Skip to contentSkip to conversation

PCI PM: Fix initialization and kexec breakage for some devices

PATCH Applied Rafael J. Wysocki 2 participants 3 messages May 17, 2009 – May 19, 2009 PCI

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 PCI PM: Fix initialization and kexec breakage for some devices

From: Rafael J. Wysocki <[email protected]>

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.

---
 drivers/pci/pci.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/pci/pci.c +2 -1
Index: 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
#1 lore raw
Quoted 48 lines · On Sun, 17 May 2009 20:17:06 +0200 "Rafael J. Wysocki" <[email protected]> wrote:

From: Rafael J. Wysocki <[email protected]>

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.

---
 drivers/pci/pci.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Index: linux-2.6/drivers/pci/pci.c
===================================================================

drivers/pci/pci.c +2 -1
@@ -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;
 	}
 
Quoted 2 lines

return error;

Applied to my for-linus branch, thanks Rafael.

Signature · 1 line
Jesse Barnes, Intel Open Source Technology Center
Applied
#2 lore raw
In reply to Rafael J. Wysocki
Quoted 48 lines · On Sun, 17 May 2009 20:17:06 +0200 "Rafael J. Wysocki" <[email protected]> wrote:

From: Rafael J. Wysocki <[email protected]>

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.

---
 drivers/pci/pci.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Index: linux-2.6/drivers/pci/pci.c
===================================================================

drivers/pci/pci.c +2 -1
@@ -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;
 	}
 
Quoted 2 lines

return error;

Applied to my for-linus branch, thanks Rafael.

Signature · 1 line
Jesse Barnes, Intel Open Source Technology Center