@@ -1856,24 +1856,31 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
* significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when
* hugetlbfs is in use.
*/
-static void vfio_test_domain_fgsp(struct vfio_domain *domain)
+static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *regions)
{
- struct page *pages;
int ret, order = get_order(PAGE_SIZE * 2);
+ struct vfio_iova *region;
+ struct page *pages;
pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!pages)
return;
- ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
- IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
- if (!ret) {
- size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
+ list_for_each_entry(region, regions, list) {
+ if (region->end - region->start < PAGE_SIZE * 2)
+ continue;
- if (unmapped == PAGE_SIZE)
- iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE);
- else
- domain->fgsp = true;
+ ret = iommu_map(domain->domain, region->start, page_to_phys(pages), PAGE_SIZE * 2,
+ IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+ if (!ret) {
+ size_t unmapped = iommu_unmap(domain->domain, region->start, PAGE_SIZE);
+
+ if (unmapped == PAGE_SIZE)
+ iommu_unmap(domain->domain, region->start + PAGE_SIZE, PAGE_SIZE);
+ else
+ domain->fgsp = true;
+ }
+ break;
}
__free_pages(pages, order);
@@ -2326,7 +2333,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
}
}
- vfio_test_domain_fgsp(domain);
+ vfio_test_domain_fgsp(domain, &iova_copy);
/* replay mappings on new domains */
ret = vfio_iommu_replay(iommu, domain);
Since commit cbf7827bc5dc ("iommu/s390: Fix potential s390_domain aperture shrinking") the s390 IOMMU driver uses a reserved region instead of an artificially shrunk aperture to restrict IOMMU use based on the system provided DMA ranges of devices. In particular on current machines this prevents use of DMA addresses below 2^32 for all devices. While usually just IOMMU mapping below these addresses is harmless. However our virtual ISM PCI device looks at new mappings on IOTLB flush and immediately goes into the error state if such a mapping violates its allowed DMA ranges. This then breaks pass-through of the ISM device to a KVM guest. Analysing this we found that vfio_test_domain_fgsp() maps 2 pages at DMA address 0 irrespective of the IOMMUs reserved regions. Even if usually harmless this seems wrong in the general case so instead go through the freshly updated IOVA list and try to find a range that isn't reserved and fits 2 pages and use that for testing for fine grained super pages. Fixes: 6fe1010d6d9c ("vfio/type1: DMA unmap chunking") Reported-by: Matthew Rosato <mjrosato@linux.ibm.com> Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com> --- - Testing: I tested this based on current master on both on s390 where it skips the reserved 0x0-0x100000000 range and on AMD Vi where it continues to do the test on DMA address 0 and sets domain->fgsp to true. drivers/vfio/vfio_iommu_type1.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-)