Description
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.
Published: 2026-08-10
Score: 8.8 High
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

The flaw is a timing race in the Linux IOMMU driver that allows the need_sync flag to be cleared before all queued commands complete. In a multi‑CPU environment, a process may observe need_sync as false, return from iommu_completion_wait(), and proceed to free resources such as page‑table pages while the IOMMU still holds stale references. This window can be exploited to corrupt kernel memory, potentially enabling arbitrary code execution or escalation of privileges. The weakness is a classic race condition that violates the expected FIFO completion contract of the IOMMU interface.

Affected Systems

All Linux kernels that include the AMD IOMMU driver, meaning any Linux distribution that ships a kernel built from code containing the iommu/amd implementation. The specific kernel versions are not enumerated in the CVE data, so any release that incorporates unrestricted access to the IOMMU functions is impacted.

Risk and Exploitability

The CVSS score of 8.8 indicates high severity, and the EPSS score is less than 1%, suggesting a low probability of exploitation in the wild. The vulnerability is not listed in the CISA KEV catalog, so no public exploits are known. This race condition can still result in a use‑after‑free when a local attacker with adequate privilege manipulates IOMMU commands on a multithreaded system. Although the exploitation likelihood remains low, a successful attack would lead to kernel memory corruption, potentially allowing privilege escalation.

Generated by OpenCVE AI on August 14, 2026 at 00:44 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Apply the latest kernel update that includes the fix for iommu/amd race condition
  • If a kernel update is not immediately available, rebuild the kernel with the patch corresponding to the commit referenced in the advisory links
  • Disable unused IOMMU functionality or set CONFIG_IOMMU_SUPPORT to 'n' if the system does not need device assignment

Generated by OpenCVE AI on August 14, 2026 at 00:44 UTC.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Debian DLA Debian DLA DLA-4745-1 linux-6.12 security update
History

Thu, 13 Aug 2026 23:15:00 +0000

Type Values Removed Values Added
Metrics cvssV3_1

{'score': 4.7, 'vector': 'CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:N/I:L/A:H'}

cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H'}


Thu, 13 Aug 2026 05:15:00 +0000

Type Values Removed Values Added
Weaknesses CWE-416
CWE-847

Wed, 12 Aug 2026 00:15:00 +0000

Type Values Removed Values Added
Weaknesses CWE-367
References
Metrics threat_severity

None

cvssV3_1

{'score': 4.7, 'vector': 'CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:N/I:L/A:H'}

threat_severity

Moderate


Mon, 10 Aug 2026 16:15:00 +0000

Type Values Removed Values Added
Weaknesses CWE-416
CWE-847

Mon, 10 Aug 2026 12:30:00 +0000

Type Values Removed Values Added
Description 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.
Title iommu/amd: Wait for completion instead of returning early in iommu_completion_wait()
First Time appeared Linux
Linux linux Kernel
CPEs cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*
Vendors & Products Linux
Linux linux Kernel
References

Subscriptions

Linux Linux Kernel
cve-icon MITRE

Status: PUBLISHED

Assigner: Linux

Published:

Updated: 2026-08-17T05:03:27.689Z

Reserved: 2026-07-30T09:28:09.383Z

Link: CVE-2026-68329

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-10T13:20:23.160

Modified: 2026-08-17T06:17:40.947

Link: CVE-2026-68329

cve-icon Redhat

Severity : Moderate

Publid Date: 2026-08-10T12:03:05Z

Links: CVE-2026-68329 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2026-08-14T00:45:17Z

Weaknesses
  • CWE-367

    Time-of-check Time-of-use (TOCTOU) Race Condition