CVE-2024-46848: perf/x86/intel: Limit the period on Haswell
In the Linux kernel, the following vulnerability has been resolved:
perf/x86/intel: Limit the period on Haswell
Running the ltp test cve-2015-3290 concurrently reports the following warnings.
perfevents: irq loop stuck! WARNING: CPU: 31 PID: 32438 at arch/x86/events/intel/core.c:3174 intelpmuhandleirq+0x285/0x370 Call Trace: <NMI> ? warn+0xa4/0x220 ? intelpmuhandleirq+0x285/0x370 ? reportbug+0x123/0x130 ? intelpmuhandleirq+0x285/0x370 ? reportbug+0x123/0x130 ? intelpmuhandleirq+0x285/0x370 ? reportbug+0x3e/0xa0 ? handlebug+0x3c/0x70 ? excinvalidop+0x18/0x50 ? asmexcinvalidop+0x1a/0x20 ? irqworkclaim+0x1e/0x40 ? intelpmuhandleirq+0x285/0x370 perfeventnmihandler+0x3d/0x60 nmihandle+0x104/0x330
Thanks to Thomas Gleixner's analysis, the issue is caused by the low initial period (1) of the frequency estimation algorithm, which triggers the defects of the HW, specifically erratum HSW11 and HSW143. (For the details, please refer https://lore.kernel.org/lkml/87plq9l5d2.ffs@tglx/)
The HSW11 requires a period larger than 100 for the INSTRETIRED.ALL event, but the initial period in the freq mode is 1. The erratum is the same as the BDM11, which has been supported in the kernel. A minimum period of 128 is enforced as well on HSW.
HSW143 is regarding that the fixed counter 1 may overcount 32 with the Hyper-Threading is enabled. However, based on the test, the hardware has more issues than it tells. Besides the fixed counter 1, the message 'interrupt took too long' can be observed on any counter which was armed with a period < 32 and two events expired in the same NMI. A minimum period of 32 is enforced for the rest of the events. The recommended workaround code of the HSW143 is not implemented. Because it only addresses the issue for the fixed counter. It brings extra overhead through extra MSR writing. No related overcounting issue has been reported so far.
Other sources
This CVE was automatically created from a reference found in an email or other text. If you are reading this, then this CVE entry is probably erroneous, since this text should be replaced by the official CVE description automatically.
— Launchpad
Affected Software
Remediation
Event History
Frequently Asked Questions
What is the severity of CVE-2024-46848?
The severity of CVE-2024-46848 is considered medium, as it affects the performance of the Linux kernel without exposing critical vulnerabilities.
How do I fix CVE-2024-46848?
To fix CVE-2024-46848, update the Linux kernel to version 6.1.123-1 or later, or apply relevant patches.
What versions of the Linux kernel are affected by CVE-2024-46848?
CVE-2024-46848 affects Linux kernel versions from 3.11 to 6.1.110, 6.7 to 6.10.10, and 6.2 to 6.6.51, among others.
What symptoms indicate the presence of CVE-2024-46848?
Symptoms of CVE-2024-46848 may include warning messages such as 'perfevents: irq loop stuck!' during certain tests.
Is CVE-2024-46848 specific to any particular distribution of Linux?
CVE-2024-46848 is not specific to any one distribution; it affects the Linux kernel across various distributions using the vulnerable versions.