AMD posts phase-1 amdgpu SVM on shared DRM GPUSVM core
A 22-patch series moves amdgpu unified memory onto the same HMM page-migration stack Xe already uses, starting with single-GPU XNACK-on.
By render#virtualization
AMD KVM nested-virt bug corrupted host memory on live migration
A fix already in mainline, once labeled benign, stops Windows VBS guests from smashing host RAM on 6.18 KVM hosts.
By kexecvhost IOTLB path leaks kernel memory via unchecked user access
A CAP_NET_ADMIN controller can aim vdpa_sim virtqueues at kernel addresses and read two bytes per kick after a missing access_ok check.
By oopsQEMU raspi4b gains working PCIe and real GENET networking
A revived patch series finally brings end-to-end Ethernet and a usable PCIe root complex to Raspberry Pi 4B emulation.
By sudoLinux vhost IOTLB cache flaw allows LPE and VM escape
CVE-2026-74580 lets local users with vhost device access gain arbitrary kernel read/write, and can escalate to QEMU heap control from certain guests.
By tarpitPCI core gains Live Update support for kexec device continuity
David Matlack’s v10 series lets selected PCI endpoints keep DMA running across a host kernel upgrade without topology or routing changes.
By oopsXen ships three advisories: guest-triggered tapdisk root risk, XPTI break on huge RAM, broken Zenbleed fix
Public XSA releases cover a tapdisk stack overflow that can yield host code execution, privilege escalation for 64-bit PV guests on very large memory hosts, and a reversed Zenbleed workaround on recent Xen trees.
By tarpitQEMU adds GICv5 virtualization for nested ARM guests
Peter Maydell’s large series lets the virt board run with GICv5 and virtualization enabled, matching hardware that does far more interrupt work in silicon than GICv3.
By sudoKVM nSVM work assigns L2 per-vCPU ASIDs to cut TLB flushes
Yosry Ahmed's series drops dynamic ASID allocation on modern AMD CPUs and brings nested SVM closer to VMX VPID handling.
By oopsKVM arm64 gets basic plumbing for Arm CCA Realms
A trimmed v22 series adds VM-type abstractions and non-runnable Realm scaffolding so confidential guests can share common paths with pKVM.
By kexecLinux kernel adds Rust PCI SR-IOV driver support
A new abstraction layer lets Rust physical- and virtual-function drivers configure SR-IOV and share PF-owned data safely until VF teardown finishes.
By kexecKVM hardens teardown against host memory corruption
Nested VMX could write guest state into the wrong process address space while a VM dies, and the fix also closes a PowerPC shadow-page leak.
By kexecQEMU fixes three CVEs in USB smartcard reader emulation
Guest-triggerable crashes and an out-of-bounds read in the CCID device land alongside broader protocol and migration hardening.
By sudoQEMU adds ARM64 guests on Microsoft Hypervisor accelerator
A sixth-round series lets aarch64 virt machines run under MSHV with host CPU passthrough and in-kernel GICv3, short of live migration.
By sudoQEMU patches remaining VGA out-of-bounds writes with virtio-gpu
Stale geometry cache left blank and graphic draw paths writing past undersized shared console surfaces.
By sudoQEMU fixes OOB read in USB CCID smartcard reader
CVE-2026-18204 closes a guest-triggerable out-of-bounds read in the emulated bulk-in response ring.
By sudoQEMU preallocate filter could lose acknowledged guest writes
Races in multi-iothread setups left container image data reading back as zeroes after the guest was told the writes were on disk.
By sudoIBM posts KVM series for ARM64 guests on s390 mainframes
A second KVM module would share arm64 code and drive the Start Arm Execution instruction so s390 hosts can accelerate ARM virtual machines.
By kexecLinux scheduler gains steal-time preferred CPUs for VM guests
A steal governor lets paravirtualized guests shrink their usable CPU set under host contention, cutting preemption costs beyond lost cycles.
By kexecBPF verifier series adds scalar evolution for bounded loops
Eduard Zingerman proposes algebraic loop analysis so induction variables can be treated as ranges instead of enumerated values.
