Merge tag 'vfio-v6.17-rc1-v2' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Fix imbalance where the no-iommu/cdev device path skips too much on
   open, failing to increment a reference, but still decrements the
   reference on close. Add bounds checking to prevent such underflows
   (Jacob Pan)

 - Fill missing detach_ioas op for pds_vfio_pci, fixing probe failure
   when used with IOMMUFD (Brett Creeley)

 - Split SR-IOV VFs to separate dev_set, avoiding unnecessary
   serialization between VFs that appear on the same bus (Alex
   Williamson)

 - Fix a theoretical integer overflow is the mlx5-vfio-pci variant
   driver (Artem Sadovnikov)

 - Implement missing VF token checking support via vfio cdev/IOMMUFD
   interface (Jason Gunthorpe)

 - Update QAT vfio-pci variant driver to claim latest VF devices
   (Małgorzata Mielnik)

 - Add a cond_resched() call to avoid holding the CPU too long during
   DMA mapping operations (Keith Busch)

* tag 'vfio-v6.17-rc1-v2' of https://github.com/awilliam/linux-vfio:
  vfio/type1: conditional rescheduling while pinning
  vfio/qat: add support for intel QAT 6xxx virtual functions
  vfio/qat: Remove myself from VFIO QAT PCI driver maintainers
  vfio/pci: Do vf_token checks for VFIO_DEVICE_BIND_IOMMUFD
  vfio/mlx5: fix possible overflow in tracking max message size
  vfio/pci: Separate SR-IOV VF dev_set
  vfio/pds: Fix missing detach_ioas op
  vfio: Prevent open_count decrement to negative
  vfio: Fix unbalanced vfio_df_close call in no-iommu mode

18 files changed, 99 insertions, 22 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index fda151dbf229..58789aad5c90 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26455,7 +26455,6 @@ S:	Maintained
 F:	drivers/vfio/platform/
 
 VFIO QAT PCI DRIVER
-M:	Xin Zeng <xin.zeng@intel.com>
 M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
 L:	kvm@vger.kernel.org
 L:	qat-linux@intel.com
diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index 281a8dc3ed49..480cac3a0c27 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -60,22 +60,50 @@ static void vfio_df_get_kvm_safe(struct vfio_device_file *df)
 	spin_unlock(&df->kvm_ref_lock);
 }
 
+static int vfio_df_check_token(struct vfio_device *device,
+			       const struct vfio_device_bind_iommufd *bind)
+{
+	uuid_t uuid;
+
+	if (!device->ops->match_token_uuid) {
+		if (bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN)
+			return -EINVAL;
+		return 0;
+	}
+
+	if (!(bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN))
+		return device->ops->match_token_uuid(device, NULL);
+
+	if (copy_from_user(&uuid, u64_to_user_ptr(bind->token_uuid_ptr),
+			   sizeof(uuid)))
+		return -EFAULT;
+	return device->ops->match_token_uuid(device, &uuid);
+}
+
 long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
 				struct vfio_device_bind_iommufd __user *arg)
 {
+	const u32 VALID_FLAGS = VFIO_DEVICE_BIND_FLAG_TOKEN;
 	struct vfio_device *device = df->device;
 	struct vfio_device_bind_iommufd bind;
 	unsigned long minsz;
+	u32 user_size;
 	int ret;
 
 	static_assert(__same_type(arg->out_devid, df->devid));
 
 	minsz = offsetofend(struct vfio_device_bind_iommufd, out_devid);
 
-	if (copy_from_user(&bind, arg, minsz))
-		return -EFAULT;
+	ret = get_user(user_size, &arg->argsz);
+	if (ret)
+		return ret;
+	if (user_size < minsz)
+		return -EINVAL;
+	ret = copy_struct_from_user(&bind, minsz, arg, user_size);
+	if (ret)
+		return ret;
 
-	if (bind.argsz < minsz || bind.flags || bind.iommufd < 0)
+	if (bind.iommufd < 0 || bind.flags & ~VALID_FLAGS)
 		return -EINVAL;
 
 	/* BIND_IOMMUFD only allowed for cdev fds */
@@ -93,6 +121,10 @@ long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
 		goto out_unlock;
 	}
 
+	ret = vfio_df_check_token(device, &bind);
+	if (ret)
+		goto out_unlock;
+
 	df->iommufd = iommufd_ctx_from_fd(bind.iommufd);
 	if (IS_ERR(df->iommufd)) {
 		ret = PTR_ERR(df->iommufd);
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index c321d442f0da..c376a6279de0 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -192,11 +192,10 @@ static int vfio_df_group_open(struct vfio_device_file *df)
 		 * implies they expected translation to exist
 		 */
 		if (!capable(CAP_SYS_RAWIO) ||
-		    vfio_iommufd_device_has_compat_ioas(device, df->iommufd))
+		    vfio_iommufd_device_has_compat_ioas(device, df->iommufd)) {
 			ret = -EPERM;
-		else
-			ret = 0;
-		goto out_put_kvm;
+			goto out_put_kvm;
+		}
 	}
 
 	ret = vfio_df_open(df);
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
index c8c3a2d53f86..a38d262c6028 100644
--- a/drivers/vfio/iommufd.c
+++ b/drivers/vfio/iommufd.c
@@ -25,6 +25,10 @@ int vfio_df_iommufd_bind(struct vfio_device_file *df)
 
 	lockdep_assert_held(&vdev->dev_set->lock);
 
