Merge tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These update PCI and ACPI power management (improved handling of ACPI
  power resources and PCIe link delays, fixes related to corner cases,
  hibernation handling rework), fix and extend the operating performance
  points (OPP) framework, add new cpufreq drivers for Raspberry Pi and
  imx8m chips, update some other cpufreq drivers, clean up assorted
  pieces of PM code and documentation and update tools.

  Specifics:

   - Improve the handling of shared ACPI power resources in the PCI bus
     type layer (Mika Westerberg).

   - Make the PCI layer take link delays required by the PCIe spec into
     account as appropriate and avoid polling devices in D3cold for PME
     (Mika Westerberg).

   - Fix some corner case issues in ACPI device power management and in
     the PCI bus type layer, optimiza and clean up the handling of
     runtime-suspended PCI devices during system-wide transitions to
     sleep states (Rafael Wysocki).

   - Rework hibernation handling in the ACPI core and the PCI bus type
     to resume runtime-suspended devices before hibernation (which
     allows some functional problems to be avoided) and fix some ACPI
     power management issues related to hiberation (Rafael Wysocki).

   - Extend the operating performance points (OPP) framework to support
     a wider range of devices (Rajendra Nayak, Stehpen Boyd).

   - Fix issues related to genpd_virt_devs and issues with platforms
     using the set_opp() callback in the OPP framework (Viresh Kumar,
     Dmitry Osipenko).

   - Add new cpufreq driver for Raspberry Pi (Nicolas Saenz Julienne).

   - Add new cpufreq driver for imx8m and imx7d chips (Leonard Crestez).

   - Fix and clean up the pcc-cpufreq, brcmstb-avs-cpufreq, s5pv210, and
     armada-37xx cpufreq drivers (David Arcari, Florian Fainelli, Paweł
     Chmiel, YueHaibing).

   - Clean up and fix the cpufreq core (Viresh Kumar, Daniel Lezcano).

   - Fix minor issue in the ACPI system sleep support code and export
     one function from it (Lenny Szubowicz, Dexuan Cui).

   - Clean up assorted pieces of PM code and documentation (Kefeng Wang,
     Andy Shevchenko, Bart Van Assche, Greg Kroah-Hartman, Fuqian Huang,
     Geert Uytterhoeven, Mathieu Malaterre, Rafael Wysocki).

   - Update the pm-graph utility to v5.4 (Todd Brandt).

   - Fix and clean up the cpupower utility (Abhishek Goel, Nick Black)"

* tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (57 commits)
  ACPI: PM: Make acpi_sleep_state_supported() non-static
  PM: sleep: Drop dev_pm_skip_next_resume_phases()
  ACPI: PM: Unexport acpi_device_get_power()
  Documentation: ABI: power: Add missing newline at end of file
  ACPI: PM: Drop unused function and function header
  ACPI: PM: Introduce "poweroff" callbacks for ACPI PM domain and LPSS
  ACPI: PM: Simplify and fix PM domain hibernation callbacks
  PCI: PM: Simplify bus-level hibernation callbacks
  PM: ACPI/PCI: Resume all devices during hibernation
  cpufreq: Avoid calling cpufreq_verify_current_freq() from handle_update()
  cpufreq: Consolidate cpufreq_update_current_freq() and __cpufreq_get()
  kernel: power: swap: use kzalloc() instead of kmalloc() followed by memset()
  cpufreq: Don't skip frequency validation for has_target() drivers
  PCI: PM/ACPI: Refresh all stale power state data in pci_pm_complete()
  PCI / ACPI: Add _PR0 dependent devices
  ACPI / PM: Introduce concept of a _PR0 dependent device
  PCI / ACPI: Use cached ACPI device state to get PCI device power state
  ACPI: PM: Allow transitions to D0 to occur in special cases
  ACPI: PM: Avoid evaluating _PS3 on transitions from D3hot to D3cold
  cpufreq: Use has_target() instead of !setpolicy
  ...

1 files changed, 82 insertions, 34 deletions

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8abc843b1615..b1f563916036 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -777,6 +777,12 @@ static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev)
 	return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN;
 }
 
+static inline void platform_pci_refresh_power_state(struct pci_dev *dev)
+{
+	if (pci_platform_pm && pci_platform_pm->refresh_state)
+		pci_platform_pm->refresh_state(dev);
+}
+
 static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev)
 {
 	return pci_platform_pm ?
@@ -938,6 +944,21 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
 }
 
