GHSA-9CP7-7XJ6-HH85
Vulnerability from github – Published: 2026-09-11 21:31 – Updated: 2026-09-14 15:32In the Linux kernel, the following vulnerability has been resolved:
svcrdma: Fix offset arithmetic in read_chunk_range
svc_rdma_read_chunk_range() walks a Read chunk's segment list to build a sub-range starting at byte offset and spanning length bytes for a Position-Zero or Call chunk. Two arithmetic defects in the per-segment loop produce wrong DMA lengths and a u32 underflow:
pcl_for_each_segment(segment, chunk) {
if (offset > segment->rs_length) {
offset -= segment->rs_length;
continue;
}
dummy.rs_handle = segment->rs_handle;
dummy.rs_length = min_t(u32, length,
segment->rs_length) - offset;
dummy.rs_offset = segment->rs_offset + offset;
First, the skip predicate uses '>' instead of '>='. When offset equals the segment's full rs_length, the segment is fully consumed and should be skipped, but the loop falls through into the body. The resulting dummy.rs_length is min_t(u32, length, rs_length) - rs_length, which underflows to a near-UINT_MAX u32 when length is smaller than rs_length, or is zero otherwise.
Second, the length formula subtracts offset from the min_t() result rather than from segment->rs_length before the cap. For offset > 0 the segment's residual is rs_length - offset, not rs_length, so the cap must be applied to the residual. With the current bracketing, whenever length is smaller than rs_length - offset the per-segment length becomes length - offset instead of length, silently dropping offset bytes from the rebuilt chunk. Combined with the boundary case above it also enables the u32 underflow path, which propagates a huge nr_bvec into svc_rdma_build_read_segment() and a multi-MiB kmalloc_array_node() in svc_rdma_get_rw_ctxt().
Additionally, svc_rdma_read_call_chunk() can invoke this function with length == 0 when the last Read chunk ends exactly at the end of the Call chunk. With the corrected >= predicate, every segment is skipped and the function returns the initial -EINVAL, rejecting a valid request. Return success immediately when length is zero. Also break out of the loop once length is fully consumed to avoid passing zero-length segments to svc_rdma_build_read_segment().
Fix by using '>=' so a fully-consumed segment is skipped, by moving '- offset' inside min_t() so the cap is applied to the segment's residual length, by returning success for zero-length requests, and by stopping iteration when the requested range has been consumed.
{
"affected": [],
"aliases": [
"CVE-2026-89533"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-09-11T20:19:36Z",
"severity": "CRITICAL"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nsvcrdma: Fix offset arithmetic in read_chunk_range\n\nsvc_rdma_read_chunk_range() walks a Read chunk\u0027s segment list to\nbuild a sub-range starting at byte offset and spanning length bytes\nfor a Position-Zero or Call chunk. Two arithmetic defects in the\nper-segment loop produce wrong DMA lengths and a u32 underflow:\n\n pcl_for_each_segment(segment, chunk) {\n if (offset \u003e segment-\u003ers_length) {\n offset -= segment-\u003ers_length;\n continue;\n }\n\n dummy.rs_handle = segment-\u003ers_handle;\n dummy.rs_length = min_t(u32, length,\n segment-\u003ers_length) - offset;\n dummy.rs_offset = segment-\u003ers_offset + offset;\n\nFirst, the skip predicate uses \u0027\u003e\u0027 instead of \u0027\u003e=\u0027. When offset\nequals the segment\u0027s full rs_length, the segment is fully consumed\nand should be skipped, but the loop falls through into the body.\nThe resulting dummy.rs_length is min_t(u32, length, rs_length) -\nrs_length, which underflows to a near-UINT_MAX u32 when length is\nsmaller than rs_length, or is zero otherwise.\n\nSecond, the length formula subtracts offset from the min_t() result\nrather than from segment-\u003ers_length before the cap. For offset \u003e 0\nthe segment\u0027s residual is rs_length - offset, not rs_length, so the\ncap must be applied to the residual. With the current bracketing,\nwhenever length is smaller than rs_length - offset the per-segment\nlength becomes length - offset instead of length, silently dropping\noffset bytes from the rebuilt chunk. Combined with the boundary\ncase above it also enables the u32 underflow path, which propagates\na huge nr_bvec into svc_rdma_build_read_segment() and a multi-MiB\nkmalloc_array_node() in svc_rdma_get_rw_ctxt().\n\nAdditionally, svc_rdma_read_call_chunk() can invoke this function\nwith length == 0 when the last Read chunk ends exactly at the end\nof the Call chunk. With the corrected \u003e= predicate, every segment\nis skipped and the function returns the initial -EINVAL, rejecting\na valid request. Return success immediately when length is zero.\nAlso break out of the loop once length is fully consumed to avoid\npassing zero-length segments to svc_rdma_build_read_segment().\n\nFix by using \u0027\u003e=\u0027 so a fully-consumed segment is skipped, by\nmoving \u0027- offset\u0027 inside min_t() so the cap is applied to the\nsegment\u0027s residual length, by returning success for zero-length\nrequests, and by stopping iteration when the requested range has\nbeen consumed.",
"id": "GHSA-9cp7-7xj6-hh85",
"modified": "2026-09-14T15:32:28Z",
"published": "2026-09-11T21:31:30Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-89533"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/10873311f91db9454e2fadbf9866bc819e0646d9"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/4493c96bbd0068fadf69cbae8d13426202e34cdc"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/4a44c140cc2f3643a39e258bb0c0ab9d0f494f5e"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/6ee4dc7476b3abc92ec1d444533a559f33f59561"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/a46b35f213c2426f5d6a0458a8f7e873fc59cdfd"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/addbf02dfe3b25e7e38e03bbd4e2a6ed86a14be7"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/cba8543c18cf42fd80fd63effb6df6ff4f7e73ce"
}
],
"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.