CVE-2021-47523: IB/hfi1: Fix leak of rcvhdrtail_dummy_kvaddr
In the Linux kernel, the following vulnerability has been resolved:
IB/hfi1: Fix leak of rcvhdrtail_dummy_kvaddr
This buffer is currently allocated in hfi1_init():
if (reinit)
ret = init_after_reset(dd);
else
ret = loadtime_init(dd);
if (ret)
goto done;
/* allocate dummy tail memory for all receive contexts */
dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
sizeof(u64),
&dd->rcvhdrtail_dummy_dma,
GFP_KERNEL);
if (!dd->rcvhdrtail_dummy_kvaddr) {
dd_dev_err(dd, "cannot allocate dummy tail memory\n");
ret = -ENOMEM;
goto done;
}
The reinit triggered path will overwrite the old allocation and leak it.
Fix by moving the allocation to hfi1_alloc_devdata() and the deallocation
to hfi1_free_devdata().
Security readout for executives and security teams
Plain-English summary
This is a Linux kernel memory leak in the hfi1 InfiniBand/Omni-Path driver. During device reinitialization, the driver could allocate a new receive-header tail buffer without freeing the old one. The source does not describe remote code execution, data theft, or active exploitation.
Executive priority
Handle through normal Linux kernel patch management unless hfi1-equipped systems are business-critical or experiencing memory pressure. There is no sourced evidence of active exploitation.
Technical view
The hfi1 driver allocated rcvhdrtail_dummy_kvaddr in hfi1_init(). On the reinit path, that pointer could be overwritten, leaking the previous coherent DMA allocation. The fix moves allocation into hfi1_alloc_devdata() and deallocation into hfi1_free_devdata().
Likely exposure
Exposure appears limited to Linux systems using the IB/hfi1 driver and affected kernel builds. Systems without this driver or relevant hardware are unlikely to be exposed based on the provided sources.
Exploitation context
No KEV listing, exploit report, CVSS vector, or public exploitation evidence is provided. The described impact is a kernel memory leak triggered by a reinitialization path, not a directly documented external attack path.
Researcher notes
The evidence supports a resource leak in driver lifecycle handling. The affected-version data is incomplete in the prompt, so validate exact exposure against upstream stable commits and distribution-specific kernel backports.
Mitigation direction
Check vendor kernel advisories for a backported hfi1 fix.
Upgrade to a kernel containing the referenced stable fixes.
Prioritize systems using IB/hfi1 hardware or loaded hfi1 modules.
Monitor affected systems for memory pressure until patched.
Validation and detection
Inventory kernel versions across Linux hosts.
Identify hosts with the hfi1 driver loaded or packaged.
Confirm deployed kernels include a referenced stable commit or vendor backport.
Review change records for hfi1 reset or reinitialization events.
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.
cve · low confidence lookup
CVE-2021-47523 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
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.