Bug 208741
Summary: | Incorrect calculation of latency in ASPM | ||
---|---|---|---|
Product: | Drivers | Reporter: | Ian Kumlien (Ian.kumlien) |
Component: | PCI | Assignee: | drivers_pci (drivers_pci) |
Status: | NEW --- | ||
Severity: | normal | ||
Priority: | P1 | ||
Hardware: | All | ||
OS: | Linux | ||
Kernel Version: | 5.8-rc* | Subsystem: | |
Regression: | No | Bisected commit-id: | |
Attachments: |
lspci output - the ASPM of 03:00.0 has been manually disabled
lspci output as booted with my patch lspci tree output for reference full dumps along the path dmesg with pci=earlydump |
Description
Ian Kumlien
2020-07-29 22:41:39 UTC
Created attachment 290677 [details]
lspci output as booted with my patch
Created attachment 290679 [details]
lspci tree output for reference
The differences between both - this was from a try to just disable the endpoint but the data was validated against the old lspci output. diff -u lscpi-root.output lscpi-endpoint.output --- lscpi-root.output 2020-07-25 21:24:10.661458522 +0200 +++ lscpi-endpoint.output 2020-07-25 21:20:50.316049129 +0200 @@ -3,7 +3,6 @@ 00:00.2 00:01.0 00:01.2 - LnkCtl: ASPM Disabled; RCB 64 bytes, Disabled- CommClk+ 00:02.0 00:03.0 00:03.1 @@ -27,7 +26,6 @@ 00:18.6 00:18.7 01:00.0 - LnkCtl: ASPM Disabled; Disabled- CommClk+ 02:03.0 02:04.0 LnkCtl: ASPM Disabled; Disabled- CommClk+ (difference between both == difference between unpatched and patched. So two bridges are disabled that wasn't disabled before) Created attachment 292563 [details]
full dumps along the path
So that we can look at all latency values in raw data.
Created attachment 292601 [details]
dmesg with pci=earlydump
This is still with a patched kernel but booting with pci=earlydump
(5.8.11)
|