Added a check such that only singleton IOMMU groups can pin pages. >From the point when vendor driver pins any pages, consider IOMMU group dirty page scope to be limited to pinned pages. To optimize to avoid walking list often, added flag pinned_page_dirty_scope to indicate if all of the vfio_groups for each vfio_domain in the domain_list dirty page scope is limited to pinned pages. This flag is updated on first pinned pages request for that IOMMU group and on attaching/detaching group.
Showing the changes to include/linux (1 of 3 files). Show all
Unified · Split
| @@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops { · 75 unmodified lines | |||
| 76 | struct iommu_group *group); | 76 | struct iommu_group *group); |
| 77 | void (*detach_group)(void *iommu_data, | 77 | void (*detach_group)(void *iommu_data, |
| 78 | struct iommu_group *group); | 78 | struct iommu_group *group); |
| 79 | int (*pin_pages)(void *iommu_data, unsigned long *user_pfn, | 79 | int (*pin_pages)(void *iommu_data, |
| 80 | struct iommu_group *group, | ||
| 81 | unsigned long *user_pfn, | ||
| 80 | int npage, int prot, | 82 | int npage, int prot, |
| 81 | unsigned long *phys_pfn); | 83 | unsigned long *phys_pfn); |
| 82 | int (*unpin_pages)(void *iommu_data, | 84 | int (*unpin_pages)(void *iommu_data, |