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;
next 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®