Secure hybrid replacement policy: Mitigating conflict-based cache side channel attacks

The sharing of last-level cache (LLC) among different CPU cores makes cache vulnerable to side channel attacks. An attacker can get private information about co-running applications (victims) by monitoring their accesses in LLC. Cache side channel attacks can be mitigated by partitioning cache between the victim and attacker. However, previous partition works either make weak assumptions about the attacker's strength or force their security mechanisms and thus overhead to every user on the system, regardless of their security requirement. We argue that offering security protection as a service is a better choice for secure cache design. To achieve this, we propose Invisible-Victim cache (IVcache), a new cache partition design targeting both the original LLC attack and the new variant. IVcache classifies all security domains on the system as protected and unprotected. For LLC accesses from protected domains, IVcache handles cache state changes in a slightly different way to make those accesses invisible to any other security domains. We implement and evaluate IVcache in Gem5. The experimental results show that IVcache can defend against real-world attacks, and that it introduces negligible performance overhead to protected domains and no overhead to unprotected domains.

Many cache side-channel attacks have been proposed, and they threaten sensitive programs in real-world. The success of the attacks depends on how accurately to decide whether a set of cache lines are in cache or not. However, external factors insert noise into cache attacks, and the noise disturbs the attacks’ decision process. Attacks in last-level cache (LLC) have more noise compared with core-dedicated caches.

The performance of modern multicore processes largely depends on the performance of their shared Last Level Cache (LLC). A larger LLC can reduce misses while increasing access latency. Tile-based chipmultiprocessors (TCMP) are also proposed with two levels of shared caches to handle such situations. Among the two levels of shared caches, the bottom level is designed with DRAM technology for better capacity, and the upper level is designed with SRAM technology for better latency. Because it is in the last level, the LLC is the DRAM-based shared cache. Both the shared caches are normally divided into multiple banks. The core in such TCMPs can have its own private cache above these two levels of shared caches. Process variation has been observed to have a much greater impact on DRAM-based memory chips than on SRAM-based memories. Hence, the banks of the DRAM-based LLC may not behave uniformly. Some of the banks may experience high energy costs and access latency because of PV. In this work, we have proposed a replacement policy for the SRAM-based shared cache (upper-level shared cache), which reduces the requirements to access the PV-affected LLC banks significantly. This is achieved by relaxing the blocks of the affected LLC banks to remain in the upper-level shared cache (SRAM-based) for a longer time. The experimental analysis found that the proposed replacement policy improves performance by 13%, 10%, and 6% as compared to three existing replacement policies.

Recent years have seen a large volume of proposals on managing the shared last-level cache (LLC) of chip-multiprocessors (CMPs). However, most of these proposals primarily focus on reducing the amount of destructive interference between competing independent threads of multi-programmed workloads. While very few of these studies evaluate the proposed policies on shared memory multi-threaded applications, they do not improve constructive cross-thread sharing of data in the LLC In this paper, we characterize a set of multi-threaded applications drawn from the PARSEC, SPEC OMP, and SPLASH-2 suites with the goal of introducing sharing-awareness in LLC replacement policies. We motivate our characterization study by quantifying the potential contributions of the shared and the private blocks toward the overall volume of the LLC hits in these applications and show that the shared blocks are more important than the private blocks. Next, we characterize the amount of sharing-awareness enjoyed by recent proposals compared to the optimal policy. We design and evaluate a generic oracle that can be used in conjunction with any existing policy to quantify the potential improvement that can come from introducing sharing-awareness. The oracle analysis shows that introducing sharing-awareness reduces the number of LLC misses incurred by the least-recently-used (LRU) policy by 6% and 10% on average for a 4MB and 8MB LLC respectively. A realistic implementation of this oracle requires the LLC controller to have the capability to accurately predict, at the time a block is filled into the LLC, whether the block will be shared during its residency in the LLC. We explore the feasibility of designing such a predictor based on the address of the fill and the program counter of the instruction that triggers the fill. Our sharing behavior predictability study of two history-based fill-time predictors that use block addresses and program counters concludes that achieving acceptable levels of accuracy with such predictors will require other architectural and/or high-level program semantic features that have strong correlations with active sharing phases of the LLC blocks.

