Linux kernel denial of service in io_uring cancellation
- Exploited
- No known exploitation
- Fix
- No fix listed
- Who is exposed
- Not reported
Summary
The Linux kernel's io_uring subsystem can keep a lock held while an exiting SQPOLL thread waits, which can stall other rings sharing that thread so they cannot be freed. A pending zero-copy send notification that the peer never reads can keep the lock held for as long as a user chooses.
Written by a model
Original description
In the Linux kernel, the following vulnerability has been resolved:
io_uring/cancel: drop sqd->lock while SQPOLL waits
An exiting SQPOLL thread calls io_uring_cancel_generic() with sqd->lock held, and keeps it across cond_resched() and the sleep until nothing is in flight anymore. A zero-copy send notification can't be canceled and stays pending as long as the peer doesn't read, so the lock is held for as long as a user cares to. io_ring_exit_work() needs it to park the thread, and so do IORING_REGISTER_IOWQ_AFF and IOWQ_MAX_WORKERS. With 64 such rings sharing the thread, every iou_exit slot sleeps on the lock and no ring gets freed for anyone.
Drop the lock around cond_resched() and the sleep, like the main loop of the thread does. Each walk of ctx_list is still under one hold, and nothing is kept across the unlock. The thread drops its io-wq, frees its tctx and clears sqd->thread under one hold after the loop, so whoever holds the lock and finds sqd->thread set can still use them.
[axboe: adapted to the schedule_timeout() based loop]
What to do
Check your systems with an agent
Paste this into a coding or ops agent. It checks your systems read-only and reports a table per asset.
Check whether my systems are affected by CVE-2026-99797 (io_uring/cancel: drop sqd->lock while SQPOLL waits), using the cve.now data below.
Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.
What cve.now has for CVE-2026-99797 (entry last updated 2026-11-20):
Affected:
- Linux Linux: version range not reported
- Linux Linux: versions 6.0
Fixed versions: none listed yet.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-99797 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-99797 only. If you also check another CVE, look up its own KEV status; never assume it from this one.
How to check:
- Installed software: check what is actually running, not what a repo declares. Read the version from each host, container image and Kubernetes node (the binary's version output, the OS package database, image layers), and check whether the conditions above hold there. Distribution packages may carry a backported fix under an older version number; confirm against the distribution's own advisory.
Verify against the linked advisories before concluding, and cite the date you read each one:
- https://git.kernel.org/stable/c/9ebfcc60793a46eaf60fc34792486c9a6e114460
- https://git.kernel.org/stable/c/96ba960a6099935cfc5ea17aef056553f0c8e647
- https://git.kernel.org/stable/c/682a8804640b6266a4b7fae5a131c57dd8711f70
- https://git.kernel.org/stable/c/cb0306c52ffae083a86fb283de67875ae7a9500e
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.
Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.
Entry: https://cve.now/CVE-2026-99797
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example execute with name cve.get and arguments {"id": "CVE-2026-99797"}.Affected versions
- Linux LinuxVersion range not reported
- Linux Linux6.0
cve.now Index
- Exploitation?/40Unknown. No CISA SSVC exploitation rating yet
- Exposure?/25Unknown. No advisory context yet
- Reach20/20Affects Linux kernel (software on nearly every server, desktop or phone)
- Severity?/10Unknown. No CVSS score or vendor rating
- No patch5/5No patch listed yet
What would change the score
- Would score about 80 if added to CISA KEV
- Would score about 75 if CISA's SSVC rates exploitation active
- Would score about 47 if advisories confirm default setups are exposed
Timeline
- CVE published
- First seen by cve.now
Evidence 6
| Kind | Source |
|---|---|
| CVE record 2Establishes: The identifier and description. | |
| Record | CVE List · CVE-2026-99797 |
| Record | NVD · CVE-2026-99797 |
| Other links 4 | |
| Link | git.kernel.org · stable/c/9ebfcc60793a46eaf60fc34792486c9a6e114460 |
| Link | git.kernel.org · stable/c/96ba960a6099935cfc5ea17aef056553f0c8e647 |
| Link | git.kernel.org · stable/c/682a8804640b6266a4b7fae5a131c57dd8711f70 |
| Link | git.kernel.org · stable/c/cb0306c52ffae083a86fb283de67875ae7a9500e |
Questions about CVE-2026-99797
Is CVE-2026-99797 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.
Source: cve.now feed data
Which versions are affected by CVE-2026-99797?
Linux: version 6.0.
Source: cve.now feed data
Related
- CVE-2026-99804io_uring/io-wq: save worker type before dropping its reference
- CVE-2026-99803io_uring/net: mask socket type with SOCK_TYPE_MASK in io_socket_bpf_populate()
- CVE-2026-99802io_uring/register: enforce per-task restrictions in io_uring_register_blind()
- CVE-2026-99801io_uring/bpf-ops: clear bpf_ctx while submitting SQEs
- CVE-2026-99800io_uring: free the task context after a grace period
- CVE-2026-99799io_uring/sqpoll: don't wait for the thread to exit
No corrections so far. Something wrong on this page? Report an error.