---
id: CVE-2026-64289
title: 'iommufd: Set upper bounds on cache invalidation entry_num and entry_len'
summary: |-
  In the Linux kernel, the following vulnerability has been resolved:

  iommufd: Set upper bounds on cache invalidation entry_num and entry_len

  iommufd_hwpt_invalidate() takes a user-controlled entry_num and entry_len,
  each bounded only by…
severity: none
vendor: Linux
product: Linux
affected:
  - >-
    Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c <
    d2bd041e0efaf7d81789779b135279d18b33d6d5
  - >-
    Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c <
    32ca4aed2a66205b072fcfecabe220289a8149ff
  - >-
    Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c <
    2c6381d90898089287e0a358f06f89f6b4b389f2
  - >-
    Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c <
    4d70986002f2f3eaaed89124fb2522bded38b016
  - Linux 6.8
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-11-06T16:33:46.830505Z'
published: '2026-07-25'
updated: '2026-11-06'
sourceUpdated: '2026-11-06T16:34:32.610Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-64289'
references:
  - url: 'https://git.kernel.org/stable/c/d2bd041e0efaf7d81789779b135279d18b33d6d5'
  - url: 'https://git.kernel.org/stable/c/32ca4aed2a66205b072fcfecabe220289a8149ff'
  - url: 'https://git.kernel.org/stable/c/2c6381d90898089287e0a358f06f89f6b4b389f2'
  - url: 'https://git.kernel.org/stable/c/4d70986002f2f3eaaed89124fb2522bded38b016'
tags:
  - cve.org
epss: 0.00159
epssPercentile: 0.05107
ingestedAt: '2026-11-06T16:57:43.210Z'
---

## Overview

In the Linux kernel, the following vulnerability has been resolved:

iommufd: Set upper bounds on cache invalidation entry_num and entry_len

iommufd_hwpt_invalidate() takes a user-controlled entry_num and entry_len,
each bounded only by U32_MAX. An entry_len beyond the kernel's struct size
makes the copy helper verify the extra bytes are zero, scanning that excess
in one uninterruptible pass; a multi-gigabyte value over zeroed user memory
trips the soft-lockup watchdog.

A large entry_num is the other half, driving the backend invalidation loop
with no reschedule. The VT-d nested handler, for one, copies each entry and
flushes caches per iteration, pinning the CPU on a non-preemptible kernel.

Cap both in the ioctl. entry_len is held under PAGE_SIZE, above any request
struct, and entry_num under 1 << 19, the order of a hardware invalidation
queue and well beyond any real batch, bounding the per-call loop length.

## Affected

- `Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c < d2bd041e0efaf7d81789779b135279d18b33d6d5`
- `Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c < 32ca4aed2a66205b072fcfecabe220289a8149ff`
- `Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c < 2c6381d90898089287e0a358f06f89f6b4b389f2`
- `Linux >= 8c6eabae3807e048b9f17733af5e20500fbf858c < 4d70986002f2f3eaaed89124fb2522bded38b016`
- `Linux 6.8`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.