Nowadays, embedded device applications have become partially correlated and can share platform resources. Cross-execution and sharing resources can cause memory access conflicts, especially in the Last Level Cache (LLC). LLC is a promising candidate for improving system performance on multicore embedded systems. It leads to a reduction in the number of high-latency main memory accesses. Currently, commercial devices can use cache partitioning. The software could better utilize the LLC and conserve energy by caching. This paper proposes a new energy-optimization model for embedded multicore systems based on a reconfigurable artificial neural network LLC architecture. The proposed model uses a machine-learning approach to express the reconfiguration of LLC, and can predict each task’s next interval LLC partitioning factor at runtime. The obtained experimental results reveal that the proposed model - compared to other algorithms - improves energy consumption by 28%, and gives 33% reduction in the LLC miss rate.

Ideally, we could solve all memory performance problems by storing everything in high performance caches. However, the associated high-cost forces us to keep only a limited amount of working sets of data in these caches and the replacement of disposable blocks of data with the desired one is a fundamental property to caches. Ultimately, the performance of a cache is heavily influenced by the replacement policy it uses. In this paper, we conduct a comparative analysis of a few replacement policies currently in use from traditional strategies to the ones that attempt to emulate optimal replacement and simulate a few replacement strategies to test the performance of multilevel cache by configuring the cache memory subsystem in the Multi2sim simulator. We have focused on the shared nature of the last Level Cache (LLC) which includes many coherence problems. This is where directories and coherence protocols come into play. However, the blocks suffer when the directory entries are themselves evicted from the directory. In this paper, we look into a cache coherence mechanism that instead of evicting the block from the private caches when the directory entry is evicted, rather than storing the entry in the LLC slice. This guarantees freedom from the Directory Eviction Victim Blocks (DEVB). We analyze the performance of our proposed replacement technique, namely, coalesce private or spill shared (CPOSS) by varying the size and associativity of the sparse directory by providing the workload from Parsec, Splash2 and FFTW benchmarks and we observe that the CPOSS outperforms the existing least recently used (LRU) in slice LLC banks in Multicore processors.

Closely coupled CPU and GPGPU system with the shared last level cache (LLC) enables fine-grained data exchange. However, traditional data exchange causes unnecessary LLC misses and degrades the entire system performance. We believe that the cache organization is not suitable for the temporary data exchange in the closely coupled system. We analyze the memory access pattern and discover the inefficiency data exchange. When the exchanged data cannot fit in the LLC, the low LLC hit rate exacerbates core stalls and memory contention. We also show that the stalls cannot be entirely covered by increasing the compute load or parallelism. In previous work, a simple LLC buffer is introduced to replace the cache with an architecture-supported data queue. However, the simple design limits the data element size and requires a potentially very large storage for pending requests. In this paper, we propose an improved LLC buffer. It adopts element-atom data organization to enable data exchange of arbitrary size. A simple hardware-software collaborated protocol is adopted, and eliminates the pending requests. The experiment results reveal that it has an average speedup of 48.2% compared with the traditional way, but incurs a 7.5% slowdown compared with the simple LLC buffer due to the overhead of the protocol. We also compare it with the fine-grain task, which implements a data exchange channel between CPU and GPGPU. The results show that the improved LLC buffer has less storage overhead but higher access efficiency than the fine-grain task.

Cache side channel attacks are attacks that leak secret information through physical implementation of cryptographic operations, nullifying cryptographic protection. Recently, these attacks have received great interest. Previous research found that software countermeasures alone are not enough to defend against cache side channel attacks. Secure cache designs can thwart the root causes of cache side channels and are more efficient. For instance, Newcache is a cache design that can enhance security, performance and power efficiency simultaneously through dynamic memory-cache remapping and eviction randomization. However, these cache designs seldom had their security verified experimentally by mounting cache side channel attacks on them.In this paper, we test the security of Newcache using representative classes of cache side channel attacks proposed for conventional set-associative caches. The results show that Newcache can defeat all these attacks. However, what if a very knowledgeable attacker crafted the attack strategy targeting the secure caches design? We redesign the attacks specifically for Newcache. The results show that Newcache can defeat even crafted access-driven attacks specifically targeted at it but sometimes succumbs to the specifically crafted timing attacks, which is due to a very subtle vulnerability in its replacement algorithm. We further secure Newcache by modifying its replacement algorithm slightly, thus defeating these specifically crafted timing attacks. In addition, the improved Newcache simplifies the replacement algorithm in the original Newcache design.

