CROct 27, 2018

FRAMER: A Software-based Capability Model

arXiv:1810.11622v2
Originality Incremental advance
AI Analysis

This work addresses performance and compatibility issues in memory safety for systems programming, offering an incremental improvement over prior methods.

The paper tackles the problem of high overhead in fine-grained memory protection for C/C++ programs by proposing FRAMER, a software capability model that efficiently manages per-object metadata, resulting in improved performance and space savings compared to existing approaches.

Fine-grained memory protection for C and C++ programs must track individual objects (or pointers), and store bounds information per object (pointer). Its cost is dominated by metadata updates and lookups, making efficient metadata management the key for minimizing performance impact. Existing approaches reduce metadata management overheads by sacrificing precision, breaking binary compatibility by changing object memory layout, or wasting space by excessive alignment or large shadow memory spaces. We propose FRAMER, a software capability model for object-granularity memory protection. Its efficient per-object metadata management mechanism enables direct access to metadata by calculating their location from a tagged pointer to the object and, for large objects, a compact supplementary table. The number of bits in this tag and the size of the supplementary table are balanced to minimize both using a novel technique. FRAMER is a general proposal for object metadata management with potential applications in memory safety, type safety, thread safety and garbage collection that improves over previous solutions by (1) increasing locality of reference by having objects carry their metadata, (2) streamlining expensive metadata lookups, (3) saving space by avoiding superfluous alignment and padding, (4) avoiding internal object memory layout changes.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes