---
id: "CVE-2026-99268"
kind: "vulnerability"
aliases: ["CVE-2026-99268"]
title: "Linux kernel: io_uring ring pollers can sleep through pending completions"
severity: "unknown"
cvss: null
epss: null
exploited: false
status: "open"
category: "runtime"
products: []
ecosystems: []
tags: ["io_uring", "kernel", "linux", "runtime"]
not_affected_if: []
published_at: "2026-11-03T12:17:33+00:00"
first_seen_at: "2026-11-03T12:20:40+00:00"
updated_at: "2026-11-03T12:22:38+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-99268", "first_seen_at": "2026-11-03T12:20:40+00:00"}]
---

# Linux kernel: io_uring ring pollers can sleep through pending completions

With IORING_SETUP_DEFER_TASKRUN, a process polling the io_uring ring fd is not woken when completion work is queued, so it can sleep past work that is ready. The sources describe a missed wakeup and do not state an attacker capability.

_Summary, check and fix written by a model from the sources; labelled as such._

## Timeline

- 2026-11-03T12:20:40+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-99268

## From the sources

In the Linux kernel, the following vulnerability has been resolved:

io_uring: wake ring pollers for local task_work

With IORING_SETUP_DEFER_TASKRUN completions are queued as local work, and
only become CQEs when the submitter enters the kernel to wait for events.
For an application that finds out via poll() or epoll on the ring fd when
it is time to do that, io_uring_poll() reports EPOLLIN if local work is
pending.

That only helps if the work is there at the time of the call. When
DEFER_TASKRUN was added, io_req_local_work_add() did io_cqring_wake(),
which took care of tasks sleeping in poll() as well. Then polling got a
wait queue of its own, ->poll_wq, and the wake up in
io_req_local_work_add() was replaced by waking the submitter directly.
Since then ->poll_wq is only woken when CQEs are committed, which for
such a ring is done by the very task that is waiting to be told to:

  submitter                           completion
  poll(ring_fd)
    io_uring_poll()  // nothing yet
    schedule()
                                      io_req_local_work_add()
                                        // ->cq_wait_nr: nobody waits
  // sleeps on

Wake ->poll_wq when the first entry is put on the work list. Like for the
eventfd, that must not be done right away if the work is queued from a
wake up handler, as the chain of wake ups could get back to the wait
queue whose lock is held. Use an RCU callback in that case, with a
reference to the ring.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_