Re: [PATCH] vfio: selftests: Skip vfio_dma_map_limit_test if mapping returns -EINVAL

[Alex Mastro <amastro@fb.com>]

On Fri, Nov 07, 2025 at 04:17:24PM -0800, Alex Mastro wrote:
> On Fri, Nov 07, 2025 at 10:20:58PM +0000, David Matlack wrote:
> > Skip vfio_dma_map_limit_test.{unmap_range,unmap_all} (instead of
> > failing) on systems that do not support mapping in the page-sized region
> > at the top of the u64 address space. Use -EINVAL as the signal for
> > detecting systems with this limitation, as that is what both VFIO Type1
> > and iommufd return.
> > 
> > A more robust solution that could be considered in the future would be
> > to explicitly check the range of supported IOVA regions and key off
> > that, instead of inferring from -EINVAL.
> > 
> > Fixes: de8d1f2fd5a5 ("vfio: selftests: add end of address space DMA map/unmap tests")
> > Signed-off-by: David Matlack <dmatlack@google.com>
> 
> Makes sense -- thanks David. Agree about keying this off
> VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE longer term.
> 
> Reviewed-by: Alex Mastro <amastro@fb.com>

Here's my attempt at adding some machinery to query iova ranges, with
normalization to iommufd's struct. I kept the vfio capability chain stuff
relatively generic so we can use it for other things in the future if needed.

I can sequence this after your fix?

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h
index 240409bf5f8a..fb5efec52316 100644
--- a/tools/testing/selftests/vfio/lib/include/vfio_util.h
+++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h
@@ -4,9 +4,12 @@
 
 #include <fcntl.h>
 #include <string.h>
-#include <linux/vfio.h>
+
+#include <uapi/linux/types.h>
+#include <linux/iommufd.h>
 #include <linux/list.h>
 #include <linux/pci_regs.h>
+#include <linux/vfio.h>
 
 #include "../../../kselftest.h"
 
@@ -206,6 +209,9 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_
 void vfio_pci_device_cleanup(struct vfio_pci_device *device);
 void vfio_pci_device_reset(struct vfio_pci_device *device);
 
+struct iommu_iova_range *vfio_pci_iova_ranges(struct vfio_pci_device *device,
+					      size_t *nranges);
+
 int __vfio_pci_dma_map(struct vfio_pci_device *device,
 		       struct vfio_dma_region *region);
 int __vfio_pci_dma_unmap(struct vfio_pci_device *device,
diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
index a381fd253aa7..3297a41fdc31 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -29,6 +29,145 @@
 	VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \
 } while (0)
 
