forked from Minki/linux
b3bad72e49
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> |
||
---|---|---|
.. | ||
hotplug | ||
pcie | ||
.gitignore | ||
access.c | ||
bus.c | ||
dmar.c | ||
hotplug-pci.c | ||
hotplug.c | ||
htirq.c | ||
intel-iommu.c | ||
intr_remapping.c | ||
intr_remapping.h | ||
iov.c | ||
iova.c | ||
irq.c | ||
Kconfig | ||
Makefile | ||
msi.c | ||
msi.h | ||
pci-acpi.c | ||
pci-driver.c | ||
pci-stub.c | ||
pci-sysfs.c | ||
pci.c | ||
pci.h | ||
probe.c | ||
proc.c | ||
quirks.c | ||
remove.c | ||
rom.c | ||
search.c | ||
setup-bus.c | ||
setup-irq.c | ||
setup-res.c | ||
slot.c | ||
syscall.c |