All reports
High

Oxia affected by server crash via race condition in session heartbeat handling

Affected versions

Version ranges need review.

Affected versions
<0.16.2
Fixed version
0.16.2
Affected versions
<= 0.16.1
Fixed version
0.16.2

Exploitation

CVE-2026-40943

Probability of exploitation in the next 30 days: 0.21%

FIRST EPSS · 2026-11-18

Description

Summary

A race condition between session heartbeat processing and session closure can cause the server to panic with send on closed channel. The heartbeat() method uses a blocking channel send while holding a mutex, and under specific timing with concurrent close() calls, this can lead to either a deadlock (channel buffer full) or a panic (send on closed channel after TOCTOU gap in KeepAlive).

Impact

A remote client can trigger a server crash by sending rapid KeepAlive requests while a session is expiring or being closed. This is a denial-of-service vulnerability that crashes the entire data server process.

All versions are affected.

Details

In oxiad/dataserver/controller/lead/session.go, the heartbeat() method performs a blocking s.heartbeatCh <- true send. If the channel buffer is full (size 1), this blocks while holding the session mutex, preventing close() from acquiring the lock to close the channel — a deadlock.

Additionally, in session_manager.go, KeepAlive() releases the session manager's read lock before calling heartbeat(), creating a TOCTOU window where the session can be removed and closed between the lookup and the heartbeat call.

Patches

Fixed by changing heartbeat() to use a non-blocking select with a default case, and by holding the session manager read lock through the entire KeepAlive() operation.

Workarounds

No workaround available.

Links