Modern extensible web platforms like Facebook and Yammer depend on third-party software to offer a rich experience to their users. Unfortunately, users running a third-party "app" have little control over what it does with their private data. Today's platforms offer only ad-hoc constraints on app behavior, leaving users an unfortunate trade-off between convenience and privacy. A principled approach to code confinement could allow the integration of untrusted code while enforcing flexible, end-to-end policies on data access. This paper presents a new web framework, Hails, that adds mandatory access control and a declarative policy language to the familiar MVC architecture. We demonstrate the flexibility of Hails through GitStar.com, a code-hosting website that enforces robust privacy policies on user data even while allowing untrusted apps to deliver extended features to users.

Abstract. Information flow control allows untrusted code to access sensitive and trustworthy information without leaking this information. However, the presence of covert channels subverts this security mechanism, allowing processes to communicate information in violation of IFC policies. In this paper, we show that concurrent deterministic IFC systems that use time-based scheduling are vulnerable to a cache-based internal timing channel. We demonstrate this vulnerability with a concrete attack on Hails, one particular IFC web framework. To eliminate this internal timing channel, we implement instruction-based scheduling, a new kind of scheduler that is indifferent to timing perturbations from underlying hardware components, such as the cache, TLB, and CPU buses. We show this scheduler is secure against cache-based internal timing attacks for applications using a single CPU. To show the feasibility of instruction-based scheduling, we have implemented a version of Hails that uses the CPU retired-instruction counters available on commodity Intel and AMD hardware. We show that instruction-based scheduling does not impose significant performance penalties. Additionally, we formally prove that our modifications to Hails' underlying IFC system preserve non-interference in the presence of caches.

We present Castor, a record/replay system for multi-core applications that provides consistently low and predictable overheads. With Castor, developers can leave record and replay on by default, making it practical to record and reproduce production bugs, or employ fault tolerance to recover from hardware failures. Castor is inspired by several observations: First, an efficient mechanism for logging non-deterministic events is critical for recording demanding workloads with low overhead. Through careful use of hardware we were able to increase log throughput by 10× or more, e.g., we could record a server handling 10× more requests per second for the same record overhead. Second, most applications can be recorded without modifying source code by using the compiler to instrument language level sources of non-determinism, in conjunction with more familiar techniques like shared library interposition. Third, while Castor cannot deterministically replay all data races, this limitation is generally unimportant in practice, contrary to what prior work has assumed. Castor currently supports applications written in C, C++, and Go on FreeBSD. We have evaluated Castor on parallel and server workloads, including a commercial implementation of memcached in Go, which runs Castor in production. CCS Concepts • Software and its engineering → Operating systems

We present Castor, a record/replay system for multi-core applications that provides consistently low and predictable overheads. With Castor, developers can leave record and replay on by default, making it practical to record and reproduce production bugs, or employ fault tolerance to recover from hardware failures. Castor is inspired by several observations: First, an efficient mechanism for logging non-deterministic events is critical for recording demanding workloads with low overhead. Through careful use of hardware we were able to increase log throughput by 10× or more, e.g., we could record a server handling 10× more requests per second for the same record overhead. Second, most applications can be recorded without modifying source code by using the compiler to instrument language level sources of non-determinism, in conjunction with more familiar techniques like shared library interposition. Third, while Castor cannot deterministically replay all data races, this limitation is generally unimportant in practice, contrary to what prior work has assumed. Castor currently supports applications written in C, C++, and Go on FreeBSD. We have evaluated Castor on parallel and server workloads, including a commercial implementation of memcached in Go, which runs Castor in production. CCS Concepts • Software and its engineering → Operating systems

No abstract