ++++++-
>> 1 file changed, 6 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
>> index 2f1304b..904bc1e 100644
>> --- a/drivers/iommu/arm-smmu-v3.c
>> +++ b/drivers/iommu/arm-smmu-v3.c
>> @@ -1622,6 +1622,11 @@ static int arm_smmu_domain_finalise(struct
>> iommu_domain *domain)
>> if (smmu->features & ARM_SMMU_FEAT_COHERENCY)
>> pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
>>
>> + if (domain->type == IOMMU_DOMAIN_DMA) {
>> + domain->non_strict = 1;
>> + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
>> + }
>> +
>> pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
>> if (!pgtbl_ops)
>> return -ENOMEM;
>> @@ -1782,7 +1787,7 @@ static void arm_smmu_iotlb_sync(struct iommu_domain
>> *domain)
>> {
>> struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
>>
>> - if (smmu)
>> + if (smmu && !domain->non_strict)
>
> That doesn't smell right - even in non-strict domains we still need stuff
> like walk cache invalidations for non-leaf unmaps to be synchronous, so we
> can't just ignore all sync operations at the driver level. I think the right
> thing to do to elide the "normal" sync on unmap is to first convert
> __iommu_dma_unmap to use iommu_unmap_fast()/iommu_tlb_sync(), then make it
> not issue that sync at all for non-strict domains.
OK, I will try it.
>
> Robin.
>
>> __arm_smmu_tlb_sync(smmu);
>> }
>>
>> --
>> 1.8.3
>>
>>
>
> .
>
--
Thanks!
BestRegards
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu