diff options
Diffstat (limited to 'drivers/base/power')
| -rw-r--r-- | drivers/base/power/Makefile | 5 | ||||
| -rw-r--r-- | drivers/base/power/clock_ops.c | 311 | ||||
| -rw-r--r-- | drivers/base/power/common.c | 267 | ||||
| -rw-r--r-- | drivers/base/power/domain.c | 2990 | ||||
| -rw-r--r-- | drivers/base/power/domain_governor.c | 259 | ||||
| -rw-r--r-- | drivers/base/power/generic_ops.c | 113 | ||||
| -rw-r--r-- | drivers/base/power/main.c | 1427 | ||||
| -rw-r--r-- | drivers/base/power/power.h | 24 | ||||
| -rw-r--r-- | drivers/base/power/qos-test.c | 117 | ||||
| -rw-r--r-- | drivers/base/power/qos.c | 147 | ||||
| -rw-r--r-- | drivers/base/power/runtime-test.c | 249 | ||||
| -rw-r--r-- | drivers/base/power/runtime.c | 976 | ||||
| -rw-r--r-- | drivers/base/power/sysfs.c | 270 | ||||
| -rw-r--r-- | drivers/base/power/trace.c | 26 | ||||
| -rw-r--r-- | drivers/base/power/wakeirq.c | 178 | ||||
| -rw-r--r-- | drivers/base/power/wakeup.c | 327 | ||||
| -rw-r--r-- | drivers/base/power/wakeup_stats.c | 219 |
17 files changed, 3232 insertions, 4673 deletions
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile index e1bb691cf8f1..2989e42d0161 100644 --- a/drivers/base/power/Makefile +++ b/drivers/base/power/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_PM) += sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o -obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o +obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o wakeup_stats.o obj-$(CONFIG_PM_TRACE_RTC) += trace.o -obj-$(CONFIG_PM_GENERIC_DOMAINS) += domain.o domain_governor.o obj-$(CONFIG_HAVE_CLK) += clock_ops.o +obj-$(CONFIG_PM_QOS_KUNIT_TEST) += qos-test.o +obj-$(CONFIG_PM_RUNTIME_KUNIT_TEST) += runtime-test.o ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 5a42ae4078c2..b69bcb37c830 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -1,9 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks * * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp. - * - * This file is released under the GPLv2. */ #include <linux/kernel.h> @@ -13,6 +12,7 @@ #include <linux/pm_clock.h> #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/of_clk.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/pm_domain.h> @@ -23,6 +23,7 @@ enum pce_status { PCE_STATUS_NONE = 0, PCE_STATUS_ACQUIRED, + PCE_STATUS_PREPARED, PCE_STATUS_ENABLED, PCE_STATUS_ERROR, }; @@ -32,10 +33,114 @@ struct pm_clock_entry { char *con_id; struct clk *clk; enum pce_status status; + bool enabled_when_prepared; }; /** - * pm_clk_enable - Enable a clock, reporting any errors + * pm_clk_list_lock - ensure exclusive access for modifying the PM clock + * entry list. + * @psd: pm_subsys_data instance corresponding to the PM clock entry list + * and clk_op_might_sleep count to be modified. + * + * Get exclusive access before modifying the PM clock entry list and the + * clock_op_might_sleep count to guard against concurrent modifications. + * This also protects against a concurrent clock_op_might_sleep and PM clock + * entry list usage in pm_clk_suspend()/pm_clk_resume() that may or may not + * happen in atomic context, hence both the mutex and the spinlock must be + * taken here. + */ +static void pm_clk_list_lock(struct pm_subsys_data *psd) + __acquires(&psd->lock) +{ + mutex_lock(&psd->clock_mutex); + spin_lock_irq(&psd->lock); +} + +/** + * pm_clk_list_unlock - counterpart to pm_clk_list_lock(). + * @psd: the same pm_subsys_data instance previously passed to + * pm_clk_list_lock(). + */ +static void pm_clk_list_unlock(struct pm_subsys_data *psd) + __releases(&psd->lock) +{ + spin_unlock_irq(&psd->lock); + mutex_unlock(&psd->clock_mutex); +} + +/** + * pm_clk_op_lock - ensure exclusive access for performing clock operations. + * @psd: pm_subsys_data instance corresponding to the PM clock entry list + * and clk_op_might_sleep count being used. + * @flags: stored irq flags. + * @fn: string for the caller function's name. + * + * This is used by pm_clk_suspend() and pm_clk_resume() to guard + * against concurrent modifications to the clock entry list and the + * clock_op_might_sleep count. If clock_op_might_sleep is != 0 then + * only the mutex can be locked and those functions can only be used in + * non atomic context. If clock_op_might_sleep == 0 then these functions + * may be used in any context and only the spinlock can be locked. + * Returns -EINVAL if called in atomic context when clock ops might sleep. + */ +static int pm_clk_op_lock(struct pm_subsys_data *psd, unsigned long *flags, + const char *fn) + /* sparse annotations don't work here as exit state isn't static */ +{ + bool atomic_context = in_atomic() || irqs_disabled(); + +try_again: + spin_lock_irqsave(&psd->lock, *flags); + if (!psd->clock_op_might_sleep) { + /* the __release is there to work around sparse limitations */ + __release(&psd->lock); + return 0; + } + + /* bail out if in atomic context */ + if (atomic_context) { + pr_err("%s: atomic context with clock_ops_might_sleep = %d", + fn, psd->clock_op_might_sleep); + spin_unlock_irqrestore(&psd->lock, *flags); + might_sleep(); + return -EPERM; + } + + /* we must switch to the mutex */ + spin_unlock_irqrestore(&psd->lock, *flags); + mutex_lock(&psd->clock_mutex); + + /* + * There was a possibility for psd->clock_op_might_sleep + * to become 0 above. Keep the mutex only if not the case. + */ + if (likely(psd->clock_op_might_sleep)) + return 0; + + mutex_unlock(&psd->clock_mutex); + goto try_again; +} + +/** + * pm_clk_op_unlock - counterpart to pm_clk_op_lock(). + * @psd: the same pm_subsys_data instance previously