Introduce a new IOMMUFD_OBJ_VDEVICE to represent a physical device, i.e. iommufd_device (idev) object, against an iommufd_viommu (vIOMMU) object in the VM. This vDEVICE object (and its structure) holds all the information and attributes in a 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 ID 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 an iommufd_device object and an iommufd_viommu object, require both as the ioctl inputs and take refcounts in the ioctl handler.
Then, let the idev structure hold the allocated vdev pointer with a proper locking protection.
Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 20 +++++ include/linux/iommufd.h | 3 + include/uapi/linux/iommufd.h | 26 ++++++ drivers/iommu/iommufd/device.c | 11 +++ drivers/iommu/iommufd/main.c | 7 ++ drivers/iommu/iommufd/viommu.c | 101 ++++++++++++++++++++++++ 6 files changed, 168 insertions(+)
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 8c9ab35eaea5..365cf5a56cdf 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -391,6 +391,7 @@ struct iommufd_device { struct iommufd_object obj; struct iommufd_ctx *ictx; struct iommufd_group *igroup; + struct iommufd_vdevice *vdev; struct list_head group_item; /* always the physical device */ struct device *dev; @@ -505,8 +506,27 @@ 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); +void iommufd_vdevice_abort(struct iommufd_object *obj); + +struct iommufd_vdevice { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommufd_device *idev; + struct iommufd_viommu *viommu; + u64 id; /* per-vIOMMU virtual ID */ +};
#ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 083ceb209704..e6cd288e8b83 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -31,6 +31,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_ACCESS, IOMMUFD_OBJ_FAULT, IOMMUFD_OBJ_VIOMMU, + IOMMUFD_OBJ_VDEVICE, #ifdef CONFIG_IOMMUFD_TEST IOMMUFD_OBJ_SELFTEST, #endif @@ -89,6 +90,8 @@ struct iommufd_viommu {
const struct iommufd_viommu_ops *ops;
+ struct xarray vdevs; + unsigned int type; };
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 56c742106a45..b699ecb7aa9c 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -52,6 +52,7 @@ enum { IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d, IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e, IOMMUFD_CMD_VIOMMU_ALLOC = 0x8f, + IOMMUFD_CMD_VDEVICE_ALLOC = 0x90, };
/** @@ -896,4 +897,29 @@ struct iommu_viommu_alloc { __u32 out_viommu_id; }; #define IOMMU_VIOMMU_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VIOMMU_ALLOC) + +/** + * struct iommu_vdevice_alloc - ioctl(IOMMU_VDEVICE_ALLOC) + * @size: sizeof(struct iommu_vdevice_alloc) + * @viommu_id: vIOMMU ID to associate with the virtual device + * @dev_id: The pyhsical device to allocate a virtual instance on the vIOMMU + * @__reserved: Must be 0 + * @virt_id: Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID + * of AMD IOMMU, and vID of a nested Intel VT-d to a Context Table. + * @out_vdevice_id: Output virtual instance ID for the allocated object + * @__reserved2: Must be 0 + * + * Allocate a virtual device instance (for a physical device) against a vIOMMU. + * This instance holds the device's information (related to its vIOMMU) in a VM. + */ +struct iommu_vdevice_alloc { + __u32 size; + __u32 viommu_id; + __u32 dev_id; + __u32 __reserved; + __aligned_u64 virt_id; + __u32 out_vdevice_id; + __u32 __reserved2; +}; +#define IOMMU_VDEVICE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VDEVICE_ALLOC) #endif diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 5fd3dd420290..e50113305a9c 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -277,6 +277,17 @@ EXPORT_SYMBOL_NS_GPL(iommufd_ctx_has_group, IOMMUFD); */ void iommufd_device_unbind(struct iommufd_device *idev) { + u32 vdev_id = 0; + + /* idev->vdev object should be destroyed prior, yet just in case.. */ + mutex_lock(&idev->igroup->lock); + if (idev->vdev) + vdev_id = idev->vdev->obj.id; + mutex_unlock(&idev->igroup->lock); + /* Relying on xa_lock against a race with iommufd_destroy() */ + if (vdev_id) + iommufd_object_remove(idev->ictx, NULL, vdev_id, 0); + iommufd_object_destroy_user(idev->ictx, &idev->obj); } EXPORT_SYMBOL_NS_GPL(iommufd_device_unbind, IOMMUFD); diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index ab5ee325d809..696ac9e0e74b 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -322,6 +322,7 @@ 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 @@ -375,6 +376,8 @@ 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, __reserved2), #ifdef CONFIG_IOMMUFD_TEST IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last), #endif @@ -513,6 +516,10 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_VIOMMU] = { .destroy = iommufd_viommu_destroy, }, + [IOMMUFD_OBJ_VDEVICE] = { + .destroy = iommufd_vdevice_destroy, + .abort = iommufd_vdevice_abort, + }, #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 eb41e15ebab1..2b9a9a80298d 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -12,6 +12,7 @@ void iommufd_viommu_destroy(struct iommufd_object *obj) if (viommu->ops && viommu->ops->free) viommu->ops->free(viommu); refcount_dec(&viommu->hwpt->common.obj.users); + xa_destroy(&viommu->vdevs); }
int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) @@ -70,6 +71,7 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) */ viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev);
+ xa_init(&viommu->vdevs); refcount_inc(&viommu->hwpt->common.obj.users);
cmd->out_viommu_id = viommu->obj.id; @@ -87,3 +89,102 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &idev->obj); return rc; } + +void iommufd_vdevice_abort(struct iommufd_object *obj) +{ + struct iommufd_vdevice *old, + *vdev = container_of(obj, struct iommufd_vdevice, obj); + struct iommufd_viommu *viommu = vdev->viommu; + struct iommufd_device *idev = vdev->idev; + + lockdep_assert_held(&idev->igroup->lock); + + old = xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL); + if (old) + WARN_ON(old != vdev); + + refcount_dec(&viommu->obj.users); + refcount_dec(&idev->obj.users); + idev->vdev = NULL; +} + +void iommufd_vdevice_destroy(struct iommufd_object *obj) +{ + struct iommufd_vdevice *vdev = + container_of(obj, struct iommufd_vdevice, obj); + + mutex_lock(&vdev->idev->igroup->lock); + iommufd_vdevice_abort(obj); + mutex_unlock(&vdev->idev->igroup->lock); +} + +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; + + 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; + } + + mutex_lock(&idev->igroup->lock); + if (idev->vdev) { + rc = -EEXIST; + goto out_unlock_igroup; + } + + vdev = iommufd_object_alloc(ucmd->ictx, vdev, IOMMUFD_OBJ_VDEVICE); + if (IS_ERR(vdev)) { + rc = PTR_ERR(vdev); + goto out_unlock_igroup; + } + + rc = iommufd_verify_unfinalized_object(ucmd->ictx, &vdev->obj); + if (rc) { + kfree(vdev); + goto out_unlock_igroup; + } + + vdev->idev = idev; + vdev->id = virt_id; + vdev->viommu = viommu; + + idev->vdev = vdev; + refcount_inc(&idev->obj.users); + refcount_inc(&viommu->obj.users); + + curr = xa_cmpxchg(&viommu->vdevs, virt_id, NULL, vdev, GFP_KERNEL); + if (curr) { + rc = xa_err(curr) ?: -EBUSY; + 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_unlock_igroup; + +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &vdev->obj); +out_unlock_igroup: + mutex_unlock(&idev->igroup->lock); + iommufd_put_object(ucmd->ictx, &idev->obj); +out_put_viommu: + iommufd_put_object(ucmd->ictx, &viommu->obj); + return rc; +}