Bug 209323 - pcieport devices take longer than 1 second in resume
Summary: pcieport devices take longer than 1 second in resume
Status: NEW
Alias: None
Product: Drivers
Classification: Unclassified
Component: PCI (show other bugs)
Hardware: All Linux
: P1 normal
Assignee: Mika Westerberg
Depends on:
Blocks: 178231
  Show dependency tree
Reported: 2020-09-18 21:20 UTC by Todd Brandt
Modified: 2021-01-27 17:26 UTC (History)
3 users (show)

See Also:
Kernel Version: 5.8.0-rc4
Regression: No
Bisected commit-id:

otcpl-dell-9380-cfl_freeze.html (697.84 KB, text/html)
2020-09-18 21:20 UTC, Todd Brandt
issue.def (467 bytes, text/plain)
2020-09-18 21:21 UTC, Todd Brandt
otcpl-dell-7390-cmlu_freeze.html (642.37 KB, text/html)
2020-09-23 14:24 UTC, Todd Brandt
otcpl-dell-p3520_freeze.html (745.20 KB, text/html)
2020-09-23 14:25 UTC, Todd Brandt
otcpl-dell-p5510-xeon-1_freeze.html (719.90 KB, text/html)
2020-09-23 14:26 UTC, Todd Brandt
otcpl-hp-elite-x2-kbl_mem.html (892.69 KB, text/html)
2020-09-23 14:27 UTC, Todd Brandt

Description Todd Brandt 2020-09-18 21:20:38 UTC
Created attachment 292541 [details]

pcieport devices are taking longer than 1 second across several machines. This bug is there to monitor which machines and kernel release this happens on.
Comment 1 Todd Brandt 2020-09-18 21:21:10 UTC
Created attachment 292543 [details]
Comment 2 Todd Brandt 2020-09-21 21:24:28 UTC
This bug seems to have started in 5.8.0-rc4. It's affecting multiple machines, such as:

Comment 3 Todd Brandt 2020-09-23 14:24:59 UTC
Created attachment 292577 [details]
Comment 4 Todd Brandt 2020-09-23 14:25:16 UTC
Created attachment 292579 [details]
Comment 5 Todd Brandt 2020-09-23 14:26:34 UTC
Created attachment 292581 [details]
Comment 6 Todd Brandt 2020-09-23 14:27:01 UTC
Created attachment 292583 [details]
Comment 7 Todd Brandt 2020-09-23 14:36:09 UTC
Mika, should I run a bisect on this between 5.8-rc3 and 5.8-rc4?
Comment 8 Mika Westerberg 2020-09-23 14:50:24 UTC
Yes, I think that would help. I did not see any changes in drivers/pci between v5.8-rc3 and v5.8-rc4 which is surprising.
Comment 9 Todd Brandt 2020-10-08 19:47:49 UTC
Actually I didn't go far back enough, it apparently disappeared from 5.8-rc1-3 but reappeared in 5.7.0. I'll dig deeper to see where it really began.
Comment 10 Len Brown 2021-01-27 17:11:44 UTC
I have an Icelake Dell 9300, which comes pre-installed with Ubuntu.

It reproduces this issue 100% of the time, no matter what kernel is used.
Dell shipped 5.0, and I've tested every kernel 5.4 - 5.10.

I'll be happy to run experiments on this system if it may result
in making this problem go away -- even if under limited
conditions or configurations.
Comment 11 Mika Westerberg 2021-01-27 17:24:00 UTC
IIRC you guys have tools that can show where the resume time is spent? Maybe you can run that one and we can then go it over? The BIOS ASL methods for the TBT PCIe root ports have some delays but for those we cannot affect from the kernel side.

Also is this with device connected to any of the TBT ports or not?
Comment 12 Bjorn Helgaas 2021-01-27 17:26:22 UTC
Looking at https://bugzilla.kernel.org/attachment.cgi?id=292541 (otcpl-dell-9380-cfl_freeze.html).  I don't really know how to interpret this graph.  Is it telling me that \_SB.PCI0.RP09._PS0 took 1583ms to execute?  Is that the bulk of the delay?  If so, I'm not sure what the kernel can do about that.

Note You need to log in before you can comment on or make changes to this bug.