diff options
| -rw-r--r-- | drivers/acpi/power.c | 135 | ||||
| -rw-r--r-- | drivers/pci/pci-acpi.c | 14 | ||||
| -rw-r--r-- | drivers/pci/pci-driver.c | 31 | ||||
| -rw-r--r-- | drivers/pci/pci.c | 116 | ||||
| -rw-r--r-- | drivers/pci/pci.h | 8 | ||||
| -rw-r--r-- | drivers/pci/pcie/portdrv_core.c | 66 | ||||
| -rw-r--r-- | include/acpi/acpi_bus.h | 4 |
7 files changed, 333 insertions, 41 deletions
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index a916417b9e70..fe1e7bc91a5e 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -42,6 +42,11 @@ ACPI_MODULE_NAME("power"); #define ACPI_POWER_RESOURCE_STATE_ON 0x01 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF +struct acpi_power_dependent_device { + struct device *dev; + struct list_head node; +}; + struct acpi_power_resource { struct acpi_device device; struct list_head list_node; @@ -51,6 +56,7 @@ struct acpi_power_resource { unsigned int ref_count; bool wakeup_enabled; struct mutex resource_lock; + struct list_head dependents; }; struct acpi_power_resource_entry { @@ -232,8 +238,121 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return 0; } +static int +acpi_power_resource_add_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + int ret = 0; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + /* Only add it once */ + if (dep->dev == dev) + goto unlock; + } + + dep = kzalloc(sizeof(*dep), GFP_KERNEL); + if (!dep) { + ret = -ENOMEM; + goto unlock; + } + + dep->dev = dev; + list_add_tail(&dep->node, &resource->dependents); + dev_dbg(dev, "added power dependency to [%s]\n", resource->name); + +unlock: + mutex_unlock(&resource->resource_lock); + return ret; +} + +static void +acpi_power_resource_remove_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + if (dep->dev == dev) { + list_del(&dep->node); + kfree(dep); + dev_dbg(dev, "removed power dependency to [%s]\n", + resource->name); + break; + } + } + mutex_unlock(&resource->resource_lock); +} + +/** + * acpi_device_power_add_dependent - Add dependent device of this ACPI device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * If @adev has non-empty _PR0 the @dev is added as dependent device to all + * power resources returned by it. This means that whenever these power + * resources are turned _ON the dependent devices get runtime resumed. This + * is needed for devices such as PCI to allow its driver to re-initialize + * it after it went to D0uninitialized. + * + * If @adev does not have _PR0 this does nothing. + * + * Returns %0 in case of success and negative errno otherwise. + */ +int acpi_device_power_add_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + int ret; + + if (!adev->flags.power_manageable) + return 0; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry(entry, resources, node) { + ret = acpi_power_resource_add_dependent(entry->resource, dev); + if (ret) + goto err; + } + + return 0; + +err: + list_for_each_entry(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); + + return ret; +} + +/** + * acpi_device_power_remove_dependent - Remove dependent device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * Does the opposite of acpi_device_power_add_dependent() and removes the + * dependent device if it is found. Can be called to @adev that does not + * have _PR0 as well. + */ +void acpi_device_power_remove_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + + if (!adev->flags.power_manageable) + return; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry_reverse(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); +} + static int __acpi_power_on(struct acpi_power_resource *resource) { + struct acpi_power_dependent_device *dep; acpi_status status = AE_OK; status = acpi_evaluate_object(resource->device.handle, "_ON", NULL, NULL); @@ -243,6 +362,21 @@ static int __acpi_power_on(struct acpi_power_resource *resource) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n", resource->name)); + /* + * If there are other dependents on this power resource we need to + * resume them now so that their drivers can re-initialize the + * hardware properly after it went back to D0. + */ + if (list_empty(&resource->dependents) || + list_is_singular(&resource->dependents)) + return 0; + + list_for_each_entry(dep, &resource->dependents, node) { + dev_dbg(dep->dev, "runtime resuming because [%s] turned