1 files changed, 22 insertions, 238 deletions

diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
index 0921b2451ba5..13fdb4b0b10f 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -2,6 +2,7 @@
 #include <dirent.h>
 #include <fcntl.h>
 #include <libgen.h>
+#include <stdint.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -11,50 +12,18 @@
 #include <sys/mman.h>
 
 #include <uapi/linux/types.h>
+#include <linux/iommufd.h>
 #include <linux/limits.h>
 #include <linux/mman.h>
+#include <linux/overflow.h>
 #include <linux/types.h>
 #include <linux/vfio.h>
-#include <linux/iommufd.h>
 
 #include "../../../kselftest.h"
-#include <vfio_util.h>
+#include <libvfio.h>
 
 #define PCI_SYSFS_PATH	"/sys/bus/pci/devices"
 
-#define ioctl_assert(_fd, _op, _arg) do {						       \
-	void *__arg = (_arg);								       \
-	int __ret = ioctl((_fd), (_op), (__arg));					       \
-	VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \
-} while (0)
-
-iova_t __to_iova(struct vfio_pci_device *device, void *vaddr)
-{
-	struct vfio_dma_region *region;
-
-	list_for_each_entry(region, &device->dma_regions, link) {
-		if (vaddr < region->vaddr)
-			continue;
-
-		if (vaddr >= region->vaddr + region->size)
-			continue;
-
-		return region->iova + (vaddr - region->vaddr);
-	}
-
-	return INVALID_IOVA;
-}
-
-iova_t to_iova(struct vfio_pci_device *device, void *vaddr)
-{
-	iova_t iova;
-
-	iova = __to_iova(device, vaddr);
-	VFIO_ASSERT_NE(iova, INVALID_IOVA, "%p is not mapped into device.\n", vaddr);
-
-	return iova;
-}
-
 static void vfio_pci_irq_set(struct vfio_pci_device *device,
 			     u32 index, u32 vector, u32 count, int *fds)
 {
@@ -141,84 +110,6 @@ static void vfio_pci_irq_get(struct vfio_pci_device *device, u32 index,
 	ioctl_assert(device->fd, VFIO_DEVICE_GET_IRQ_INFO, irq_info);
 }
 
-static void vfio_iommu_dma_map(struct vfio_pci_device *device,
-			       struct vfio_dma_region *region)
-{
-	struct vfio_iommu_type1_dma_map args = {
-		.argsz = sizeof(args),
-		.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE,
-		.vaddr = (u64)region->vaddr,
-		.iova = region->iova,
-		.size = region->size,
-	};
-
-	ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &args);
-}
-
-static void iommufd_dma_map(struct vfio_pci_device *device,
-			    struct vfio_dma_region *region)
-{
-	struct iommu_ioas_map args = {
-		.size = sizeof(args),
-		.flags = IOMMU_IOAS_MAP_READABLE |
-			 IOMMU_IOAS_MAP_WRITEABLE |
-			 IOMMU_IOAS_MAP_FIXED_IOVA,
-		.user_va = (u64)region->vaddr,
-		.iova = region->iova,
-		.length = region->size,
-		.ioas_id = device->ioas_id,
-	};
-
-	ioctl_assert(device->iommufd, IOMMU_IOAS_MAP, &args);
-}
-
-void vfio_pci_dma_map(struct vfio_pci_device *device,
-		      struct vfio_dma_region *region)
-{
-	if (device->iommufd)
-		iommufd_dma_map(device, region);
-	else
-		vfio_iommu_dma_map(device, region);
-
-	list_add(&region->link, &device->dma_regions);
-}
-
-static void vfio_iommu_dma_unmap(struct vfio_pci_device *device,
-				 struct vfio_dma_region *region)
-{
-	struct vfio_iommu_type1_dma_unmap args = {
-		.argsz = sizeof(args),
-		.iova = region->iova,
-		.size = region->size,
-	};
-
-	ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &args);
-}
-
-static void iommufd_dma_unmap(struct vfio_pci_device *device,
-			      struct vfio_dma_region *region)
-{
-	struct iommu_ioas_unmap args = {
-		.size = sizeof(args),
-		.iova = region->iova,
-		.length = region->size,
-		.ioas_id = device->ioas_id,
-	};
-
-	ioctl_assert(device->iommufd, IOMMU_IOAS_UNMAP, &args);
-}
-
-void vfio_pci_dma_unmap(struct vfio_pci_device *device,
-			struct vfio_dma_region *region)
-{
-	if (device->iommufd)
-		iommufd_dma_unmap(device, region);
-	else
-		vfio_iommu_dma_unmap(device, region);
-
-	list_del(&region->link);
-}
-
 static void vfio_pci_region_get(struct vfio_pci_device *device, int index,
 				struct vfio_region_info *info)
 {
@@ -325,28 +216,26 @@ static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf
 	ioctl_assert(device->group_fd, VFIO_GROUP_GET_STATUS, &group_status);
 	VFIO_ASSERT_TRUE(group_status.flags & VFIO_GROUP_FLAGS_VIABLE);
 
