Marly Salazar

Staff Software Engineer

LinkedIn logo
Passing a TPU Through to a Paravirtualized Guest A customer asked us to run Google TPUs inside our zones. The obvious way to hand a guest a piece of PCI hardware is IOMMU-backed passthrough, and Xen has supported that for HVM guests for years. Our zones default to PV, without hardware virtualization extensions or a VT-x or AMD-V dependency. That is a big part of why they boot and fork as fast as they do. Moving these workloads to a different guest model would have meant giving up properties we deliberately built the runtime around, so the interesting problem was making passthrough work without changing the execution model. Xen's PV mode had never had an IOMMU story for a domU. Every DMA a PV guest issues goes out under dom0's address space, because PV was designed before device passthrough to an unprivileged domain was something anyone needed from it. The TPU work ended up being three problems stacked on top of each other. We had to give Xen an IOMMU interface a PV guest could actually

October 27, 2026

Passing a TPU Through to a Paravirtualized Guest

Read more
It's Beginning to Look a Lot Like CVE Season: PHP2Shell and Beyond

October 23, 2026

It's Beginning to Look a Lot Like CVE Season: PHP2Shell and Beyond

Read more
The Futility of Threat Modeling AI Agents

October 22, 2026

The Futility of Threat Modeling AI Agents

Read more

CrackArmor: When Linux “Armor” Quietly Cracked

March 13, 2026

Read it Now

Introducing Edera for GPUs and the Era of Continuous Compute Delivery

March 12, 2026

Read it Now

Faster Than runc: Benchmarking Edera on Amazon EKS

March 11, 2026

Read it Now

Who Gives a SOC 2? The Truth About SOC 2 Security Theater

March 9, 2026

Read it Now

What Is an AI Agent Sandbox?

March 6, 2026

Read it Now

Open Standards and Zero Trust on Commodity Hardware

March 3, 2026

Read it Now

What AI Agent Sandboxing Means for Production Infrastructure

February 23, 2026

Read it Now