Superpage and page coloring are two important practical techniques to improve the performance of Translation Lookaside Buffers (TLBs) and shared Last Level Cache (LLC) respectively. However, there exists a gap between these two techniques in current hardware-architecture design, resulting in the contradiction in adopting these two optimizations simultaneously: a superpage requires hundreds of contiguous (e.g. a power of two) base pages in both virtual and physical memory, which would compulsorily occupy all available page colors (or cache sets), thus making page coloring failed to work. This is because most contemporary architecture adopts the design with cache set indexes placed in the least significant part of block address. In this paper, we propose a lightweight approach named Scattered Superpage to bridge this gap. Scattered Superpage decouples a superpage from the limitation of occupying multiple contiguous physical base pages. A superpage is still contiguous in virtual memory, but it is scattered mapping into multiple physical superpages, and it just occupies specified partial page colors in each physical superpage, thus it allows us to configure page color for each superpage. The huge TLB is slightly modified to store page color configuration for each superpage and to calculate target physical address based on this configuration when doing address translation. The experimental results show that the Scattered Superpage can improve system performance by 20.51% and reduce unfairness by 27.77% in our 4-core simulation system (with multi-program memory-intensive workloads). It achieves this by reducing last level cache miss by 17.05% and reducing TLB miss by 86.02% simultaneously.

Cloud computing offers cost effective services on-demand which encourage critical infrastructure providers to consider migrating to the cloud. Critical infrastructures are considered as a backbone of modern societies such as power plants and water. Information in cloud computing is likely to be shared among different entities, which could have various degrees of sensitivity. This requires robust isolation and access control mechanisms. Although various access control models and policies have been developed, they cannot fulfil requirements for a cloud based access control system. The reason is that cloud computing has a diverse sets of security requirements and unique security challenges such as multi-tenant and heterogeneity of security policies, rules and domains. This thesis provides a detailed study of cloud computing security challenges and threats, which were used to identify security requirements for various critical infrastructure providers. We found that an access control system is a crucial security requirement for the surveyed critical infrastructure providers. Furthermore, the requirement analysis was used to propose a new criteria to evaluate access control systems for cloud computing. Moreover, this work presents a new cloud based access control model to meet the identified cloud access control requirements. The model does not only ensure the secure sharing of resources among potential untrusted tenants, but also has the capacity to support different access permissions for the same cloud user. Our focused in the proposed model is the lack of data isolation in lower levels (CPU caches), which could lead to bypass access control models to gain some sensitive information by using cache side-channel attacks. Therefore, the thesis investigates various real attack scenarios and the gaps in existing mitigation approaches. It presents a new Prime and Probe cache side-channel attack, which can give detailed information about addresses accessed by a virtual machine with no need for any information about cache sets accessed by the virtual machine. The design, implementation and evaluation of a proposed solution preventing cache side-channel attacks are also presented in the thesis. It is a new lightweight solution, which introduces very low overhead (less than 15,000 CPU cycles). It can be applied in any operating system and prevents cache side-channel attacks in cloud computing. The thesis also presents a new detecting cache side-channel attacks solution. It focuses on the infrastructure used to host cloud computing tenants by counting cache misses caused by a virtual machine. The detection solutions has 0% false negative and 15% false positive.

Die-stacked DRAM technology enables a large Last Level Cache (LLC) that provides high bandwidth data access to the processor. However, it requires a large tag array that may take a significant portion of the on-chip SRAM budget. To reduce this SRAM overhead, systems like Intel Haswell relies on a large block (Mblock) size. One drawback of a large Mblock size is that many bytes of an Mblock are not needed by the processor but are fetched into the cache. A recent technique (Footprint cache) to solve this problem works by dividing the Mblock into smaller blocks where only blocks predicted to be needed by the processor are brought into the LLC. While it helps to alleviate the excessive bandwidth consumption from fetching unneeded blocks, the capacity waste remains: only blocks that are predicted useful are fetched and allocated, and the remaining area of the Mblock is left empty, creating holes. Unfortunately, holes create significant capacity overheads which could have been used for useful data, hence wasted refresh power on useless data. In this paper, we propose a new design, Dense Footprint Cache (DFC). Similar to Footprint cache, DFC uses a large Mblock and relies on useful block prediction in order to reduce memory bandwidth consumption. However, when blocks of an Mblock are fetched, the blocks are placed contiguously in the cache, thereby eliminating holes, increasing capacity and power efficiency, and increasing performance. Mblocks in DFC have variable sizes and a cache set has a variable associativity, hence it presents new challenges in designing its management policies (placement, replacement, and update). Through simulation of Big Data applications, we show that DFC reduces LLC miss ratios by about 43%, speeds up applications by 9.5%, while consuming 4.3% less energy on average.