passed to + * pm_clk_op_lock(). + * @flags: irq flags provided by pm_clk_op_lock(). + */ +static void pm_clk_op_unlock(struct pm_subsys_data *psd, unsigned long *flags) + /* sparse annotations don't work here as entry state isn't static */ +{ + if (psd->clock_op_might_sleep) { + mutex_unlock(&psd->clock_mutex); + } else { + /* the __acquire is there to work around sparse limitations */ + __acquire(&psd->lock); + spin_unlock_irqrestore(&psd->lock, *flags); + } +} + +/** + * __pm_clk_enable - Enable a clock, reporting any errors * @dev: The device for the given clock * @ce: PM clock entry corresponding to the clock. */ @@ -43,14 +148,21 @@ static inline void __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce { int ret; - if (ce->status < PCE_STATUS_ERROR) { + switch (ce->status) { + case PCE_STATUS_ACQUIRED: + ret = clk_prepare_enable(ce->clk); + break; + case PCE_STATUS_PREPARED: ret = clk_enable(ce->clk); - if (!ret) - ce->status = PCE_STATUS_ENABLED; - else - dev_err(dev, "%s: failed to enable clk %p, error %d\n", - __func__, ce->clk, ret); + break; + default: + return; } + if (!ret) + ce->status = PCE_STATUS_ENABLED; + else + dev_err(dev, "%s: failed to enable clk %p, error %d\n", + __func__, ce->clk, ret); } /** @@ -64,12 +176,20 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce) ce->clk = clk_get(dev, ce->con_id); if (IS_ERR(ce->clk)) { ce->status = PCE_STATUS_ERROR; - } else { - clk_prepare(ce->clk); + return; + } else if (clk_is_enabled_when_prepared(ce->clk)) { + /* we defer preparing the clock in that case */ ce->status = PCE_STATUS_ACQUIRED; - dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n", - ce->clk, ce->con_id); + ce->enabled_when_prepared = true; + } else if (clk_prepare(ce->clk)) { + ce->status = PCE_STATUS_ERROR; + dev_err(dev, "clk_prepare() failed\n"); + return; + } else { + ce->status = PCE_STATUS_PREPARED; } + dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n", + ce->clk, ce->con_id); } static int __pm_clk_add(struct device *dev, const char *con_id, @@ -88,8 +208,6 @@ static int __pm_clk_add(struct device *dev, const char *con_id, if (con_id) { ce->con_id = kstrdup(con_id, GFP_KERNEL); if (!ce->con_id) { - dev_err(dev, - "Not enough memory for clock connection ID.\n"); kfree(ce); return -ENOMEM; } @@ -103,9 +221,11 @@ static int __pm_clk_add(struct device *dev, const char *con_id, pm_clk_acquire(dev, ce); - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_add_tail(&ce->node, &psd->clock_list); - spin_unlock_irq(&psd->lock); + if (ce->enabled_when_prepared) + psd->clock_op_might_sleep++; + pm_clk_list_unlock(psd); return 0; } @@ -139,39 +259,6 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk) } EXPORT_SYMBOL_GPL(pm_clk_add_clk); - -/** - * of_pm_clk_add_clk - Start using a device clock for power management. - * @dev: Device whose clock is going to be used for power management. - * @name: Name of clock that is going to be used for power management. - * - * Add the clock described in the 'clocks' device-tree node that matches - * with the 'name' provided, to the list of clocks used for the power - * management of @dev. On success, returns 0. Returns a negative error - * code if the clock is not found or cannot be added. - */ -int of_pm_clk_add_clk(struct device *dev, const char *name) -{ - struct clk *clk; - int ret; - - if (!dev || !dev->of_node || !name) - return -EINVAL; - - clk = of_clk_get_by_name(dev->of_node, name); - if (IS_ERR(clk)) - return PTR_ERR(clk); - - ret = pm_clk_add_clk(dev, clk); - if (ret) { - clk_put(clk); - return ret; - } - - return 0; -} -EXPORT_SYMBOL_GPL(of_pm_clk_add_clk); - /** * of_pm_clk_add_clks - Start using device clock(s) for power management. * @dev: Device whose clock(s) is going to be used for power management. @@ -191,8 +278,7 @@ int of_pm_clk_add_clks(struct device *dev) if (!dev || !dev->of_node) return -EINVAL; - count = of_count_phandle_with_args(dev->of_node, "clocks", - "#clock-cells"); + count = of_clk_get_parent_count(dev->of_node); if (count <= 0) return -ENODEV; @@ -237,14 +323,20 @@ static void __pm_clk_remove(struct pm_clock_entry *ce) if (!ce) return; - if (ce->status < PCE_STATUS_ERROR) { - if (ce->status == PCE_STATUS_ENABLED) - clk_disable(ce->clk); - - if (ce->status >= PCE_STATUS_ACQUIRED) { - clk_unprepare(ce->clk); + switch (ce->status) { + case PCE_STATUS_ENABLED: + clk_disable(ce->clk); + fallthrough; + case PCE_STATUS_PREPARED: + clk_unprepare(ce->clk); + fallthrough; + case PCE_STATUS_ACQUIRED: + case PCE_STATUS_ERROR: + if (!IS_ERR(ce->clk)) clk_put(ce->clk); - } + break; + default: + break; } kfree(ce->con_id); @@ -252,44 +344,6 @@ static void __pm_clk_remove(struct pm_clock_entry *ce) } /** - * pm_clk_remove - Stop using a device clock for power management. - * @dev: Device whose clock should not be used for PM any more. - * @con_id: Connection ID of the clock. - * - * Remove the clock represented by @con_id from the list of clocks used for - * the power management of @dev. - */ -void pm_clk_remove(struct device *dev, const char *con_id) -{ - struct pm_subsys_data *psd = dev_to_psd(dev); - struct pm_clock_entry *ce; - - if (!psd) - return; - - spin_lock_irq(&psd->lock); - - list_for_each_entry(ce, &psd->clock_list, node) { - if (!con_id && !ce->con_id) - goto remove; - else if (!con_id || !ce->con_id) - continue; - else if (!strcmp(con_id, ce->con_id)) - goto remove; - } - - spin_unlock_irq(&psd->lock); - return; - - remove: - list_del(&ce->node); - spin_unlock_irq(&psd->lock); - - __pm_clk_remove(ce); -} -EXPORT_SYMBOL_GPL(pm_clk_remove); - -/** * pm_clk_remove_clk - Stop using a device clock for power management. * @dev: Device whose clock should not be used for PM any more. * @clk: Clock pointer @@ -305,19 +359,21 @@ void pm_clk_remove_clk(struct device *dev, struct clk *clk) if (!psd || !clk) return; - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_for_each_entry(ce, &psd->clock_list, node) { if (clk == ce->clk) goto remove; } - spin_unlock_irq(&psd->lock); + pm_clk_list_unlock(psd); return; remove: list_del(&ce->node); - spin_unlock_irq(&psd->lock); + if (ce->enabled_when_prepared) + psd->clock_op_might_sleep--; + pm_clk_list_unlock(psd); __pm_clk_remove(ce); } @@ -328,13 +384,16 @@ EXPORT_SYMBOL_GPL(pm_clk_remove_clk); * @dev: Device to initialize the list of PM clocks for. * * Initialize the lock and clock_list members of the device's pm_subsys_data - * object. + * object, set the count of clocks that might sleep to 0. */ void pm_clk_init(struct device *dev) { struct pm_subsys_data *psd = dev_to_psd(dev); - if (psd) + if (psd) { INIT_LIST_HEAD(&psd->clock_list); + mutex_init(&psd->clock_mutex); + psd->clock_op_might_sleep = 0; + } } EXPORT_SYMBOL_GPL(pm_clk_init); @@ -370,12 +429,13 @@ void pm_clk_destroy(struct device *dev) INIT_LIST_HEAD(&list); - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node) list_move(&ce->node, &list); + psd->clock_op_might_sleep = 0; - spin_unlock_irq(&psd->lock); + pm_clk_list_unlock(psd); dev_pm_put_subsys_data(dev); @@ -386,6 +446,23 @@ void pm_clk_destroy(struct device *dev) } EXPORT_SYMBOL_GPL(pm_clk_destroy); +static void pm_clk_destroy_action(void *data) +{ + pm_clk_destroy(data); +} + +int devm_pm_clk_create(struct device *dev) +{ + int ret; + + ret = pm_clk_create(dev); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, pm_clk_destroy_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_clk_create); + /** * pm_clk_suspend - Disable clocks in a device's PM clock list. * @dev: Device to disable the clocks for. @@ -395,23 +472,30 @@ int pm_clk_suspend(struct device *dev) struct pm_subsys_data *psd = dev_to_psd(dev); struct pm_clock_entry *ce; unsigned long flags; + int ret; dev_dbg(dev, "%s()\n", __func__); if (!psd) return 0; - spin_lock_irqsave(&psd->lock, flags); + ret = pm_clk_op_lock(psd, &flags, __func__); + if (ret) + return ret; list_for_each_entry_reverse(ce, &psd->clock_list, node) { - if (ce->status < PCE_STATUS_ERROR) { - if (ce->status == PCE_STATUS_ENABLED) + if (ce->status == PCE_STATUS_ENABLED) { + if (ce->enabled_when_prepared) { + clk_disable_unprepare(ce->clk); + ce->status = PCE_STATUS_ACQUIRED; + } else { clk_disable(ce->clk); - ce->status = PCE_STATUS_ACQUIRED; + ce->status = PCE_STATUS_PREPARED; + } } } - spin_unlock_irqrestore(&psd->lock, flags); + pm_clk_op_unlock(psd, &flags); return 0; } @@ -426,18 +510,21 @@ int pm_clk_resume(struct device *dev) struct pm_subsys_data *psd = dev_to_psd(dev); struct pm_clock_entry *ce; unsigned long flags; + int ret; dev_dbg(dev, "%s()\n", __func__); if (!psd) return 0; - spin_lock_irqsave(&psd->lock, flags); + ret = pm_clk_op_lock(psd, &flags, __func__); + if (ret) + return ret; list_for_each_entry(ce, &psd->clock_list, node) __pm_clk_enable(dev, ce); - spin_unlock_irqrestore(&psd->lock, flags); + pm_clk_op_unlock(psd, &flags); return 0; } @@ -633,7 +720,7 @@ static int pm_clk_notify(struct notifier_block *nb, * the remaining members of @clknb should be populated prior to calling this * routine. */ -void pm_clk_add_notifier(struct bus_type *bus, +void pm_clk_add_notifier(const struct bus_type *bus, struct pm_clk_notifier_block *clknb) { if (!bus || !clknb) diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index b413951c6abc..6ecf9ce4a4e6 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/common.c - Common device power management code. * * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp. - * - * This file is released under the GPLv2. */ - #include <linux/kernel.h> #include <linux/device.h> #include <linux/export.h> @@ -13,6 +11,7 @@ #include <linux/pm_clock.h> #include <linux/acpi.h> #include <linux/pm_domain.h> +#include <linux/pm_opp.h> #include "power.h" @@ -84,7 +83,7 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); /** * dev_pm_domain_attach - Attach a device to its PM domain. * @dev: Device to attach. - * @power_on: Used to indicate whether we should power on the device. + * @flags: indicate whether we should power on/off the device on attach/detach * * The @dev may only be attached to a single PM domain. By iterating through * the available alternatives we try to find a valid PM domain for the device. @@ -101,17 +100,20 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); * Returns 0 on successfully attached PM domain, or when it is found that the * device doesn't need a PM domain, else a negative error code. */ -int dev_pm_domain_attach(struct device *dev, bool power_on) +int dev_pm_domain_attach(struct device *dev, u32 flags) { int ret; if (dev->pm_domain) return 0; - ret = acpi_dev_pm_attach(dev, power_on); + ret = acpi_dev_pm_attach(dev, !!(flags & PD_FLAG_ATTACH_POWER_ON)); if (!ret) ret = genpd_dev_pm_attach(dev); + if (dev->pm_domain) + dev->power.detach_power_off = !!