Efficient Buffer Overflow Detection on GPU
- 8 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 32 (5) , 1161-1177
Abstract
Rich thread-level parallelism of GPU has motivated co-running GPU kernels on a single GPU. However, when GPU kernels co-run, it is possible that one kernel can leverage buffer overflow to attack another kernel running on the same GPU. Existing work has either large performance overhead or limited capability in detecting buffer overflow. In this paper, we introduce GMODx, a runtime software system that can detect GPU buffer overflow. GMODx performs always-on monitoring on allocated memory based on canary-based design. First, for fine-grained memory management, GMODx introduces a set of byte arrays to store buffer information for overflow detection. Techniques, including lock-free accesses to the byte arrays, delayed memory free, efficient memory reallocation, and garbage collection for the byte arrays, are proposed to achieve high performance. Second, for coarse-grained memory management, GMODx utilizes unified memory to delegate the always-on monitoring to the CPU. To reduce performance overhead, we propose several techniques, including customized list data structure and specific optimizations against the unified memory. Our experiments show that GMODx is capable of detecting buffer overflow for the fine-grained memory management without performance loss, and that it incurs small runtime overhead (4.2% on average and up to 9.7%) for the coarse-grained memory management.Keywords
Funding Information
- National Natural Science Foundation of China (61972137, 61772183)
- Natural Science Foundation of Hunan Province (2016JJ3042)
This publication has 33 references indexed in Scilit:
- Redundant Network Traffic Elimination with GPU Accelerated Rabin FingerprintingIEEE Transactions on Parallel and Distributed Systems, 2015
- Register Efficient Dynamic Memory Allocator for GPUsComputer Graphics Forum, 2015
- NUPAR2015
- Performance Optimization Using Partitioned SpMV on GPUs and Multicore CPUsIEEE Transactions on Computers, 2014
- Confidentiality Issues on a GPU in a Virtualized Environment2014
- Parallel Implementation of MAFFT on CUDA-Enabled Graphics HardwareIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2014
- BAG: Managing GPU as Buffer Cache in Operating SystemsIEEE Transactions on Parallel and Distributed Systems, 2013
- The Morris worm: a fifteen-year perspectiveIEEE Security & Privacy, 2003
- Inside the Slammer wormIEEE Security & Privacy, 2003
- Code red worm propagation modeling and analysis2002