+	/* Returns 0 to permit device opening under noiommu mode */
+	if (vfio_device_is_noiommu(vdev))
+		return 0;
+
 	return vdev->ops->bind_iommufd(vdev, ictx, &df->devid);
 }
 
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 2149f49aeec7..397f5e445136 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -1583,6 +1583,7 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 5b919a0b2524..a92b095b90f6 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -1523,8 +1523,8 @@ int mlx5vf_start_page_tracker(struct vfio_device *vdev,
 	log_max_msg_size = MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_max_msg_size);
 	max_msg_size = (1ULL << log_max_msg_size);
 	/* The RQ must hold at least 4 WQEs/messages for successful QP creation */
-	if (rq_size < 4 * max_msg_size)
-		rq_size = 4 * max_msg_size;
+	if (rq_size < 4ULL * max_msg_size)
+		rq_size = 4ULL * max_msg_size;
 
 	memset(tracker, 0, sizeof(*tracker));
 	tracker->uar = mlx5_get_uars_page(mdev);
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 93f894fe60d2..7ec47e736a8e 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -1372,6 +1372,7 @@ static const struct vfio_device_ops mlx5vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index e5ac39c4cc6b..d95761dcdd58 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -696,6 +696,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = {
 	.mmap		= nvgrace_gpu_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
@@ -715,6 +716,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = {
 	.mmap		= vfio_pci_core_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 76a80ae7087b..f3ccb0008f67 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -201,9 +201,11 @@ static const struct vfio_device_ops pds_vfio_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
 const struct vfio_device_ops *pds_vfio_ops_info(void)
diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c
index 845ed15b6771..a19b68043eb2 100644
--- a/drivers/vfio/pci/qat/main.c
+++ b/drivers/vfio/pci/qat/main.c
@@ -614,6 +614,7 @@ static const struct vfio_device_ops qat_vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
@@ -675,6 +676,8 @@ static const struct pci_device_id qat_vf_vfio_pci_table[] = {
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4941) },
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4943) },
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4945) },
+	/* Intel QAT GEN6 6xxx VF device */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4949) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, qat_vf_vfio_pci_table);
@@ -696,5 +699,5 @@ module_pci_driver(qat_vf_vfio_pci_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Xin Zeng <xin.zeng@intel.com>");
-MODULE_DESCRIPTION("QAT VFIO PCI - VFIO PCI driver with live migration support for Intel(R) QAT GEN4 device family");
+MODULE_DESCRIPTION("QAT VFIO PCI - VFIO PCI driver with live migration support for Intel(R) QAT device family");
 MODULE_IMPORT_NS("CRYPTO_QAT");
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 5ba39f7623bb..ac10f14417f2 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -138,6 +138,7 @@ static const struct vfio_device_ops vfio_pci_ops = {
 	.mmap		= vfio_pci_core_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 31bdb9110cc0..7dcf5439dedc 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1818,9 +1818,13 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count)
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_request);
 
-static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
-				      bool vf_token, uuid_t *uuid)
+int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev,
+				   const uuid_t *uuid)
+
 {
+	struct vfio_pci_core_device *vdev =
+		container_of(core_vdev, struct vfio_pci_core_device, vdev);
+
 	/*
 	 * There's always some degree of trust or collaboration between SR-IOV
 	 * PF and VFs, even if just that the PF hosts the SR-IOV capability and
@@ -1851,7 +1855,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 		bool match;
 
 		if (!pf_vdev) {
-			if (!vf_token)
+			if (!uuid)
 				return 0; /* PF is not vfio-pci, no VF token */
 
 			pci_info_ratelimited(vdev->pdev,
@@ -1859,7 +1863,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 			return -EINVAL;
 		}
 
-		if (!vf_token) {
+		if (!uuid) {
 			pci_info_ratelimited(vdev->pdev,
 				"VF token required to access device\n");
 			return -EACCES;
@@ -1877,7 +1881,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 	} else if (vdev->vf_token) {
 		mutex_lock(&vdev->vf_token->lock);
 		if (vdev->vf_token->users) {
-			if (!vf_token) {
+			if (!uuid) {
 				mutex_unlock(&vdev->vf_token->lock);
 				pci_info_ratelimited(vdev->pdev,
 					"VF token required to access device\n");
@@ -1890,12 +1894,12 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 					"Incorrect VF token provided for device\n");
 				return -EACCES;
 			}
-		} else if (vf_token) {
+		} else if (uuid) {
 			uuid_copy(&vdev->vf_token->uuid, uuid);
 		}
 
 		mutex_unlock(&vdev->vf_token->lock);
-	} else if (vf_token) {
+	} else if (uuid) {
 		pci_info_ratelimited(vdev->pdev,
 			"VF token incorrectly provided, not a PF or VF\n");
 		return -EINVAL;
@@ -1903,6 +1907,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_match_token_uuid);
 
