Virtualization · Cluster
Hypervisors
Trap-and-emulate, paravirtualization, and hardware assist.
- 01 Trap-and-Emulate: The Popek-Goldberg Conditions and Sensitive Instructions Why a guest kernel running without real privilege can still appear to control the machine, which instructions break that illusion, and how the 1974 virtualization theorem decides where traps must land.
- 02 Ring Compression: Deprivileging a Guest Kernel Without Losing Its Own Protection How a hypervisor moves a guest kernel down the x86 privilege ladder, why the choice between ring 1 and ring 3 changes what the guest can enforce against its own processes, and which instructions leak the difference.
- 03 Shadow Page Tables: Keeping Two Guest Mappings Consistent With One Hardware Walk Why a hypervisor must build its own page tables from the guest's, which guest writes force a rebuild, and how the reverse-map and write-protection machinery bounds the cost of keeping them honest.
- 04 Inside the VMCS: What Hardware Virtualization Actually Saves and Restores The control structure that replaced ring deprivileging, which fields decide whether a guest instruction exits, and why the exit path costs more than the instruction it intercepts.
- 05 Second-Level Address Translation: Composing Two Page Walks in Hardware How EPT and nested paging remove the shadow-table trap per guest page-table write, what the extra walk costs in memory references, and why accessed and dirty bits become a virtualization problem.
- 06 Paravirtualization and the Hypercall ABI: Trading Transparency for Fewer Traps How a modified guest replaces trapping instructions with explicit calls into the hypervisor, what a hypercall looks like at the instruction level, and why the ABI has to be versioned and discoverable.
- 07 The Virtio Split Ring: Descriptor Tables, Available Rings, and the Notification Suppression How a guest and a hypervisor exchange buffers without a trap per request, what the three-ring layout enforces, and why the notification flags matter more than the data path.
- 08 Virtual Interrupts: APIC Emulation, Interrupt Remapping, and Posted Delivery How a guest programs its own interrupt controller without touching the host's, what the IOMMU must check before a device interrupt is delivered, and why posted interrupts remove the exit from the delivery path.
- 09 Nested Virtualization: Running a Hypervisor Inside a Guest Why the L1 hypervisor's control structure must be virtualized by L0, how exit causes are merged across two levels, and what the recursion costs in exit latency and state tracking.
- 10 The Fabricated Machine: ACPI Tables, SMBIOS, and PCI Configuration Space How a hypervisor describes hardware that does not exist, which tables the guest kernel trusts for topology and interrupt routing, and why a wrong table entry survives every test until the guest boots on real silicon.