Bug 1549939

Summary: AMD-Vi: Unable to write to IOMMU perf counter.
Product: [Fedora] Fedora Reporter: Talha Khan <talha.khan1>
Component: kernelAssignee: Kernel Maintainer List <kernel-maint>
Status: CLOSED WORKSFORME QA Contact: Fedora Extras Quality Assurance <extras-qa>
Severity: medium Docs Contact:
Priority: unspecified    
Version: 27CC: airlied, ajax, bskeggs, ewk, hdegoede, ichavero, itamar, jarodwilson, jglisse, john.j5live, jonathan, jorgeml, josef, jvdelisle, kernel-maint, labbott, linville, mchehab, mjg59, steved
Target Milestone: ---   
Target Release: ---   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: If docs needed, set a value
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2018-04-02 15:05:35 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description Talha Khan 2018-02-28 06:19:21 UTC 
Description of problem:
During boot up, the following message comes up and also in journalctl/dmesg

Version-Release number of selected component (if applicable):

4.15.4-300.fc27.x86_64


How reproducible:

Restart computer

Steps to Reproduce:
1.
2.
3.

Actual results:

message appears:

journalctl:
Feb 22 11:40:30 infinity.localdomain kernel: AMD-Vi: Unable to write to IOMMU perf counter.

dmesg:
[    0.449070] AMD-Vi: Unable to write to IOMMU perf counter.

Expected results:

not sure, but maybe that it is able to write to IOMMU perf counter?

Additional info:
HP Envy x360 laptop
AMD Ryzen 2500U APU
Virtualization enabled in BIOS
Comment 1 Talha Khan 2018-03-15 04:20:57 UTC 
Still happening in kernel 4.15.8-300.fc27.x86_64
Comment 2 Jerry 2018-03-30 21:45:21 UTC 
Likewise: Linux version 4.15.12-301.fc27.x86_64
Comment 3 Jerry 2018-03-31 01:42:31 UTC 
Later in the message stream AMD-VI also reports finding the IOMMU and proceeds to configure for it so I dont think this is a bug at all.
Comment 4 Laura Abbott 2018-04-02 15:05:35 UTC 
Yeah, if everything is working okay, I'm inclined to agree this is just a driver being overly aggressive about printing a message. I think it makes sense to close this bug. Feel free to reopen if something stops working.