-	ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->container_fd);
+	ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->iommu->container_fd);
 }
 
 static void vfio_pci_container_setup(struct vfio_pci_device *device, const char *bdf)
 {
-	unsigned long iommu_type = device->iommu_mode->iommu_type;
-	const char *path = device->iommu_mode->container_path;
-	int version;
+	struct iommu *iommu = device->iommu;
+	unsigned long iommu_type = iommu->mode->iommu_type;
 	int ret;
 
-	device->container_fd = open(path, O_RDWR);
-	VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", path);
-
-	version = ioctl(device->container_fd, VFIO_GET_API_VERSION);
-	VFIO_ASSERT_EQ(version, VFIO_API_VERSION, "Unsupported version: %d\n", version);
-
 	vfio_pci_group_setup(device, bdf);
 
-	ret = ioctl(device->container_fd, VFIO_CHECK_EXTENSION, iommu_type);
+	ret = ioctl(iommu->container_fd, VFIO_CHECK_EXTENSION, iommu_type);
 	VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type);
 
-	ioctl_assert(device->container_fd, VFIO_SET_IOMMU, (void *)iommu_type);
+	/*
+	 * Allow multiple threads to race to set the IOMMU type on the
+	 * container. The first will succeed and the rest should fail
+	 * because the IOMMU type is already set.
+	 */
+	(void)ioctl(iommu->container_fd, VFIO_SET_IOMMU, (void *)iommu_type);
 
 	device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf);
 	VFIO_ASSERT_GE(device->fd, 0);
@@ -410,52 +299,6 @@ const char *vfio_pci_get_cdev_path(const char *bdf)
 	return cdev_path;
 }
 
-/* Reminder: Keep in sync with FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(). */
-static const struct vfio_iommu_mode iommu_modes[] = {
-	{
-		.name = "vfio_type1_iommu",
-		.container_path = "/dev/vfio/vfio",
-		.iommu_type = VFIO_TYPE1_IOMMU,
-	},
-	{
-		.name = "vfio_type1v2_iommu",
-		.container_path = "/dev/vfio/vfio",
-		.iommu_type = VFIO_TYPE1v2_IOMMU,
-	},
-	{
-		.name = "iommufd_compat_type1",
-		.container_path = "/dev/iommu",
-		.iommu_type = VFIO_TYPE1_IOMMU,
-	},
-	{
-		.name = "iommufd_compat_type1v2",
-		.container_path = "/dev/iommu",
-		.iommu_type = VFIO_TYPE1v2_IOMMU,
-	},
-	{
-		.name = "iommufd",
-	},
-};
-
-const char *default_iommu_mode = "iommufd";
-
-static const struct vfio_iommu_mode *lookup_iommu_mode(const char *iommu_mode)
-{
-	int i;
-
-	if (!iommu_mode)
-		iommu_mode = default_iommu_mode;
-
-	for (i = 0; i < ARRAY_SIZE(iommu_modes); i++) {
-		if (strcmp(iommu_mode, iommu_modes[i].name))
-			continue;
-
-		return &iommu_modes[i];
-	}
-
-	VFIO_FAIL("Unrecognized IOMMU mode: %s\n", iommu_mode);
-}
-
 static void vfio_device_bind_iommufd(int device_fd, int iommufd)
 {
 	struct vfio_device_bind_iommufd args = {
@@ -466,16 +309,6 @@ static void vfio_device_bind_iommufd(int device_fd, int iommufd)
 	ioctl_assert(device_fd, VFIO_DEVICE_BIND_IOMMUFD, &args);
 }
 
