GHSA-RJF9-X7MR-46PH
Vulnerability from github – Published: 2026-09-17 18:31 – Updated: 2026-09-18 18:31In the Linux kernel, the following vulnerability has been resolved:
iommu/dma: Restore locking around msi_page_list
Unlike a group's default domain, which is always freshly allocated and privately owned (iommu_group_alloc_default_domain()), VFIO type1's legacy container merges any newly attached group into an existing domain whenever their iommu_ops and cache-coherency enforcement match.
iommu_dma_get_msi_page() only asserts the caller's own group mutex is held (iommu_group_mutex_assert()). On an IOMMU that publishes IOMMU_RESV_SW_MSI, e.g. ARM SMMU, a VM with two such devices assigned through the legacy container can have their guest drivers probe and allocate MSIs in parallel; each host-side VFIO_DEVICE_SET_IRQS lands on a different device fd and group mutex, but both devices' domains are the same merged domain, so both can enter iommu_dma_get_msi_page() concurrently and corrupt msi_page_list.
commit 288683c92b1a ("iommu: Make iommu_dma_prepare_msi() into a generic operation") dropped the prior msi_prepare_lock on the reasoning that "each iommu_domain is unique to a group," which holds for default domains but not this VFIO type1 case. Restore the static lock, since it's only guarding a corner case and will likely never be contended.
iommufd avoids the equivalent problem by having its own callers (iommufd_sw_map_msi()) take a ctx-wide sw_msi_lock before ever reaching the shared list. VFIO type1 can't mirror that since it dispatches to iommu_dma_sw_msi() which is outside VFIO's jurisdiction.
{
"affected": [],
"aliases": [
"CVE-2026-90244"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-09-17T17:17:20Z",
"severity": "HIGH"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\niommu/dma: Restore locking around msi_page_list\n\nUnlike a group\u0027s default domain, which is always freshly allocated\nand privately owned (iommu_group_alloc_default_domain()), VFIO type1\u0027s\nlegacy container merges any newly attached group into an existing\ndomain whenever their iommu_ops and cache-coherency enforcement match.\n\niommu_dma_get_msi_page() only asserts the caller\u0027s own group mutex is\nheld (iommu_group_mutex_assert()). On an IOMMU that publishes\nIOMMU_RESV_SW_MSI, e.g. ARM SMMU, a VM with two such devices assigned\nthrough the legacy container can have their guest drivers probe and\nallocate MSIs in parallel; each host-side VFIO_DEVICE_SET_IRQS lands\non a different device fd and group mutex, but both devices\u0027 domains\nare the same merged domain, so both can enter\niommu_dma_get_msi_page() concurrently and corrupt msi_page_list.\n\ncommit 288683c92b1a (\"iommu: Make iommu_dma_prepare_msi() into a\ngeneric operation\") dropped the prior msi_prepare_lock on the\nreasoning that \"each iommu_domain is unique to a group,\" which holds\nfor default domains but not this VFIO type1 case. Restore the static\nlock, since it\u0027s only guarding a corner case and will likely never\nbe contended.\n\niommufd avoids the equivalent problem by having its own callers\n(iommufd_sw_map_msi()) take a ctx-wide sw_msi_lock before ever\nreaching the shared list. VFIO type1 can\u0027t mirror that since it\ndispatches to iommu_dma_sw_msi() which is outside VFIO\u0027s jurisdiction.",
"id": "GHSA-rjf9-x7mr-46ph",
"modified": "2026-09-18T18:31:28Z",
"published": "2026-09-17T18:31:57Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-90244"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/2af1e99ec14d226d66ceb9f16c663ee2568e6676"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/5a9e89ea34e0e34ac5d7e949042d665533549e40"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/e3c53e9173a47d5ce1fae020f2c6b1fb3c1123c2"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/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.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.