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

RDMA/rxe: Avoid reprocessing the current packet after the QP enters the error state

When do_complete() finds the QP in the error state it returns
RESPST_CHK_RESOURCE. Before commit 49dc9c1f0c7e ("RDMA/rxe: Cleanup
reset state handling in rxe_resp.c") this was the flush loop:
check_resource() had an error-state branch that fetched each remaining
recv WQE and completed it with IB_WC_WR_FLUSH_ERR, without touching
the current packet. That commit removed the error-state branch from
check_resource() (draining is now done at rxe_receiver() entry) but
kept the do_complete() error-state return.

As a result, when a QP moves to the error state while a packet is
being completed - e.g. an rdma_cm disconnect racing with receive
processing - the responder state machine loops back into the request
processing chain with the already-completed packet still in hand:
check_resource() fetches a fresh recv WQE, execute()/send_data_in()
copies the same packet payload again, do_complete() posts another
IB_WC_SUCCESS CQE (qp->resp.status is still 0), and control returns
to the error-state check. The loop re-executes the same packet once
per posted recv WQE (observed: ~1000 duplicate IB_WC_SUCCESS
completions of one SEND, one per ~8us, matching the RQ occupancy)
until the RQ is exhausted, after which qp->resp.wqe is NULL and
send_data_in() dereferences it:

BUG: kernel NULL pointer dereference, address: 0000000000000014
Workqueue: rxe_wq do_work
RIP: copy_data+0x29/0x1f0
Call Trace:
send_data_in+0x25/0x50
rxe_receiver+0xf36/0x1dd0

The duplicate completions are indistinguishable from real receives to
the ULP. During an rds stress test, the message was accepted as new and
delivered the same datagram to user space hundreds of times, corrupting
the stream; any ULP that relies on RC exactly-once delivery is affected.

A live packet reaching the error-state check in do_complete() has
been executed and completed exactly once and must be consumed, not
re-processed. Return RESPST_CLEANUP for it (dequeue and free); keep
returning RESPST_CHK_RESOURCE for the pkt == NULL case.
Published: 2026-09-17
Score: 8.2 High
EPSS: < 1% Very Low
KEV: No
Impact: Denial of Service
Action: Immediate Patch
AI Analysis

Impact

A flaw in the Linux kernel RDMA/rxe driver causes a query path to re‑process a packet that is already marked for completion when the Queue Pair (QP) enters an error state. The driver ends up posting the same successful completion to the completion queue repeatedly, and when the work queue becomes empty a NULL pointer dereference occurs, causing a kernel panic. The duplicate completions also lead to the same payload being delivered to user space multiple times, corrupting streams for protocols that assume one‑to‑one delivery.

Affected Systems

All Linux kernels that contain the RDMA/rxe driver are affected; the issue exists in the current release series erroneous error‑state branch is applied. No specific version list is provided, so any kernel containing the vulnerable code path is considered at risk.

Risk and Exploitability

The CVSS score of 8.2 indicates a high severity. The EPSS score is below 1 %, meaning it is unlikely to be actively exploited at present, and it is not listed in the CISA KEV catalog. The vulnerability is exploitable through RDMA traffic sent to the target system; a malicious remote party can trigger the kernel crash by causing a QP to transit to the error state while a packet is being processed. The impact is primarily a denial‑of‑service via kernel crash, with secondary data corruption for applications that rely on exactly‑once delivery.

Generated by OpenCVE AI on September 19, 2026 at 15:59 UTC.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade the Linux kernel to a version that includes the RDMA/rxe fix (e.g., the patch that removes the error‑state branch from ``check_resource()``);
  • If a kernel upgrade is not feasible, apply the specific patch that implements the commit 49dc9c1f0c7e to eliminate the residual error‑state handling and rebuild the kernel.
  • Verify that RDMA applications handle duplicate completions gracefully or modify them to ignore repeat CQE entries to mitigate accidental data corruption while the kernel patch is pending.

Generated by OpenCVE AI on September 19, 2026 at 15:59 UTC.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Debian DLA Debian DLA DLA-4817-1 linux-6.12 security update
Debian DSA Debian DSA DSA-6528-1 linux security update
History

Sat, 19 Sep 2026 07:45:00 +0000

Type Values Removed Values Added
Weaknesses CWE-476

Fri, 18 Sep 2026 21:30:00 +0000

Type Values Removed Values Added
Metrics cvssV3_1

{'score': 8.2, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H'}

Thu, 17 Sep 2026 16:30:00 +0000

Type Values Removed Values Added
Description In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Avoid reprocessing the current packet after the QP enters the error state When do_complete() finds the QP in the error state it returns RESPST_CHK_RESOURCE. Before commit 49dc9c1f0c7e ("RDMA/rxe: Cleanup reset state handling in rxe_resp.c") this was the flush loop: check_resource() had an error-state branch that fetched each remaining recv WQE and completed it with IB_WC_WR_FLUSH_ERR, without touching the current packet. That commit removed the error-state branch from check_resource() (draining is now done at rxe_receiver() entry) but kept the do_complete() error-state return. As a result, when a QP moves to the error state while a packet is being completed - e.g. an rdma_cm disconnect racing with receive processing - the responder state machine loops back into the request processing chain with the already-completed packet still in hand: check_resource() fetches a fresh recv WQE, execute()/send_data_in() copies the same packet payload again, do_complete() posts another IB_WC_SUCCESS CQE (qp->resp.status is still 0), and control returns to the error-state check. The loop re-executes the same packet once per posted recv WQE (observed: ~1000 duplicate IB_WC_SUCCESS completions of one SEND, one per ~8us, matching the RQ occupancy) until the RQ is exhausted, after which qp->resp.wqe is NULL and send_data_in() dereferences it: BUG: kernel NULL pointer dereference, address: 0000000000000014 Workqueue: rxe_wq do_work RIP: copy_data+0x29/0x1f0 Call Trace: send_data_in+0x25/0x50 rxe_receiver+0xf36/0x1dd0 The duplicate completions are indistinguishable from real receives to the ULP. During an rds stress test, the message was accepted as new and delivered the same datagram to user space hundreds of times, corrupting the stream; any ULP that relies on RC exactly-once delivery is affected. A live packet reaching the error-state check in do_complete() has been executed and completed exactly once and must be consumed, not re-processed. Return RESPST_CLEANUP for it (dequeue and free); keep returning RESPST_CHK_RESOURCE for the pkt == NULL case.
Title RDMA/rxe: Avoid reprocessing the current packet after the QP enters the error state
First Time appeared Linux
Linux linux Kernel
CPEs cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*
Vendors & Products Linux
Linux linux Kernel
References

Subscriptions

Linux Linux Kernel
cve-icon MITRE

Status: PUBLISHED

Assigner: Linux

Published:

Updated: 2026-09-18T17:55:57.609Z

Reserved: 2026-09-17T16:02:15.085Z

Link: CVE-2026-93107

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-09-17T17:18:05.060

Modified: 2026-09-18T18:18:20.813

Link: CVE-2026-93107

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-09-20T08:45:17Z

Weaknesses