on\n", + resource->name); + pm_request_resume(dep->dev); + } + return 0; } @@ -810,6 +944,7 @@ int acpi_add_power_resource(acpi_handle handle) ACPI_STA_DEFAULT); mutex_init(&resource->resource_lock); INIT_LIST_HEAD(&resource->list_node); + INIT_LIST_HEAD(&resource->dependents); resource->name = device->pnp.bus_id; strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_POWER_CLASS); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 1897847ceb0c..45049f558860 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -685,12 +685,21 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return PCI_UNKNOWN; - if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN) + state = adev->power.state; + if (state == ACPI_STATE_UNKNOWN) return PCI_UNKNOWN; return state_conv[state]; } +static void acpi_pci_refresh_power_state(struct pci_dev *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + + if (adev && acpi_device_power_manageable(adev)) + acpi_device_update_power(adev, NULL); +} + static int acpi_pci_propagate_wakeup(struct pci_bus *bus, bool enable) { while (bus->parent) { @@ -748,6 +757,7 @@ static const struct pci_platform_pm_ops acpi_pci_platform_pm = { .is_manageable = acpi_pci_power_manageable, .set_state = acpi_pci_set_power_state, .get_state = acpi_pci_get_power_state, + .refresh_state = acpi_pci_refresh_power_state, .choose_state = acpi_pci_choose_state, .set_wakeup = acpi_pci_wakeup, .need_resume = acpi_pci_need_resume, @@ -901,6 +911,7 @@ static void pci_acpi_setup(struct device *dev) device_wakeup_enable(dev); acpi_pci_wakeup(pci_dev, false); + acpi_device_power_add_dependent(adev, dev); } static void pci_acpi_cleanup(struct device *dev) @@ -913,6 +924,7 @@ static void pci_acpi_cleanup(struct device *dev) pci_acpi_remove_pm_notifier(adev); if (adev->wakeup.flags.valid) { + acpi_device_power_remove_dependent(adev, dev); if (pci_dev->bridge_d3) device_wakeup_disable(dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index ca3793002e2f..a00820d8aa74 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -678,6 +678,7 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) static int pci_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; + struct pci_dev *pci_dev = to_pci_dev(dev); if (drv && drv->pm && drv->pm->prepare) { int error = drv->pm->prepare(dev); @@ -687,7 +688,15 @@ static int pci_pm_prepare(struct device *dev) if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE)) return 0; } - return pci_dev_keep_suspended(to_pci_dev(dev)); + if (pci_dev_need_resume(pci_dev)) + return 0; + + /* + * The PME setting needs to be adjusted here in case the direct-complete + * optimization is used with respect to this device. + */ + pci_dev_adjust_pme(pci_dev); + return 1; } static void pci_pm_complete(struct device *dev) @@ -701,7 +710,14 @@ static void pci_pm_complete(struct device *dev) if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) { pci_power_t pre_sleep_state = pci_dev->current_state; - pci_update_current_state(pci_dev, pci_dev->current_state); + pci_refresh_power_state(pci_dev); + /* + * On platforms with ACPI this check may also trigger for + * devices sharing power resources if one of those power + * resources has been activated as a result of a change of the + * power state of another device sharing it. However, in that + * case it is also better to resume the device, in general. + */ if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } @@ -757,9 +773,11 @@ static int pci_pm_suspend(struct device *dev) * better to resume the device from runtime suspend here. */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) { + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); } if (pm->suspend) { @@ -1130,10 +1148,13 @@ static int pci_pm_poweroff(struct device *dev) /* The reason to do that is the same as in pci_pm_suspend(). */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); + pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); + } - pci_dev->state_saved = false; if (pm->poweroff) { int error; 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; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9cb99380c61e..5db6f985f16d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -51,6 +51,8 @@ int pci_bus_error_reset(struct pci_dev *dev); * * @get_state: queries the platform firmware for a device's current power state * + * @refresh_state: