Linux kernel race condition in GUP PUD walk for DAX mappings
- Exploited
- No known exploitation
- Fix
- No fix listed
- Who is exposed
- Not reported
Summary
The Linux kernel's page-walk code in `follow_pud_mask()` reads a PUD entry without holding the page table lock, so a concurrent zap and refault can leave it inconsistent. This only affects device-dax mappings that use PUD entries.
Written by a model
Original description
In the Linux kernel, the following vulnerability has been resolved:
mm/gup: recheck the PUD under PTL in follow_pud_mask()
follow_pud_mask() reads the PUD without a lock. If it is a leaf, it takes the lock and calls follow_huge_pud(), which reads the entry again, but only tests whether it is present.
A leaf can be zapped concurrently and a page fault can fill the empty entry with a page table.
This currently only applies when device-dax makes use of PUD entries, and the fault after e.g., MADV_DONTNEED would find THPs to be disabled.
That requires a sequence like
- Fault in the PUD
- Disable THP
- Have GUP race against concurrent MADV_DONTNEED + refault
Which is rather unlikely to happen in practice, which is why we never received a report about such a problem.
Before commit 1b1676180246 ("mm/gup: handle huge pud for follow_pud_mask()"), we performed that check in follow_devmap_pud() by testing for pud_devmap().
Let's fix it by just structuring follow_pud_mask() similar to follow_pmd_mask(), minus protnone stuff that does not apply and minus FOLL_SPLIT_PMD handling. That makes it much easier to spot any such inconsistencies.
Perform the pud_bad() check early in follow_pmd_mask() and just forward the PUD value. We can drop the pud_present() check in follow_huge_pud(), just like we have in follow_huge_pmd().
Even though we are performing more changes than strictly necessary, the fix should be easy to backport.
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-2026-99664 (mm/gup: recheck the PUD under PTL in follow_pud_mask()), 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-2026-99664 (entry last updated 2026-11-20):
Affected:
- Linux Linux: version range not reported
- Linux Linux: versions 6.10
Fixed versions: none listed yet.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-99664 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-99664 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/da57b6bce646946c083a48df644d43bb9d011f5f
- https://git.kernel.org/stable/c/9eaedd598cd25eb0e18958e2456153a4c1f3db03
- https://git.kernel.org/stable/c/79cb51d538abc459f74e046d27797d36b133ce0e
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-2026-99664
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-2026-99664"}.Affected versions
- Linux LinuxVersion range not reported
- Linux Linux6.10
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 5
| Kind | Source |
|---|---|
| CVE record 2Establishes: The identifier and description. | |
| Record | CVE List · CVE-2026-99664 |
| Record | NVD · CVE-2026-99664 |
| Other links 3 | |
| Link | git.kernel.org · stable/c/da57b6bce646946c083a48df644d43bb9d011f5f |
| Link | git.kernel.org · stable/c/9eaedd598cd25eb0e18958e2456153a4c1f3db03 |
| Link | git.kernel.org · stable/c/79cb51d538abc459f74e046d27797d36b133ce0e |
Questions about CVE-2026-99664
Is CVE-2026-99664 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-2026-99664?
Linux: version 6.10.
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.