(flags & PD_FLAG_DETACH_POWER_OFF); + return ret < 0 ? ret : 0; } EXPORT_SYMBOL_GPL(dev_pm_domain_attach); @@ -160,7 +162,7 @@ EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id); * For a detailed function description, see dev_pm_domain_attach_by_id(). */ struct device *dev_pm_domain_attach_by_name(struct device *dev, - char *name) + const char *name) { if (dev->pm_domain) return ERR_PTR(-EEXIST); @@ -170,14 +172,187 @@ struct device *dev_pm_domain_attach_by_name(struct device *dev, EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name); /** + * dev_pm_domain_attach_list - Associate a device with its PM domains. + * @dev: The device used to lookup the PM domains for. + * @data: The data used for attaching to the PM domains. + * @list: An out-parameter with an allocated list of attached PM domains. + * + * This function helps to attach a device to its multiple PM domains. The + * caller, which is typically a driver's probe function, may provide a list of + * names for the PM domains that we should try to attach the device to, but it + * may also provide an empty list, in case the attach should be done for all of + * the available PM domains. + * + * Callers must ensure proper synchronization of this function with power + * management callbacks. + * + * Returns the number of attached PM domains or a negative error code in case of + * a failure. Note that, to detach the list of PM domains, the driver shall call + * dev_pm_domain_detach_list(), typically during the remove phase. + */ +int dev_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + struct device_node *np = dev->of_node; + struct dev_pm_domain_list *pds; + struct device *pd_dev = NULL; + int ret, i, num_pds = 0; + bool by_id = true; + size_t size; + u32 pd_flags = data ? data->pd_flags : 0; + u32 link_flags = pd_flags & PD_FLAG_NO_DEV_LINK ? 0 : + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME; + + if (dev->pm_domain) + return -EEXIST; + + /* For now this is limited to OF based platforms. */ + if (!np) + return 0; + + if (data && data->pd_names) { + num_pds = data->num_pd_names; + by_id = false; + } else { + num_pds = of_count_phandle_with_args(np, "power-domains", + "#power-domain-cells"); + } + + if (num_pds <= 0) + return 0; + + pds = kzalloc(sizeof(*pds), GFP_KERNEL); + if (!pds) + return -ENOMEM; + + size = sizeof(*pds->pd_devs) + sizeof(*pds->pd_links) + + sizeof(*pds->opp_tokens); + pds->pd_devs = kcalloc(num_pds, size, GFP_KERNEL); + if (!pds->pd_devs) { + ret = -ENOMEM; + goto free_pds; + } + pds->pd_links = (void *)(pds->pd_devs + num_pds); + pds->opp_tokens = (void *)(pds->pd_links + num_pds); + + if (link_flags && pd_flags & PD_FLAG_DEV_LINK_ON) + link_flags |= DL_FLAG_RPM_ACTIVE; + + for (i = 0; i < num_pds; i++) { + if (by_id) + pd_dev = dev_pm_domain_attach_by_id(dev, i); + else + pd_dev = dev_pm_domain_attach_by_name(dev, + data->pd_names[i]); + if (IS_ERR_OR_NULL(pd_dev)) { + ret = pd_dev ? PTR_ERR(pd_dev) : -ENODEV; + goto err_attach; + } + + if (pd_flags & PD_FLAG_REQUIRED_OPP) { + struct dev_pm_opp_config config = { + .required_dev = pd_dev, + .required_dev_index = i, + }; + + ret = dev_pm_opp_set_config(dev, &config); + if (ret < 0) + goto err_link; + + pds->opp_tokens[i] = ret; + } + + if (link_flags) { + struct device_link *link; + + link = device_link_add(dev, pd_dev, link_flags); + if (!link) { + ret = -ENODEV; + goto err_link; + } + + pds->pd_links[i] = link; + } + + pds->pd_devs[i] = pd_dev; + } + + pds->num_pds = num_pds; + *list = pds; + return num_pds; + +err_link: + dev_pm_opp_clear_config(pds->opp_tokens[i]); + dev_pm_domain_detach(pd_dev, true); +err_attach: + while (--i >= 0) { + dev_pm_opp_clear_config(pds->opp_tokens[i]); + if (pds->pd_links[i]) + device_link_del(pds->pd_links[i]); + dev_pm_domain_detach(pds->pd_devs[i], true); + } + kfree(pds->pd_devs); +free_pds: + kfree(pds); + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_domain_attach_list); + +/** + * devm_pm_domain_detach_list - devres-enabled version of dev_pm_domain_detach_list. + * @_list: The list of PM domains to detach. + * + * This function reverse the actions from devm_pm_domain_attach_list(). + * it will be invoked during the remove phase from drivers implicitly if driver + * uses devm_pm_domain_attach_list() to attach the PM domains. + */ +static void devm_pm_domain_detach_list(void *_list) +{ + struct dev_pm_domain_list *list = _list; + + dev_pm_domain_detach_list(list); +} + +/** + * devm_pm_domain_attach_list - devres-enabled version of dev_pm_domain_attach_list + * @dev: The device used to lookup the PM domains for. + * @data: The data used for attaching to the PM domains. + * @list: An out-parameter with an allocated list of attached PM domains. + * + * NOTE: this will also handle calling devm_pm_domain_detach_list() for + * you during remove phase. + * + * Returns the number of attached PM domains or a negative error code in case of + * a failure. + */ +int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + int ret, num_pds; + + num_pds = dev_pm_domain_attach_list(dev, data, list); + if (num_pds <= 0) + return num_pds; + + ret = devm_add_action_or_reset(dev, devm_pm_domain_detach_list, *list); + if (ret) + return ret; + + return num_pds; +} +EXPORT_SYMBOL_GPL(devm_pm_domain_attach_list); + +/** * dev_pm_domain_detach - Detach a device from its PM domain. * @dev: Device to detach. * @power_off: Used to indicate whether we should power off the device. * - * This functions will reverse the actions from dev_pm_domain_attach() and - * dev_pm_domain_attach_by_id(), thus it detaches @dev from its PM domain. - * Typically it should be invoked during the remove phase, either from - * subsystem level code or from drivers. + * This functions will reverse the actions from dev_pm_domain_attach(), + * dev_pm_domain_attach_by_id() and dev_pm_domain_attach_by_name(), thus it + * detaches @dev from its PM domain. Typically it should be invoked during the + * remove phase, either from subsystem level