An efficient cache-based access anomaly detection scheme

MinSang, L; ChoiJong-Deok,

doi:10.1145/106973.106996

Cited by 5 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in Section 1, previous works have also investigated hardware and coherence protocol supports for data race detection. Examples include [23,28,32], almost all of which implement the happens-before race detection algorithm by combining with cache coherence protocols in distributed shared memory systems. Most recently, ReEnact [31] employs advanced TLS architecture for race detection and CORD [30] uses scalar logical timestamps to improve the scalability.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

AVIO: Detecting Atomicity Violations via Access-Interleaving Invariants

et al. 2007

View full text Add to dashboard Cite

Concurrency bugs are among the most difficult to test and diagnose of all software bugs. The multicore technology trend worsens this problem. Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important due to the emerging trend of transactional memory models. This paper proposes an innovative, comprehensive, invariantbased approach called AVIO to detect atomicity violations. Our idea is based on a novel observation called access interleaving invariant, which is a good indication of programmers' assumptions about the atomicity of certain code regions. By automatically extracting such invariants and detecting violations of these invariants at run time, AVIO can detect a variety of atomicity violations. Based on this idea, we have designed and built two implementations of AVIO and evaluated the trade-offs between them. The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware. AVIO-S is cheaper and more accurate but incurs much higher overhead and thus more run-time perturbation than AVIO-H. Therefore, AVIO-S is more suitable for in-house bug detection and postmortem bug diagnosis, while AVIO-H can be used for bug detection during production runs. We evaluate both implementations of AVIO using large realworld server applications (Apache and MySQL) with six representative real atomicity violation bugs, and SPLASH-2 benchmarks. Our results show that AVIO detects more tested atomicity violations of various types and has 25 times fewer false positives than previous solutions on average.

show abstract

Section: Related Workmentioning

confidence: 99%

“…A data race bug is reported when two conflicting memory accesses do not have a strict happens-before relation. Different forms of happens-before algorithm have been implemented in hardware [23,30,31] to overcome the overhead problem (i.e. factor of 10 to 100 slowdowns) in software race detection.…”

Section: Introduction 11 Motivationmentioning

confidence: 99%

AVIO: Detecting Atomicity Violations via Access-Interleaving Invariants

et al. 2007

View full text Add to dashboard Cite

show abstract

“…There are also proposals for race detectors with hardware assists. Some() detect races by tagging the state in the caches as it is being accessed and then piggybacking the tags on cache coherence protocol messages between processors so that they can be compared. The hardware can easily detect an address and an instruction involved in a race on the fly.…”

Section: Discussionmentioning

confidence: 99%

A survey of the double‐fetch vulnerabilities

Wang

Lü

et al. 2017

Concurrency and Computation

View full text Add to dashboard Cite

Summary Race conditions widely exist in concurrent programs, and concurrency errors caused by harmful races could lead to severe system failures. A double fetch is a typical situation when the system kernel inevitably accesses user space data multiple times, and it turns into a vulnerability when the data consistency is violated under a special race condition between kernel and user space. In this survey, we present the first (to the best of our knowledge) comprehensive study on double‐fetch vulnerabilities in the real world. Our study is based on the investigation of 91 real‐world double‐fetch vulnerabilities collected from the CVE database and other relevant reports, which covers a period of recent 12 years. Our work reveals some interesting findings on the double‐fetch vulnerabilities, ranging from the various occurrences across different kernels and system levels to the involvement of specific patterns. We also divide the consequences that are usually caused by the double‐fetch vulnerabilities into four categories and discuss each, summarize viable exploitation techniques from existing works, provide useful guidances to detect and practical strategies to prevent double‐fetch vulnerabilities.

show abstract

“…Their compression later became the foundation of Netzer's transitivity reduction [15]. Even lower overhead was achieved with a hardware race detector of Min and Choi [14]. Based on cache coherence, this detector timestamps cache blocks with synchronization "era" (with respect to fork/join/barrier synchronizations).…”

Section: The Upper Half Ofmentioning

confidence: 99%