-static u32 iommufd_ioas_alloc(int iommufd)
-{
-	struct iommu_ioas_alloc args = {
-		.size = sizeof(args),
-	};
-
-	ioctl_assert(iommufd, IOMMU_IOAS_ALLOC, &args);
-	return args.out_ioas_id;
-}
-
 static void vfio_device_attach_iommufd_pt(int device_fd, u32 pt_id)
 {
 	struct vfio_device_attach_iommufd_pt args = {
@@ -494,31 +327,22 @@ static void vfio_pci_iommufd_setup(struct vfio_pci_device *device, const char *b
 	VFIO_ASSERT_GE(device->fd, 0);
 	free((void *)cdev_path);
 
-	/*
-	 * Require device->iommufd to be >0 so that a simple non-0 check can be
-	 * used to check if iommufd is enabled. In practice open() will never
-	 * return 0 unless stdin is closed.
-	 */
-	device->iommufd = open("/dev/iommu", O_RDWR);
-	VFIO_ASSERT_GT(device->iommufd, 0);
-
-	vfio_device_bind_iommufd(device->fd, device->iommufd);
-	device->ioas_id = iommufd_ioas_alloc(device->iommufd);
-	vfio_device_attach_iommufd_pt(device->fd, device->ioas_id);
+	vfio_device_bind_iommufd(device->fd, device->iommu->iommufd);
+	vfio_device_attach_iommufd_pt(device->fd, device->iommu->ioas_id);
 }
 
-struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode)
+struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iommu)
 {
 	struct vfio_pci_device *device;
 
 	device = calloc(1, sizeof(*device));
 	VFIO_ASSERT_NOT_NULL(device);
 
-	INIT_LIST_HEAD(&device->dma_regions);
-
-	device->iommu_mode = lookup_iommu_mode(iommu_mode);
+	VFIO_ASSERT_NOT_NULL(iommu);
+	device->iommu = iommu;
+	device->bdf = bdf;
 
-	if (device->iommu_mode->container_path)
+	if (iommu->mode->container_path)
 		vfio_pci_container_setup(device, bdf);
 	else
 		vfio_pci_iommufd_setup(device, bdf);
@@ -547,48 +371,8 @@ void vfio_pci_device_cleanup(struct vfio_pci_device *device)
 		VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0);
 	}
 
-	if (device->iommufd) {
-		VFIO_ASSERT_EQ(close(device->iommufd), 0);
-	} else {
+	if (device->group_fd)
 		VFIO_ASSERT_EQ(close(device->group_fd), 0);
-		VFIO_ASSERT_EQ(close(device->container_fd), 0);
-	}
 
 	free(device);
 }
-
-static bool is_bdf(const char *str)
-{
-	unsigned int s, b, d, f;
-	int length, count;
-
-	count = sscanf(str, "%4x:%2x:%2x.%2x%n", &s, &b, &d, &f, &length);
-	return count == 4 && length == strlen(str);
-}
-
-const char *vfio_selftests_get_bdf(int *argc, char *argv[])
-{
-	char *bdf;
-
-	if (*argc > 1 && is_bdf(argv[*argc - 1]))
-		return argv[--(*argc)];
-
-	bdf = getenv("VFIO_SELFTESTS_BDF");
-	if (bdf) {
-		VFIO_ASSERT_TRUE(is_bdf(bdf), "Invalid BDF: %s\n", bdf);
-		return bdf;
-	}
-
-	fprintf(stderr, "Unable to determine which device to use, skipping test.\n");
-	fprintf(stderr, "\n");
-	fprintf(stderr, "To pass the device address via environment variable:\n");
-	fprintf(stderr, "\n");
-	fprintf(stderr, "    export VFIO_SELFTESTS_BDF=segment:bus:device.function\n");
-	fprintf(stderr, "    %s [options]\n", argv[0]);
-	fprintf(stderr, "\n");
-	fprintf(stderr, "To pass the device address via argv:\n");
-	fprintf(stderr, "\n");
-	fprintf(stderr, "    %s [options] segment:bus:device.function\n", argv[0]);
-	fprintf(stderr, "\n");
-	exit(KSFT_SKIP);
-}