On 12/28/2023 4:10 PM, Tian, Kevin wrote:
From: Ethan Zhao <haifeng.zhao@xxxxxxxxxxxxxxx>
Sent: Thursday, December 28, 2023 8:17 AM
@@ -181,6 +181,7 @@ static void __flush_svm_range_dev(struct intel_svm
*svm,
qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages,
ih);
if (info->ats_enabled) {
+ info->iommu->flush_target_dev = info->dev;
qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info-
pfsid,
svm->pasid, sdev->qdep, address,
order_base_2(pages));
this is wrong both in concept and function.
Yes, wrong.
an iommu instance can be shared by many devices which may all have
ongoing ATS invalidation requests to handle. Using a per-iommu field
to store the flush target is limiting (and there is no lock protection at all).
if there is a real need of passing dev pointer to qi helpers, just change
the helper to accept an explicit parameter.
seems the only way is to add parameter and refactor all affected
functions.
Thanks,
Ethan
