FKIE_CVE-2026-98520

Vulnerability from fkie_nvd - Published: 2026-10-18 16:17 - Updated: 2026-10-24 14:16
Severity
7.8 (High) - CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Summary
In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: fix use-after-free and multi-container gap in kfd_dev_mapping kfd_dev_mapping caches the address_space of the first /dev/kfd opener so that the GPU reset path can call unmap_mapping_range() to zap all userspace mappings of doorbell and MMIO ranges. This design has two bugs that both manifest under SRIOV with multiple containers: 1. Use-after-free / rwsem deadlock. The cached pointer refers to an inode owned by the first opener's container. When that container exits and its inode is released, kfd_dev_mapping becomes a dangling pointer. A subsequent GPU reset dereferences it inside unmap_mapping_range(), which takes i_mmap_rwsem on the freed inode, causing a hard hang observable as an uninterruptible rwsem wait. 2. Multi-container gap. Only the first opener's address_space is cached; VMAs created by later openers live in a different address_space and are never reached by unmap_mapping_range(). After a GPU reset those stale mappings keep doorbell and MMIO pages accessible to guest userspace with no GPU behind them, risking PCIe transaction timeouts and NMI panics. Fix both bugs with the same approach used by DRM core (drm_drv.c): create a private pseudo-filesystem at module init time and allocate one anonymous inode from it. In kfd_open() redirect every opener's file->f_mapping to that inode's address_space. The inode is module-owned, lives exactly as long as the amdgpu module, and collects VMAs from all openers in one address_space. A single unmap_mapping_range() call in the reset path then correctly reaches every container's mappings with no dangling pointer risk. The hang manifests as an NMI backtrace on the GPU reset workqueue stuck spinning in rwsem_down_read_slowpath() with a corrupted i_mmap_rwsem: Workqueue: amdgpu-reset-dev xgpu_ai_mailbox_flr_work [amdgpu] Call Trace: <TASK> kvm_wait+0x1f/0x40 __pv_queued_spin_lock_slowpath+0x31d/0x3a0 _raw_spin_lock_irq+0x51/0x80 rwsem_down_read_slowpath+0xb3/0x550 down_read+0x48/0xd0 unmap_mapping_range+0x71/0x140 kfd_dev_unmap_mapping_range+0x5b/0x140 [amdgpu] amdgpu_amdkfd_clear_kfd_mapping+0xd8/0x190 [amdgpu] amdgpu_device_gpu_recover+0x232/0x450 [amdgpu] xgpu_ai_mailbox_flr_work+0xb5/0xc0 [amdgpu] process_one_work+0x18e/0x3e0 worker_thread+0x2e3/0x420 kthread+0x10a/0x230 (cherry picked from commit 1128b4a52de1572e87431de837fd9850cb99542c)
References
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/02b74891624e09a5512c6d84f267d01fcc306a3b
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/c3a31087b1c8df679b653c1a09d9abe5ff7ec8ef
Impacted products
Vendor Product Version
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "defaultStatus": "unaffected",
          "product": "Linux",
          "programFiles": [
            "drivers/gpu/drm/amd/amdkfd/kfd_chardev.c"
          ],
          "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
          "vendor": "Linux",
          "versions": [
            {
              "lessThan": "02b74891624e09a5512c6d84f267d01fcc306a3b",
              "status": "affected",
              "version": "70cadefcc6160c575b04f763ada34c20e868d577",
              "versionType": "git"
            },
            {
              "lessThan": "c3a31087b1c8df679b653c1a09d9abe5ff7ec8ef",
              "status": "affected",
              "version": "70cadefcc6160c575b04f763ada34c20e868d577",
              "versionType": "git"
            }
          ]
        },
        {
          "defaultStatus": "affected",
          "product": "Linux",
          "programFiles": [
            "drivers/gpu/drm/amd/amdkfd/kfd_chardev.c"
          ],
          "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
          "vendor": "Linux",
          "versions": [
            {
              "status": "affected",
              "version": "7.2"
            },
            {
