PCI: Disable PTM during suspend to save power

There are systems (for example, Intel based mobile platforms since Coffee
Lake) where the power drawn while suspended can be significantly reduced by
disabling Precision Time Measurement (PTM) on PCIe root ports as this
allows the port to enter a lower-power PM state and the SoC to reach a
lower-power idle state. To save this power, disable the PTM feature on root
ports during pci_prepare_to_sleep() and pci_finish_runtime_suspend().  The
feature will be returned to its previous state during restore and error
recovery.
Suggested-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=209361
Link: https://lore.kernel.org/r/20201207223951.19667-2-david.e.box@linux.intel.comReported-by: NLen Brown <len.brown@intel.com>
Signed-off-by: NDavid E. Box <david.e.box@linux.intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

drivers/pci/pci.c

@@ -2608,12 +2608,24 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
+	/*
+	 * There are systems (for example, Intel mobile chips since Coffee
+	 * Lake) where the power drawn while suspended can be significantly
+	 * reduced by disabling PTM on PCIe root ports as this allows the
+	 * port to enter a lower-power PM state and the SoC to reach a
+	 * lower-power idle state as a whole.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+		pci_disable_ptm(dev);
+
 	pci_enable_wake(dev, target_state, wakeup);
 
 	error = pci_set_power_state(dev, target_state);
 
-	if (error)
+	if (error) {
 		pci_enable_wake(dev, target_state, false);
+		pci_restore_ptm_state(dev);
+	}
 
 	return error;
 }
@@ -2651,12 +2663,23 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
 
 	dev->runtime_d3cold = target_state == PCI_D3cold;
 
+	/*
+	 * There are systems (for example, Intel mobile chips since Coffee
+	 * Lake) where the power drawn while suspended can be significantly
+	 * reduced by disabling PTM on PCIe root ports as this allows the
+	 * port to enter a lower-power PM state and the SoC to reach a
+	 * lower-power idle state as a whole.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+		pci_disable_ptm(dev);
+
 	__pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
 
 	error = pci_set_power_state(dev, target_state);
 
 	if (error) {
 		pci_enable_wake(dev, target_state, false);
+		pci_restore_ptm_state(dev);
 		dev->runtime_d3cold = false;
 	}
 

drivers/pci/pci.h

@@ -519,9 +519,11 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
 #ifdef CONFIG_PCIE_PTM
 void pci_save_ptm_state(struct pci_dev *dev);
 void pci_restore_ptm_state(struct pci_dev *dev);
+void pci_disable_ptm(struct pci_dev *dev);
 #else
 static inline void pci_save_ptm_state(struct pci_dev *dev) { }
 static inline void pci_restore_ptm_state(struct pci_dev *dev) { }
+static inline void pci_disable_ptm(struct pci_dev *dev) { }
 #endif
 
 unsigned long pci_cardbus_resource_alignment(struct resource *);

drivers/pci/pcie/ptm.c

@@ -29,6 +29,23 @@ static void pci_ptm_info(struct pci_dev *dev)
 		 dev->ptm_root ? " (root)" : "", clock_desc);
 }
 
+void pci_disable_ptm(struct pci_dev *dev)
+{
+	int ptm;
+	u16 ctrl;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	ptm = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM);
+	if (!ptm)
+		return;
+
+	pci_read_config_word(dev, ptm + PCI_PTM_CTRL, &ctrl);
+	ctrl &= ~(PCI_PTM_CTRL_ENABLE | PCI_PTM_CTRL_ROOT);
+	pci_write_config_word(dev, ptm + PCI_PTM_CTRL, ctrl);
+}
+
 void pci_save_ptm_state(struct pci_dev *dev)
 {
 	int ptm;