iommu: Add cache_invalidate_user op

The updates of the PTEs in the nested page table will be propagated to the
hardware caches.

Add a new domain op cache_invalidate_user() for the userspace to flush the
hardware caches for a nested domain through iommufd. No wrapper for it, as
it's only supposed to be used by iommufd. Then, pass in invalidation
requests in form of a user data array containing a number of invalidation
data entries.

Link: https://lore.kernel.org/r/20240111041015.47920-2-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.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: LuBaolu

include/linux/iommu.h

@@ -284,6 +284,23 @@ struct iommu_user_data {
 	size_t len;
 };
 
+/**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
 /**
  * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
  * @dst_data: Pointer to an iommu driver specific user data that is defined in
@@ -440,6 +457,13 @@ struct iommu_ops {
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
@@ -465,6 +489,8 @@ struct iommu_domain_ops {
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);