PCI PM: Fix initialization and kexec breakage for some devices

Commit Message

Rafael Wysocki May 17, 2009, 6:17 p.m. UTC

From: Rafael J. Wysocki <[e-mail]>

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 <[e-mail]>
---
 drivers/pci/pci.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Jesse Barnes May 19, 2009, 10:27 p.m. UTC | #1

On Sun, 17 May 2009 20:17:06 +0200
"Rafael J. Wysocki" <[e-mail]> wrote:

> From: Rafael J. Wysocki <[e-mail]>
> 
> 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 <[e-mail]>
> ---
>  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.

Patch

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;