From: Bjorn Helgaas <helgaas@kernel.org>
To: Herve Codina <herve.codina@bootlin.com>
Cc: "Manivannan Sadhasivam" <mani@kernel.org>,
"Lukas Wunner" <lukas@wunner.de>,
"Christian Zigotzky" <chzigotzky@xenosoft.de>,
"Manivannan Sadhasivam" <manivannan.sadhasivam@oss.qualcomm.com>,
"Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>,
"linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
"mad skateman" <madskateman@gmail.com>,
"R.T.Dickinson" <rtd2@xtra.co.nz>,
"Christian Zigotzky" <info@xenosoft.de>,
linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
hypexed@yahoo.com.au, "Darren Stevens" <darren@stevens-zone.net>,
"debian-powerpc@lists.debian.org"
<debian-powerpc@lists.debian.org>,
"Thomas Petazzoni" <thomas.petazzoni@bootlin.com>
Subject: Re: [PPC] Boot problems after the pci-v6.18-changes
Date: Wed, 15 Oct 2025 18:40:59 -0500 [thread overview]
Message-ID: <20251015234059.GA961901@bhelgaas> (raw)
In-Reply-To: <20251015101304.3ec03e6b@bootlin.com>
On Wed, Oct 15, 2025 at 10:13:04AM +0200, Herve Codina wrote:
> ...
> I also observed issues with the commit f3ac2ff14834 ("PCI/ASPM: Enable all
> ClockPM and ASPM states for devicetree platforms")
>
> My system is an ARM board (Marvel Armada 3720 DDB)
> https://elixir.bootlin.com/linux/v6.17.1/source/arch/arm64/boot/dts/marvell/armada-3720-db.dts
>
> I use an LAN966x PCI board
> https://elixir.bootlin.com/linux/v6.17.1/source/drivers/misc/lan966x_pci.c
>
> Usually, when I did a ping using the PCI board, I have more or less the
> following timings:
> # ping 192.168.32.100
> PING 192.168.32.100 (192.168.32.100): 56 data bytes
> 64 bytes from 192.168.32.100: seq=0 ttl=64 time=3.328 ms
> 64 bytes from 192.168.32.100: seq=1 ttl=64 time=2.636 ms
> 64 bytes from 192.168.32.100: seq=2 ttl=64 time=2.928 ms
> 64 bytes from 192.168.32.100: seq=3 ttl=64 time=2.649 ms
>
> But with a vanilla v6.18-rc1 kernel, those timings become awful:
> # ping 192.168.32.100
> PING 192.168.32.100 (192.168.32.100): 56 data bytes
> 64 bytes from 192.168.32.100: seq=0 ttl=64 time=656.634 ms
> 64 bytes from 192.168.32.100: seq=1 ttl=64 time=551.812 ms
> 64 bytes from 192.168.32.100: seq=2 ttl=64 time=702.966 ms
> 64 bytes from 192.168.32.100: seq=3 ttl=64 time=725.904 ms
>
> Reverting commit f3ac2ff14834 ("PCI/ASPM: Enable all ClockPM and
> ASPM states for devicetree platforms") fixes my timing issues.
We expect *some* performance impact from enabling ASPM, but this seems
excessive. You should be able to control the ASPM settings for an
individual device via sysfs:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/ABI/testing/sysfs-bus-pci?id=v6.17-rc1#n431
My guess is that L1.2 is enabled and the threshold values in the L1 PM
Substates control registers are bogus. I don't know how to fix those,
especially on a devicetree system. But it might be possible to fiddle
with them using setpci (while ASPM is disabled). Not for the faint of
heart.
