Skip to content
Heist/ feed
Back to feed
UnratedFix available

smp: Make CSD lock acquisition atomic for debug mode

Type: advisorySources: OSV

In the Linux kernel, the following vulnerability has been resolved: smp: Make CSD lock acquisition atomic for debug mode Commit b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") changed smp_call_function_single() so that, when CSD lock debugging is enabled, async !wait calls use the destination CPU csd_data. That improves diagnostics, but it also removes the single-writer property that made the old csd_lock() safe: multiple CPUs can now prepare the same destination CPU CSD concurrently. csd_lock() currently waits for CSD_FLAG_LOCK to clear and then sets the bit with a non-atomic read-modify-write. Two senders can both see an unlocked CSD, set the bit, overwrite the callback fields, and enqueue the same llist node. Re-adding a node that is already the queue head can make node->next point to itself, leaving the target CPU stuck walking call_single_queue. Later synchronous work, such as a TLB shootdown, can then remain queued and trigger soft-lockup warnings or panics. Keep the single csd_lock() implementation, but when CSD lock debugging is enabled, acquire CSD_FLAG_LOCK with try_cmpxchg_acquire(). This makes the destination CPU CSD a real atomic lock in the only configuration where it can be shared by multiple remote senders, while preserving the existing non-debug fast path.

Products
Kernel
Affected versions
Not specified
Fixed versions
7.1.6
CVEs
CVE-2026-68438
Confirmed fixed CVEs
Not specified
Updated in this feed
3 Nov 2026, 18:14 UTC · Revision 1

Source evidence

smp: Make CSD lock acquisition atomic for debug mode

core-osv · Original source

Published 12 Aug 2026, 00:07 UTC

In the Linux kernel, the following vulnerability has been resolved: smp: Make CSD lock acquisition atomic for debug mode Commit b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") changed smp_call_function_single() so that, when CSD lock debugging is enabled, async !wait calls use the destination CPU csd_data. That improves diagnostics, but it also removes the single-writer property that made the old csd_lock() safe: multiple CPUs can now prepare the same destination CPU CSD concurrently. csd_lock() currently waits for CSD_FLAG_LOCK to clear and then sets the bit with a non-atomic read-modify-write. Two senders can both see an unlocked CSD, set the bit, overwrite the callback fields, and enqueue the same llist node. Re-adding a node that is already the queue head can make node->next point to itself, leaving the target CPU stuck walking call_single_queue. Later synchronous work, such as a TLB shootdown, can then remain queued and trigger soft-lockup warnings or panics. Keep the single csd_lock() implementation, but when CSD lock debugging is enabled, acquire CSD_FLAG_LOCK with try_cmpxchg_acquire(). This makes the destination CPU CSD a real atomic lock in the only configuration where it can be shared by multiple remote senders, while preserving the existing non-debug fast path.

osv:CVE-2026-68438

Kernel

Fixed versions: 7.1.6

Complete source record
{
  "id": "75e916416ad9ef66db0327447418b6b3702bc10a542eb8bf03774c40abb6666a",
  "url": "https://osv.dev/vulnerability/CVE-2026-68438",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "smp: Make CSD lock acquisition atomic for debug mode",
    "summary": "In the Linux kernel, the following vulnerability has been resolved: smp: Make CSD lock acquisition atomic for debug mode Commit b0473dcd4b1d (\"smp: Improve smp_call_function_single() CSD-lock diagnostics\") changed smp_call_function_single() so that, when CSD lock debugging is enabled, async !wait calls use the destination CPU csd_data. That improves diagnostics, but it also removes the single-writer property that made the old csd_lock() safe: multiple CPUs can now prepare the same destination CPU CSD concurrently. csd_lock() currently waits for CSD_FLAG_LOCK to clear and then sets the bit with a non-atomic read-modify-write. Two senders can both see an unlocked CSD, set the bit, overwrite the callback fields, and enqueue the same llist node. Re-adding a node that is already the queue head can make node->next point to itself, leaving the target CPU stuck walking call_single_queue. Later synchronous work, such as a TLB shootdown, can then remain queued and trigger soft-lockup warnings or panics. Keep the single csd_lock() implementation, but when CSD lock debugging is enabled, acquire CSD_FLAG_LOCK with try_cmpxchg_acquire(). This makes the destination CPU CSD a real atomic lock in the only configuration where it can be shared by multiple remote senders, while preserving the existing non-debug fast path.",
    "evidence": "osv:CVE-2026-68438",
    "products": [
      {
        "name": {
          "value": "Kernel",
          "evidence": "/affected/1/package/name"
        },
        "prerequisites": [],
        "fixed_versions": [
          {
            "value": "7.1.6",
            "evidence": "/affected/1/ranges"
          }
        ],
        "affected_versions": []
      }
    ],
    "severity": "unknown",
    "structured": {
      "id": "CVE-2026-68438",
      "aliases": [
        "CVE-2026-68438"
      ],
      "affected": [
        {
          "ranges": [
            {
              "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
              "type": "GIT",
              "events": [
                {
                  "introduced": "b0473dcd4b1d7e2e44947e7ac1820c73a268821a"
                },
                {
                  "fixed": "282d220bae5fbfc90cf0e3d5b5e42c00ad79f989"
                },
                {
                  "fixed": "35551efb155e3b83445a6c3f66cb498d5efc182c"
                }
              ]
            }
          ],
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-68438.json"
          }
        },
        {
          "ranges": [
            {
              "type": "ECOSYSTEM",
              "events": [
                {
                  "introduced": "7.1.0"
                },
                {
                  "fixed": "7.1.6"
                }
              ]
            }
          ],
          "package": {
            "name": "Kernel",
            "ecosystem": "Linux"
          },
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-68438.json"
          }
        }
      ],
      "modified": "2026-10-28T02:30:31.352229227Z",
      "provider": "osv",
      "references": [
        "https://git.kernel.org/stable/c/282d220bae5fbfc90cf0e3d5b5e42c00ad79f989",
        "https://git.kernel.org/stable/c/35551efb155e3b83445a6c3f66cb498d5efc182c",
        "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/68xxx/CVE-2026-68438.json",
        "https://nvd.nist.gov/vuln/detail/CVE-2026-68438",
        "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git"
      ],
      "provider_metadata": {
        "cna_assigner": "Linux",
        "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/68xxx/CVE-2026-68438.json"
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-68438",
        "evidence": "/id"
      }
    ],
    "security_relevant": true,
    "severity_evidence": null
  },
  "source_id": "core-osv",
  "document_id": 498334,
  "published_at": "2026-08-12T00:07:27.105+00:00"
}