              "lessThan": "7.2",
              "status": "unaffected",
              "version": "0",
              "versionType": "semver"
            },
            {
              "lessThanOrEqual": "7.2.*",
              "status": "unaffected",
              "version": "7.2.9",
              "versionType": "semver"
            },
            {
              "lessThanOrEqual": "*",
              "status": "unaffected",
              "version": "7.3",
              "versionType": "original_commit_for_fix"
            }
          ]
        }
      ],
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "In the Linux kernel, the following vulnerability has been resolved:\n\ndrm/amdkfd: fix use-after-free and multi-container gap in kfd_dev_mapping\n\nkfd_dev_mapping caches the address_space of the first /dev/kfd opener\nso that the GPU reset path can call unmap_mapping_range() to zap all\nuserspace mappings of doorbell and MMIO ranges.  This design has two\nbugs that both manifest under SRIOV with multiple containers:\n\n1. Use-after-free / rwsem deadlock.  The cached pointer refers to an\n   inode owned by the first opener\u0027s container.  When that container\n   exits and its inode is released, kfd_dev_mapping becomes a dangling\n   pointer.  A subsequent GPU reset dereferences it inside\n   unmap_mapping_range(), which takes i_mmap_rwsem on the freed inode,\n   causing a hard hang observable as an uninterruptible rwsem wait.\n\n2. Multi-container gap.  Only the first opener\u0027s address_space is cached;\n   VMAs created by later openers live in a different address_space and\n   are never reached by unmap_mapping_range().  After a GPU reset those\n   stale mappings keep doorbell and MMIO pages accessible to guest\n   userspace with no GPU behind them, risking PCIe transaction timeouts\n   and NMI panics.\n\nFix both bugs with the same approach used by DRM core (drm_drv.c):\ncreate a private pseudo-filesystem at module init time and allocate one\nanonymous inode from it.  In kfd_open() redirect every opener\u0027s\nfile-\u003ef_mapping to that inode\u0027s address_space.  The inode is\nmodule-owned, lives exactly as long as the amdgpu module, and collects\nVMAs from all openers in one address_space.  A single\nunmap_mapping_range() call in the reset path then correctly reaches\nevery container\u0027s mappings with no dangling pointer risk.\n\nThe hang manifests as an NMI backtrace on the GPU reset workqueue stuck\nspinning in rwsem_down_read_slowpath() with a corrupted i_mmap_rwsem:\n\n  Workqueue: amdgpu-reset-dev xgpu_ai_mailbox_flr_work [amdgpu]\n  Call Trace:\n   \u003cTASK\u003e\n   kvm_wait+0x1f/0x40\n   __pv_queued_spin_lock_slowpath+0x31d/0x3a0\n   _raw_spin_lock_irq+0x51/0x80\n   rwsem_down_read_slowpath+0xb3/0x550\n   down_read+0x48/0xd0\n   unmap_mapping_range+0x71/0x140\n   kfd_dev_unmap_mapping_range+0x5b/0x140 [amdgpu]\n   amdgpu_amdkfd_clear_kfd_mapping+0xd8/0x190 [amdgpu]\n   amdgpu_device_gpu_recover+0x232/0x450 [amdgpu]\n   xgpu_ai_mailbox_flr_work+0xb5/0xc0 [amdgpu]\n   process_one_work+0x18e/0x3e0\n   worker_thread+0x2e3/0x420\n   kthread+0x10a/0x230\n\n(cherry picked from commit 1128b4a52de1572e87431de837fd9850cb99542c)"
    }
  ],
  "id": "CVE-2026-98520",
  "lastModified": "2026-10-24T14:16:45.950",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "LOCAL",
          "availabilityImpact": "HIGH",
          "baseScore": 7.8,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 1.8,
        "impactScore": 5.9,
        "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-10-18T16:17:03.370",
  "references": [
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/02b74891624e09a5512c6d84f267d01fcc306a3b"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/c3a31087b1c8df679b653c1a09d9abe5ff7ec8ef"
    }
  ],
  "sourceIdentifier": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
  "vulnStatus": "Received"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Loading timeline…




    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.