[RFC] vfio/type1: handle case where IOMMU does not support PAGE_SIZE size

[Eric Auger]

Current vfio_pgsize_bitmap code hides the supported IOMMU page
sizes smaller than PAGE_SIZE. As a result, in case the IOMMU
does not support PAGE_SIZE page, the alignment check on map/unmap
is done with larger page sizes, if any. This can fail although
mapping could be done with pages smaller than PAGE_SIZE.

vfio_pgsize_bitmap is modified to expose the IOMMU page sizes,
supported by all domains, even those smaller than PAGE_SIZE. The
alignment check on map is performed against PAGE_SIZE if the minimum
IOMMU size is less than PAGE_SIZE or against the min page size greater
than PAGE_SIZE.

Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>

---

This was tested on AMD Seattle with 64kB page host. ARM MMU 401
currently expose 4kB, 2MB and 1GB page support. With a 64kB page host,
the map/unmap check is done against 2MB. Some alignment check fail
so VFIO_IOMMU_MAP_DMA fail while we could map using 4kB IOMMU page
size.
---
 drivers/vfio/vfio_iommu_type1.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 57d8c37..13fb974 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -403,7 +403,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
 {
 	struct vfio_domain *domain;
-	unsigned long bitmap = PAGE_MASK;
+	unsigned long bitmap = ULONG_MAX;
 
 	mutex_lock(&iommu->lock);
 	list_for_each_entry(domain, &iommu->domain_list, next)
@@ -416,20 +416,18 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
 static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 			     struct vfio_iommu_type1_dma_unmap *unmap)
 {
-	uint64_t mask;
 	struct vfio_dma *dma;
 	size_t unmapped = 0;
 	int ret = 0;
+	unsigned int min_pagesz = __ffs(vfio_pgsize_bitmap(iommu));
+	unsigned int requested_alignment = (min_pagesz < PAGE_SIZE) ?
+						PAGE_SIZE : min_pagesz;
 
-	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
-
-	if (unmap->iova & mask)
+	if (!IS_ALIGNED(unmap->iova, requested_alignment))
 		return -EINVAL;
-	if (!unmap->size || unmap->size & mask)
+	if (!unmap->size || !IS_ALIGNED(unmap->size, requested_alignment))
 		return -EINVAL;
 
-	WARN_ON(mask & PAGE_MASK);
-
 	mutex_lock(&iommu->lock);
 
 	/*
@@ -553,25 +551,24 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	size_t size = map->size;
 	long npage;
 	int ret = 0, prot = 0;
-	uint64_t mask;
 	struct vfio_dma *dma;
 	unsigned long pfn;
+	unsigned int min_pagesz = __ffs(vfio_pgsize_bitmap(iommu));
+	unsigned int requested_alignment = (min_pagesz < PAGE_SIZE) ?
+						PAGE_SIZE : min_pagesz;
 
 	/* Verify that none of our __u64 fields overflow */
 	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
 		return -EINVAL;
 
-	mask = ((uint64_t)1 << __ffs(vfio_pgsize_bitmap(iommu))) - 1;
-
-	WARN_ON(mask & PAGE_MASK);
-
 	/* READ/WRITE from device perspective */
 	if (map->flags & VFIO_DMA_MAP_FLAG_WRITE)
 		prot |= IOMMU_WRITE;
 	if (map->flags & VFIO_DMA_MAP_FLAG_READ)
 		prot |= IOMMU_READ;
 
-	if (!prot || !size || (size | iova | vaddr) & mask)
+	if (!prot || !size ||
+		!IS_ALIGNED(size | iova | vaddr, requested_alignment))
 		return -EINVAL;
 
 	/* Don't allow IOVA or virtual address wrap */
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/