iommu_gas: Perform a synchronous invalidation when not freeing the entry in dmar_qi_task()

[alc]

Summary

Previously, when the caller to iommu_domain_unload_entry() passed the value "true" for the parameter "free", there was no guarantee that the invalidation was complete, in other words, dmar_qi_task() was done with the entry, before the caller finally freed the entry.

[kib]

I think we need to force entry through the qi. From the Intel® Virtualization Technology for Directed I/O Architecture Specification, Rev. 4.0, Order Number: D51397-015

6.5.1 Register-based Invalidation Interface

Register-based invalidation has the following limitations:
• Register-based invalidation can be used only when queued-invalidations are not enabled.

I remember that the requirement was there from the start.

[alc]

In D35878#814735, @kib wrote:

I think we need to force entry through the qi. From the Intel® Virtualization Technology for Directed I/O Architecture Specification, Rev. 4.0, Order Number: D51397-015

6.5.1 Register-based Invalidation Interface

Register-based invalidation has the following limitations:
• Register-based invalidation can be used only when queued-invalidations are not enabled.

I remember that the requirement was there from the start.

I was afraid of that.

[alc]

Redo using the queued invalidation mechanism.

[alc]

Fix arm64. I previously added the new parameter to the wrong function.