On Sun, 17 May 2009 20:17:06 +0200
"Rafael J. Wysocki" <rjw@xxxxxxx> wrote:
> From: Rafael J. Wysocki <rjw@xxxxxxx>
>
> 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@xxxxxxx>
> ---
> 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;
>
Applied to my for-linus branch, thanks Rafael.
--
Jesse Barnes, Intel Open Source Technology Center
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
