Impact
An unsynchronized memory ordering bug in the Linux kernel’s RDS module allows a lost wake‑up condition in release_in_xmit(). Clearing the RDS_IN_XMIT flag without a full memory barrier can cause the receiving CPU to miss the wake‑up, leaving waiters such as rds_conn_shutdown() and rds_tcp_reset_callbacks() stuck in an uninterruptible wait_event. The consequence is that a shutdown worker or reset callback can remain hung indefinitely, potentially exhausting kernel resources and preventing RDS connections from terminating properly. This flaw is a classic data‑race and synchronization issue, categorized as CWE-754 and CWE-362.
Affected Systems
Both vendor strings identify the Linux kernel as the affected product. No specific kernel version list is provided by the CNA, so any Linux kernel image built before the commit that replaces clear_bit_unlock() with wq_has_sleeper() in release_in_xmit() is potentially vulnerable. The CPE string indicates that all Linux kernel releases may be affected until that patch is applied.
Risk and Exploitability
The CVSS score is not disclosed and EPSS is unavailable, so the exact severity cannot be quantified. The flaw is not listed in CISA’s KEV catalog, implying no known wide‑scale exploitation. Based on the description, the attack vector is likely local or requires privileged remote code that can send crafted RDS packets; it does not appear to be remotely exploitable over the network without kernel access. Nonetheless, failing to respond to a lost wake‑up can lead to a kernel‑level denial of service, making the risk significant for systems that use RDS for critical data transfers.
OpenCVE Enrichment