Cache Coherency and NUMA Balancing Performance Pathologies in AMD  SEV-SNP Confidential Virtual Machines: A Real-World Kernel-Level Case  Study

Ashish Kalra

Cache Coherency and NUMA Balancing Performance Pathologies in AMD SEV-SNP Confidential Virtual Machines: A Real-World Kernel-Level Case Study

Authors

Ashish Kalra

Keywords:

AMD SEV-SNP Cache Coherency, Confidential Virtual Machine Performance Regression, Linux KVM MMU Notifier Mechanism, NUMA Autobalancing Pinned Memory Pathology, Guest_memfd Confidential Computing Architecture

Abstract

AMD Secure Nested Paging (SNP) provides hardware-enforced memoryencryption for confidential virtual machines (VMs), but its security mechanisms can interact unexpectedly with the Linux kernel's memory

References

Confidential Computing Consortium, "A Technical Analysis of Confidential Computing," 2023. Available: https://confidentialcomputing.io/wp-content/uploads/sites/10/2023/03/CCC-A-TechnicalAnalysis-of-Confidential-Computing-v1.3_unlocked.pdf

David Kaplan et al., "AMD Memory Encryption," 2021. Available: https://docs.amd.com/v/u/enUS/memory-encryption-white-paper

Downloads

Published

2026-05-19

How to Cite

Ashish Kalra. (2026). Cache Coherency and NUMA Balancing Performance Pathologies in AMD SEV-SNP Confidential Virtual Machines: A Real-World Kernel-Level Case Study . Journal of Computational Analysis and Applications (JoCAAA), 35(5), 245–256. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/5479