GHSA-C3RF-2Q38-4HG9
Vulnerability from github – Published: 2026-09-25 12:31 – Updated: 2026-09-25 15:31In the Linux kernel, the following vulnerability has been resolved:
net/rds: acquire RDS_IN_XMIT in rds_tcp_reset_callbacks()
rds_tcp_reset_callbacks() quiesces the transmit path by setting the path state to RDS_CONN_RESETTING and then waiting for RDS_IN_XMIT to be sampled clear before swapping the underlying socket and calling rds_send_path_reset().
Sampling the bit clear is not the same as owning it: rds_send_xmit() can re-acquire RDS_IN_XMIT right after the wait_event() returns. Its state recheck after taking the lock is a store-buffering pattern (the resetter writes the state and reads the bit, the sender writes the bit and reads the state) and acquire_in_xmit() is only an acquire operation, so on weakly ordered architectures both sides can miss each other's write and the transmit path then runs concurrently with rds_send_path_reset() rewriting cp_xmit_* state - which is exactly what the comment above rds_send_path_reset() tells its callers to prevent.
Take the lock instead, hold it across the socket swap and rds_send_path_reset(), and release it with a wake-up at the end. The lock-ordering constraint documented above the wait still holds: the lock is acquired before lock_sock(), so a sender inside tcp_sendmsg() can never be waited on while we hold the socket lock.
Two details of the old code go away with the same change:
-
t_sock is now read only after the lock is acquired. The old code cached it before waiting; the teardown in rds_conn_shutdown() releases that socket and clears t_sock, so a pointer cached before the wait can be stale by the time the accept path resumes. Reading it under RDS_IN_XMIT is what makes the exclusion complete once the teardown owns the same lock, which the next patch arranges; until then the teardown still only samples the bit, and the two paths remain as exposed to each other as they are today.
-
The old !osock early path called rds_send_path_reset() with no serialization at all. It now runs under the lock like the normal path. The conditional RDS_CONN_RESETTING transition of the previous patch happens before the socket check either way: a path found without a socket is either still connecting (its reconnect worker blocked on t_conn_path_lock) and legitimately goes RESETTING -> UP on the new socket, or it has been torn down meanwhile and is dropped.
The in-function comment describing the old wait-based quiesce is rewritten to describe the lock-based one, and the stale block comment above the function (which still described a return value and an incomplete list of t_sock writers) is refreshed to name all four writers - the connect, accept, teardown and swap paths - and what serializes each of them.
{
"affected": [],
"aliases": [
"CVE-2026-98070"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-09-25T11:17:36Z",
"severity": "HIGH"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nnet/rds: acquire RDS_IN_XMIT in rds_tcp_reset_callbacks()\n\nrds_tcp_reset_callbacks() quiesces the transmit path by setting the\npath state to RDS_CONN_RESETTING and then waiting for RDS_IN_XMIT to\nbe sampled clear before swapping the underlying socket and calling\nrds_send_path_reset().\n\nSampling the bit clear is not the same as owning it: rds_send_xmit()\ncan re-acquire RDS_IN_XMIT right after the wait_event() returns. Its\nstate recheck after taking the lock is a store-buffering pattern (the\nresetter writes the state and reads the bit, the sender writes the\nbit and reads the state) and acquire_in_xmit() is only an acquire\noperation, so on weakly ordered architectures both sides can miss\neach other\u0027s write and the transmit path then runs concurrently with\nrds_send_path_reset() rewriting cp_xmit_* state - which is exactly\nwhat the comment above rds_send_path_reset() tells its callers to\nprevent.\n\nTake the lock instead, hold it across the socket swap and\nrds_send_path_reset(), and release it with a wake-up at the end. The\nlock-ordering constraint documented above the wait still holds: the\nlock is acquired before lock_sock(), so a sender inside tcp_sendmsg()\ncan never be waited on while we hold the socket lock.\n\nTwo details of the old code go away with the same change:\n\n - t_sock is now read only after the lock is acquired. The old code\n cached it before waiting; the teardown in rds_conn_shutdown()\n releases that socket and clears t_sock, so a pointer cached before\n the wait can be stale by the time the accept path resumes. Reading\n it under RDS_IN_XMIT is what makes the exclusion complete once the\n teardown owns the same lock, which the next patch arranges; until\n then the teardown still only samples the bit, and the two paths\n remain as exposed to each other as they are today.\n\n - The old !osock early path called rds_send_path_reset() with no\n serialization at all. It now runs under the lock like the normal\n path. The conditional RDS_CONN_RESETTING transition of the\n previous patch happens before the socket check either way: a path\n found without a socket is either still connecting (its reconnect\n worker blocked on t_conn_path_lock) and legitimately goes\n RESETTING -\u003e UP on the new socket, or it has been torn down\n meanwhile and is dropped.\n\nThe in-function comment describing the old wait-based quiesce is\nrewritten to describe the lock-based one, and the stale block comment\nabove the function (which still described a return value and an\nincomplete list of t_sock writers) is refreshed to name all four\nwriters - the connect, accept, teardown and swap paths - and what\nserializes each of them.",
"id": "GHSA-c3rf-2q38-4hg9",
"modified": "2026-09-25T15:31:44Z",
"published": "2026-09-25T12:31:35Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-98070"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/02c5f9dc2efd823e061954d564ce00bacd1bebeb"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/062d9e008c67289e8e1b221ecdd8f9d60566d012"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/8e4c3b7844c906c7097b4cfedd9dd1f48c9a6a92"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/d625112564c3e980e02504270222b49b82690cee"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:H/PR:N/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.