code or from drivers. * * Callers must ensure proper synchronization of this function with power * management callbacks. @@ -190,6 +365,55 @@ void dev_pm_domain_detach(struct device *dev, bool power_off) EXPORT_SYMBOL_GPL(dev_pm_domain_detach); /** + * dev_pm_domain_detach_list - Detach a list of PM domains. + * @list: The list of PM domains to detach. + * + * This function reverse the actions from dev_pm_domain_attach_list(). + * Typically it should be invoked during the remove phase from drivers. + * + * Callers must ensure proper synchronization of this function with power + * management callbacks. + */ +void dev_pm_domain_detach_list(struct dev_pm_domain_list *list) +{ + int i; + + if (!list) + return; + + for (i = 0; i < list->num_pds; i++) { + dev_pm_opp_clear_config(list->opp_tokens[i]); + if (list->pd_links[i]) + device_link_del(list->pd_links[i]); + dev_pm_domain_detach(list->pd_devs[i], true); + } + + kfree(list->pd_devs); + kfree(list); +} +EXPORT_SYMBOL_GPL(dev_pm_domain_detach_list); + +/** + * dev_pm_domain_start - Start the device through its PM domain. + * @dev: Device to start. + * + * This function should typically be called during probe by a subsystem/driver, + * when it needs to start its device from the PM domain's perspective. Note + * that, it's assumed that the PM domain is already powered on when this + * function is called. + * + * Returns 0 on success and negative error values on failures. + */ +int dev_pm_domain_start(struct device *dev) +{ + if (dev->pm_domain && dev->pm_domain->start) + return dev->pm_domain->start(dev); + + return 0; +} +EXPORT_SYMBOL_GPL(dev_pm_domain_start); + +/** * dev_pm_domain_set - Set PM domain of a device. * @dev: Device whose PM domain is to be set. * @pd: PM domain to be set, or NULL. @@ -210,3 +434,24 @@ void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) device_pm_check_callbacks(dev); } EXPORT_SYMBOL_GPL(dev_pm_domain_set); + +/** + * dev_pm_domain_set_performance_state - Request a new performance state. + * @dev: The device to make the request for. + * @state: Target performance state for the device. + * + * This function should be called when a new performance state needs to be + * requested for a device that is attached to a PM domain. Note that, the + * support for performance scaling for PM domains is optional. + * + * Returns 0 on success and when performance scaling isn't supported, negative + * error code on failure. + */ +int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state) +{ + if (dev->pm_domain && dev->pm_domain->set_performance_state) + return dev->pm_domain->set_performance_state(dev, state); + + return 0; +} +EXPORT_SYMBOL_GPL(dev_pm_domain_set_performance_state); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c deleted file mode 100644 index 500de1dee967..000000000000 --- a/drivers/base/power/domain.c +++ /dev/null @@ -1,2990 +0,0 @@ -/* - * drivers/base/power/domain.c - Common code related to device power domains. - * - * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp. - * - * This file is released under the GPLv2. - */ - -#include <linux/delay.h> -#include <linux/kernel.h> -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/pm_opp.h> -#include <linux/pm_runtime.h> -#include <linux/pm_domain.h> -#include <linux/pm_qos.h> -#include <linux/pm_clock.h> -#include <linux/slab.h> -#include <linux/err.h> -#include <linux/sched.h> -#include <linux/suspend.h> -#include <linux/export.h> - -#include "power.h" - -#define GENPD_RETRY_MAX_MS 250 /* Approximate */ - -#define GENPD_DEV_CALLBACK(genpd, type, callback, dev) \ -({ \ - type (*__routine)(struct device *__d); \ - type __ret = (type)0; \ - \ - __routine = genpd->dev_ops.callback; \ - if (__routine) { \ - __ret = __routine(dev); \ - } \ - __ret; \ -}) - -static LIST_HEAD(gpd_list); -static DEFINE_MUTEX(gpd_list_lock); - -struct genpd_lock_ops { - void (*lock)(struct generic_pm_domain *genpd); - void (*lock_nested)(struct generic_pm_domain *genpd, int depth); - int (*lock_interruptible)(struct generic_pm_domain *genpd); - void (*unlock)(struct generic_pm_domain *genpd); -}; - -static void genpd_lock_mtx(struct generic_pm_domain *genpd) -{ - mutex_lock(&genpd->mlock); -} - -static void genpd_lock_nested_mtx(struct generic_pm_domain *genpd, - int depth) -{ - mutex_lock_nested(&genpd->mlock, depth); -} - -static int genpd_lock_interruptible_mtx(struct generic_pm_domain *genpd) -{ - return mutex_lock_interruptible(&genpd->mlock); -} - -static void genpd_unlock_mtx(struct generic_pm_domain *genpd) -{ - return mutex_unlock(&genpd->mlock); -} - -static const struct genpd_lock_ops genpd_mtx_ops = { - .lock = genpd_lock_mtx, - .lock_nested = genpd_lock_nested_mtx, - .lock_interruptible = genpd_lock_interruptible_mtx, - .unlock = genpd_unlock_mtx, -}; - -static void genpd_lock_spin(struct generic_pm_domain *genpd) - __acquires(&genpd->slock) -{ - unsigned long flags; - - spin_lock_irqsave(&genpd->slock, flags); - genpd->lock_flags = flags; -} - -static void genpd_lock_nested_spin(struct generic_pm_domain *genpd, - int depth) - __acquires(&genpd->slock) -{ - unsigned long flags; - - spin_lock_irqsave_nested(&genpd->slock, flags, depth); - genpd->lock_flags = flags; -} - -static int genpd_lock_interruptible_spin(struct generic_pm_domain *genpd) - __acquires(&genpd->slock) -{ - unsigned long flags; - - spin_lock_irqsave(&genpd->slock, flags); - genpd->lock_flags = flags; - return 0; -} - -static void genpd_unlock_spin(struct generic_pm_domain *genpd) - __releases(&genpd->slock) -{ - spin_unlock_irqrestore(&genpd->slock, genpd->lock_flags); -} - -static