@@ -7,7 +7,8 @@ iommufd-y := \
ioas.o \
main.o \
pages.o \
- vfio_compat.o
+ vfio_compat.o \
+ viommu.o
iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o
@@ -504,6 +504,9 @@ static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
}
+int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd);
+void iommufd_viommu_destroy(struct iommufd_object *obj);
+
#ifdef CONFIG_IOMMUFD_TEST
int iommufd_test(struct iommufd_ucmd *ucmd);
void iommufd_selftest_destroy(struct iommufd_object *obj);
@@ -51,6 +51,7 @@ enum {
IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c,
IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d,
IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e,
+ IOMMUFD_CMD_VIOMMU_ALLOC = 0x8f,
};
/**
@@ -852,4 +853,43 @@ struct iommu_fault_alloc {
__u32 out_fault_fd;
};
#define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC)
+
+/**
+ * enum iommu_viommu_type - Virtual IOMMU Type
+ * @IOMMU_VIOMMU_TYPE_DEFAULT: Reserved for future use
+ */
+enum iommu_viommu_type {
+ IOMMU_VIOMMU_TYPE_DEFAULT = 0,
+};
+
+/**
+ * struct iommu_viommu_alloc - ioctl(IOMMU_VIOMMU_ALLOC)
+ * @size: sizeof(struct iommu_viommu_alloc)
+ * @flags: Must be 0
+ * @type: Type of the virtual IOMMU. Must be defined in enum iommu_viommu_type
+ * @dev_id: The device's physical IOMMU will be used to back the virtual IOMMU
+ * @hwpt_id: ID of a nesting parent HWPT to associate to
+ * @out_viommu_id: Output virtual IOMMU ID for the allocated object
+ *
+ * Allocate a virtual IOMMU object, representing the underlying physical IOMMU's
+ * virtualization support that is a security-isolated slice of the real IOMMU HW
+ * that is unique to a specific VM. Operations global to the IOMMU are connected
+ * to the vIOMMU, such as:
+ * - Security namespace for guest owned ID, e.g. guest-controlled cache tags
+ * - Access to a sharable nesting parent pagetable across physical IOMMUs
+ * - Non-affiliated event reporting (e.g. an invalidation queue error)
+ * - Virtualization of various platforms IDs, e.g. RIDs and others
+ * - Delivery of paravirtualized invalidation
+ * - Direct assigned invalidation queues
+ * - Direct assigned interrupts
+ */
+struct iommu_viommu_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 type;
+ __u32 dev_id;
+ __u32 hwpt_id;
+ __u32 out_viommu_id;
+};
+#define IOMMU_VIOMMU_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VIOMMU_ALLOC)
#endif
@@ -321,6 +321,7 @@ union ucmd_buffer {
struct iommu_ioas_unmap unmap;
struct iommu_option option;
struct iommu_vfio_ioas vfio_ioas;
+ struct iommu_viommu_alloc viommu;
#ifdef CONFIG_IOMMUFD_TEST
struct iommu_test_cmd test;
#endif
@@ -372,6 +373,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
val64),
IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas,
__reserved),
+ IOCTL_OP(IOMMU_VIOMMU_ALLOC, iommufd_viommu_alloc_ioctl,
+ struct iommu_viommu_alloc, out_viommu_id),
#ifdef CONFIG_IOMMUFD_TEST
IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last),
#endif
@@ -507,6 +510,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
[IOMMUFD_OBJ_FAULT] = {
.destroy = iommufd_fault_destroy,
},
+ [IOMMUFD_OBJ_VIOMMU] = {
+ .destroy = iommufd_viommu_destroy,
+ },
#ifdef CONFIG_IOMMUFD_TEST
[IOMMUFD_OBJ_SELFTEST] = {
.destroy = iommufd_selftest_destroy,
new file mode 100644
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES
+ */
+
+#include "iommufd_private.h"
+
+void iommufd_viommu_destroy(struct iommufd_object *obj)
+{
+ struct iommufd_viommu *viommu =
+ container_of(obj, struct iommufd_viommu, obj);
+
+ if (viommu->ops && viommu->ops->free)
+ viommu->ops->free(viommu);
+ refcount_dec(&viommu->hwpt->common.obj.users);
+}
+
+int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
+{
+ struct iommu_viommu_alloc *cmd = ucmd->cmd;
+ struct iommufd_hwpt_paging *hwpt_paging;
+ struct iommufd_viommu *viommu;
+ struct iommufd_device *idev;
+ const struct iommu_ops *ops;
+ int rc;
+
+ if (cmd->flags || cmd->type == IOMMU_VIOMMU_TYPE_DEFAULT)
+ return -EOPNOTSUPP;
+
+ idev = iommufd_get_device(ucmd, cmd->dev_id);
+ if (IS_ERR(idev))
+ return PTR_ERR(idev);
+
+ ops = dev_iommu_ops(idev->dev);
+ if (!ops->viommu_alloc) {
+ rc = -EOPNOTSUPP;
+ goto out_put_idev;
+ }
+
+ hwpt_paging = iommufd_get_hwpt_paging(ucmd, cmd->hwpt_id);
+ if (IS_ERR(hwpt_paging)) {
+ rc = PTR_ERR(hwpt_paging);
+ goto out_put_idev;
+ }
+
+ if (!hwpt_paging->nest_parent) {
+ rc = -EINVAL;
+ goto out_put_hwpt;
+ }
+
+ viommu = ops->viommu_alloc(idev->dev, hwpt_paging->common.domain,
+ ucmd->ictx, cmd->type);
+ if (IS_ERR(viommu)) {
+ rc = PTR_ERR(viommu);
+ goto out_put_hwpt;
+ }
+
+ rc = iommufd_verify_unfinalized_object(ucmd->ictx, &viommu->obj);
+ if (rc) {
+ kfree(viommu);
+ goto out_put_hwpt;
+ }
+
+ viommu->type = cmd->type;
+ viommu->ictx = ucmd->ictx;
+ viommu->hwpt = hwpt_paging;
+ /*
+ * It is the most likely case that a physical IOMMU is unpluggable. A
+ * pluggable IOMMU instance (if exists) is responsible for refcounting
+ * on its own.
+ */
+ viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev);
+
+ refcount_inc(&viommu->hwpt->common.obj.users);
+
+ cmd->out_viommu_id = viommu->obj.id;
+ rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+ if (rc)
+ goto out_abort;
+ iommufd_object_finalize(ucmd->ictx, &viommu->obj);
+ goto out_put_hwpt;
+
+out_abort:
+ iommufd_object_abort_and_destroy(ucmd->ictx, &viommu->obj);
+out_put_hwpt:
+ iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
+out_put_idev:
+ iommufd_put_object(ucmd->ictx, &idev->obj);
+ return rc;
+}