Live › vulnerability › CVE-2026-98729
Go to dashboardOn AMD F15h x86 systems, the kernel applies a randomised alignment to hugetlbfs mappings, so mapped addresses fall off the huge page boundary. Teardown then hits a BUG_ON in __unmap_hugepage_range, which crashes the kernel.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-23 21:57 UTC. All times on this page are UTC.
Systems running Linux on AMD F15h-class x86 CPUs (the sources name Carrizo and FX-8370E) that use hugetlbfs huge page mappings. The sources do not say which kernel versions are fixed or affected beyond this commit. Systems without AMD F15h hardware or without hugetlbfs use are unlikely to be affected.
No product ranges from the sources yet.
Unknown from the sources.
Unknown from the sources.
Each row is the first time that source carried this signal. The analyst’s rows are its own findings.
In the Linux kernel, the following vulnerability has been resolved:
x86/mm: Don't apply va_align to hugetlb mappings on AMD F15h
get_align_mask() returns huge_page_mask_align() for hugetlbfs, but get_align_bits() adds va_align.bits regardless, so vm_unmapped_area() returns an address off the huge page boundary and __unmap_hugepage_range() hits BUG_ON(start & ~huge_page_mask(h)) at teardown.
This can be triggered on Carrizo and FX-8370E, both hstates.
Pass the file to get_align_bits() and skip the randomisation for hugetlbfs.
[ bp: Massage commit message. ]
This page as .md · .json · in your agent: get_signal("CVE-2026-98729")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.