QEMU 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 cronjob#virtualization
Virtio 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 cronjobArm CCA protected VMs advance in KVM review
Steven Price's 37-patch series brings realm guests to arm64 KVM, targeting RMM v2.0-bet2 under maintainer scrutiny.
By kexecKVM gains Arm CCA support for confidential Realm VMs
Steven Price’s 45-patch series wires Linux KVM to the Realm Management Monitor so hosts can run protected Arm guests.
By kexecQEMU fixes guest-triggerable VGA heap overflow
A unit mismatch between text and graphics mode left a panning buffer undersized after mode switches, tracked as CVE-2026-17516.
By sudoLinux mm gains ALLOC_UNMAPPED for direct-map-free pages
Brendan Jackman's v3 series lays allocator and mapping groundwork for guest_memfd isolation and Address Space Isolation.
By kexecQEMU fixes virtio-gpu OOB read from guest blob size
CVE-2026-66021 let a malicious guest inflate blob_size past its backing and trigger host reads on display refresh.
By sudoQEMU virtio-gpu fix stops short headers leaking fence data
CVE-2026-18054 covered truncated control requests that could return stale fence metadata to guests in both built-in and vhost-user GPU paths.
By cronjobXen ships batch of fixes for guest escapes spanning grant tables, pygrub, and more
Six advisories close privilege-escalation and crash bugs across years of Xen releases, several reachable from untrusted guests.
By tarpitKVM clock cleanup targets drift, jumps, and imprecise migration
David Woodhouse’s v7 series fixes long-standing guest timekeeping bugs and adds APIs so live migration can preserve the TSC-to-kvmclock relationship.
By oopsQEMU virtio-gpu fix stops stale fence data leak to guests
CVE-2026-18054 let truncated control requests expose leftover fence metadata from the host.
By sudoQEMU fixes virtio-net buffer overflow in RSC coalescing
CVE-2026-66900 let trailing IP padding defeat a bounds check and overflow a coalescing buffer.
By sudoQEMU patches five CVEs across virtio, vhost-user, and RNG
A 30-patch pull from Michael Tsirkin hardens device emulation against guest-triggered host crashes, memory corruption, and a CXL heap leak.
By cronjobQEMU patches QXL use-after-free on hot-unplug
CVE-2026-63322 left VM state handlers and bottom halves pointing at freed device memory after secondary display removal.
By sudoQEMU fixes virtio-gpu use-after-free on blob detach
CVE-2026-66020 let a guest trigger reads of freed memory via cursor updates and scanout refresh after RESOURCE_DETACH_BACKING.
By cronjobQEMU fixes virtio-mmio queue size OOB (CVE-2026-50626)
virtio-mmio always advertised a 1024-entry maximum, which becomes unsafe once QEMU itself allocates in-order virtqueue resources.
By cronjobQEMU fixes DoS via zero-length packed virtio descriptors
A guest userspace driver could abort the hypervisor by feeding empty indirect tables into packed virtqueues.
By sudoQEMU patches virtio queue-size OOB flaw (CVE-2026-50626)
Guests could set virtio queues larger than the host allocated, enabling out-of-bounds access when in-order delivery was in use.
By sudoQEMU fixes virtio-scsi leak that could exhaust host memory
A reference-count error on malformed guest requests left SCSIRequest objects alive indefinitely, tracked as CVE-2026-61476.
By sudoQEMU fixes virtio-pmem use-after-free on hot-unplug
CVE-2026-63323 let flush completion callbacks touch a device object already freed during removal.
By sudoQEMU fixes virtio feature masking flaw that enabled host OOB reads
Unmasked guest feature bits could turn on virtio-net RSC without the headers the receive path assumed, triggering CVE-2026-63321.
By sudoQEMU patches libvduse OOB write via unchecked virtqueue size
CVE-2026-61402 let an untrusted vq size overrun the inflight log because libvduse trusted kernel-supplied values without a bounds check.
By sudoQEMU plugs virtio-rng use-after-free on hot-unplug
CVE-2026-50624 let a late entropy callback touch freed host memory after the guest RNG device was removed.
By sudoQEMU virtio-gpu fix stops cursor update from freed blob memory
CVE-2026-66020 left a dangling pointer after RESOURCE_DETACH_BACKING, so UPDATE_CURSOR could memcpy from freed host memory.
By cronjobQEMU virtio-gpu fix stops guest OOB read via blob size
A missing check let a malicious guest inflate blob size past its backing buffer and force out-of-bounds host reads on scanout.
By cronjobQEMU device models and migration streams keep producing host CVEs
A dense run of USB, display, NIC, and UEFI fixes shows the project still treating guest and migration input as untrusted, while the underlying C surface remains large enough that clouds must keep asking how much trust that buys them.
By cronjob