iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct

Add a new IOMMUFD_OBJ_VIOMMU with an iommufd_viommu structure to represent
a slice of physical IOMMU device passed to or shared with a user space VM.
This slice, now a vIOMMU object, is a group of virtualization resources of
a physical IOMMU's, such as:
 - Security namespace for guest owned ID, e.g. guest-controlled cache tags
 - Non-device-affiliated event reporting, e.g. invalidation queue errors
 - Access to a sharable nesting parent pagetable across physical IOMMUs
 - Virtualization of various platforms IDs, e.g. RIDs and others
 - Delivery of paravirtualized invalidation
 - Direct assigned invalidation queues
 - Direct assigned interrupts

Add a new viommu_alloc op in iommu_ops, for drivers to allocate their own
vIOMMU structures. And this allocation also needs a free(), so add struct
iommufd_viommu_ops.

To simplify a vIOMMU allocation, provide a iommufd_viommu_alloc() helper.
It's suggested that a driver should embed a core-level viommu structure in
its driver-level viommu struct and call the iommufd_viommu_alloc() helper,
meanwhile the driver can also implement a viommu ops:
    struct my_driver_viommu {
        struct iommufd_viommu core;
        /* driver-owned properties/features */
        ....
    };

    static const struct iommufd_viommu_ops my_driver_viommu_ops = {
        .free = my_driver_viommu_free,
        /* future ops for virtualization features */
        ....
    };

    static struct iommufd_viommu my_driver_viommu_alloc(...)
    {
        struct my_driver_viommu *my_viommu =
                iommufd_viommu_alloc(ictx, my_driver_viommu, core,
                                     my_driver_viommu_ops);
        /* Init my_viommu and related HW feature */
        ....
        return &my_viommu->core;
    }

    static struct iommu_domain_ops my_driver_domain_ops = {
        ....
        .viommu_alloc = my_driver_viommu_alloc,
    };

Link: https://patch.msgid.link/r/64685e2b79dea0f1dc56f6ede04809b72d578935.1730836219.git.nicolinc@nvidia.com
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

2 files changed, 54 insertions, 0 deletions

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index bd722f473635..2574fc8abaf2 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -42,6 +42,8 @@ struct notifier_block;
 struct iommu_sva;
 struct iommu_dma_cookie;
 struct iommu_fault_param;
+struct iommufd_ctx;
+struct iommufd_viommu;
 
 #define IOMMU_FAULT_PERM_READ	(1 << 0) /* read */
 #define IOMMU_FAULT_PERM_WRITE	(1 << 1) /* write */
@@ -542,6 +544,14 @@ static inline int __iommu_copy_struct_from_user_array(
  * @remove_dev_pasid: Remove any translation configurations of a specific
  *                    pasid, so that any DMA transactions with this pasid
  *                    will be blocked by the hardware.
+ * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind
+ *                the @dev, as the set of virtualization resources shared/passed
+ *                to user space IOMMU instance. And associate it with a nesting
+ *                @parent_domain. The @viommu_type must be defined in the header
+ *                include/uapi/linux/iommufd.h
+ *                It is required to call iommufd_viommu_alloc() helper for
+ *                a bundled allocation of the core and the driver structures,
+ *                using the given @ictx pointer.
  * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @owner: Driver module providing these ops
  * @identity_domain: An always available, always attachable identity
@@ -591,6 +601,10 @@ struct iommu_ops {
 	void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid,
 				 struct iommu_domain *domain);
 
+	struct iommufd_viommu *(*viommu_alloc)(
+		struct device *dev, struct iommu_domain *parent_domain,
+		struct iommufd_ctx *ictx, unsigned int viommu_type);
+
 	const struct iommu_domain_ops *default_domain_ops;
 	unsigned long pgsize_bitmap;
 	struct module *owner;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 94522d4029ca..4fc2ce332f10 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -17,6 +17,7 @@ struct iommu_group;
 struct iommufd_access;
 struct iommufd_ctx;
 struct iommufd_device;
+struct iommufd_viommu_ops;
 struct page;
 
 enum iommufd_object_type {
@@ -28,6 +29,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_IOAS,
 	IOMMUFD_OBJ_ACCESS,
 	IOMMUFD_OBJ_FAULT,
+	IOMMUFD_OBJ_VIOMMU,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
@@ -78,6 +80,26 @@ void iommufd_access_detach(struct iommufd_access *access);
 
 void iommufd_ctx_get(struct iommufd_ctx *ictx);
 
+struct iommufd_viommu {
+	struct iommufd_object obj;
+	struct iommufd_ctx *ictx;
+	struct iommu_device *iommu_dev;
+	struct iommufd_hwpt_paging *hwpt;
+
+	const struct iommufd_viommu_ops *ops;
+
+	unsigned int type;
+};
+
+/**
+ * struct iommufd_viommu_ops - vIOMMU specific operations
+ * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory
+ *           of the vIOMMU will be free-ed by iommufd core after calling this op
+ */
+struct iommufd_viommu_ops {
+	void (*destroy)(struct iommufd_viommu *viommu);
+};
+
 #if IS_ENABLED(CONFIG_IOMMUFD)
 struct iommufd_ctx *iommufd_ctx_from_file(struct file *file);
 struct iommufd_ctx *iommufd_ctx_from_fd(int fd);
@@ -148,4 +170,22 @@ _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size,
 	return ERR_PTR(-EOPNOTSUPP);
 }
 #endif /* CONFIG_IOMMUFD_DRIVER_CORE */
+
+/*
+ * Helpers for IOMMU driver to allocate driver structures that will be freed by
+ * the iommufd core. The free op will be called prior to freeing the memory.
+ */
+#define iommufd_viommu_alloc(ictx, drv_struct, member, viommu_ops)             \
+	({                                                                     \
+		drv_struct *ret;                                               \
+									       \
+		static_assert(__same_type(struct iommufd_viommu,               \
+					  ((drv_struct *)NULL)->member));      \
+		static_assert(offsetof(drv_struct, member.obj) == 0);          \
+		ret = (drv_struct *)_iommufd_object_alloc(                     \
+			ictx, sizeof(drv_struct), IOMMUFD_OBJ_VIOMMU);         \
+		if (!IS_ERR(ret))                                              \
+			ret->member.ops = viommu_ops;                          \
+		ret;                                                           \
+	})
 #endif