 /**
+ * pci_refresh_power_state - Refresh the given device's power state data
+ * @dev: Target PCI device.
+ *
+ * Ask the platform to refresh the devices power state information and invoke
+ * pci_update_current_state() to update its current PCI power state.
+ */
+void pci_refresh_power_state(struct pci_dev *dev)
+{
+	if (platform_pci_power_manageable(dev))
+		platform_pci_refresh_power_state(dev);
+
+	pci_update_current_state(dev, dev->current_state);
+}
+
+/**
  * pci_power_up - Put the given device into D0 forcibly
  * @dev: PCI device to power up
  */
@@ -1004,15 +1025,10 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
 	if (state == PCI_D0) {
 		pci_platform_power_transition(dev, PCI_D0);
 		/*
-		 * Mandatory power management transition delays, see
-		 * PCI Express Base Specification Revision 2.0 Section
-		 * 6.6.1: Conventional Reset.  Do not delay for
-		 * devices powered on/off by corresponding bridge,
-		 * because have already delayed for the bridge.
+		 * Mandatory power management transition delays are
+		 * handled in the PCIe portdrv resume hooks.
 		 */
 		if (dev->runtime_d3cold) {
-			if (dev->d3cold_delay && !dev->imm_ready)
-				msleep(dev->d3cold_delay);
 			/*
 			 * When powering on a bridge from D3cold, the
 			 * whole hierarchy may be powered on into
@@ -2065,6 +2081,13 @@ static void pci_pme_list_scan(struct work_struct *work)
 			 */
 			if (bridge && bridge->current_state != PCI_D0)
 				continue;
+			/*
+			 * If the device is in D3cold it should not be
+			 * polled either.
+			 */
+			if (pme_dev->dev->current_state == PCI_D3cold)
+				continue;
+
 			pci_pme_wakeup(pme_dev->dev, NULL);
 		} else {
 			list_del(&pme_dev->list);
@@ -2459,45 +2482,56 @@ bool pci_dev_run_wake(struct pci_dev *dev)
 EXPORT_SYMBOL_GPL(pci_dev_run_wake);
 
 /**
- * pci_dev_keep_suspended - Check if the device can stay in the suspended state.
+ * pci_dev_need_resume - Check if it is necessary to resume the device.
  * @pci_dev: Device to check.
  *
- * Return 'true' if the device is runtime-suspended, it doesn't have to be
+ * Return 'true' if the device is not runtime-suspended or it has to be
  * reconfigured due to wakeup settings difference between system and runtime
- * suspend and the current power state of it is suitable for the upcoming
- * (system) transition.
- *
- * If the device is not configured for system wakeup, disable PME for it before
- * returning 'true' to prevent it from waking up the system unnecessarily.
+ * suspend, or the current power state of it is not suitable for the upcoming
+ * (system-wide) transition.
  */
-bool pci_dev_keep_suspended(struct pci_dev *pci_dev)
+bool pci_dev_need_resume(struct pci_dev *pci_dev)
 {
 	struct device *dev = &pci_dev->dev;
-	bool wakeup = device_may_wakeup(dev);
+	pci_power_t target_state;
 
-	if (!pm_runtime_suspended(dev)
-	    || pci_target_state(pci_dev, wakeup) != pci_dev->current_state
-	    || platform_pci_need_resume(pci_dev))
-		return false;
+	if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev))
+		return true;
+
+	target_state = pci_target_state(pci_dev, device_may_wakeup(dev));
 
 	/*
-	 * At this point the device is good to go unless it's been configured
-	 * to generate PME at the runtime suspend time, but it is not supposed
-	 * to wake up the system.  In that case, simply disable PME for it
-	 * (it will have to be re-enabled on exit from system resume).
-	 *
-	 * If the device's power state is D3cold and the platform check above
-	 * hasn't triggered, the device's configuration is suitable and we don't
-	 * need to manipulate it at all.
+	 * If the earlier platform check has not triggered, D3cold is just power
+	 * removal on top of D3hot, so no need to resume the device in that
+	 * case.
 	 */
+	return target_state != pci_dev->current_state &&
+		target_state != PCI_D3cold &&
+		pci_dev->current_state != PCI_D3hot;
+}
+
+/**
+ * pci_dev_adjust_pme - Adjust PME setting for a suspended device.
+ * @pci_dev: Device to check.
+ *
+ * If the device is suspended and it is not configured for system wakeup,
+ * disable PME for it to prevent it from waking up the system unnecessarily.
+ *
+ * Note that if the device's power state is D3cold and the platform check in
+ * pci_dev_need_resume() has not triggered, the device's configuration need not
+ * be changed.
+ */
+void pci_dev_adjust_pme(struct pci_dev *pci_dev)
+{
+	struct device *dev = &pci_dev->dev;
+
 	spin_lock_irq(&dev->power.lock);
 
-	if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold &&
-	    !wakeup)
+	if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) &&
+	    pci_dev->current_state < PCI_D3cold)
 		__pci_pme_active(pci_dev, false);
 
 	spin_unlock_irq(&dev->power.lock);
-	return true;
 }
 
 /**
@@ -4568,14 +4602,16 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 
 	return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
 }
+
 /**
- * pcie_wait_for_link - Wait until link is active or inactive
+ * pcie_wait_for_link_delay - Wait until link is active or inactive
  * @pdev: Bridge device
  * @active: waiting for active or inactive?
+ * @delay: Delay to wait after link has become active (in ms)
  *
  * Use this to wait till link becomes active or inactive.
  */
-bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay)
 {
 	int timeout = 1000;
 	bool ret;
@@ -4612,13 +4648,25 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
 		timeout -= 10;
 	}
 	if (active && ret)
-		msleep(100);
+		msleep(delay);
 	else if (ret != active)
 		pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n",
 			active ? "set" : "cleared");
 	return ret == active;
 }
 
+/**
+ * pcie_wait_for_link - Wait until link is active or inactive
+ * @pdev: Bridge device
+ * @active: waiting for active or inactive?
+ *
+ * Use this to wait till link becomes active or inactive.
+ */
+bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+{
+	return pcie_wait_for_link_delay(pdev, active, 100);
+}
+
 void pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	u16 ctrl;