[RFC PATCH] PCIe: Add PCIe runtime D3cold support

[Yan, Zheng]

Hi all,

This patch adds PCIe runtime D3cold support, namely cut power supply for functions
beneath a PCIe port when they all have entered D3. A device in D3cold can only
generate wake event through the WAKE# pin. Because we can not access to a device's
configure space while it's in D3cold, pme_poll is disabled for devices in D3cold.

Any comment will be appreciated.

Signed-off-by: Zheng Yan <zheng.z.yan@xxxxxxxxx>
---
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 0f150f2..e210e8cb 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -224,7 +224,7 @@ static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		[PCI_D1] = ACPI_STATE_D1,
 		[PCI_D2] = ACPI_STATE_D2,
 		[PCI_D3hot] = ACPI_STATE_D3,
-		[PCI_D3cold] = ACPI_STATE_D3
+		[PCI_D3cold] = ACPI_STATE_D3_COLD
 	};
 	int error = -EINVAL;
 
@@ -296,7 +296,8 @@ static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
 
 static int acpi_pci_run_wake(struct pci_dev *dev, bool enable)
 {
-	if (dev->pme_interrupt)
+	/* PME interrupt isn't available in the D3cold case */
+	if (dev->pme_interrupt && !dev->runtime_d3cold)
 		return 0;
 
 	if (!acpi_pm_device_run_wake(&dev->dev, enable))
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8156744..bc16869 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -731,8 +731,8 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 	int error;
 
 	/* bound the state we're entering */
-	if (state > PCI_D3hot)
-		state = PCI_D3hot;
+	if (state > PCI_D3cold)
+		state = PCI_D3cold;
 	else if (state < PCI_D0)
 		state = PCI_D0;
 	else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev))
@@ -750,7 +750,8 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 	if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
 		return 0;
 
-	error = pci_raw_set_power_state(dev, state);
+	error = pci_raw_set_power_state(dev, state > PCI_D3hot ?
+					PCI_D3hot : state);
 
 	if (!__pci_complete_power_transition(dev, state))
 		error = 0;
@@ -1482,6 +1483,17 @@ bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
 	return !!(dev->pme_support & (1 << state));
 }
 
+static void pci_pme_poll_wakeup(struct pci_dev *dev)
+{
+	struct pci_dev *bridge = dev->bus->self;
+
+	/* don't poll the pme bit if parent is in low power state */
+	if (bridge && bridge->current_state != PCI_D0)
+		return;
+
+	pci_pme_wakeup(dev, NULL);
+}
+
 static void pci_pme_list_scan(struct work_struct *work)
 {
 	struct pci_pme_device *pme_dev, *n;
@@ -1490,7 +1502,7 @@ static void pci_pme_list_scan(struct work_struct *work)
 	if (!list_empty(&pci_pme_list)) {
 		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);
+				pci_pme_poll_wakeup(pme_dev->dev);
 			} else {
 				list_del(&pme_dev->list);
 				kfree(pme_dev);
@@ -1608,6 +1620,10 @@ int __pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 	if (enable) {
 		int error;
 
+		if (runtime && state >= PCI_D3cold)
+			dev->runtime_d3cold = true;
+		else
+			dev->runtime_d3cold = false;
 		if (pci_pme_capable(dev, state))
 			pci_pme_active(dev, true);
 		else
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index e0610bd..d66b7e9 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -11,11 +11,13 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/init.h>
 #include <linux/pcieport_if.h>
 #include <linux/aer.h>
 #include <linux/dmi.h>
 #include <linux/pci-aspm.h>
+#include <linux/delay.h>
 
 #include "portdrv.h"
 #include "aer/aerdrv.h"
@@ -99,6 +101,25 @@ static int pcie_port_resume_noirq(struct device *dev)
 	return 0;
 }
 
+static int pcie_port_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	pci_save_state(pdev);
+	return 0;
+}
+
+static int pcie_port_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	pci_restore_state(pdev);
+	if (pdev->runtime_d3cold)
+		msleep(100);
+
+	return 0;
+}
+
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.suspend	= pcie_port_device_suspend,
 	.resume		= pcie_port_device_resume,
@@ -107,6 +128,8 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.poweroff	= pcie_port_device_suspend,
 	.restore	= pcie_port_device_resume,
 	.resume_noirq	= pcie_port_resume_noirq,
+	.runtime_suspend = pcie_port_runtime_suspend,
+	.runtime_resume = pcie_port_runtime_resume,
 };
 
 #define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
@@ -144,12 +167,14 @@ static int __devinit pcie_portdrv_probe(struct pci_dev *dev,
 		return status;
 
 	pci_save_state(dev);
+	pm_runtime_put_noidle(&dev->dev);
 
 	return 0;
 }
 
 static void pcie_portdrv_remove(struct pci_dev *dev)
 {
+	pm_runtime_get_noresume(&dev->dev);
 	pcie_port_device_remove(dev);
 	pci_disable_device(dev);
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e444f5b..b41d9a1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -281,6 +281,7 @@ struct pci_dev {
 	unsigned int	no_d1d2:1;	/* Only allow D0 and D3 */
 	unsigned int	mmio_always_on:1;	/* disallow turning off io/mem
 						   decoding during bar sizing */
+	unsigned int	runtime_d3cold:1;
 	unsigned int	wakeup_prepared:1;
 	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/