---
id: "CVE-2026-98521"
kind: "vulnerability"
aliases: ["CVE-2026-98521"]
title: "Linux kernel i915 GPU driver: RCU teardown order causes endless loop"
severity: "unknown"
cvss: null
epss: null
exploited: false
status: "open"
category: "infrastructure"
products: []
ecosystems: []
tags: ["i915", "infrastructure", "intel-graphics", "kernel", "linux"]
not_affected_if: ["i915-not-loaded", "no-i915-hardware"]
published_at: "2026-10-18T16:17:03+00:00"
first_seen_at: "2026-10-23T21:57:15+00:00"
updated_at: "2026-10-25T05:25:12+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-98521", "first_seen_at": "2026-10-23T21:57:15+00:00"}]
---

# Linux kernel i915 GPU driver: RCU teardown order causes endless loop

In the Linux i915 graphics driver, the busy ioctl can loop forever when a GEM object is destroyed while the ioctl is iterating its fences. The sources describe a denial-of-service style hang on the kernel side, not code execution.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the running kernel with `uname -r` and compare against the fixed stable kernel releases listed in the upstream commit 5113479556025093bf8133bb2dcaa33be2d50921
- Confirm the i915 driver is loaded with `lsmod | grep i915`

## Fix

- Update to a Linux kernel stable release that includes upstream commit 5113479556025093bf8133bb2dcaa33be2d50921 (exact fixed version unknown from sources)
- Reboot after the kernel update so the fixed i915 module is loaded

## Timeline

- 2026-10-23T21:57:15+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-98521

## From the sources

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

drm/i915: fix incorrect RCU teardown order

i915_gem_busy_ioctl uses dma_resv_for_each_fence_unlocked() to iterate
over the fences in an GEM object without holding a reference but only
the RCU read side lock.

What can happen here is that the GEM object is destroyed concurrently
while i915_gem_busy_ioctl is still running. This won't free the GEM
objects memory, but still drops all the dma_fence references.

Now when dma_resv_for_each_fence_unlocked() sees a destroyed dma_fence it
assumes that a new fence list was installed and re-starts the loop.

But in the case of a destroyed GEM object a new fence list is never
installed, only the old one freed and therefore the iteration never
finishes resulting in an endless loop.

The solution is to drop the fence references only after the RCU grace
period.

The fixes tag is not necessary the patch introducing the problem, but the
one making it so worse that we need to address it.

This problem was pointed out by Sashiko-bot.

(cherry picked from commit 5113479556025093bf8133bb2dcaa33be2d50921)

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_