PCI PM: Fix initialization and kexec breakage for some devices

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>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

1 files changed, 2 insertions, 1 deletions

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 34bf0fd..1a91bf9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -557,7 +557,8 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
 	} 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;