Hypervisor.Framework - Virtualization on macOS
summary
Hypervisor.Framework exposes a tiny macOS kernel shim that drives Intel VMX or ARM EL2 while QEMU uses a userland library to create VM context and create vCPU containers and then implements interrupts, PMU, PSCI and device emulation in user space. A straight Linux kernel boots after only about six PSCI HVC exits, two system-register traps and ~30k other guest exits that QEMU handles, so it works and performs sensibly, but lacks nested virtualization, hardware PMU counters, fast kernel interrupt injection and a VFIO-style passthrough.
AI-written summary · about
chapters (7)
- 0:00Start
- 1:36Hypervisor Framework
- 3:27Hypervisor Framework Api for Arm
- 10:35Kvm
- 18:45How Does Hypervisor Framework Handle Debuggability for the Guest
- 25:02Overhead
- 25:25Optimizing for the Kernel User Space Switch
related talks
21mRISC V Hypervisor Support
28mTBC
32mIntroduce Virtualization and Kernel Infrastructure to Newbies
03h 01mHands-on Introduction to Virtualization
32mIntroduce Virtualization and Kernel Infrastructure to Newbies
31mKVM Nested Virtualization: Workings and Usecases
30mNested Virtualization (X86) Part I
26mHVM Dom0: Any unmodified OS as Dom0