همهٔ گزارش‌ها
متوسط

kernel: KVM: arm64: Remove VM-wide VNCR mapping counter

متن اصلی

نسخه‌های متأثر

نسخه‌های متأثر
نامشخص
نسخهٔ اصلاح‌شده
اعلام نشده

بهره‌برداری

CVE-2026-89915

احتمال بهره‌برداری در ۳۰ روز آینده: 0.19%

FIRST EPSS · ۱۴۰۵/۰۸/۲۷

شرح آسیب‌پذیری

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Remove VM-wide VNCR mapping counter The global VNCR mapping counter is used to decide whether an L1 provided VNCR page is mapped in L0 on any CPU at the point of dealing with a TLB invalidation. It is incremented when a mapping is made in the fixmap, and decremented when unmapped. As it turns out, this tracking has several flaws:

  • we are trying to invalidate TLBs, and the mapping is only an opportunistic consequence of the TLB. Checking this counter to decide whether a TLB needs to be invalidated may result in missed invalidations.

  • an L1 vcpu invalidating its own TLB (a very likely case) will not succeed in invalidating the VNCR pseudo TLB because that page is not mapped in L0 at this stage. Given that this tracking fails at delivering the minimum guarantees that are required and is only a performance optimisation, remove it completely.

A flaw was found in the Kernel-based Virtual Machine (KVM) for ARM64 architectures. The VM-wide VNCR mapping counter, a mechanism designed to optimize Translation Lookaside Buffer (TLB) invalidations, contained several issues. These flaws could lead to situations where TLB entries are not correctly invalidated, potentially causing a guest virtual machine to operate with outdated memory translations. This could result in data integrity issues within the guest.