asks the platform to refresh the device's power state data + * * @choose_state: returns PCI power state of given device preferred by the * platform; to be used during system-wide transitions from a * sleeping state to the working state and vice versa @@ -69,6 +71,7 @@ struct pci_platform_pm_ops { bool (*is_manageable)(struct pci_dev *dev); int (*set_state)(struct pci_dev *dev, pci_power_t state); pci_power_t (*get_state)(struct pci_dev *dev); + void (*refresh_state)(struct pci_dev *dev); pci_power_t (*choose_state)(struct pci_dev *dev); int (*set_wakeup)(struct pci_dev *dev, bool enable); bool (*need_resume)(struct pci_dev *dev); @@ -76,13 +79,15 @@ struct pci_platform_pm_ops { int pci_set_platform_pm(const struct pci_platform_pm_ops *ops); void pci_update_current_state(struct pci_dev *dev, pci_power_t state); +void pci_refresh_power_state(struct pci_dev *dev); void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); void pcie_clear_root_pme_status(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); void pci_pme_restore(struct pci_dev *dev); -bool pci_dev_keep_suspended(struct pci_dev *dev); +bool pci_dev_need_resume(struct pci_dev *dev); +void pci_dev_adjust_pme(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); @@ -493,6 +498,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state, u32 service); +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay); bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 1b330129089f..308c3e0c4a34 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/errno.h> #include <linux/pm.h> #include <linux/pm_runtime.h> @@ -378,6 +379,67 @@ static int pm_iter(struct device *dev, void *data) return 0; } +static int get_downstream_delay(struct pci_bus *bus) +{ + struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (!pdev->imm_ready) + min_delay = 0; + else if (pdev->d3cold_delay < min_delay) + min_delay = pdev->d3cold_delay; + if (pdev->d3cold_delay > max_delay) + max_delay = pdev->d3cold_delay; + } + + return max(min_delay, max_delay); +} + +/* + * wait_for_downstream_link - Wait for downstream link to establish + * @pdev: PCIe port whose downstream link is waited + * + * Handle delays according to PCIe 4.0 section 6.6.1 before configuration + * access to the downstream component is permitted. + * + * This blocks PCI core resume of the hierarchy below this port until the + * link is trained. Should be called before resuming port services to + * prevent pciehp from starting to tear-down the hierarchy too soon. + */ +static void wait_for_downstream_link(struct pci_dev *pdev) +{ + int delay; + + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) + return; + + if (pci_dev_is_disconnected(pdev)) + return; + + if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) || + !pdev->bridge_d3) + return; + + delay = get_downstream_delay(pdev->subordinate); + if (!delay) + return; + + dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay); + + /* + * If downstream port does not support speeds greater than 5 GT/s + * need to wait 100ms. For higher speeds (gen3) we need to wait + * first for the data link layer to become active. + */ + if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT) + msleep(delay); + else + pcie_wait_for_link_delay(pdev, true, delay); +} + /** * pcie_port_device_suspend - suspend port services associated with a PCIe port * @dev: PCI Express port to handle @@ -391,6 +453,8 @@ int pcie_port_device_suspend(struct device *dev) int pcie_port_device_resume_noirq(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, resume_noirq); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } @@ -421,6 +485,8 @@ int pcie_port_device_runtime_suspend(struct device *dev) int pcie_port_device_runtime_resume(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, runtime_resume); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } #endif /* PM */ diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 31b6c87d6240..4752ff0a9d9b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -513,6 +513,10 @@ int acpi_device_fix_up_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); +int acpi_device_power_add_dependent(struct acpi_device *adev, + struct device *dev); +void acpi_device_power_remove_dependent(struct acpi_device *adev, + struct device *dev); #ifdef CONFIG_PM bool acpi_bus_can_wakeup(acpi_handle handle); |