Kernel 5.9.1 cleans up some very old boot errors.

This journalctl ouput has been around for over a year in both openSUSE and Fedora for many, many kernel versions.


> cat kernel.5.8*
-- Logs begin at Thu 2020-10-08 09:45:29 PDT, end at Wed 2020-10-28 09:34:25 PDT. --
Oct 28 09:33:06 Mobile-PC kernel: pci 0000:00:00.2: AMD-Vi: Unable to read/write to IOMMU perf counter.
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver ID)
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:   device [1022:15d3] error status/mask=000000c0/00006000
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:     6] BadTLP                
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:     7] BadDLLP               
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Receiver ID)
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:   device [1022:15d3] error status/mask=00000040/00006000
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:     6] BadTLP                
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER: PCIe Bus Error: severity=Corrected, type=Data Link Layer, (Transmitter ID)
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:   device [1022:15d3] error status/mask=00001040/00006000
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:     6] BadTLP                
Oct 28 09:33:13 Mobile-PC kernel: pcieport 0000:00:01.7: AER:    [12] Timeout               
Oct 28 09:33:19 Mobile-PC lightdm[1695]: gkr-pam: unable to locate daemon control file
Oct 28 09:33:20 Mobile-PC bluetoothd[1243]: Failed to set mode: Blocked through rfkill (0x12)

A lot of those errors went away with kernel 5.9.1.


 > cat kernel.5.9*
-- Logs begin at Thu 2020-10-08 09:45:29 PDT, end at Wed 2020-10-28 09:36:01 PDT. --
Oct 28 09:35:17 Mobile-PC kernel: pci 0000:00:00.2: AMD-Vi: Unable to read/write to IOMMU perf counter.
Oct 28 09:35:29 Mobile-PC lightdm[1692]: gkr-pam: unable to locate daemon control file
Oct 28 09:35:30 Mobile-PC bluetoothd[1235]: Failed to set mode: Blocked through rfkill (0x12)

Thankyou!

Gene

@Gene_S:

Here on openSUSE Leap 15.2:

Kernel Version: 5.3.18-lp152.47-default
Processors: 8 × AMD Ryzen 5 3400G with Radeon Vega Graphics
Memory: 13,6 GiB


Okt 28 11:15:44 xxx kernel: pci 0000:00:00.2: AMD-Vi: Unable to read/write to IOMMU perf counter.
Okt 28 11:15:44 xxx kernel: pci 0000:00:00.2: can't derive routing for PCI INT A
Okt 28 11:15:44 xxx kernel: pci 0000:00:00.2: PCI INT A: not connected
Okt 28 11:15:44 xxx kernel: pci 0000:00:01.0: Adding to iommu group 0
Okt 28 11:15:44 xxx kernel: pci 0000:00:01.2: Adding to iommu group 1
Okt 28 11:15:44 xxx kernel: pci 0000:00:08.0: Adding to iommu group 2
Okt 28 11:15:44 xxx kernel: pci 0000:00:08.1: Adding to iommu group 3
Okt 28 11:15:44 xxx kernel: pci 0000:00:08.2: Adding to iommu group 4
Okt 28 11:15:44 xxx kernel: pci 0000:00:14.0: Adding to iommu group 5
Okt 28 11:15:44 xxx kernel: pci 0000:00:14.3: Adding to iommu group 5
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.0: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.1: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.2: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.3: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.4: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.5: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.6: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:00:18.7: Adding to iommu group 6
Okt 28 11:15:44 xxx kernel: pci 0000:01:00.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:01:00.1: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:01:00.2: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:02:00.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:02:01.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:02:04.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:02:06.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:02:07.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:03:00.0: Adding to iommu group 7
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.0: Adding to iommu group 8
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.1: Adding to iommu group 9
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.2: Adding to iommu group 9
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.3: Adding to iommu group 9
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.4: Adding to iommu group 9
Okt 28 11:15:44 xxx kernel: pci 0000:08:00.6: Adding to iommu group 9
Okt 28 11:15:44 xxx kernel: pci 0000:09:00.0: Adding to iommu group 10
Okt 28 11:15:44 xxx kernel: pci 0000:00:00.2: AMD-Vi: Found IOMMU cap 0x40
Okt 28 11:15:44 xxx kernel: pci 0000:00:00.2: AMD-Vi: Extended features (0x4f77ef22294ada):
Okt 28 11:15:44 xxx kernel:  PPR NX GT IA GA PC GA_vAPIC
Okt 28 11:15:44 xxx kernel: AMD-Vi: Interrupt remapping enabled
Okt 28 11:15:44 xxx kernel: AMD-Vi: Virtual APIC enabled
Okt 28 11:15:44 xxx kernel: AMD-Vi: Lazy IO/TLB flushing enabled
Okt 28 11:15:44 xxx kernel: PCI-DMA: Using software bounce buffering for IO (SWIOTLB)
Okt 28 11:15:44 xxx kernel: software IO TLB: mapped [mem 0x4d271000-0x51271000] (64MB)
Okt 28 11:15:44 xxx kernel: amd_uncore: AMD NB counters detected
Okt 28 11:15:44 xxx kernel: amd_uncore: AMD LLC counters detected
Okt 28 11:15:44 xxx kernel: AMD-Vi: AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de>

AFAICS, initially AMD-Vi can neither read nor write the IOMMU performance counters and then, on “pci 0000:00:00.2” it finds an IOMMU capability (hexadecimal 40) and, some extended features …

  • And then, it seems to be happy … – Interrupt remapping is enabled – Virtual APIC is enabled – Lazy IO/TLB flushing is enabled …
  • TLB: “Translation Lookaside Buffer” …
  • “AMD-Vi”: AMD’s implementation of IOMMU …
  • Using software bounce buffering for IO (SWIOTLB)
    ” – here in the Kernel documentation: <https://www.kernel.org/doc/Documentation/x86/x86_64/boot-options.txt&gt; – search for “iommu” …

[HR][/HR]I haven’t yet found anything related to the counters and, how one can check if they’re ticking, or not …