PCI / PM: Extend PME polling to all PCI devices
The land of PCI power management is a land of sorrow and ugliness,
especially in the area of signaling events by devices. There are
devices that set their PME Status bits, but don't really bother
to send a PME message or assert PME#. There are hardware vendors
who don't connect PME# lines to the system core logic (they know
who they are). There are PCI Express Root Ports that don't bother
to trigger interrupts when they receive PME messages from the devices
below. There are ACPI BIOSes that forget to provide _PRW methods for
devices capable of signaling wakeup. Finally, there are BIOSes that
do provide _PRW methods for such devices, but then don't bother to
call Notify() for those devices from the corresponding _Lxx/_Exx
GPE-handling methods. In all of these cases the kernel doesn't have
a chance to receive a proper notification that it should wake up a
device, so devices stay in low-power states forever. Worse yet, in
some cases they continuously send PME Messages that are silently
ignored, because the kernel simply doesn't know that it should clear
the device's PME Status bit.
This problem was first observed for "parallel" (non-Express) PCI
devices on add-on cards and Matthew Garrett addressed it by adding
code that polls PME Status bits of such devices, if they are enabled
to signal PME, to the kernel. Recently, however, it has turned out
that PCI Express devices are also affected by this issue and that it
is not limited to add-on devices, so it seems necessary to extend
the PME polling to all PCI devices, including PCI Express and planar
ones. Still, it would be wasteful to poll the PME Status bits of
devices that are known to receive proper PME notifications, so make
the kernel (1) poll the PME Status bits of all PCI and PCIe devices
enabled to signal PME and (2) disable the PME Status polling for
devices for which correct PME notifications are received.
Tested-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index d36f41e..cd3c4f1 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -46,6 +46,9 @@
struct pci_dev *pci_dev = context;
if (event == ACPI_NOTIFY_DEVICE_WAKE && pci_dev) {
+ if (pci_dev->pme_poll)
+ pci_dev->pme_poll = false;
+
pci_wakeup_event(pci_dev);
pci_check_pme_status(pci_dev);
pm_runtime_resume(&pci_dev->dev);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9651f0..7cd417e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1407,13 +1407,16 @@
/**
* pci_pme_wakeup - Wake up a PCI device if its PME Status bit is set.
* @dev: Device to handle.
- * @ign: Ignored.
+ * @pme_poll_reset: Whether or not to reset the device's pme_poll flag.
*
* Check if @dev has generated PME and queue a resume request for it in that
* case.
*/
-static int pci_pme_wakeup(struct pci_dev *dev, void *ign)
+static int pci_pme_wakeup(struct pci_dev *dev, void *pme_poll_reset)
{
+ if (pme_poll_reset && dev->pme_poll)
+ dev->pme_poll = false;
+
if (pci_check_pme_status(dev)) {
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
@@ -1428,7 +1431,7 @@
void pci_pme_wakeup_bus(struct pci_bus *bus)
{
if (bus)
- pci_walk_bus(bus, pci_pme_wakeup, NULL);
+ pci_walk_bus(bus, pci_pme_wakeup, (void *)true);
}
/**
@@ -1446,31 +1449,26 @@
static void pci_pme_list_scan(struct work_struct *work)
{
- struct pci_pme_device *pme_dev;
+ struct pci_pme_device *pme_dev, *n;
mutex_lock(&pci_pme_list_mutex);
if (!list_empty(&pci_pme_list)) {
- list_for_each_entry(pme_dev, &pci_pme_list, list)
- pci_pme_wakeup(pme_dev->dev, NULL);
- schedule_delayed_work(&pci_pme_work, msecs_to_jiffies(PME_TIMEOUT));
+ list_for_each_entry_safe(pme_dev, n, &pci_pme_list, list) {
+ if (pme_dev->dev->pme_poll) {
+ pci_pme_wakeup(pme_dev->dev, NULL);
+ } else {
+ list_del(&pme_dev->list);
+ kfree(pme_dev);
+ }
+ }
+ if (!list_empty(&pci_pme_list))
+ schedule_delayed_work(&pci_pme_work,
+ msecs_to_jiffies(PME_TIMEOUT));
}
mutex_unlock(&pci_pme_list_mutex);
}
/**
- * pci_external_pme - is a device an external PCI PME source?
- * @dev: PCI device to check
- *
- */
-
-static bool pci_external_pme(struct pci_dev *dev)
-{
- if (pci_is_pcie(dev) || dev->bus->number == 0)
- return false;
- return true;
-}
-
-/**
* pci_pme_active - enable or disable PCI device's PME# function
* @dev: PCI device to handle.
* @enable: 'true' to enable PME# generation; 'false' to disable it.
@@ -1503,7 +1501,7 @@
hit, and the power savings from the devices will still be a
win. */
- if (pci_external_pme(dev)) {
+ if (dev->pme_poll) {
struct pci_pme_device *pme_dev;
if (enable) {
pme_dev = kmalloc(sizeof(struct pci_pme_device),
@@ -1821,6 +1819,7 @@
(pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
(pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
+ dev->pme_poll = true;
/*
* Make device's PM flags reflect the wake-up capability, but
* let the user space enable it to wake up the system as needed.
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 0057344..001f1b7 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -84,6 +84,9 @@
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip PCIe devices in case we started from a root port. */
if (!pci_is_pcie(dev) && pci_check_pme_status(dev)) {
+ if (dev->pme_poll)
+ dev->pme_poll = false;
+
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
ret = true;
@@ -142,6 +145,9 @@
/* First, check if the PME is from the root port itself. */
if (port->devfn == devfn && port->bus->number == busnr) {
+ if (port->pme_poll)
+ port->pme_poll = false;
+
if (pci_check_pme_status(port)) {
pm_request_resume(&port->dev);
found = true;
@@ -187,6 +193,9 @@
/* The device is there, but we have to check its PME status. */
found = pci_check_pme_status(dev);
if (found) {
+ if (dev->pme_poll)
+ dev->pme_poll = false;
+
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
}