GHSA-2QHP-87PG-JH75
Vulnerability from github – Published: 2026-08-10 15:33 – Updated: 2026-08-14 00:31In 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.
{
"affected": [],
"aliases": [
"CVE-2026-68329"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-08-10T13:20:23Z",
"severity": "HIGH"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\niommu/amd: Wait for completion instead of returning early in iommu_completion_wait()\n\nneed_sync is a per-IOMMU flag shared by all domains and devices behind\nthat IOMMU. It is set whenever a command is queued with sync == true and\ncleared when a completion-wait (CWAIT) command is queued. However, a\ncleared need_sync only means that a covering CWAIT has been queued, not\nthat all previously queued commands have actually completed in hardware.\n\niommu_completion_wait() read need_sync locklessly and returned early\nwhen it was false. This breaks the \"block until all previously queued\ncommands have completed\" contract in a multi-CPU scenario:\n\n CPU2: queue inv-B =\u003e need_sync = true\n CPU1: queue CWAIT(N); need_sync = false; then wait_on_sem(N)\n CPU2: read need_sync == false =\u003e return 0 (no wait!)\n\nCPU2 returns without waiting for any sequence number even though its\ninv-B may not have completed yet (CWAIT(N), queued after inv-B, has not\nbeen signaled). CPU2 then proceeds to, for example, free page-table\npages while the IOMMU can still walk stale translations, opening a\nuse-after-free window. This is a logical race in the meaning of the\nflag, not a memory-visibility issue, so barriers alone do not help.\n\nFix it without losing the optimization of avoiding redundant CWAIT\ncommands: take iommu-\u003elock before testing need_sync, and when it is\nfalse do not return early but wait for the last allocated sequence\nnumber (cmd_sem_val). Since need_sync == false implies no sync command\nwas queued after the last CWAIT, that CWAIT is FIFO-ordered after every\nnot-yet-completed command, so waiting for its sequence number guarantees\nall prior commands (possibly queued by another CPU) have completed. The\ncommon path with pending work is unchanged and no extra hardware command\nis issued.",
"id": "GHSA-2qhp-87pg-jh75",
"modified": "2026-08-14T00:31:55Z",
"published": "2026-08-10T15:33:46Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-68329"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/02f8cefa2ad95ea3754f0cfd6fbae7f866202ccb"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/1e75a8255f11c81fb07e81e5029cfd75804350a0"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/93494bd446396c257fb589f59894577e96e406e2"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/ab7faf5a172ebfdc423ebb3eea4d472740de82f9"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/d053eb7e09e10cbdca3fca8b35c1017d438091b2"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
"type": "CVSS_V3"
}
]
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.