GHSA-9VWJ-6Q4V-P5M2
Vulnerability from github – Published: 2026-08-15 06:32 – Updated: 2026-08-17 06:33In the Linux kernel, the following vulnerability has been resolved:
gve: fix header buffer corruption with header-split and HW-GRO
The DQO RX datapath programs a per-buffer-queue-descriptor header_buf_addr at post time and reads the split header back at completion time. Both the post and the read currently index the header buffer by queue position rather than by the buffer's identity:
- post (gve_rx_post_buffers_dqo): header_buf_addr is computed from bufq->tail
- read (gve_rx_dqo): the header is read from desc_idx (the completion queue head index)
This relies on the buffer-queue index and the completion-queue index being equal for the start of every packet, i.e. on the device consuming posted buffers and returning completions in the exact same order. That assumption does not hold once HW-GRO is enabled with multiple flows: coalesced segments are accepted and completed in an order that may differ from the order buffers were posted, and segments from different flows may interleave.
That results in two problems:
-
Wrong header slot on read. Because the read offset is derived from the completion index (desc_idx) while the device wrote the header to the address programmed for the buffer's buf_id, the driver can copy a header belonging to a different packet. This shows up as throughput drop (about 30% drop and large numbers of TCP retransmissions) with header-split and HW-GRO both enabled and many streams.
-
Header buffer reused while still owned by the device. The driver advances bufq->head by one per completion and re-posts buffers based on that. Arrival of N RX completions only guarantees that at least N RX buffer descriptors have been read by the device. It does not guarantee that the device has relinquished the ownership of all the buffers corresponding to those N descriptors. With out-of-order completions (e.g. the completion for a packet copied into buffer N arrives before the completion for a packet copied into buffer N-1), the driver can re-post and overwrite a header buffer that the device is still going to write into, corrupting the header of a packet whose completion has not yet been processed.
Fix both issues by indexing the header buffer by buf_id on both the post and read paths. Reading from buf_id's slot is therefore always correct regardless of completion ordering (fixes problem 1).
Indexing by buf_id also ties each header slot to the lifetime of its buffer state. A buffer state is only returned to the free/recycle lists when its own completion (buf_id) is processed, so its header slot can only be re-posted after the device is done with it. This makes header slot reuse safe under out-of-order completions (fixes problem 2).
Allocate (gve_rx_alloc_hdr_bufs) and free (gve_rx_free_hdr_bufs) the header buffers based on num_buf_states to match the buf_id indexing.
{
"affected": [],
"aliases": [
"CVE-2026-72046"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-08-15T06:21:13Z",
"severity": "CRITICAL"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\ngve: fix header buffer corruption with header-split and HW-GRO\n\nThe DQO RX datapath programs a per-buffer-queue-descriptor\nheader_buf_addr at post time and reads the split header back at\ncompletion time. Both the post and the read currently index the\nheader buffer by queue position rather than by the buffer\u0027s identity:\n\n - post (gve_rx_post_buffers_dqo): header_buf_addr is computed from\n bufq-\u003etail\n - read (gve_rx_dqo): the header is read from desc_idx (the completion\n queue head index)\n\nThis relies on the buffer-queue index and the completion-queue index\nbeing equal for the start of every packet, i.e. on the device consuming\nposted buffers and returning completions in the exact same order. That\nassumption does not hold once HW-GRO is enabled with multiple\nflows: coalesced segments are accepted and completed in an order that\nmay differ from the order buffers were posted, and segments from\ndifferent flows may interleave.\n\nThat results in two problems:\n\n1. Wrong header slot on read. Because the read offset is derived from\n the completion index (desc_idx) while the device wrote the header to\n the address programmed for the buffer\u0027s buf_id, the driver can copy\n a header belonging to a different packet. This shows up as\n throughput drop (about 30% drop and large numbers of TCP\n retransmissions) with header-split and HW-GRO both enabled and many\n streams.\n\n2. Header buffer reused while still owned by the device. The driver\n advances bufq-\u003ehead by one per completion and re-posts buffers based\n on that. Arrival of N RX completions only guarantees that at least N\n RX buffer descriptors have been read by the device. It does not\n guarantee that the device has relinquished the ownership of all the\n buffers corresponding to those N descriptors. With out-of-order\n completions (e.g. the completion for a packet copied into buffer N\n arrives before the completion for a packet copied into buffer N-1),\n the driver can re-post and overwrite a header buffer that the device\n is still going to write into, corrupting the header of a packet\n whose completion has not yet been processed.\n\nFix both issues by indexing the header buffer by buf_id on both the post\nand read paths. Reading from buf_id\u0027s slot is therefore always correct\nregardless of completion ordering (fixes problem 1).\n\nIndexing by buf_id also ties each header slot to the lifetime of its\nbuffer state. A buffer state is only returned to the free/recycle lists\nwhen its own completion (buf_id) is processed, so its header slot can\nonly be re-posted after the device is done with it. This makes header\nslot reuse safe under out-of-order completions (fixes problem 2).\n\nAllocate (gve_rx_alloc_hdr_bufs) and free (gve_rx_free_hdr_bufs) the\nheader buffers based on num_buf_states to match the buf_id indexing.",
"id": "GHSA-9vwj-6q4v-p5m2",
"modified": "2026-08-17T06:33:06Z",
"published": "2026-08-15T06:32:10Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-72046"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/35267819b25074084130b6a7be18bbaf44d3ae74"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/84d3753d4bf284ef770ead6dee2270aaabb3ef41"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/9f8e7f59b0c2f466be74bd923726b0f5496c27ad"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/d676c9a73bdcd8237425dbb826f2bd1a25c36e40"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/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.