A device and method for performing saturated addressing load and store operations

Abstract

The present invention relates to apparatus and methods for performing saturated addressing load and store operations, providing logic for receiving and executing saturated addressing data move instructions to compute upper and lower bound locations of an array from array pointers and array pointer metadata. If the source position of the load operation is higher than the upper bound position or lower than the lower bound position, the data is transferred from the upper bound position or the lower bound position to the destination position, otherwise, it is transferred from the source position to the destination position. If the destination location of the store operation is higher than the upper bound location or lower than the lower bound location, the data is transferred from the source location to the upper bound location or the lower bound location, otherwise, it is transferred from the source location to the destination location.

Description

technical field [0001] The invention belongs to the field of memory security, and in particular relates to a processing method and device for saturated memory access operations. Background technique [0002] Computing equipment is currently widely used in medical care, transportation, infrastructure and manufacturing industries, and is responsible for such as: collection and processing of data information in the physical world, network data exchange, data processing analysis calculation and service provision. Computing devices usually have the characteristics of exchanging data through the network, providing real-time services for people's daily life, and carrying important private data; they are also gathering points for illegal personnel to obtain private data and destroy various services. At present, attacks against computing devices emerge in endlessly, and the damage is huge. The more famous ones are bleeding attacks, worms, and so on. At present, the attacks on comput...

AI Technical Summary

Problems solved by technology

[0003] Software attacks based on buffer overflow can basically pass through the CFI (Control Flow Integrity) and DFI (Data Flow Integrity) inspection mechanisms, and report in the form of exceptions or errors, but the unsupervised feature makes exceptions or errors impossible Being processed also makes the inspection meaningless. Secondly, this type of inspection mechanism mostly finds buffer overflow problems in the form of software, which often has a relatively large additional performance loss. The way to check buffer overflow has a small performance loss, but because BIMA indicates that the buffer base address and boundary are relatively complicated, the judgment of buffer overflow still has a relatively high cost and needs to be further improved; mainstream computing equipment is safe The defense methods are all detection technologies. Generally, once the attack is attacked, the program will be terminated and the abnormal information will be reported, or only the abnormal information will be reported, but the attack has not terminated.

Of the above two methods, the former will cause the service to be unavailable, and the latter will cause the user’s private data to be stolen as well.

Buffer overflow attacks cannot be reasonably eliminated, and the problems of service availability and user data security cannot be considered at the same time

[0004] To sum up, for this type of critical computing equipment, the existing buffer overflow detection mechanism has the problems of large additional performance loss, overflow exception cannot be processed in time, and user data is highly dangerous

Images