All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
To: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: "Neil Greatorex" <neil@fatboyfat.co.uk>,
	"Willy Tarreau" <w@1wt.eu>,
	"Matthew Minter" <matthew_minter@xyratex.com>,
	"Gerlando Falauto" <gerlando.falauto@keymile.com>,
	linux-arm-kernel@lists.infradead.org,
	"Jason Cooper" <jason@lakedaemon.net>,
	"Gregory Clément" <gregory.clement@free-electrons.com>,
	"Ezequiel Garcia" <ezequiel.garcia@free-electrons.com>,
	"Andrew Lunn" <andrew@lunn.ch>,
	linux-pci@vger.kernel.org, "Tawfik Bayouk" <tawfik@marvell.com>,
	"Lior Amsalem" <alior@marvell.com>
Subject: Re: Fixing PCIe issues on Armada XP
Date: Tue, 22 Apr 2014 11:56:05 -0600	[thread overview]
Message-ID: <20140422175605.GE23955@obsidianresearch.com> (raw)
In-Reply-To: <20140418145847.709b29ce@skate>

> mvebu-pcie pcie-controller.2: PCIe0.0: performing link reset
> mvebu-pcie pcie-controller.2: PCIe0.0: link went down after 20 tries
> mvebu-pcie pcie-controller.2: PCIe0.0: link came back up after 100 tries

So the '100' here says the timeout expired. My first stab would be to
set the timeout longer.. Maybe your chip takes longer to train the
link.

You also mentioned that setting Conf_TrainingDisable doesn't cause the
link to go down? That would be useful to verify (in a clean
environment without clock gating weirdness..)

> # /usr/sbin/lspci 
> 00:01.0 PCI bridge: Marvell Technology Group Ltd. Device 6710
> 00:02.0 PCI bridge: Marvell Technology Group Ltd. Device 6710

I'm guessing:

echo 1 > /sys/bus/pci/rescan

Will make it appear?

Jason

WARNING: multiple messages have this Message-ID (diff)
From: jgunthorpe@obsidianresearch.com (Jason Gunthorpe)
To: linux-arm-kernel@lists.infradead.org
Subject: Fixing PCIe issues on Armada XP
Date: Tue, 22 Apr 2014 11:56:05 -0600	[thread overview]
Message-ID: <20140422175605.GE23955@obsidianresearch.com> (raw)
In-Reply-To: <20140418145847.709b29ce@skate>

> mvebu-pcie pcie-controller.2: PCIe0.0: performing link reset
> mvebu-pcie pcie-controller.2: PCIe0.0: link went down after 20 tries
> mvebu-pcie pcie-controller.2: PCIe0.0: link came back up after 100 tries

So the '100' here says the timeout expired. My first stab would be to
set the timeout longer.. Maybe your chip takes longer to train the
link.

You also mentioned that setting Conf_TrainingDisable doesn't cause the
link to go down? That would be useful to verify (in a clean
environment without clock gating weirdness..)

> # /usr/sbin/lspci 
> 00:01.0 PCI bridge: Marvell Technology Group Ltd. Device 6710
> 00:02.0 PCI bridge: Marvell Technology Group Ltd. Device 6710

I'm guessing:

echo 1 > /sys/bus/pci/rescan

Will make it appear?

Jason

  reply	other threads:[~2014-04-22 17:56 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-10 16:19 Fixing PCIe issues on Armada XP Thomas Petazzoni
2014-04-10 16:19 ` Thomas Petazzoni
2014-04-10 16:57 ` Jason Gunthorpe
2014-04-10 16:57   ` Jason Gunthorpe
2014-04-10 18:01   ` Thomas Petazzoni
2014-04-10 18:01     ` Thomas Petazzoni
2014-04-10 20:12     ` Jason Gunthorpe
2014-04-10 20:12       ` Jason Gunthorpe
2014-04-10 21:04       ` Thomas Petazzoni
2014-04-10 21:04         ` Thomas Petazzoni
2014-04-10 21:56       ` Neil Greatorex
2014-04-10 21:56         ` Neil Greatorex
2014-04-10 22:06         ` Jason Gunthorpe
2014-04-10 22:06           ` Jason Gunthorpe
2014-04-10 22:15           ` Neil Greatorex
2014-04-10 22:15             ` Neil Greatorex
2014-04-11 10:23         ` Thomas Petazzoni
2014-04-11 10:23           ` Thomas Petazzoni
2014-04-11 16:31           ` Jason Gunthorpe
2014-04-11 16:31             ` Jason Gunthorpe
2014-04-11 17:21             ` Matthew Minter
2014-04-11 17:21               ` Matthew Minter
2014-04-11 17:29               ` Jason Gunthorpe
2014-04-11 17:29                 ` Jason Gunthorpe
2014-04-18 13:02             ` Thomas Petazzoni
2014-04-18 13:02               ` Thomas Petazzoni
2014-04-22 17:34               ` Jason Gunthorpe
2014-04-22 17:34                 ` Jason Gunthorpe
2014-04-18 12:58         ` Thomas Petazzoni
2014-04-18 12:58           ` Thomas Petazzoni
2014-04-22 17:56           ` Jason Gunthorpe [this message]
2014-04-22 17:56             ` Jason Gunthorpe
2014-04-10 17:10 ` Willy Tarreau
2014-04-10 17:10   ` Willy Tarreau
2014-04-10 18:02   ` Thomas Petazzoni
2014-04-10 18:02     ` Thomas Petazzoni
2014-04-10 23:13     ` Willy Tarreau
2014-04-10 23:13       ` Willy Tarreau
2014-04-10 23:40       ` Jason Gunthorpe
2014-04-10 23:40         ` Jason Gunthorpe
2014-04-11  6:23         ` Willy Tarreau
2014-04-11  6:23           ` Willy Tarreau
2014-04-10 18:20 ` Neil Greatorex
2014-04-10 18:20   ` Neil Greatorex
2014-04-10 21:07   ` Thomas Petazzoni
2014-04-10 21:07     ` Thomas Petazzoni
2014-04-11 14:32 ` Thomas Petazzoni
2014-04-11 14:32   ` Thomas Petazzoni
2014-04-11 15:57   ` Neil Greatorex
2014-04-11 15:57     ` Neil Greatorex

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=20140422175605.GE23955@obsidianresearch.com \
    --to=jgunthorpe@obsidianresearch.com \
    --cc=alior@marvell.com \
    --cc=andrew@lunn.ch \
    --cc=ezequiel.garcia@free-electrons.com \
    --cc=gerlando.falauto@keymile.com \
    --cc=gregory.clement@free-electrons.com \
    --cc=jason@lakedaemon.net \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=matthew_minter@xyratex.com \
    --cc=neil@fatboyfat.co.uk \
    --cc=tawfik@marvell.com \
    --cc=thomas.petazzoni@free-electrons.com \
    --cc=w@1wt.eu \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.