CVE-2024-58057

Source
https://nvd.nist.gov/vuln/detail/CVE-2024-58057
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2024-58057.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2024-58057
Downstream
Related
Published
2025-03-06T15:54:00Z
Modified
2025-10-15T21:48:45.869050Z
Summary
idpf: convert workqueues to unbound
Details

In the Linux kernel, the following vulnerability has been resolved:

idpf: convert workqueues to unbound

When a workqueue is created with WQ_UNBOUND, its work items are served by special worker-pools, whose host workers are not bound to any specific CPU. In the default configuration (i.e. when queue_delayed_work and friends do not specify which CPU to run the work item on), WQ_UNBOUND allows the work item to be executed on any CPU in the same node of the CPU it was enqueued on. While this solution potentially sacrifices locality, it avoids contention with other processes that might dominate the CPU time of the processor the work item was scheduled on.

This is not just a theoretical problem: in a particular scenario misconfigured process was hogging most of the time from CPU0, leaving less than 0.5% of its CPU time to the kworker. The IDPF workqueues that were using the kworker on CPU0 suffered large completion delays as a result, causing performance degradation, timeouts and eventual system crash.

  • I have also run a manual test to gauge the performance improvement. The test consists of an antagonist process (./stress --cpu 2) consuming as much of CPU 0 as possible. This process is run under taskset 01 to bind it to CPU0, and its priority is changed with chrt -pQ 9900 10000 ${pid} and renice -n -20 ${pid} after start.

    Then, the IDPF driver is forced to prefer CPU0 by editing all calls to queue_delayed_work, mod_delayed_work, etc... to use CPU 0.

    Finally, ktraces for the workqueue events are collected.

    Without the current patch, the antagonist process can force arbitrary delays between workqueue_queue_work and workqueue_execute_start, that in my tests were as high as 30ms. With the current patch applied, the workqueue can be migrated to another unloaded CPU in the same node, and, keeping everything else equal, the maximum delay I could see was 6us.

References

Affected packages

Git / git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git

Affected ranges

Type
GIT
Repo
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Events
Introduced
0fe45467a1041ea3657a7fa3a791c84c104fbd34
Fixed
66bf9b3d9e1658333741f075320dc8e7cd6f8d09
Type
GIT
Repo
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Events
Introduced
0fe45467a1041ea3657a7fa3a791c84c104fbd34
Fixed
868202ec3854e13de1164e4a3e25521194c5af72
Type
GIT
Repo
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Events
Introduced
0fe45467a1041ea3657a7fa3a791c84c104fbd34
Fixed
9a5b021cb8186f1854bac2812bd4f396bb1e881c

Affected versions

v6.*

v6.10
v6.10-rc1
v6.10-rc2
v6.10-rc3
v6.10-rc4
v6.10-rc5
v6.10-rc6
v6.10-rc7
v6.11
v6.11-rc1
v6.11-rc2
v6.11-rc3
v6.11-rc4
v6.11-rc5
v6.11-rc6
v6.11-rc7
v6.12
v6.12-rc1
v6.12-rc2
v6.12-rc3
v6.12-rc4
v6.12-rc5
v6.12-rc6
v6.12-rc7
v6.12.1
v6.12.10
v6.12.11
v6.12.12
v6.12.2
v6.12.3
v6.12.4
v6.12.5
v6.12.6
v6.12.7
v6.12.8
v6.12.9
v6.13
v6.13-rc1
v6.13-rc2
v6.13-rc3
v6.13-rc4
v6.13-rc5
v6.13-rc6
v6.13-rc7
v6.13.1
v6.6
v6.6-rc1
v6.6-rc2
v6.6-rc3
v6.6-rc4
v6.6-rc5
v6.6-rc6
v6.6-rc7
v6.7
v6.7-rc1
v6.7-rc2
v6.7-rc3
v6.7-rc4
v6.7-rc5
v6.7-rc6
v6.7-rc7
v6.7-rc8
v6.8
v6.8-rc1
v6.8-rc2
v6.8-rc3
v6.8-rc4
v6.8-rc5
v6.8-rc6
v6.8-rc7
v6.9
v6.9-rc1
v6.9-rc2
v6.9-rc3
v6.9-rc4
v6.9-rc5
v6.9-rc6
v6.9-rc7

Linux / Kernel

Package

Name
Kernel

Affected ranges

Type
ECOSYSTEM
Events
Introduced
6.7.0
Fixed
6.12.13
Type
ECOSYSTEM
Events
Introduced
6.13.0
Fixed
6.13.2