 #define VF_TOKEN_ARG "vf_token="
 
@@ -1949,7 +1954,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf)
 		}
 	}
 
-	ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid);
+	ret = core_vdev->ops->match_token_uuid(core_vdev,
+					       vf_token ? &uuid : NULL);
 	if (ret)
 		return ret;
 
@@ -2146,7 +2152,7 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 		return -EBUSY;
 	}
 
-	if (pci_is_root_bus(pdev->bus)) {
+	if (pci_is_root_bus(pdev->bus) || pdev->is_virtfn) {
 		ret = vfio_assign_device_set(&vdev->vdev, vdev);
 	} else if (!pci_probe_reset_slot(pdev->slot)) {
 		ret = vfio_assign_device_set(&vdev->vdev, pdev->slot);
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
index 515fe1b9f94d..8084f3e36a9f 100644
--- a/drivers/vfio/pci/virtio/main.c
+++ b/drivers/vfio/pci/virtio/main.c
@@ -94,6 +94,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_lm_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
@@ -114,6 +115,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
@@ -134,6 +136,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 1136d7ac6b59..f8d68fe77b41 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -647,6 +647,13 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
 
 	while (npage) {
 		if (!batch->size) {
+			/*
+			 * Large mappings may take a while to repeatedly refill
+			 * the batch, so conditionally relinquish the CPU when
+			 * needed to avoid stalls.
+			 */
+			cond_resched();
+
 			/* Empty batch, so refill it. */
 			ret = vaddr_get_pfns(mm, vaddr, npage, dma->prot,
 					     &pfn, batch);
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 1fd261efc582..5046cae05222 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -583,7 +583,8 @@ void vfio_df_close(struct vfio_device_file *df)
 
 	lockdep_assert_held(&device->dev_set->lock);
 
-	vfio_assert_device_open(device);
+	if (!vfio_assert_device_open(device))
+		return;
 	if (device->open_count == 1)
 		vfio_df_device_last_close(df);
 	device->open_count--;
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 707b00772ce1..eb563f538dee 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -105,6 +105,9 @@ struct vfio_device {
  * @match: Optional device name match callback (return: 0 for no-match, >0 for
  *         match, -errno for abort (ex. match with insufficient or incorrect
  *         additional args)
+ * @match_token_uuid: Optional device token match/validation. Return 0
+ *         if the uuid is valid for the device, -errno otherwise. uuid is NULL
+ *         if none was provided.
  * @dma_unmap: Called when userspace unmaps IOVA from the container
  *             this device is attached to.
  * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl
@@ -132,6 +135,7 @@ struct vfio_device_ops {
 	int	(*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma);
 	void	(*request)(struct vfio_device *vdev, unsigned int count);
 	int	(*match)(struct vfio_device *vdev, char *buf);
+	int	(*match_token_uuid)(struct vfio_device *vdev, const uuid_t *uuid);
 	void	(*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length);
 	int	(*device_feature)(struct vfio_device *device, u32 flags,
 				  void __user *arg, size_t argsz);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index fbb472dd99b3..f541044e42a2 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -122,6 +122,8 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu
 int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma);
 void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count);
 int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
+int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev,
+				   const uuid_t *uuid);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5764f315137f..75100bf009ba 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -905,10 +905,12 @@ struct vfio_device_feature {
  * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
  *				   struct vfio_device_bind_iommufd)
  * @argsz:	 User filled size of this data.
- * @flags:	 Must be 0.
+ * @flags:	 Must be 0 or a bit flags of VFIO_DEVICE_BIND_*
  * @iommufd:	 iommufd to bind.
  * @out_devid:	 The device id generated by this bind. devid is a handle for
  *		 this device/iommufd bond and can be used in IOMMUFD commands.
+ * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte
+ *                  UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN.
  *
  * Bind a vfio_device to the specified iommufd.
  *
@@ -917,13 +919,21 @@ struct vfio_device_feature {
  *
  * Unbind is automatically conducted when device fd is closed.
  *
+ * A token is sometimes required to open the device, unless this is known to be
+ * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is
+ * ignored. The only case today is a PF/VF relationship where the VF bind must
+ * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to
+ * the PF.
+ *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_device_bind_iommufd {
 	__u32		argsz;
 	__u32		flags;
+#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0)
 	__s32		iommufd;
 	__u32		out_devid;
+	__aligned_u64	token_uuid_ptr;
 };
 
 #define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 18)