TwinVisor: Hardware-isolated Confidential Virtual Machines for ARM

47Citations
Citations of this article
30Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Confidential VM, which offers an isolated execution environment for cloud tenants with limited trust in the cloud provider, has recently been deployed in major clouds such as AWS and Azure. However, while ARM has become increasingly popular in cloud data centers, existing confidential VM designs mainly leverage specialized x86 hardware extensions (e.g., AMD SEV and Intel TDX) to isolate VMs upon a shared hypervisor. This paper proposes TwinVisor, the first system that enables the hardware-enforced isolation of confidential VMs on ARM platforms. TwinVisor takes advantage of the mature ARM TrustZone to run two isolated hypervisors, one in the secure world (called S-visor in this paper) and the other in the normal world (called N-visor), to support normal VMs and confidential VMs respectively. Instead of building a new S-visor from scratch, our design decouples protection from resource management, and reuses most functionalities of a full-fledged N-visor to minimize the size of S-visor. We have built two prototypes of TwinVisor: one on an official ARM simulator with S-EL2 enabled to validate functional correctness and the other on an ARM development board to evaluate performance. The S-visor comprises 5.8K LoCs while the N-visor introduces 906 LoC changes to KVM. According to our evaluation, TwinVisor can run unmodified VM images as confidential VMs while incurring less than 5% performance overhead for various real-world workloads on SMP VMs.

Cite

CITATION STYLE

APA

Li, D., Mi, Z., Xia, Y., Zang, B., Chen, H., & Guan, H. (2021). TwinVisor: Hardware-isolated Confidential Virtual Machines for ARM. In SOSP 2021 - Proceedings of the 28th ACM Symposium on Operating Systems Principles (pp. 638–654). Association for Computing Machinery, Inc. https://doi.org/10.1145/3477132.3483554

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free