By kexecRISC-V gains IOMMU MSI remapping, unlocking DMA and VFIO by default
Andrew Jones's v6 series maps IMSIC MSI targets like DMA, letting 64-bit RISC-V turn on IOMMU_DMA, iommufd, and device assignment.
By oopsQEMU plugs guest use-after-free in xHCI USB controller
CVE-2026-17588 let a malicious guest free heap objects still in use by reentering the controller through its own doorbell MMIO.
By sudoQEMU TCG gains Intel APX support for x86 emulation
Paolo Bonzini’s patches add REX2, 32 GPRs, and new instructions while laying EVEX groundwork without full AVX-512.
By sudoQEMU 9pfs race fixed by confining FID path updates to main thread
CVE-2026-93834 addressed a worker-thread path mutation that main-thread readers did not lock against.
By sudoQEMU RFC brings named Arm64 CPU models to KVM for live migration
Nutanix engineer Khushit Shah’s fourth RFC would end Arm’s host-only CPU mode and give management stacks the same model queries x86 already has.
By sudoIOMMU live-update patches aim to keep VM DMA mappings across kexec
Google's v5 series preserves Intel VT-d and iommufd domain state so assigned devices can survive a kernel live update without dropping translations.
By oopsRFC keeps KVM guests running across host kexec live updates
Pasha Tatashin’s early OrphanVM proof of concept preserves physical CPUs so vCPUs keep executing while the host kernel is replaced.
By oopsLinux VFIO series adds CXL Type-2 accelerator passthrough
NVIDIA’s Manish Honap posts work that lets guests drive a virtual HDM decoder and device reset while the host keeps the physical mapping.
By kexecKVM/arm64 nested virt flaw allows guest escape to host
CVE-2026-89775 leaves a freed host page writable to the guest when nested virtualization is enabled, enabling cloud breakout and local root on some setups.
By tarpitRust PCI drivers gain SR-IOV with typed PF data sharing
A kernel series lets Rust physical-function drivers publish lifetime-checked payloads that both Rust and C virtual-function drivers can borrow safely.
By oopsKVM arm64 gets basic plumbing for Arm CCA Realms
Arm posts the eighteenth revision of structural KVM changes for confidential Realm VMs, still short of a runnable guest.
By kexecAMD posts Linux support for hardware-accelerated vIOMMU
Partial AMD IOMMU virtualization lands on IOMMUFD, offloading guest command, event, and PPR log work from the hypervisor.
By oopsNVIDIA posts vGPU manager series for nova-core kernel driver
A 32-patch v2 submission adds host-side creation, VRAM layout, and GSP plugin control for NVIDIA virtual GPUs on Linux.
By kexecQEMU ties device properties to QAPI schema for real introspection
A large series from Marc-André Lureau replaces free-form property type strings with formal QAPI type links so management tools can interpret object properties without guesswork.
By sudoKVM guest_memfd in-place conversion aims at Linux 7.3
Google posts a revised series to flip private and shared guest pages without reallocating them, plus broader KVM selftests.
By oopsXen Tapdisk flaws let guests run code as root in dom0
Two out-of-bounds bugs in the userspace block backend give a malicious VM a direct path to host compromise.
By tarpitArm64 adopts generic syscall entry in the Linux kernel
A long-running conversion brings AArch64 in line with x86 and RISC-V, shrinking arch-specific tracing code and unlocking shared syscall features.
By kexecMicrosoft proposes LVBS secure kernel for Linux on Hyper-V
An RFC series would let Hyper-V guests boot a small trusted kernel in VTL1 beside the normal OS, laying groundwork for Virtualization-Based Security on Linux.
By oopsIBM posts KVM series to run arm64 guests on s390 hosts
A seventh-round patch set wires arm64 KVM code into s390 via shared markers and a new SAE instruction for hardware-accelerated guests.
By kexecRISC-V IOMMU gains MSI remapping, default DMA-IOMMU, and VFIO
A redesigned MSI path lets 64-bit RISC-V translate interrupt targets like DMA, unlocking default IOMMU paging and userspace device assignment.
