Back

CRITICAL

nvmet-tcp: fix out-of-bounds write when receiving an over-long PDU

Published Sep 16, 2026

Description

nvmet_tcp_try_recv_pdu() reads a PDU header into the fixed 128-byte queue->pdu union, then computes the remaining payload length as

queue->left = hdr->hlen - queue->offset + hdgst;

and reads that many more bytes into &queue->pdu + queue->offset, without ever bounding the result against sizeof(queue->pdu).

A struct nvme_tcp_icreq_pdu is itself 128 bytes, exactly the size of the union. Once a header digest has been negotiated (hdgst = 4), a second ICReq passes the hlen == nvmet_tcp_pdu_size() check but yields queue->left = 128 - 8 + 4 = 124, so bytes 8..132 are written into the 128-byte buffer -- 4 bytes past its end, over queue->hdr_digest and queue->data_digest. Those bytes are attacker-controlled (an ICReq carries no digest), and the duplicate ICReq is only rejected later, after the overflow. A remote unauthenticated host can thus corrupt kernel memory adjacent to the receive buffer.

Reject any PDU whose declared length would read past the end of queue->pdu before the second recv.

Affected products

Remediation

No remediation recorded yet.

Weaknesses (0)

No CWE recorded.

References (9)

Change history (0)

No recorded changes yet.

Sources
CVE.org / MITRE
Status PUBLISHED
Assigner Linux
Published Sep 16, 2026
Updated Sep 16, 2026
Reserved Sep 11, 2026
NVD
Status Received
Modified Sep 16, 2026
Red Hat
Severity n/a
Public date n/a
ENISA EUVD
Assigner Linux
Published Sep 16, 2026
Updated Sep 16, 2026
Exploited since n/a
EUVD-2026-80569