mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Rafael J. Wysocki" <rjw@sisk.pl>
To: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	pm list <linux-pm@lists.linux-foundation.org>,
	Linux PCI <linux-pci@vger.kernel.org>,
	Jiri Slaby <jirislaby@gmail.com>
Subject: [PATCH] PCI PM: Fix initialization and kexec breakage for some devices
Date: Sun, 17 May 2009 20:17:06 +0200	[thread overview]
Message-ID: <200905172017.08207.rjw@sisk.pl> (raw)

From: Rafael J. Wysocki <rjw@sisk.pl>

Recent PCI PM changes introduced a bug that causes some devices to be
mishandled after kexec and during early initialization.  The failure
scenario in the kexec case is the following:

* Assume a PCI device is not power-manageable by the platform and has
  PCI_PM_CTRL_NO_SOFT_RESET set in PMCSR.
* The device is put into D3 before kexec (using the native PCI PM).
* After kexec, pci_setup_device() sets the device's power state to
  PCI_UNKNOWN.
* pci_set_power_state(dev, PCI_D0) is called by the device's driver.
* __pci_start_power_transition(dev, PCI_D0) is called and since the
  device is not power-manageable by the platform, it causes
  pci_update_current_state(dev, PCI_D0) to be called.  As a result
  the device's current_state field is updated to PCI_D3, in
  accordance with the contents of its PCI PM registers.
* pci_raw_set_power_state() is called and it changes the device power
  state to D0.  *However*, it should also call pci_restore_bars() to
  reinitialize the device, but it doesn't, because the device's
  current_state field has been modified earlier.

To prevent this from happening, modify
pci_platform_power_transition() so that it doesn't use
pci_update_current_state() to update the current_state field for
devices that aren't power-manageable by the platform.  Instead, this
field should be updated directly for devices that don't support the
native PCI PM.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 drivers/pci/pci.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Index: linux-2.6/drivers/pci/pci.c
===================================================================
--- linux-2.6.orig/drivers/pci/pci.c
+++ linux-2.6/drivers/pci/pci.c
@@ -557,7 +557,8 @@ static int pci_platform_power_transition
 	} else {
 		error = -ENODEV;
 		/* Fall back to PCI_D0 if native PM is not supported */
-		pci_update_current_state(dev, PCI_D0);
+		if (!dev->pm_cap)
+			dev->current_state = PCI_D0;
 	}
 
 	return error;

             reply	other threads:[~2009-05-17 18:17 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-05-17 18:17 Rafael J. Wysocki [this message]
2009-05-19 22:27 ` Jesse Barnes

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=200905172017.08207.rjw@sisk.pl \
    --to=rjw@sisk.pl \
    --cc=jbarnes@virtuousgeek.org \
    --cc=jirislaby@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-pm@lists.linux-foundation.org \
    /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

all inboxes | Powered by JetHome®