The rise in memory demands of emerging datacenter applications has placed virtual memory translation in the spotlight, exposing it as a significant performance bottleneck.To address this problem, this paper introduces Learned Virtual Memory (LVM), a page table structure that effectively provides optimal single-access address translation.LVM is founded on a novel learned index model that dynamically adapts the address translation procedure based on the characteristics of an application's virtual address space.Furthermore, LVM's learned index requires minimal memory space, does not impose stringent physical contiguity requirements, enjoys high cacheability in the MMU, efficiently supports insertions, and relies on simple fixed-point arithmetic.Finally, LVM supports all features of virtual memory, including multiple page sizes.We evaluate LVM with a set of operating system (OS) extensions in Linux, RTL synthesis, and full-system simulations across a wide range of workloads.LVM reduces the address translation overhead by an average of 44% over radix page tables, while reducing the page walk cache area required by 1.5×.Overall, LVM achieves a 2-27% speedup in application execution time and is within 1% of an ideal page table.

Transient execution attacks present an unprecedented threat to computing systems. Protecting the operating system (OS) is exceptionally challenging because a transient execution gadget in the OS can potentially leak the entire memory In this work, we propose Perspective, a principled framework for building pliable and secure speculative execution defenses for the OS. Perspective offers a pliable interface that allows the OS to communicate its security requirements to hardware defenses, enabling tailored protection against transient execution attacks with little performance overhead. The design of Perspective is driven by a taxonomy of transient execution attacks in the OS kernel: (i) active transient execution attacks, where the attacker process exploits its own kernel thread to speculatively execute a transient execution gadget in the kernel, and (ii) passive transient execution attacks, where the attacker coerces the victim process’s kernel thread to execute a transient execution gadget. Based on the taxonomy, Perspective introduces Data Speculation Views (DSVs) and Instruction Speculation Views (ISVs), to mitigate active and passive attacks, respectively. DSVs define the ownership of kernel data by a given execution context and block any speculative access to data outside the DSV. ISVs define the set of kernel functions that can be speculatively executed by a given execution context. Any transmitter instructions—whose execution could leak secrets, such as load instructions—that belong to kernel functions outside the ISVs are blocked from speculative execution. ISVs open up new opportunities of (i) swiftly patching gadgets in the OS, (ii) reducing the surface of passive attacks, and (iii) speeding up the process of auditing transient execution gadgets in the OS.We build Perspective’s software components in the Linux kernel and model the hardware components in gem5. We evaluate the security and performance of Perspective on a set of microbenchmarks and datacenter applications. Perspective has an execution overhead over an unprotected kernel of only $3.5 \%$ on microbenchmarks and only $1.2 \%$ on datacenter applications.

The unabating growth of the memory needs of emerging datacenter applications has exacerbated the scalability bottleneck of virtual memory. However, reducing the excessive overhead of address translation will remain onerous until the physical memory contiguity predicament gets resolved. To address this problem, this paper presents Contiguitas, a novel redesign of memory management in the operating system and hardware that provides ample physical memory contiguity. We identify that the primary cause of memory fragmentation in Meta's datacenters is unmovable allocations scattered across the address space that impede large contiguity from being formed. To provide ample physical memory contiguity by design, Contiguitas first separates regular movable allocations from unmovable ones by placing them into two different continuous regions in physical memory and dynamically adjusts the boundary of the two regions based on memory demand. Drastically reducing unmovable allocations is challenging because the majority of unmovable pages cannot be moved with software alone given that access to the page cannot be blocked for a migration to take place. Furthermore, page migration is expensive as it requires a long downtime to (a) perform TLB shootdowns that scale poorly with the number of victim TLBs, and (b) copy the page. To this end, Contiguitas eliminates the primary source of unmovable allocations by introducing hardware extensions in the last-level cache to enable the transparent and efficient migration of unmovable pages even while the pages remain in use.

Serverless computing is an increasingly attractive paradigm in the cloud due to its ease of use and fine-grained pay-for-what-you-use billing. However, serverless computing poses new challenges to system design due to its short-lived function execution model. Our detailed analysis reveals that memory management is responsible for a major amount of function execution cycles. This is because functions pay the full critical-path costs of memory management in both userspace and the operating system without the opportunity to amortize these costs over their short lifetimes.

Fork has long been the process creation system call for Unix. At its inception, fork was hailed as an efficient system call due to its use of copy-on-write on memory shared between parent and child processes. However, application memory demand has increased drastically since the early days and the cost incurred by fork to simply set up virtual memory (e.g., copy page tables) is now a concern, even for applications that only require hundreds of MBs of memory. In practice, fork performance already holds back system efficiency and latency across a range of uses cases that fork large processes, such as fault-tolerant systems, serverless frameworks, and testing frameworks.