iommufd: Add IOMMU_HWPT_INVALIDATE

In nested translation, the stage-1 page table is user-managed but cached
by the IOMMU hardware, so an update on present page table entries in the
stage-1 page table should be followed with a cache invalidation.

Add an IOMMU_HWPT_INVALIDATE ioctl to support such a cache invalidation.
It takes hwpt_id to specify the iommu_domain, and a multi-entry array to
support multiple invalidation data in one ioctl.

enum iommu_hwpt_invalidate_data_type is defined to tag the data type of
the entries in the multi-entry array.

Link: https://lore.kernel.org/r/20240111041015.47920-3-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Co-developed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Author: yiliu1765

drivers/iommu/iommufd/hw_pagetable.c

@@ -371,3 +371,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}

drivers/iommu/iommufd/iommufd_private.h

@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)

drivers/iommu/iommufd/main.c

@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,

include/uapi/linux/iommufd.h

@@ -49,6 +49,7 @@ enum {
 	IOMMUFD_CMD_GET_HW_INFO,
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
+	IOMMUFD_CMD_HWPT_INVALIDATE,
 };
 
 /**
@@ -613,4 +614,46 @@ struct iommu_hwpt_get_dirty_bitmap {
 #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
 					IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
 
+/**
+ * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation
+ *                                        Data Type
+ * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1
+ */
+enum iommu_hwpt_invalidate_data_type {
+	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+};
+
+/**
+ * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
+ * @size: sizeof(struct iommu_hwpt_invalidate)
+ * @hwpt_id: ID of a nested HWPT for cache invalidation
+ * @data_uptr: User pointer to an array of driver-specific cache invalidation
+ *             data.
+ * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data
+ *             type of all the entries in the invalidation request array. It
+ *             should be a type supported by the hwpt pointed by @hwpt_id.
+ * @entry_len: Length (in bytes) of a request entry in the request array
+ * @entry_num: Input the number of cache invalidation requests in the array.
+ *             Output the number of requests successfully handled by kernel.
+ * @__reserved: Must be 0.
+ *
+ * Invalidate the iommu cache for user-managed page table. Modifications on a
+ * user-managed page table should be followed by this operation to sync cache.
+ * Each ioctl can support one or more cache invalidation requests in the array
+ * that has a total size of @entry_len * @entry_num.
+ *
+ * An empty invalidation request array by setting @entry_num==0 is allowed, and
+ * @entry_len and @data_uptr would be ignored in this case. This can be used to
+ * check if the given @data_type is supported or not by kernel.
+ */
+struct iommu_hwpt_invalidate {
+	__u32 size;
+	__u32 hwpt_id;
+	__aligned_u64 data_uptr;
+	__u32 data_type;
+	__u32 entry_len;
+	__u32 entry_num;
+	__u32 __reserved;
+};
+#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
 #endif