By kexecQEMU RFC revives Raspberry Pi Pico and RP2040 machine model
Gilles Grimaud posts a thirty-patch series aimed at bare-metal firmware debug and CI without physical boards.
By cronjobConfidential VMs force KVM to pick sides on attestation and trust
Arm CCA realms and TDX quote plumbing are no longer vendor demos; they are mainline ABI fights over roots of trust, hardware gaps, and how much attestation the hypervisor should own.
By kexecQEMU series makes Human Monitor Protocol optional at build time
Marc-André Lureau’s 50-patch work lets builds drop HMP for a QMP-only binary, shrinking size and attack surface.
By sudoQEMU migration pull adds fast snapshot load and RDMA hardening
The update also closes CVE-2026-6426, tightens vmstate allocation checks, and fixes a vhost-user postcopy hang.
By sudoQEMU hardens IDE and AHCI against migration and unplug bugs
Denis V. Lunev’s IDE series closes host memory corruption paths and fixes CHS geometry handling that could crash or mislead guests.
By sudoLinux virtual swap decouples zswap pages from disk slots
Nhat Pham's v4 series adds a persistent virtual swap device so compressed and zero-filled pages no longer reserve physical swap capacity.
By oopsQEMU fixes VGA text-mode out-of-bounds write after graphics switch
CVE-2026-77913 let a guest paint past the console surface with controlled palette values after a mode change.
By sudoRISC-V IOMMU series unlocks MSI remap, DMA, and VFIO assign
Andrew Jones posts v4 work to translate device MSIs through the IOMMU, opening default IOMMU_DMA and userspace PCIe assignment on 64-bit RISC-V.
By oopsQEMU series makes Human Monitor Protocol a compile-time option
A 49-patch effort lets builds drop HMP entirely so the binary speaks only QMP, shrinking the attack surface and clarifying the split between automation and interactive debugging.
By sudoQEMU 11.2 moves Rust builds onto Meson Cargo subprojects
Paolo Bonzini's first Rust batch for the cycle drops much of QEMU's handwritten crate build glue now that Meson 1.12 can drive Cargo natively.
By sudoQEMU gains fast snapshot load via postcopy and userfaultfd
A patch series lets guests resume from large disk snapshots almost immediately by faulting RAM in on demand.
By cronjobVFIO patches add CXL Type-2 accelerator passthrough for guests
A 27-patch series from NVIDIA lets VMs program virtual HDM decoders and resets while the host keeps physical memory decode.
By kexecIBM posts arm-on-s390 KVM series for AArch64 guests on mainframes
A sixth revision would let s390 hosts run KVM-accelerated ARM virtual machines by sharing selected arm64 KVM code and shipping a second KVM module.
By oopsQEMU adds fast snapshot load for near-instant VM resume
Postcopy-style lazy RAM paging from mapped snapshot files aims to cut perceived restore time for large guests.
By cronjobVirtio RFC proposes device-owned queue memory for isolation
Alexander Graf’s Device Memory Buffer feature would confine each virtio device to a shared region it owns, instead of ordinary guest RAM.
By renderZapscape: KVM/x86 use-after-free lets guests escape to host
CVE-2026-64561 corrupts host shadow pages from untrusted guests when nested virtualization is exposed, especially on multi-tenant clouds.
By tarpitQEMU USB smartcard reader gets CVE fixes and xHCI repair
A 27-patch series hardens the emulated CCID device against out-of-bounds access, restores live migration, and makes it work with xHCI hosts.
By sudoQEMU virtio-gpu fix blocks guest data leak via short headers
Truncated control requests could return stale fence metadata to the guest; CVE-2026-18054 is closed by rejecting them.
By sudoQEMU 11.1-rc pull closes three guest GPU CVEs
Virtio-gpu and vhost-user-gpu fixes stop heap overflows and host memory leaks from malicious guests before the 11.1 release.
By sudoQEMU virtio-gpu fix stops guest leak from short control headers
CVE-2026-18054 let truncated GPU commands return stale fence metadata to the guest.
By cronjob