GHSA-RFFJ-59X2-VRX3
Vulnerability from github – Published: 2026-08-15 06:32 – Updated: 2026-08-15 06:32In the Linux kernel, the following vulnerability has been resolved:
net/mlx5e: Fix publication race for priv->channel_stats[]
mlx5e_channel_stats_alloc() publishes a new entry to priv->channel_stats[] and then increments priv->stats_nch as a publication token, but neither store carries any memory barrier:
priv->channel_stats[ix] = kvzalloc_node(...);
if (!priv->channel_stats[ix])
return -ENOMEM;
priv->stats_nch++;
Concurrent readers compute the loop bound from priv->stats_nch and then dereference priv->channel_stats[i] using plain accesses, e.g.
for (i = 0; i < priv->stats_nch; i++) {
struct mlx5e_channel_stats *cs = priv->channel_stats[i];
... cs->rq.packets ...
}
On weakly-ordered architectures (ARM, PowerPC, RISC-V) the writes to channel_stats[ix] and stats_nch may become visible to other CPUs out of program order. A reader can observe stats_nch == N while still seeing channel_stats[N-1] == NULL, leading to a NULL pointer dereference in the channel_stats loop.
This has been observed in production on BlueField-3 DPUs (arm64), where ovs-vswitchd queries netdev statistics over netlink during NIC bringup, racing mlx5e_open_channel() -> mlx5e_channel_stats_alloc() on another CPU:
Unable to handle kernel NULL pointer dereference at virtual address 0x840 Hardware name: BlueField-3 DPU pc : mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core] Call trace: mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core] dev_get_stats+0x50/0xc0 ovs_vport_get_stats+0x38/0xac [openvswitch] ovs_vport_cmd_fill_info+0x194/0x290 [openvswitch] ovs_vport_cmd_get+0xbc/0x10c [openvswitch] genl_family_rcv_msg_doit+0xd0/0x160 genl_rcv_msg+0xec/0x1f0 netlink_rcv_skb+0x64/0x130 genl_rcv+0x40/0x60 netlink_unicast+0x2fc/0x370 netlink_sendmsg+0x1dc/0x454 ... __arm64_sys_sendmsg+0x2c/0x40
Add mlx5e_stats_nch_write() and mlx5e_stats_nch_read() helpers in en.h that wrap the smp_store_release()/smp_load_acquire() pair on stats_nch. The release/acquire pair establishes the contract:
stats_nch == N => channel_stats[0..N-1] are visible and non-NULL.
Publish the stats_nch increment via mlx5e_stats_nch_write() in the writer (mlx5e_channel_stats_alloc()), and read stats_nch via mlx5e_stats_nch_read() in all readers: mlx5e RX/TX queue stats, mlx5e_get_base_stats(), ethtool channels stats, IPoIB stats, the sw_stats fold and the HV VHCA stats agent.
{
"affected": [],
"aliases": [
"CVE-2026-72341"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-08-15T06:22:07Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nnet/mlx5e: Fix publication race for priv-\u003echannel_stats[]\n\nmlx5e_channel_stats_alloc() publishes a new entry to\npriv-\u003echannel_stats[] and then increments priv-\u003estats_nch as a\npublication token, but neither store carries any memory barrier:\n\n\tpriv-\u003echannel_stats[ix] = kvzalloc_node(...);\n\tif (!priv-\u003echannel_stats[ix])\n\t\treturn -ENOMEM;\n\tpriv-\u003estats_nch++;\n\nConcurrent readers compute the loop bound from priv-\u003estats_nch and\nthen dereference priv-\u003echannel_stats[i] using plain accesses, e.g.\n\n\tfor (i = 0; i \u003c priv-\u003estats_nch; i++) {\n\t\tstruct mlx5e_channel_stats *cs = priv-\u003echannel_stats[i];\n\t\t... cs-\u003erq.packets ...\n\t}\n\nOn weakly-ordered architectures (ARM, PowerPC, RISC-V) the writes to\nchannel_stats[ix] and stats_nch may become visible to other CPUs out\nof program order. A reader can observe stats_nch == N while still\nseeing channel_stats[N-1] == NULL, leading to a NULL pointer\ndereference in the channel_stats loop.\n\nThis has been observed in production on BlueField-3 DPUs (arm64),\nwhere ovs-vswitchd queries netdev statistics over netlink during NIC\nbringup, racing mlx5e_open_channel() -\u003e mlx5e_channel_stats_alloc()\non another CPU:\n\n Unable to handle kernel NULL pointer dereference at virtual address 0x840\n Hardware name: BlueField-3 DPU\n pc : mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core]\n Call trace:\n mlx5e_fold_sw_stats64+0x30/0x180 [mlx5_core]\n dev_get_stats+0x50/0xc0\n ovs_vport_get_stats+0x38/0xac [openvswitch]\n ovs_vport_cmd_fill_info+0x194/0x290 [openvswitch]\n ovs_vport_cmd_get+0xbc/0x10c [openvswitch]\n genl_family_rcv_msg_doit+0xd0/0x160\n genl_rcv_msg+0xec/0x1f0\n netlink_rcv_skb+0x64/0x130\n genl_rcv+0x40/0x60\n netlink_unicast+0x2fc/0x370\n netlink_sendmsg+0x1dc/0x454\n ...\n __arm64_sys_sendmsg+0x2c/0x40\n\nAdd mlx5e_stats_nch_write() and mlx5e_stats_nch_read() helpers in en.h\nthat wrap the smp_store_release()/smp_load_acquire() pair on stats_nch.\nThe release/acquire pair establishes the contract:\n\n stats_nch == N =\u003e channel_stats[0..N-1] are visible and non-NULL.\n\nPublish the stats_nch increment via mlx5e_stats_nch_write() in the\nwriter (mlx5e_channel_stats_alloc()), and read stats_nch via\nmlx5e_stats_nch_read() in all readers: mlx5e RX/TX queue stats,\nmlx5e_get_base_stats(), ethtool channels stats, IPoIB stats, the\nsw_stats fold and the HV VHCA stats agent.",
"id": "GHSA-rffj-59x2-vrx3",
"modified": "2026-08-15T06:32:21Z",
"published": "2026-08-15T06:32:20Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-72341"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/5a799714e8ca0bce9ea40694f49914cf1adbbaa9"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/5c7e3755abf663f033de24f917b77685e9543045"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/815515ec68f527ca755cb1e2c1ff9148f6b3ea56"
}
],
"schema_version": "1.4.0",
"severity": []
}
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.