From 4ba7d17f2b3b60556e8e5832b55064d6bc800f0c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 10 Jan 2023 17:44:27 +0100 Subject: vfio/type1: Respect IOMMU reserved regions in vfio_test_domain_fgsp() [ Upstream commit 895c0747f726bb50c9b7a805613a61d1b6f9fa06 ] Since commit cbf7827bc5dc ("iommu/s390: Fix potential s390_domain aperture shrinking") the s390 IOMMU driver uses reserved regions for the system provided DMA ranges of PCI devices. Previously it reduced the size of the IOMMU aperture and checked it on each mapping operation. On current machines the system denies use of DMA addresses below 2^32 for all PCI devices. Usually mapping IOVAs in a reserved regions is harmless until a DMA actually tries to utilize the mapping. However on s390 there is a virtual PCI device called ISM which is implemented in firmware and used for cross LPAR communication. Unlike real PCI devices this device does not use the hardware IOMMU but inspects IOMMU translation tables directly on IOTLB flush (s390 RPCIT instruction). If it detects IOVA mappings outside the allowed ranges it goes into an error state. This error state then causes the device to be unavailable to the 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, is PAGE_SIZE * 2 aligned. If found use that for testing for fine grained super pages. Fixes: af029169b8fd ("vfio/type1: Check reserved region conflict and update iova list") Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230110164427.4051938-2-schnelle@linux.ibm.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/vfio_iommu_type1.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) (limited to 'drivers/vfio') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 23c24fe98c00..2209372f236d 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1856,24 +1856,33 @@ unwind: * 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; + dma_addr_t start; 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) { + start = ALIGN(region->start, PAGE_SIZE * 2); + if (start >= region->end || (region->end - 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, start, page_to_phys(pages), PAGE_SIZE * 2, + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + if (!ret) { + size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE); + + if (unmapped == PAGE_SIZE) + iommu_unmap(domain->domain, start + PAGE_SIZE, PAGE_SIZE); + else + domain->fgsp = true; + } + break; } __free_pages(pages, order); @@ -2326,7 +2335,7 @@ 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); -- cgit v1.2.3