[PATCH v3 03/11] iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct

[Nicolin Chen <nicolinc@nvidia.com>]

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
 - 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
 - Non-affiliated event reporting

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,
    };

To make the Kernel config work between a driver and the iommufd core, put
the for-driver allocation helpers into a new viommu_api file building with
CONFIG_IOMMUFD_DRIVER.

Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/iommu/iommufd/Makefile          |  2 +-
 drivers/iommu/iommufd/iommufd_private.h |  1 +
 include/linux/iommu.h                   | 14 ++++++
 include/linux/iommufd.h                 | 43 +++++++++++++++++++
 drivers/iommu/iommufd/main.c            | 32 --------------
 drivers/iommu/iommufd/viommu_api.c      | 57 +++++++++++++++++++++++++
 6 files changed, 116 insertions(+), 33 deletions(-)
 create mode 100644 drivers/iommu/iommufd/viommu_api.c

diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile
index cf4605962bea..93daedd7e5c8 100644
--- a/drivers/iommu/iommufd/Makefile
+++ b/drivers/iommu/iommufd/Makefile
@@ -12,4 +12,4 @@ iommufd-y := \
 iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o
 
 obj-$(CONFIG_IOMMUFD) += iommufd.o
-obj-$(CONFIG_IOMMUFD_DRIVER) += iova_bitmap.o
+obj-$(CONFIG_IOMMUFD_DRIVER) += iova_bitmap.o viommu_api.o
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index f2f3a906eac9..6a364073f699 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -131,6 +131,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_IOAS,
 	IOMMUFD_OBJ_ACCESS,
 	IOMMUFD_OBJ_FAULT,
+	IOMMUFD_OBJ_VIOMMU,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c8d18f5f644e..3a50f57b0861 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 +544,13 @@ 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 an @iommu_dev as the group of
+ *                virtualization resources shared/passed to user space IOMMU
+ *                instance. Associate it with a nesting parent @domain. The
+ *                @viommu_type must be defined in include/uapi/linux/iommufd.h
+ *                It is suggested 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 +600,11 @@ struct iommu_ops {
 	void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid,
 				 struct iommu_domain *domain);
 
+	struct iommufd_viommu *(*viommu_alloc)(struct iommu_device *iommu_dev,
+					       struct iommu_domain *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 6b9d46981870..069a38999cdd 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;
 
 /* Base struct for all objects with a userspace ID handle. */
@@ -63,6 +64,26 @@ 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
+ * @free: Free all driver-specific parts of an iommufd_viommu. The memory of the
+ *        vIOMMU will be free-ed by iommufd core after calling this free op.
+ */
+struct iommufd_viommu_ops {
+	void (*free)(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);
@@ -79,6 +100,9 @@ int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
 int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id);
 int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx);
 int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx);
+struct iommufd_viommu *
+__iommufd_viommu_alloc(struct iommufd_ctx *ictx, size_t size,
+		       const struct iommufd_viommu_ops *ops);
 #else /* !CONFIG_IOMMUFD */
 static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file)
 {
@@ -119,5 +143,24 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
 {
 	return -EOPNOTSUPP;
 }
+
+static inline struct iommufd_viommu *
+__iommufd_viommu_alloc(struct iommufd_ctx *ictx, size_t size,
+		       const struct iommufd_viommu_ops *ops)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 #endif /* CONFIG_IOMMUFD */
+
+/*
+ * Helpers for IOMMU driver to allocate driver structures that will be freed by
+ * the iommufd core. Yet, a driver is responsible for its own struct cleanup.
+ */
+#define iommufd_viommu_alloc(ictx, drv_struct, member, ops)                    \
+	container_of(__iommufd_viommu_alloc(ictx,                              \
+					    sizeof(struct drv_struct) +        \
+					    BUILD_BUG_ON_ZERO(offsetof(        \
+						struct drv_struct, member)),   \
+					    ops),                              \
+		     struct drv_struct, member)
 #endif
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 28e1ef5666e9..92bd075108e5 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -29,38 +29,6 @@ struct iommufd_object_ops {
 static const struct iommufd_object_ops iommufd_object_ops[];
 static struct miscdevice vfio_misc_dev;
 
-struct iommufd_object *iommufd_object_alloc_elm(struct iommufd_ctx *ictx,
-						size_t size,
-						enum iommufd_object_type type)
-{
-	struct iommufd_object *obj;
-	int rc;
-
-	obj = kzalloc(size, GFP_KERNEL_ACCOUNT);
-	if (!obj)
-		return ERR_PTR(-ENOMEM);
-	obj->type = type;
-	/* Starts out bias'd by 1 until it is removed from the xarray */
-	refcount_set(&obj->shortterm_users, 1);
-	refcount_set(&obj->users, 1);
-
-	/*
-	 * Reserve an ID in the xarray but do not publish the pointer yet since
-	 * the caller hasn't initialized it yet. Once the pointer is published
-	 * in the xarray and visible to other threads we can't reliably destroy
-	 * it anymore, so the caller must complete all errorable operations
-	 * before calling iommufd_object_finalize().
-	 */
-	rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY,
-		      xa_limit_31b, GFP_KERNEL_ACCOUNT);
-	if (rc)
-		goto out_free;
-	return obj;
-out_free:
-	kfree(obj);
-	return ERR_PTR(rc);
-}
-
 /*
  * Allow concurrent access to the object.
  *
diff --git a/drivers/iommu/iommufd/viommu_api.c b/drivers/iommu/iommufd/viommu_api.c
new file mode 100644
index 000000000000..c1731f080d6b
--- /dev/null
+++ b/drivers/iommu/iommufd/viommu_api.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES
+ */
+
+#include "iommufd_private.h"
+
+struct iommufd_object *iommufd_object_alloc_elm(struct iommufd_ctx *ictx,
+						size_t size,
+						enum iommufd_object_type type)
+{
+	struct iommufd_object *obj;
+	int rc;
+
+	obj = kzalloc(size, GFP_KERNEL_ACCOUNT);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+	obj->type = type;
+	/* Starts out bias'd by 1 until it is removed from the xarray */
+	refcount_set(&obj->shortterm_users, 1);
+	refcount_set(&obj->users, 1);
+
+	/*
+	 * Reserve an ID in the xarray but do not publish the pointer yet since
+	 * the caller hasn't initialized it yet. Once the pointer is published
+	 * in the xarray and visible to other threads we can't reliably destroy
+	 * it anymore, so the caller must complete all errorable operations
+	 * before calling iommufd_object_finalize().
+	 */
+	rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY,
+		      xa_limit_31b, GFP_KERNEL_ACCOUNT);
+	if (rc)
+		goto out_free;
+	return obj;
+out_free:
+	kfree(obj);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_object_alloc_elm, IOMMUFD);
+
+struct iommufd_viommu *
+__iommufd_viommu_alloc(struct iommufd_ctx *ictx, size_t size,
+		       const struct iommufd_viommu_ops *ops)
+{
+	struct iommufd_viommu *viommu;
+	struct iommufd_object *obj;
+
+	if (WARN_ON(size < sizeof(*viommu)))
+		return ERR_PTR(-EINVAL);
+	obj = iommufd_object_alloc_elm(ictx, size, IOMMUFD_OBJ_VIOMMU);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+	viommu = container_of(obj, struct iommufd_viommu, obj);
+	if (ops)
+		viommu->ops = ops;
+	return viommu;
+}
+EXPORT_SYMBOL_NS_GPL(__iommufd_viommu_alloc, IOMMUFD);
-- 
2.43.0