+static struct vfio_info_cap_header *next_cap_hdr(void *buf, size_t bufsz,
+						 size_t *cap_offset)
+{
+	struct vfio_info_cap_header *hdr;
+
+	if (!*cap_offset)
+		return NULL;
+
+	/* Cap offset must be in bounds */
+	VFIO_ASSERT_LT(*cap_offset, bufsz);
+	/* There must be enough remaining space to contain the header */
+	VFIO_ASSERT_GE(bufsz - *cap_offset, sizeof(*hdr));
+	hdr = (struct vfio_info_cap_header *)((u8 *)buf + *cap_offset);
+	/* If there is a next, offset must monotonically increase */
+	if (hdr->next)
+		VFIO_ASSERT_GT(hdr->next, *cap_offset);
+	*cap_offset = hdr->next;
+
+	return hdr;
+}
+
+static struct vfio_info_cap_header *vfio_iommu_info_cap_hdr(struct vfio_iommu_type1_info *buf,
+							    u16 cap_id)
+{
+	struct vfio_info_cap_header *hdr;
+	size_t cap_offset = buf->cap_offset;
+
+	if (!(buf->flags & VFIO_IOMMU_INFO_CAPS))
+		return NULL;
+
+	if (cap_offset)
+		VFIO_ASSERT_GE(cap_offset, sizeof(struct vfio_iommu_type1_info));
+
+	while ((hdr = next_cap_hdr(buf, buf->argsz, &cap_offset))) {
+		if (hdr->id == cap_id)
+			return hdr;
+	}
+
+	return NULL;
+}
+
+/* Return buffer including capability chain, if present. Free with free() */
+static struct vfio_iommu_type1_info *vfio_iommu_info_buf(struct vfio_pci_device *device)
+{
+	struct vfio_iommu_type1_info *buf;
+
+	buf = malloc(sizeof(*buf));
+	VFIO_ASSERT_NOT_NULL(buf);
+
+	*buf = (struct vfio_iommu_type1_info) {
+		.argsz = sizeof(*buf),
+	};
+
+	ioctl_assert(device->container_fd, VFIO_IOMMU_GET_INFO, buf);
+
+	buf = realloc(buf, buf->argsz);
+	VFIO_ASSERT_NOT_NULL(buf);
+
+	ioctl_assert(device->container_fd, VFIO_IOMMU_GET_INFO, buf);
+
+	return buf;
+}
+
+/*
+ * Normalize vfio_iommu_type1 to report iommufd's iommu_iova_range. Free with
+ * free().
+ */
+static struct iommu_iova_range *vfio_iommu_iova_ranges(struct vfio_pci_device *device,
+						       size_t *nranges)
+{
+	struct vfio_iommu_type1_info_cap_iova_range *cap_range;
+	struct vfio_iommu_type1_info *buf;
+	struct vfio_info_cap_header *hdr;
+	struct iommu_iova_range *ranges = NULL;
+
+	buf = vfio_iommu_info_buf(device);
+	VFIO_ASSERT_NOT_NULL(buf);
+
+	hdr = vfio_iommu_info_cap_hdr(buf, VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE);
+	if (!hdr)
+		goto free_buf;
+
+	cap_range = container_of(hdr, struct vfio_iommu_type1_info_cap_iova_range, header);
+	if (!cap_range->nr_iovas)
+		goto free_buf;
+
+	ranges = malloc(cap_range->nr_iovas * sizeof(*ranges));
+	VFIO_ASSERT_NOT_NULL(ranges);
+
+	for (u32 i = 0; i < cap_range->nr_iovas; i++) {
+		ranges[i] = (struct iommu_iova_range){
+			.start = cap_range->iova_ranges[i].start,
+			.last = cap_range->iova_ranges[i].end,
+		};
+	}
+
+	*nranges = cap_range->nr_iovas;
+
+free_buf:
+	free(buf);
+	return ranges;
+}
+
+struct iommu_iova_range *iommufd_iova_ranges(struct vfio_pci_device *device,
+					     size_t *nranges)
+{
+	struct iommu_iova_range *ranges;
+	int ret;
+
+	struct iommu_ioas_iova_ranges query = {
+		.size = sizeof(query),
+		.ioas_id = device->ioas_id,
+	};
+
+	ret = ioctl(device->iommufd, IOMMU_IOAS_IOVA_RANGES, &query);
+	VFIO_ASSERT_EQ(ret, -1);
+	VFIO_ASSERT_EQ(errno, EMSGSIZE);
+	VFIO_ASSERT_GT(query.num_iovas, 0);
+
+	ranges = malloc(query.num_iovas * sizeof(*ranges));
+	VFIO_ASSERT_NOT_NULL(ranges);
+
+	query.allowed_iovas = (uintptr_t)ranges;
+
+	ioctl_assert(device->iommufd, IOMMU_IOAS_IOVA_RANGES, &query);
+	*nranges = query.num_iovas;
+
+	return ranges;
+}
+
+struct iommu_iova_range *vfio_pci_iova_ranges(struct vfio_pci_device *device,
+					      size_t *nranges)
+{
+	if (device->iommufd)
+		return iommufd_iova_ranges(device, nranges);
+
+	return vfio_iommu_iova_ranges(device, nranges);
+}
+
 iova_t __to_iova(struct vfio_pci_device *device, void *vaddr)
 {
 	struct vfio_dma_region *region;
diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
index 4f1ea79a200c..78983c4c293b 100644
--- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
+++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c
@@ -3,6 +3,8 @@
 #include <sys/mman.h>
 #include <unistd.h>
 
+#include <uapi/linux/types.h>
+#include <linux/iommufd.h>
 #include <linux/limits.h>
 #include <linux/mman.h>
 #include <linux/sizes.h>
@@ -243,12 +245,31 @@ FIXTURE_TEARDOWN(vfio_dma_map_limit_test)
 	ASSERT_EQ(munmap(self->region.vaddr, self->mmap_size), 0);
 }
 
+static iova_t last_legal_iova(struct vfio_pci_device *device)
+{
+	struct iommu_iova_range *ranges;
+	size_t nranges;
+	iova_t ret;
+
+	ranges = vfio_pci_iova_ranges(device, &nranges);
+	VFIO_ASSERT_NOT_NULL(ranges);
+
+	ret = ranges[nranges - 1].last;
+	free(ranges);
+
+	return ret;
+}
+
 TEST_F(vfio_dma_map_limit_test, unmap_range)
 {
+	iova_t last_iova = last_legal_iova(self->device);
 	struct vfio_dma_region *region = &self->region;
 	u64 unmapped;
 	int rc;
 
+	if (last_iova != ~(iova_t)0)
+		SKIP(return, "last legal iova=0x%lx\n", last_iova);
+
 	vfio_pci_dma_map(self->device, region);
 	ASSERT_EQ(region->iova, to_iova(self->device, region->vaddr));
 
@@ -259,10 +280,14 @@ TEST_F(vfio_dma_map_limit_test, unmap_range)
 
 TEST_F(vfio_dma_map_limit_test, unmap_all)
 {
+	iova_t last_iova = last_legal_iova(self->device);
 	struct vfio_dma_region *region = &self->region;
 	u64 unmapped;
 	int rc;
 
+	if (last_iova != ~(iova_t)0)
+		SKIP(return, "last legal iova=0x%lx\n", last_iova);
+
 	vfio_pci_dma_map(self->device, region);
 	ASSERT_EQ(region->iova, to_iova(self->device, region->vaddr));