Bjorn
next prev parent reply other threads:[~2025-10-15 23:41 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <3eedbe78-1fbd-4763-a7f3-ac5665e76a4a@xenosoft.de>
[not found] ` <15731ad7-83ff-c7ef-e4a1-8b11814572c2@xenosoft.de>
[not found] ` <17e37b22-5839-0e3a-0dbf-9c676adb0dec@xenosoft.de>
[not found] ` <3b210c92-4be6-ce49-7512-bb194475eeab@xenosoft.de>
2021-11-09 15:10 ` [PASEMI] Nemo board doesn't recognize any ATA disks with the pci-v5.16 updates Christian Zigotzky
2021-11-09 16:58 ` Bjorn Helgaas
2021-11-09 22:40 ` Krzysztof Wilczyński
2021-11-09 23:05 ` Arnd Bergmann
2021-11-09 23:18 ` Krzysztof Wilczyński
2021-11-10 16:42 ` Robert Święcki
2021-11-10 3:52 ` Damien Le Moal
2021-11-10 18:07 ` Christian Zigotzky
2021-11-10 18:41 ` Bjorn Helgaas
2021-11-10 19:09 ` Marc Zyngier
2021-11-11 5:24 ` Christian Zigotzky
2021-11-11 7:13 ` Marc Zyngier
2021-11-11 7:47 ` Christian Zigotzky
2021-11-11 10:20 ` Marc Zyngier
2021-11-11 10:44 ` Christian Zigotzky
2021-11-11 11:24 ` Marc Zyngier
2021-11-11 11:54 ` Christian Zigotzky
2021-11-11 22:21 ` Olof Johansson
2021-11-12 11:49 ` Segher Boessenkool
2021-11-11 17:39 ` Marc Zyngier
2021-11-12 9:40 ` Christian Zigotzky
2021-11-12 10:11 ` Christian Zigotzky
2021-11-12 11:00 ` Christian Zigotzky
2021-11-12 13:41 ` Marc Zyngier
2021-11-12 14:15 ` Christian Zigotzky
2021-11-12 14:46 ` Marc Zyngier
2021-11-12 15:01 ` Christian Zigotzky
2021-11-12 15:05 ` Christian Zigotzky
2025-10-08 16:35 ` [PPC] Boot problems after the pci-v6.18-changes Christian Zigotzky
2025-10-08 16:40 ` John Paul Adrian Glaubitz
2025-10-08 16:47 ` Christian Zigotzky
2025-10-08 19:51 ` Bjorn Helgaas
2025-10-09 4:54 ` Christian Zigotzky
2025-10-09 5:37 ` Lukas Wunner
2025-10-11 5:12 ` Christian Zigotzky
2025-10-11 5:25 ` Lukas Wunner
2025-10-11 15:11 ` Manivannan Sadhasivam
2025-10-11 19:34 ` Christian Zigotzky
2025-10-12 7:47 ` Christian Zigotzky
2025-10-12 8:26 ` Christian Zigotzky
2025-10-13 4:46 ` Christian Zigotzky
2025-10-13 5:02 ` Christian Zigotzky
2025-10-13 5:23 ` Christian Zigotzky
2025-10-13 14:50 ` Christian Zigotzky
2025-10-13 15:02 ` Christian Zigotzky
2025-10-13 15:38 ` Christian Zigotzky
2025-10-13 15:58 ` Manivannan Sadhasivam
[not found] ` <a2ee06b1-28a5-4cb1-9940-b225f9e6d6ee@xenosoft.de>
2025-10-14 4:55 ` Christian Zigotzky
2025-10-15 6:41 ` Manivannan Sadhasivam
2025-10-13 16:01 ` Manivannan Sadhasivam
2025-10-15 8:13 ` Herve Codina
2025-10-15 11:30 ` Christian Zigotzky
2025-10-15 11:58 ` Herve Codina
2025-10-15 12:27 ` Christian Zigotzky
2025-10-15 12:59 ` Herve Codina
[not found] ` <76026544-3472-4953-910A-376DD42BC6D0@xenosoft.de>
2025-10-15 13:17 ` Christian Zigotzky
2025-10-15 13:34 ` Herve Codina
2025-10-15 16:54 ` Christian Zigotzky
2025-10-15 17:15 ` Christian Zigotzky
2025-10-16 3:28 ` Christian Zigotzky
2025-10-16 7:36 ` Christian Zigotzky
2025-10-16 7:53 ` Manivannan Sadhasivam
2025-10-16 10:44 ` Christian Zigotzky
2025-10-17 5:35 ` Christian Zigotzky
2025-10-15 16:23 ` Manivannan Sadhasivam
2025-10-15 13:07 ` Christian Zigotzky
2025-10-15 12:50 ` Manivannan Sadhasivam
2025-10-23 7:38 ` Herve Codina
2025-10-23 8:49 ` Manivannan Sadhasivam
2025-10-23 9:19 ` Herve Codina
2025-10-23 16:59 ` Bjorn Helgaas
2025-10-15 23:40 ` Bjorn Helgaas [this message]
2025-10-13 21:06 ` Bjorn Helgaas
2025-10-14 18:51 ` Bjorn Helgaas
2025-10-30 22:11 ` Bjorn Helgaas
2025-11-01 5:39 ` Christian Zigotzky
2025-11-01 7:59 ` Christian Zigotzky
2025-11-01 17:06 ` Manivannan Sadhasivam
2025-11-03 18:28 ` Christian Zigotzky
2025-11-05 22:09 ` Bjorn Helgaas
2025-11-06 8:48 ` Hongxing Zhu
2025-11-06 18:25 ` Bjorn Helgaas
2025-11-07 2:26 ` Hongxing Zhu
2025-11-07 5:06 ` Christian Zigotzky
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=20251015234059.GA961901@bhelgaas \
--to=helgaas@kernel.org \
--cc=chzigotzky@xenosoft.de \
--cc=darren@stevens-zone.net \
--cc=debian-powerpc@lists.debian.org \
--cc=herve.codina@bootlin.com \
--cc=hypexed@yahoo.com.au \
--cc=ilpo.jarvinen@linux.intel.com \
--cc=info@xenosoft.de \
--cc=linux-pci@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=lukas@wunner.de \
--cc=madskateman@gmail.com \
--cc=mani@kernel.org \
--cc=manivannan.sadhasivam@oss.qualcomm.com \
--cc=rtd2@xtra.co.nz \
--cc=thomas.petazzoni@bootlin.com \
/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).