Bug 208785 - ThunderX2: Thousands errors "PCC check channel failed for ss: XXX. ret=-110" - Gigabyte R281-T94 server based on two 32-cores ThunderX2 ARM processor
Summary: ThunderX2: Thousands errors "PCC check channel failed for ss: XXX. ret=-110" ...
Status: NEW
Alias: None
Product: ACPI
Classification: Unclassified
Component: Config-Processors (show other bugs)
Hardware: ARM Linux
: P1 normal
Assignee: acpi_config-processors
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2020-08-03 12:49 UTC by ww8987
Modified: 2020-10-09 06:32 UTC (History)
2 users (show)

See Also:
Kernel Version: 5.4.0-42-generic
Subsystem:
Regression: No
Bisected commit-id:

Attachments
Add an attachment (proposed patch, testcase, etc.)

Description ww8987 2020-08-03 12:49:58 UTC 
I manage Gigabyte R281-T94 server based on two 32-cores ThunderX2 ARM processor. I found that my ubuntu 20.04 generates thousands such errors:
```
Aug  3 00:33:45 XXXXX kernel: [196168.486836] ACPI CPPC: PCC check channel failed for ss: 11. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.518217] ACPI CPPC: PCC check channel failed for ss: 46. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.518255] ACPI CPPC: PCC check channel failed for ss: 36. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.554905] ACPI CPPC: PCC check channel failed for ss: 53. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.778789] ACPI CPPC: PCC check channel failed for ss: 6. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.824350] ACPI CPPC: PCC check channel failed for ss: 41. ret=-110
Aug  3 00:33:45 XXXXX kernel: [196168.877658] ACPI CPPC: PCC check channel failed for ss: 39. ret=-110
```

As I understand that return code `-110` means timeout. I also found that the message appears in following part of linux kernel code: https://github.com/torvalds/linux/blame/194098915ac74daddca9d6ed46fd11be57f45e16/drivers/acpi/cppc_acpi.c#L206-L222

```
:~$ cat /proc/version
Linux version 5.4.0-42-generic (buildd@bos02-arm64-077) (gcc version 9.3.0 (Ubuntu 9.3.0-10ubuntu2)) #46-Ubuntu SMP Fri Jul 10 00:24:02 UTC 2020
```

BIOS version: F31 (the most fresh today)
BMC version: 12.44.04 (the most fresh today)
MB_CPLD version: M11 (the most fresh today)

My BIOS have three modes for ACPI:
- Autonomous - CPPC On
- OSPM Turbo
- OSPM Non-Turbo

`OSPM Turbo` is default for me now. I tried all three modes without any effect on errors.

P.S. I'm ready to communicate and can attach additional information which you need.
Note You need to log in before you can comment on or make changes to this bug.