iommufd/viommu: Add IOMMUFD_OBJ_VDEVICE and IOMMU_VDEVICE_ALLOC ioctl

Introduce a new IOMMUFD_OBJ_VDEVICE to represent a physical device (struct
device) against a vIOMMU (struct iommufd_viommu) object in a VM.

This vDEVICE object (and its structure) holds all the infos and attributes
in the VM, regarding the device related to the vIOMMU.

As an initial patch, add a per-vIOMMU virtual ID. This can be:
 - Virtual StreamID on a nested ARM SMMUv3, an index to a Stream Table
 - Virtual DeviceID on a nested AMD IOMMU, an index to a Device Table
 - Virtual RID on a nested Intel VT-D IOMMU, an index to a Context Table
Potentially, this vDEVICE structure would hold some vData for Confidential
Compute Architecture (CCA). Use this virtual ID to index an "vdevs" xarray
that belongs to a vIOMMU object.

Add a new ioctl for vDEVICE allocations. Since a vDEVICE is a connection
of a device object and an iommufd_viommu object, take two refcounts in the
ioctl handler.

Link: https://patch.msgid.link/r/cda8fd2263166e61b8191a3b3207e0d2b08545bf.1730836308.git.nicolinc@nvidia.com
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

3 files changed, 100 insertions, 0 deletions

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index e8f5ef550cc9..062656c19a07 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -507,8 +507,26 @@ static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
 	return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
 }
 
+static inline struct iommufd_viommu *
+iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_VIOMMU),
+			    struct iommufd_viommu, obj);
+}
+
 int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_viommu_destroy(struct iommufd_object *obj);
+int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd);
+void iommufd_vdevice_destroy(struct iommufd_object *obj);
+
+struct iommufd_vdevice {
+	struct iommufd_object obj;
+	struct iommufd_ctx *ictx;
+	struct iommufd_viommu *viommu;
+	struct device *dev;
+	u64 id; /* per-vIOMMU virtual ID */
+};
 
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index cc514f9bc3e6..d735fe04197f 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -308,6 +308,7 @@ union ucmd_buffer {
 	struct iommu_option option;
 	struct iommu_vfio_ioas vfio_ioas;
 	struct iommu_viommu_alloc viommu;
+	struct iommu_vdevice_alloc vdev;
 #ifdef CONFIG_IOMMUFD_TEST
 	struct iommu_test_cmd test;
 #endif
@@ -363,6 +364,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_VIOMMU_ALLOC, iommufd_viommu_alloc_ioctl,
 		 struct iommu_viommu_alloc, out_viommu_id),
+	IOCTL_OP(IOMMU_VDEVICE_ALLOC, iommufd_vdevice_alloc_ioctl,
+		 struct iommu_vdevice_alloc, virt_id),
 #ifdef CONFIG_IOMMUFD_TEST
 	IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last),
 #endif
@@ -501,6 +504,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 	[IOMMUFD_OBJ_VIOMMU] = {
 		.destroy = iommufd_viommu_destroy,
 	},
+	[IOMMUFD_OBJ_VDEVICE] = {
+		.destroy = iommufd_vdevice_destroy,
+	},
 #ifdef CONFIG_IOMMUFD_TEST
 	[IOMMUFD_OBJ_SELFTEST] = {
 		.destroy = iommufd_selftest_destroy,
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 888239b78667..69b88e8c7c26 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -11,6 +11,7 @@ void iommufd_viommu_destroy(struct iommufd_object *obj)
 	if (viommu->ops && viommu->ops->destroy)
 		viommu->ops->destroy(viommu);
 	refcount_dec(&viommu->hwpt->common.obj.users);
+	xa_destroy(&viommu->vdevs);
 }
 
 int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
@@ -53,6 +54,7 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		goto out_put_hwpt;
 	}
 
+	xa_init(&viommu->vdevs);
 	viommu->type = cmd->type;
 	viommu->ictx = ucmd->ictx;
 	viommu->hwpt = hwpt_paging;
@@ -79,3 +81,77 @@ out_put_idev:
 	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
+
+void iommufd_vdevice_destroy(struct iommufd_object *obj)
+{
+	struct iommufd_vdevice *vdev =
+		container_of(obj, struct iommufd_vdevice, obj);
+	struct iommufd_viommu *viommu = vdev->viommu;
+
+	/* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */
+	xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL);
+	refcount_dec(&viommu->obj.users);
+	put_device(vdev->dev);
+}
+
+int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_vdevice_alloc *cmd = ucmd->cmd;
+	struct iommufd_vdevice *vdev, *curr;
+	struct iommufd_viommu *viommu;
+	struct iommufd_device *idev;
+	u64 virt_id = cmd->virt_id;
+	int rc = 0;
+
+	/* virt_id indexes an xarray */
+	if (virt_id > ULONG_MAX)
+		return -EINVAL;
+
+	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);
+	if (IS_ERR(viommu))
+		return PTR_ERR(viommu);
+
+	idev = iommufd_get_device(ucmd, cmd->dev_id);
+	if (IS_ERR(idev)) {
+		rc = PTR_ERR(idev);
+		goto out_put_viommu;
+	}
+
+	if (viommu->iommu_dev != __iommu_get_iommu_dev(idev->dev)) {
+		rc = -EINVAL;
+		goto out_put_idev;
+	}
+
+	vdev = iommufd_object_alloc(ucmd->ictx, vdev, IOMMUFD_OBJ_VDEVICE);
+	if (IS_ERR(vdev)) {
+		rc = PTR_ERR(vdev);
+		goto out_put_idev;
+	}
+
+	vdev->id = virt_id;
+	vdev->dev = idev->dev;
+	get_device(idev->dev);
+	vdev->viommu = viommu;
+	refcount_inc(&viommu->obj.users);
+
+	curr = xa_cmpxchg(&viommu->vdevs, virt_id, NULL, vdev, GFP_KERNEL);
+	if (curr) {
+		rc = xa_err(curr) ?: -EEXIST;
+		goto out_abort;
+	}
+
+	cmd->out_vdevice_id = vdev->obj.id;
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+	if (rc)
+		goto out_abort;
+	iommufd_object_finalize(ucmd->ictx, &vdev->obj);
+	goto out_put_idev;
+
+out_abort:
+	iommufd_object_abort_and_destroy(ucmd->ictx, &vdev->obj);
+out_put_idev:
+	iommufd_put_object(ucmd->ictx, &idev->obj);
+out_put_viommu:
+	iommufd_put_object(ucmd->ictx, &viommu->obj);
+	return rc;
+}