GHSA-4H26-3W83-PFH6
Vulnerability from github – Published: 2026-03-25 12:30 – Updated: 2026-04-02 15:31In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix race in devmap on PREEMPT_RT
On PREEMPT_RT kernels, the per-CPU xdp_dev_bulk_queue (bq) can be accessed concurrently by multiple preemptible tasks on the same CPU.
The original code assumes bq_enqueue() and __dev_flush() run atomically with respect to each other on the same CPU, relying on local_bh_disable() to prevent preemption. However, on PREEMPT_RT, local_bh_disable() only calls migrate_disable() (when PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable preemption, which allows CFS scheduling to preempt a task during bq_xmit_all(), enabling another task on the same CPU to enter bq_enqueue() and operate on the same per-CPU bq concurrently.
This leads to several races:
-
Double-free / use-after-free on bq->q[]: bq_xmit_all() snapshots cnt = bq->count, then iterates bq->q[0..cnt-1] to transmit frames. If preempted after the snapshot, a second task can call bq_enqueue() -> bq_xmit_all() on the same bq, transmitting (and freeing) the same frames. When the first task resumes, it operates on stale pointers in bq->q[], causing use-after-free.
-
bq->count and bq->q[] corruption: concurrent bq_enqueue() modifying bq->count and bq->q[] while bq_xmit_all() is reading them.
-
dev_rx/xdp_prog teardown race: __dev_flush() clears bq->dev_rx and bq->xdp_prog after bq_xmit_all(). If preempted between bq_xmit_all() return and bq->dev_rx = NULL, a preempting bq_enqueue() sees dev_rx still set (non-NULL), skips adding bq to the flush_list, and enqueues a frame. When __dev_flush() resumes, it clears dev_rx and removes bq from the flush_list, orphaning the newly enqueued frame.
-
__list_del_clearprev() on flush_node: similar to the cpumap race, both tasks can call __list_del_clearprev() on the same flush_node, the second dereferences the prev pointer already set to NULL.
The race between task A (__dev_flush -> bq_xmit_all) and task B (bq_enqueue -> bq_xmit_all) on the same CPU:
Task A (xdp_do_flush) Task B (ndo_xdp_xmit redirect) ---------------------- -------------------------------- __dev_flush(flush_list) bq_xmit_all(bq) cnt = bq->count / e.g. 16 / / start iterating bq->q[] / <-- CFS preempts Task A --> bq_enqueue(dev, xdpf) bq->count == DEV_MAP_BULK_SIZE bq_xmit_all(bq, 0) cnt = bq->count / same 16! / ndo_xdp_xmit(bq->q[]) / frames freed by driver / bq->count = 0 <-- Task A resumes --> ndo_xdp_xmit(bq->q[]) / use-after-free: frames already freed! /
Fix this by adding a local_lock_t to xdp_dev_bulk_queue and acquiring it in bq_enqueue() and __dev_flush(). These paths already run under local_bh_disable(), so use local_lock_nested_bh() which on non-RT is a pure annotation with no overhead, and on PREEMPT_RT provides a per-CPU sleeping lock that serializes access to the bq.
{
"affected": [],
"aliases": [
"CVE-2026-23294"
],
"database_specific": {
"cwe_ids": [
"CWE-362"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-03-25T11:16:24Z",
"severity": "HIGH"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nbpf: Fix race in devmap on PREEMPT_RT\n\nOn PREEMPT_RT kernels, the per-CPU xdp_dev_bulk_queue (bq) can be\naccessed concurrently by multiple preemptible tasks on the same CPU.\n\nThe original code assumes bq_enqueue() and __dev_flush() run atomically\nwith respect to each other on the same CPU, relying on\nlocal_bh_disable() to prevent preemption. However, on PREEMPT_RT,\nlocal_bh_disable() only calls migrate_disable() (when\nPREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable\npreemption, which allows CFS scheduling to preempt a task during\nbq_xmit_all(), enabling another task on the same CPU to enter\nbq_enqueue() and operate on the same per-CPU bq concurrently.\n\nThis leads to several races:\n\n1. Double-free / use-after-free on bq-\u003eq[]: bq_xmit_all() snapshots\n cnt = bq-\u003ecount, then iterates bq-\u003eq[0..cnt-1] to transmit frames.\n If preempted after the snapshot, a second task can call bq_enqueue()\n -\u003e bq_xmit_all() on the same bq, transmitting (and freeing) the\n same frames. When the first task resumes, it operates on stale\n pointers in bq-\u003eq[], causing use-after-free.\n\n2. bq-\u003ecount and bq-\u003eq[] corruption: concurrent bq_enqueue() modifying\n bq-\u003ecount and bq-\u003eq[] while bq_xmit_all() is reading them.\n\n3. dev_rx/xdp_prog teardown race: __dev_flush() clears bq-\u003edev_rx and\n bq-\u003exdp_prog after bq_xmit_all(). If preempted between\n bq_xmit_all() return and bq-\u003edev_rx = NULL, a preempting\n bq_enqueue() sees dev_rx still set (non-NULL), skips adding bq to\n the flush_list, and enqueues a frame. When __dev_flush() resumes,\n it clears dev_rx and removes bq from the flush_list, orphaning the\n newly enqueued frame.\n\n4. __list_del_clearprev() on flush_node: similar to the cpumap race,\n both tasks can call __list_del_clearprev() on the same flush_node,\n the second dereferences the prev pointer already set to NULL.\n\nThe race between task A (__dev_flush -\u003e bq_xmit_all) and task B\n(bq_enqueue -\u003e bq_xmit_all) on the same CPU:\n\n Task A (xdp_do_flush) Task B (ndo_xdp_xmit redirect)\n ---------------------- --------------------------------\n __dev_flush(flush_list)\n bq_xmit_all(bq)\n cnt = bq-\u003ecount /* e.g. 16 */\n /* start iterating bq-\u003eq[] */\n \u003c-- CFS preempts Task A --\u003e\n bq_enqueue(dev, xdpf)\n bq-\u003ecount == DEV_MAP_BULK_SIZE\n bq_xmit_all(bq, 0)\n cnt = bq-\u003ecount /* same 16! */\n ndo_xdp_xmit(bq-\u003eq[])\n /* frames freed by driver */\n bq-\u003ecount = 0\n \u003c-- Task A resumes --\u003e\n ndo_xdp_xmit(bq-\u003eq[])\n /* use-after-free: frames already freed! */\n\nFix this by adding a local_lock_t to xdp_dev_bulk_queue and acquiring\nit in bq_enqueue() and __dev_flush(). These paths already run under\nlocal_bh_disable(), so use local_lock_nested_bh() which on non-RT is\na pure annotation with no overhead, and on PREEMPT_RT provides a\nper-CPU sleeping lock that serializes access to the bq.",
"id": "GHSA-4h26-3w83-pfh6",
"modified": "2026-04-02T15:31:36Z",
"published": "2026-03-25T12:30:22Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-23294"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/1872e75375c40add4a35990de3be77b5741c252c"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/6c10b019785dc282c5f45d21e4a3f468b8fd6476"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/ab1a56c9d99189aa5c6e03940d06e40ba6a28240"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H",
"type": "CVSS_V3"
}
]
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.