(Mostly) Exitless VM Protection from Untrusted Hypervisor through Disaggregated Nested Virtualization
Zeyu Mi, Dingji Li, Haibo Chen, Binyu Zang, Haibing Guan
摘要
Today's cloud tenants are facing severe security threats such as compromised hypervisors, which forces a strong adversary model where the hypervisor should be excluded out of the TCB. Previous approaches to shielding guest VMs either suffer from insufficient protection or result in suboptimal performance due to frequent VM exits (especially for I/O operations). This paper presents CloudVisor-D, an efficient nested hypervisor design that embraces both strong protection and high performance. The core idea of CloudVisor-D is to disaggregate the nested hypervisor by separating major protection logics into a protected Guardian-VM alongside each guest VM. The Guardian-VM is securely isolated and protected by the nested hypervisor and provides secure services for most privileged operations like hypercalls, EPT violations and I/O operations from guest VMs. By leveraging recent hardware features, most privileged operations from a guest VM require no VM exits to the nested hypervisor, which are the major sources of performance slowdown in prior designs. We have implemented CloudVisor-D on a commercially available machine with these recent hardware features. Experimental evaluation shows that CloudVisor-D incurs negligible performance overhead even for I/O intensive benchmarks and in some cases outperforms a vanilla hypervisor due to the reduced number of VM exits.
Contributions. To summarize, this paper makes the following contributions:
• A disaggregated nested virtualization design to shield
VMs from an untrusted hypervisor which reduces a large number of VM exits.
• A set of techniques to achieve the same level of security as the nested virtualization.
• Implementation and evaluation of our design on a commercially available machine.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- TwinVisor: Hardware-isolated Confidential Virtual Machines for ARMDingji Li, Zeyu Mi, Yubin Xia, Binyu Zang 等SOSP 2021 · 被引用 39 次
- Blindfold: Confidential Memory Management by Untrusted Operating SystemCaihua Li, Seung-Seob Lee, Lin ZhongNDSS 2025
- BULKHEAD: Secure, Scalable, and Efficient Kernel Compartmentalization with PKSYinggang Guo, Zicheng Wang, Weiheng Bai, Qingkai Zeng 等NDSS 2025
它引用的顶会 Paper6
- Spectre Attacks: Exploiting Speculative ExecutionPaul Kocher, Jann Horn, Anders Fogh, Daniel Genkin 等S&P 2019 · 被引用 2,435 次
- Meltdown: Reading Kernel Memory from User SpaceMoritz Lipp, Michael Schwarz, Daniel Gruss, Thomas Prescher 等USENIX Security 2018 · 被引用 1,456 次
- T-SGX: Eradicating Controlled-Channel Attacks Against Enclave ProgramsMing-Wei Shih, Sangho Lee, Taesoo Kim, Marcus PeinadoNDSS 2017 · 被引用 431 次
- SGX-Shield: Enabling Address Space Layout Randomization for SGX ProgramsJaebaek Seo, Byoungyoung Lee, Seong-Min Kim, Ming-Wei Shih 等NDSS 2017 · 被引用 227 次
- Deconstructing XenLe Shi, Yuming Wu, Yubin Xia, Nathan Dautenhahn 等NDSS 2017 · 被引用 54 次
相关 Paper
- Nested SEV: Secure and Generic SEV Support for Nested VirtualizationKazuki Takiguchi, Kenichi KouraiOSDI 2026
- Security and Performance in the Delegated User-level VirtualizationJiahao Chen, Dingji Li, Zeyu Mi, Yuxuan Liu 等OSDI 2023 · 被引用 10 次
- Optimizing Nested Virtualization Performance Using Direct Virtual HardwareJin Tack Lim, Jason NiehASPLOS 2020 · 被引用 34 次
- Hardening Hypervisors with OmbroEthan Johnson, Colin Pronovost, John CriswellUSENIX ATC 2022
- Protecting Cloud Virtual Machines from Hypervisor and Host Operating System ExploitsShih-Wei Li, John S. Koh, Jason NiehUSENIX Security 2019 · 被引用 49 次
