Cloud Server Hardware Partitioning for Secure Core Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud computing environments, such as bare-metal and VM environments, face inefficiencies in resource allocation and security vulnerabilities due to shared computing resources and hypervisor management.
Innovation Solution
A cloud computing system that statically partitions a cloud server's computing resources, using a management core to partition processor cores and implement distributed virtual memory hubs and interrupt interposers to ensure secure, isolated usage of resources without a hypervisor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If cloud computing environments use shared computing resources and hypervisor management, then resource allocation flexibility is improved, but security vulnerabilities increase
Solution Approach 1:
The system segments processor cores into distinct partitions, where each partition is isolated from others. This segmentation allows flexible resource allocation to different customers while preventing security vulnerabilities from propagating across partitions, as each partition operates independently with its own set of processor cores.
2Productivity
If cloud computing environments use shared computing resources, then resource utilization efficiency is improved, but security vulnerabilities due to inter-partition communication increase
Solution Approach 1:
Processor cores are divided into separate partitions that can be independently allocated to different customers. This segmentation maintains high resource utilization efficiency by allowing flexible allocation while eliminating security vulnerabilities associated with inter-partition communication, as partitions are isolated by default.
Solution Approach 2:
The system extracts and removes the hypervisor layer that enables inter-partition communication. By taking out this intermediary component, the patent achieves secure isolation between partitions while maintaining efficient resource utilization through direct hardware partitioning.
3Adaptability or versatility
If cloud computing environments use hypervisor management, then resource allocation flexibility is improved, but susceptibility to hypervisor attacks increases
Solution Approach 1:
The patent extracts and removes the hypervisor from the system architecture. By eliminating this component, the system achieves resource allocation flexibility through direct hardware partitioning while completely eliminating the attack surface associated with hypervisor vulnerabilities.
Solution Approach 2:
The system replaces the hypervisor intermediary with direct hardware-based partitioning mechanisms. This elimination of the software intermediary removes the possibility of hypervisor attacks while maintaining resource allocation flexibility through hardware-enforced isolation.
4Productivity
If cloud computing environments use virtualization, then resource sharing is improved, but security isolation between partitions deteriorates
Solution Approach 1:
The system implements hardware-based segmentation of processor cores into partitions, providing strong security isolation while enabling resource sharing. Each partition is physically isolated at the hardware level, preventing security breaches between partitions while allowing efficient resource allocation and sharing across multiple customers.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system comprises one or more processor cores, including a management processor core that executes instructions to partition at least a portion of the one or more processor cores into one or more partitions. The system includes at least one distributed virtual memory (DVM) hub that obtains a first DVM message from a processor core; determines, based on a processor core identifier of the DVM message, one or more recipient processor cores for the first DVM message; and provides the first DVM message to the one or more recipient processor cores. The system includes one or more interrupt interposers that are each associated with a processor core and prevent an interrupt originating from the associated processor core from being provided to a processor core that is outside the partition of the associated processor core.