linux-kernel - [PATCH] PCI PM: Fix initialization and kexec breakage for some devices

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <200905172017.08207.rjw@sisk.pl>
Date:	Sun, 17 May 2009 20:17:06 +0200
From:	"Rafael J. Wysocki" <rjw@...k.pl>
To:	Jesse Barnes <jbarnes@...tuousgeek.org>
Cc:	LKML <linux-kernel@...r.kernel.org>,
	pm list <linux-pm@...ts.linux-foundation.org>,
	Linux PCI <linux-pci@...r.kernel.org>,
	Jiri Slaby <jirislaby@...il.com>
Subject: [PATCH] PCI PM: Fix initialization and kexec breakage for some devices

From: Rafael J. Wysocki <rjw@...k.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@...k.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;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/