Skip to content
Fencer Vulns
high 8.8

CVE-2026-68329 json

iommu/amd: Wait for completion instead of returning early in iommu_completion_wait()

published 2026-08-10 2 mo ago modified 2026-10-30 10 d ago also EUVD-2026-55430

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.1%
EPSS 0.1% chance of exploitation in 30 days, percentile 2%
public exploits
0
none known

Summary

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

iommu/amd: Wait for completion instead of returning early in iommu_completion_wait()

need_sync is a per-IOMMU flag shared by all domains and devices behind that IOMMU. It is set whenever a command is queued with sync == true and cleared when a completion-wait (CWAIT) command is queued. However, a cleared need_sync only means that a covering CWAIT has been queued, not that all previously queued commands have actually completed in hardware.

iommu_completion_wait() read need_sync locklessly and returned early when it was false. This breaks the "block until all previously queued commands have completed" contract in a multi-CPU scenario:

CPU2: queue inv-B => need_sync = true CPU1: queue CWAIT(N); need_sync = false; then wait_on_sem(N) CPU2: read need_sync == false => return 0 (no wait!)

CPU2 returns without waiting for any sequence number even though its inv-B may not have completed yet (CWAIT(N), queued after inv-B, has not been signaled). CPU2 then proceeds to, for example, free page-table pages while the IOMMU can still walk stale translations, opening a use-after-free window. This is a logical race in the meaning of the flag, not a memory-visibility issue, so barriers alone do not help.

Fix it without losing the optimization of avoiding redundant CWAIT commands: take iommu->lock before testing need_sync, and when it is false do not return early but wait for the last allocated sequence number (cmd_sem_val). Since need_sync == false implies no sync command was queued after the last CWAIT, that CWAIT is FIFO-ordered after every not-yet-completed command, so waiting for its sequence number guarantees all prior commands (possibly queued by another CPU) have completed. The common path with pending work is unchanged and no extra hardware command is issued.

Patch / fix

  • Linux Linux 6.1.191, 6.6.148, 6.12.101, 6.18.42, 7.1.6, 7.2
  • linux Debian 13 6.12.101-1
  • linux Debian 14 7.1.6-1
  • linux-6.12 Debian 12 6.12.101-1~deb12u1

debian advisories DEBIAN-CVE-2026-68329

  • linux Ubuntu 24.04 LTS 6.8.0-147.147
  • linux Ubuntu 26.04 LTS 7.0.0-38.38
  • linux-aws Ubuntu 24.04 LTS 6.8.0-1067.70
  • linux-aws Ubuntu 26.04 LTS 7.0.0-1014.14
  • linux-gcp Ubuntu 24.04 LTS 6.8.0-1071.79
  • linux-gcp Ubuntu 26.04 LTS 7.0.0-1014.14
  • linux-gke Ubuntu 24.04 LTS 6.8.0-1066.74
  • linux-gke Ubuntu 26.04 LTS 7.0.0-1008.9

ubuntu advisories UBUNTU-CVE-2026-68329

Ubuntu security data © Canonical Ltd., from https://github.com/canonical/ubuntu-security-notices via OSV; changed: normalised to fixed package versions per release. CC BY-SA 4.0

  • kernel-64kb SLE Module for Basesystem 15 SP7 6.4.0-150700.53.81.1
  • kernel-syms SLE Module for Development Tools 15 SP7 6.4.0-150700.53.81.1
  • kernel-azure SLE Module for Public Cloud 15 SP7 6.4.0-150700.53.81.1
  • kernel-source SLE Module for Development Tools 15 SP7, SLE Module for Basesystem 15 SP7 6.4.0-150700.53.81.1
  • kernel-default SLE Workstation Extension 15 SP7, SLE Module for Legacy 15 SP7, SLE Module for Basesystem 15 SP7 +2 more 6.4.0-150700.53.81.1
  • kernel-zfcpdump SLE Module for Basesystem 15 SP7 6.4.0-150700.53.81.1
  • kernel-obs-build SLE Module for Development Tools 15 SP7 6.4.0-150700.53.81.1
  • kernel-default-base SLE Module for Basesystem 15 SP7 6.4.0-150700.53.81.1.150700.17.45.1

suse advisories SUSE-SU-2026:4254-1SUSE-SU-2026:23887-1SUSE-SU-2026:23902-1SUSE-SU-2026:23897-1SUSE-SU-2026:23881-1SUSE-SU-2026:4282-1

  • kernel-rt openSUSE Leap 16.0 6.12.0-160000.38.1
  • dtb-aarch64 openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-64kb openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-syms openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-azure openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-obs-qa openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-source openSUSE Leap 16.0 6.12.0-160000.38.1
  • kernel-default openSUSE Leap 16.0 6.12.0-160000.38.1

opensuse advisories openSUSE-SU-2026:21910-1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-68329 updated cvss 7.0

kernel: iommu/amd: Wait for completion instead of returning early in iommu_completion_wait()

  • Red Hat Enterprise Linux 8 perf, kernel, bpftool, kernel-rt, kernel-core, kernel-tools, +30 more Red Hat Enterprise Linux 9 rv, perf, rtla, kernel, bpftool, libperf, +84 more Red Hat Enterprise Linux 10 kernel 6.12.0-55.94.1.el10_0
    affected: no fix available
  • Red Hat OpenShift Container Platform 4 openshift/ose-rhel-coreos-9 Red Hat OpenShift Container Platform 5 openshift/ose-rhel-coreos-9
    affected: no fix available “Fix deferred”
  • Red Hat Enterprise Linux 6 perf, kernel, python-perf, kernel-kdump, kernel-firmware, kernel-bootwrapper, +2 more Red Hat Enterprise Linux 7 perf, kernel, bpftool, kernel-rt, python-perf, kernel-kdump, +9 more Red Hat Enterprise Linux for NVIDIA 26 kernel 6.12.0-55.94.1.el10_0 Red Hat OpenShift Container Platform 4 openshift/ose-rhel-coreos-8
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
23 d ago

Exploit prediction

0.13% chance of exploitation in the next 30 days, higher than 2% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 8.8 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Affected products

  • Linux Linux

Classification

Weakness
  • CWE-362 Concurrent Execution using Shared Resource with Improper Synchronization
Technology feeds

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.