Cache side-channel attacks exploit cache state changes to steal confidential information. The emergence of transient execution attacks, a new form of microarchitecture side-channel attack that can access any address, makes cache side-channel attacks more threatening. Most of these attacks infer information by measuring the execution time of load operations. Therefore, from the microarchitecture perspective, we propose a novel countermeasure against cache side-channel attacks by eliminating the access time difference caused by cache hits or misses. We use the constant-time loading mechanism to limit each load instruction's execution to a fixed time and specify this mechanism's wake-up condition to avoid excessive performance loss. We modify the CPU pipeline to simulate this design and run SPEC2006 applications. The results show that the performance loss of our mechanism is negligible.

Current Chip Multiprocessors (CMPs) consist of several cores, cache memories and interconnection networks in the same chip. Private last level cache (LLC) configurations assign a static portion of the LLC to each core. This provides lower latency and isolation, at the cost of depriving the system of the possibility of reassigning underutilized resources. A way of taking advantage of underutilized resources in other private LLCs in the same chip is to use the coherence mechanism to determine the state of those caches and spill lines to them. Also, it is well known that memory references are not uniformly distributed across the sets of a set-associative cache. Therefore, applying a uniform spilling policy to all the sets in a cache may not be the best option. This paper proposes Adaptive Set-Granular Cooperative Caching (ASCC), which measures the degree of stress of each set and performs spills between spiller and potential receiver sets, while it tackles capacity problems. Also, it adds a neutral state to prevent sets from being either spillers or receivers when it could be harmful. Furthermore, we propose Adaptive Variable-Granularity Cooperative Caching (AVGCC), which dynamically adjusts the granularity for applying these policies. Both techniques have a negligible storage overhead and can adapt to many core environments using scalable structures. AVGCC improved average performance by 7.8% and reduced average memory latency by 27% related to a traditional private LLC configuration in a 4-core CMP. Finally, we propose an extension of AVGCC to provide Quality of Service that increases the average performance gain to 8.1%.

Inclusive cache hierarchies are widely adopted in modern processors, since they can simplify the implementation of cache coherence. However, it sacrifices some performance to guarantee inclusion. Many recent intelligent management policies are proposed to improve the last-level cache (LLC) performance by evicting blocks with poor locality earlier. Unfortunately, they are inapplicable in inclusive LLCs. In this paper, we propose Two-level Eviction Priority (TEP) policy. Besides the eviction priority provided by the baseline replacement policy, TEP appends an additional high level of eviction priority to LLC blocks, which is decided at the insertion time and cannot be changed during their lifetime in the LLC. When blocks with high eviction priority are not in inner caches anymore, they get evicted from the LLC preferentially. Thus, the LLC can retain more useful blocks to improve performance. TEP can cooperate well with various baseline replacement policies. Our evaluation shows that TEP with NRU can improve the performance of inclusive LLCs significantly while requiring negligible extra storage. It also outperforms other recent proposals including QBS, DIP, and DRRIP.

Cache side-channels are a major threat to cryptographic implementations, particularly block ciphers. Traditional manual hardening methods transform block ciphers into Boolean circuits, a practice refined since the late 90s. The only existing automatic approach based on Boolean circuits achieves security but suffers from performance issues. This paper examines the use of Lookup Tables (LUTs) for automatic hardening of block ciphers against cache side-channel attacks. We present a novel method combining LUT-based synthesis with quantitative static analysis in our HyCaMi framework. Applied to seven block cipher implementations, HyCaMi shows significant improvement in efficiency, being 9.5× more efficient than previous methods, while effectively protecting against cache side-channel attacks. Additionally, for the first time, we explore balancing speed with security by adjusting LUT sizes, providing faster performance with slightly reduced leakage guarantees, suitable for scenarios where absolute security and speed must be balanced.