From: Andy Shevchenko <andy.shevchenko@gmail.com>
To: "larsh@apache.org" <larsh@apache.org>,
"Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: "ibm-acpi-devel@lists.sourceforge.net"
<ibm-acpi-devel@lists.sourceforge.net>,
"platform-driver-x86@vger.kernel.org"
<platform-driver-x86@vger.kernel.org>,
ACPI Devel Maling List <linux-acpi@vger.kernel.org>
Subject: Re: Low Latency Tolerance preventing Intel Package from entering deep sleep states
Date: Sat, 16 May 2020 00:41:16 +0300 [thread overview]
Message-ID: <CAHp75VfC0NdyyR1zXbk47G_9y5ResrpV+w3cOntDqP_naocuvQ@mail.gmail.com> (raw)
In-Reply-To: <1505028180.591737.1589564161284@mail.yahoo.com>
+Cc: ACPI ML and Rafael
On Fri, May 15, 2020 at 8:36 PM larsh@apache.org <larsh@apache.org> wrote:
>
> Hi. I hope this is the right forum to raise this...
>
> For a while I have noticed that my CPU (i9-9880H in a Lenovo X1 Extreme Gen2) never enters any sleep mode below pc2.
> (Confirmed with powertop and /sys/kernel/debug/pmc_core/package_cstate_show)
>
> Interestingly the CPU *can* reachers deeper C states *after* a resume from sleep (either S0ix or S3, i.e. freeze or mem).
>
> This article finally pointed me in the right direction: https://01.org/blogs/qwang59/2020/linux-s0ix-troubleshooting
>
> Somehow SOUTHPORT_A is requesting a max latency of 1 us.
> There are no external devices attached.
>
> This is before a resume:
>
> $ cat /sys/kernel/debug/pmc_core/ltr_show
> SOUTHPORT_A LTR: RAW: 0x88018c01 Non-Snoop(ns): 1024 Snoop(ns): 32768 <-------
> SOUTHPORT_B LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SATA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> GIGABIT_ETHERNET LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> XHCI LTR: RAW: 0x13ff Non-Snoop(ns): 0 Snoop(ns): 0
> Reserved LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ME LTR: RAW: 0x8000800 Non-Snoop(ns): 0 Snoop(ns): 0
> EVA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SOUTHPORT_C LTR: RAW: 0x9f409f4 Non-Snoop(ns): 0 Snoop(ns): 0
> HD_AUDIO LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CNV LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> LPSS LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SOUTHPORT_D LTR: RAW: 0x8c548c54 Non-Snoop(ns): 2752512 Snoop(ns): 2752512
> SOUTHPORT_E LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CAMERA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ESPI LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SCC LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ISH LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> UFSX2 LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> EMMC LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> WIGIG LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CURRENT_PLATFORM LTR: RAW: 0x40201 Non-Snoop(ns): 0 Snoop(ns): 0
> AGGREGATED_SYSTEM LTR: RAW: 0x7fbfdfe Non-Snoop(ns): 0 Snoop(ns): 0
>
> Notice the 1000ns max latency requirement for SOUTHPORT_A.
>
> Ignoring SOUTHPORT_A via /sys/kernel/debug/pmc_core/ltr_ignore subsequently allows the CPU to reach deep sleep states.
>
> After a resume it looks like suddenly SOUTHPORT_C is active and with a less tight latency requirement:
>
> $ cat /sys/kernel/debug/pmc_core/ltr_show
> SOUTHPORT_A LTR: RAW: 0x8010c01 Non-Snoop(ns): 0 Snoop(ns): 0 <--------
> SOUTHPORT_B LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SATA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> GIGABIT_ETHERNET LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> XHCI LTR: RAW: 0x13ff Non-Snoop(ns): 0 Snoop(ns): 0
> Reserved LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ME LTR: RAW: 0x8000800 Non-Snoop(ns): 0 Snoop(ns): 0
> EVA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SOUTHPORT_C LTR: RAW: 0x88468846 Non-Snoop(ns): 71680 Snoop(ns): 71680 <---------
> HD_AUDIO LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CNV LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> LPSS LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SOUTHPORT_D LTR: RAW: 0x8c548c54 Non-Snoop(ns): 2752512 Snoop(ns): 2752512
> SOUTHPORT_E LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CAMERA LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ESPI LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> SCC LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> ISH LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> UFSX2 LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> EMMC LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> WIGIG LTR: RAW: 0x0 Non-Snoop(ns): 0 Snoop(ns): 0
> CURRENT_PLATFORM LTR: RAW: 0x40201 Non-Snoop(ns): 0 Snoop(ns): 0
> AGGREGATED_SYSTEM LTR: RAW: 0x904824 Non-Snoop(ns): 0 Snoop(ns): 0
>
> Does anybody know what's going on or how to debug this further?
>
> As stated above, I was able to work around this problem by ignoring SOUTHPORT_A via /sys/kernel/debug/pmc_core/ltr_ignore.
> There has to be a better way, and I'm sure I'm not the only one running into this.
>
> Thanks.
>
> -- Lars
--
With Best Regards,
Andy Shevchenko
next parent reply other threads:[~2020-05-15 21:41 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1505028180.591737.1589564161284.ref@mail.yahoo.com>
[not found] ` <1505028180.591737.1589564161284@mail.yahoo.com>
2020-05-15 21:41 ` Andy Shevchenko [this message]
2020-05-18 10:26 ` Low Latency Tolerance preventing Intel Package from entering deep sleep states Rafael J. Wysocki
2020-05-19 16:03 ` David E. Box
2020-05-22 6:14 ` larsh
2020-05-22 8:58 ` Andy Shevchenko
2020-05-22 16:16 ` larsh
2020-05-25 5:37 ` Adrian Hunter
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAHp75VfC0NdyyR1zXbk47G_9y5ResrpV+w3cOntDqP_naocuvQ@mail.gmail.com \
--to=andy.shevchenko@gmail.com \
--cc=ibm-acpi-devel@lists.sourceforge.net \
--cc=larsh@apache.org \
--cc=linux-acpi@vger.kernel.org \
--cc=platform-driver-x86@vger.kernel.org \
--cc=rjw@rjwysocki.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).