In the Linux kernel, the following vulnerability has been resolved:
drm/amdkfd: Fix UBSAN shift-out-of-bounds warning
If get_num_sdma_queues or get_num_xgmi_sdma_queues is 0, we end up
doing a shift operation where the number of bits shifted equals
number of bits in the operand. This behaviour is undefined.
Set num_sdma_queues or num_xgmi_sdma_queues to ULLONG_MAX, if the
count is >= number of bits in the operand.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1472
Security readout for executives and security teams
Plain-English summary
CVE-2021-4460 is a Linux kernel issue in the AMD KFD graphics/compute driver. A local low-privileged user could potentially trigger undefined behavior tied to SDMA queue handling, with rated impact to confidentiality and availability. The provided sources do not show active exploitation.
Executive priority
Treat as a high-priority kernel maintenance issue for shared Linux GPU environments. It is not presented as remotely exploitable or actively exploited, but the confidentiality and availability impacts justify timely patching where AMD KFD is used.
Technical view
The flaw is in drm/amdkfd SDMA queue bit-shift logic. If queue count is zero, the code can shift by the operand width, which is undefined behavior. The fix adjusts handling when counts reach operand bit width. CVSS 3.1 is 7.1, local attack vector, low privileges required.
Likely exposure
Exposure is likely limited to Linux systems running affected kernel versions with AMD KFD/amdkfd functionality present, especially shared GPU, workstation, or compute environments with local user access. Internet-facing exposure is not indicated by the provided sources.
Exploitation context
The CVSS vector indicates local exploitation requiring low privileges and no user interaction. The bundle marks KEV as false, and no cited source claims exploitation in the wild. Evidence of practical exploitability is incomplete in the provided material.
Researcher notes
The public description centers on undefined behavior from shift-out-of-bounds in drm/amdkfd, while CWE is listed as CWE-125. The source bundle gives commit references but not a detailed exploit narrative, affected distribution matrix, or operational workaround.
Mitigation direction
Update affected Linux kernels using vendor or distribution-supported packages.
Confirm the update includes one of the referenced stable kernel fixes.
Prioritize shared GPU and compute hosts with untrusted local users.
If updates are unavailable, follow vendor guidance for temporary risk reduction.
Validation and detection
Inventory Linux hosts running AMD GPU or KFD-capable workloads.
Compare kernel versions against affected ranges and vendor advisories.
Verify patched kernels include the relevant stable commit backport.
Check whether untrusted users have local access to exposed GPU systems.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Potential ATT&CK relevance
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
cwe · low confidence lookup
CWE-125: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE-125 · source CWE mapping
Out-of-bounds Read
Out-of-bounds Read represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.