const struct genpd_lock_ops genpd_spin_ops = { - .lock = genpd_lock_spin, - .lock_nested = genpd_lock_nested_spin, - .lock_interruptible = genpd_lock_interruptible_spin, - .unlock = genpd_unlock_spin, -}; - -#define genpd_lock(p) p->lock_ops->lock(p) -#define genpd_lock_nested(p, d) p->lock_ops->lock_nested(p, d) -#define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) -#define genpd_unlock(p) p->lock_ops->unlock(p) - -#define genpd_status_on(genpd) (genpd->status == GPD_STATE_ACTIVE) -#define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) -#define genpd_is_always_on(genpd) (genpd->flags & GENPD_FLAG_ALWAYS_ON) -#define genpd_is_active_wakeup(genpd) (genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP) - -static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, - const struct generic_pm_domain *genpd) -{ - bool ret; - - ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); - - /* - * Warn once if an IRQ safe device is attached to a no sleep domain, as - * to indicate a suboptimal configuration for PM. For an always on - * domain this isn't case, thus don't warn. - */ - if (ret && !genpd_is_always_on(genpd)) - dev_warn_once(dev, "PM domain %s will not be powered off\n", - genpd->name); - - return ret; -} - -/* - * Get the generic PM domain for a particular struct device. - * This validates the struct device pointer, the PM domain pointer, - * and checks that the PM domain pointer is a real generic PM domain. - * Any failure results in NULL being returned. - */ -static struct generic_pm_domain *genpd_lookup_dev(struct device *dev) -{ - struct generic_pm_domain *genpd = NULL, *gpd; - - if (IS_ERR_OR_NULL(dev) || IS_ERR_OR_NULL(dev->pm_domain)) - return NULL; - - mutex_lock(&gpd_list_lock); - list_for_each_entry(gpd, &gpd_list, gpd_list_node) { - if (&gpd->domain == dev->pm_domain) { - genpd = gpd; - break; - } - } - mutex_unlock(&gpd_list_lock); - - return genpd; -} - -/* - * This should only be used where we are certain that the pm_domain - * attached to the device is a genpd domain. - */ -static struct generic_pm_domain *dev_to_genpd(struct device *dev) -{ - if (IS_ERR_OR_NULL(dev->pm_domain)) - return ERR_PTR(-EINVAL); - - return pd_to_genpd(dev->pm_domain); -} - -static int genpd_stop_dev(const struct generic_pm_domain *genpd, - struct device *dev) -{ - return GENPD_DEV_CALLBACK(genpd, int, stop, dev); -} - -static int genpd_start_dev(const struct generic_pm_domain *genpd, - struct device *dev) -{ - return GENPD_DEV_CALLBACK(genpd, int, start, dev); -} - -static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd) -{ - bool ret = false; - - if (!WARN_ON(atomic_read(&genpd->sd_count) == 0)) - ret = !!atomic_dec_and_test(&genpd->sd_count); - - return ret; -} - -static void genpd_sd_counter_inc(struct generic_pm_domain *genpd) -{ - atomic_inc(&genpd->sd_count); - smp_mb__after_atomic(); -} - -#ifdef CONFIG_DEBUG_FS -static void genpd_update_accounting(struct generic_pm_domain *genpd) -{ - ktime_t delta, now; - - now = ktime_get(); - delta = ktime_sub(now, genpd->accounting_time); - - /* - * If genpd->status is active, it means we are just - * out of off and so update the idle time and vice - * versa. - */ - if (genpd->status == GPD_STATE_ACTIVE) { - int state_idx = genpd->state_idx; - - genpd->states[state_idx].idle_time = - ktime_add(genpd->states[state_idx].idle_time, delta); - } else { - genpd->on_time = ktime_add(genpd->on_time, delta); - } - - genpd->accounting_time = now; -} -#else -static inline void genpd_update_accounting(struct generic_pm_domain *genpd) {} -#endif - -static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd, - unsigned int state) -{ - struct generic_pm_domain_data *pd_data; - struct pm_domain_data *pdd; - struct gpd_link *link; - - /* New requested state is same as Max requested state */ - if (state == genpd->performance_state) - return state; - - /* New requested state is higher than Max requested state */ - if (state > genpd->performance_state) - return state; - - /* Traverse all devices within the domain */ - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - pd_data = to_gpd_data(pdd); - - if (pd_data->performance_state > state) - state = pd_data->performance_state; - } - - /* - * Traverse all sub-domains within the domain. This can be - * done without any additional locking as the link->performance_state - * field is protected by the master genpd->lock, which is already taken. - * - * Also note that link->performance_state (subdomain's performance state - * requirement to master domain) is different from - * link->slave->performance_state (current performance state requirement - * of the devices/sub-domains of the subdomain) and so can have a - * different value. - * - * Note that we also take vote from powered-off sub-domains into account - * as the same is done for devices right now. - */ - list_for_each_entry(link, &genpd->master_links, master_node) { - if (link->performance_state > state) - state = link->performance_state; - } - - return state; -} - -static int _genpd_set_performance_state(struct generic_pm_domain *genpd, - unsigned int state, int depth) -{ - struct generic_pm_domain *master; - struct gpd_link *link; - int master_state, ret; - - if (state == genpd->performance_state) - return 0; - - /* Propagate to masters of genpd */ - list_for_each_entry(link, &genpd->slave_links, slave_node) { - master = link->master; - - if (!master->set_performance_state) - continue; - - /* Find master's performance state */ - ret = dev_pm_opp_xlate_performance_state(genpd->opp_table, - master->opp_table, - state); - if (unlikely(ret < 0)) - goto err; - - master_state = ret; - - genpd_lock_nested(master, depth + 1); - - link->prev_performance_state = link->performance_state; - link->performance_state = master_state; - master_state = _genpd_reeval_performance_state(master, - master_state); - ret = _genpd_set_performance_state(master, master_state, depth + 1); - if (ret) - link->performance_state = link->prev_performance_state; - - genpd_unlock(master); - - if (ret) - goto err; - } - - ret = genpd->set_performance_state(genpd, state); - if (ret) - goto err; - - genpd->performance_state = state; - return 0; - -err: - /* Encountered an error, lets rollback */ - list_for_each_entry_continue_reverse(link, &genpd->slave_links, - slave_node) { - master = link->master; - - if (!master->set_performance_state) - continue; - - genpd_lock_nested(master, depth + 1); - - master_state = link->prev_performance_state; - link->performance_state = master_state; - - master_state = _genpd_reeval_performance_state(master, - master_state); - if (_genpd_set_performance_state(master, master_state, depth + 1)) { - pr_err("%s: Failed to roll back to %d performance state\n", - master->name, master_state); - } - - genpd_unlock(master); - } - - return ret; -} - -/** - * dev_pm_genpd_set_performance_state- Set performance state of device's power - * domain. - * - * @dev: Device for which the performance-state needs to be set. - * @state: Target performance state of the device. This can be set as 0 when the - * device doesn't have any performance state constraints left (And so - * the device wouldn't participate anymore to find the target - * performance state of the genpd). - * - * It is assumed that the users guarantee that the genpd wouldn't be detached - * while this routine is getting called. - * - * Returns 0 on success and negative error values on failures. - */ -int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) -{ - struct generic_pm_domain *genpd; - struct generic_pm_domain_data *gpd_data; - unsigned int prev; - int ret; - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -ENODEV; - - if (unlikely(!genpd->set_performance_state)) - return -EINVAL; - - if (unlikely(!dev->power.subsys_data || - !dev->power.subsys_data->domain_data)) { - WARN_ON(1); - return -EINVAL; - } - - genpd_lock(genpd); - - gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); - prev = gpd_data->performance_state; - gpd_data->performance_state = state; - - state = _genpd_reeval_performance_state(genpd, state); - ret = _genpd_set_performance_state(genpd, state, 0); - if (ret) - gpd_data->performance_state = prev; - - genpd_unlock(genpd); - - return ret; -} -EXPORT_SYMBOL_GPL(dev_pm_genpd_set_performance_state); - -static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) -{ - unsigned int state_idx = genpd->state_idx; - ktime_t time_start; - s64 elapsed_ns; - int ret; - - if (!genpd->power_on) - return 0; - - if (!timed) - return genpd->power_on(genpd); - - time_start = ktime_get(); - ret = genpd->power_on(genpd); - if (ret) - return ret; - - elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns) - return ret; - - genpd->states[state_idx].power_on_latency_ns = elapsed_ns; - genpd->max_off_time_changed = true; - pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", - genpd->name, "on", elapsed_ns); - - return ret; -} - -static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed) -{ - unsigned int state_idx = genpd->state_idx; - ktime_t time_start; - s64 elapsed_ns; - int ret; - - if (!genpd->power_off) - return 0; - - if (!timed) - return genpd->power_off(genpd); - - time_start = ktime_get(); - ret = genpd->power_off(genpd); - if (ret == -EBUSY) - return ret; - - elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns) - return ret; - - genpd->states[state_idx].power_off_latency_ns = elapsed_ns; - genpd->max_off_time_changed = true; - pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n", - genpd->name, "off", elapsed_ns); - - return ret; -} - -/** - * genpd_queue_power_off_work - Queue up the execution of genpd_power_off(). - * @genpd: PM domain to power off. - * - * Queue up the execution of genpd_power_off() unless it's already been done - * before. - */ -static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) -{ - queue_work(pm_wq, &genpd->power_off_work); -} - -/** - * genpd_power_off - Remove power from a given PM domain. - * @genpd: PM domain to power down. - * @one_dev_on: If invoked from genpd's ->runtime_suspend|resume() callback, the - * RPM status of the releated device is in an intermediate state, not yet turned - * into RPM_SUSPENDED. This means genpd_power_off() must allow one device to not - * be RPM_SUSPENDED, while it tries to power off the PM domain. - * - * If all of the @genpd's devices have been suspended and all of its subdomains - * have been powered down, remove power from @genpd. - */ -static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, - unsigned int depth) -{ - struct pm_domain_data *pdd; - struct gpd_link *link; - unsigned int not_suspended = 0; - - /* - * Do not try to power off the domain in the following situations: - * (1) The domain is already in the "power off" state. - * (2) System suspend is in progress. - */ - if (!genpd_status_on(genpd) || genpd->prepared_count > 0) - return 0; - - /* - * Abort power off for the PM domain in the following situations: - * (1) The domain is configured as always on. - * (2) When the domain has a subdomain being powered on. - */ - if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0) - return -EBUSY; - - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - enum pm_qos_flags_status stat; - - stat = dev_pm_qos_flags(pdd->dev, PM_QOS_FLAG_NO_POWER_OFF); - if (stat > PM_QOS_FLAGS_NONE) - return -EBUSY; - - /* - * Do not allow PM domain to be powered off, when an IRQ safe - * device is part of a non-IRQ safe domain. - */ - if (!pm_runtime_suspended(pdd->dev) || - irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) - not_suspended++; - } - - if (not_suspended > 1 || (not_suspended == 1 && !one_dev_on)) - return -EBUSY; - - if (genpd->gov && genpd->gov->power_down_ok) { - if (!genpd->gov->power_down_ok(&genpd->domain)) - return -EAGAIN; - } - - /* Default to shallowest state. */ - if (!genpd->gov) - genpd->state_idx = 0; - - if (genpd->power_off) { - int ret; - - if (atomic_read(&genpd->sd_count) > 0) - return -EBUSY; - - /* - * If sd_count > 0 at this point, one of the subdomains hasn't - * managed to call genpd_power_on() for the master yet after - * incrementing it. In that case genpd_power_on() will wait - * for us to drop the lock, so we can call .power_off() and let - * the genpd_power_on() restore power for us (this shouldn't - * happen very often). - */ - ret = _genpd_power_off(genpd, true); - if (ret) - return ret; - } - - genpd->status = GPD_STATE_POWER_OFF; - genpd_update_accounting(genpd); - - list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_dec(link->master); - genpd_lock_nested(link->master, depth + 1); - genpd_power_off(link->master, false, depth + 1); - genpd_unlock(link->master); - } - - return 0; -} - -/** - * genpd_power_on - Restore power to a given PM domain and its masters. - * @genpd: PM domain to power up. - * @depth: nesting count for lockdep. - * - * Restore power to @genpd and all of its masters so that it is possible to - * resume a device belonging to it. - */ -static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth) -{ - struct gpd_link *link; - int ret = 0; - - if (genpd_status_on(genpd)) - return 0; - - /* - * The list is guaranteed not to change while the loop below is being - * executed, unless one of the masters' .power_on() callbacks fiddles - * with it. - */ - list_for_each_entry(link, &genpd->slave_links, slave_node) { - struct generic_pm_domain *master = link->master; - - genpd_sd_counter_inc(master); - - genpd_lock_nested(master, depth + 1); - ret = genpd_power_on(master, depth + 1); - genpd_unlock(master); - - if (ret) { - genpd_sd_counter_dec(master); - goto err; - } - } - - ret = _genpd_power_on(genpd, true); - if (ret) - goto err; - - genpd->status = GPD_STATE_ACTIVE; - genpd_update_accounting(genpd); - - return 0; - - err: - list_for_each_entry_continue_reverse(link, - &genpd->slave_links, - slave_node) { - genpd_sd_counter_dec(link->master); - genpd_lock_nested(link->master, depth + 1); - genpd_power_off(link->master, false, depth + 1); - genpd_unlock(link->master); - } - - return ret; -} - -static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, - unsigned long val, void *ptr) -{ - struct generic_pm_domain_data *gpd_data; - struct device *dev; - - gpd_data = container_of(nb, struct generic_pm_domain_data, nb); - dev = gpd_data->base.dev; - - for (;;) { - struct generic_pm_domain *genpd; - struct pm_domain_data *pdd; - - spin_lock_irq(&dev->power.lock); - - pdd = dev->power.subsys_data ? - dev->power.subsys_data->domain_data : NULL; - if (pdd) { - to_gpd_data(pdd)->td.constraint_changed = true; - genpd = dev_to_genpd(dev); - } else { - genpd = ERR_PTR(-ENODATA); - } - - spin_unlock_irq(&dev->power.lock); - - if (!IS_ERR(genpd)) { - genpd_lock(genpd); - genpd->max_off_time_changed = true; - genpd_unlock(genpd); - } - - dev = dev->parent; - if (!dev || dev->power.ignore_children) - break; - } - - return NOTIFY_DONE; -} - -/** - * genpd_power_off_work_fn - Power off PM domain whose subdomain count is 0. - * @work: Work structure used for scheduling the execution of this function. - */ -static void genpd_power_off_work_fn(struct work_struct *work) -{ - struct generic_pm_domain *genpd; - - genpd = container_of(work, struct generic_pm_domain, power_off_work); - - genpd_lock(genpd); - genpd_power_off(genpd, false, 0); - genpd_unlock(genpd); -} - -/** - * __genpd_runtime_suspend - walk the hierarchy of ->runtime_suspend() callbacks - * @dev: Device to handle. - */ -static int __genpd_runtime_suspend(struct device *dev) -{ - int (*cb)(struct device *__dev); - - if (dev->type && dev->type->pm) - cb = dev->type->pm->runtime_suspend; - else if (dev->class && dev->class->pm) - cb = dev->class->pm->runtime_suspend; - else if (dev->bus && dev->bus->pm) - cb = dev->bus->pm->runtime_suspend; - else - cb = NULL; - - if (!cb && dev->driver && dev->driver->pm) - cb = dev->driver->pm->runtime_suspend; - - return cb ? cb(dev) : 0; -} - -/** - * __genpd_runtime_resume - walk the hierarchy of ->runtime_resume() callbacks - * @dev: Device to handle. - */ -static int __genpd_runtime_resume(struct device *dev) -{ - int (*cb)(struct device *__dev); - - if (dev->type && dev->type->pm) - cb = dev->type->pm->runtime_resume; - else if (dev->class && dev->class->pm) - cb = dev->class->pm->runtime_resume; - else if (dev->bus && dev->bus->pm) - cb = dev->bus->pm->runtime_resume; - else - cb = NULL; - - if (!cb && dev->driver && dev->driver->pm) - cb = dev->driver->pm->runtime_resume; - - return cb ? cb(dev) : 0; -} - -/** - * genpd_runtime_suspend - Suspend a device belonging to I/O PM domain. - * @dev: Device to suspend. - * - * Carry out a runtime suspend of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a PM domain consisting of I/O devices. - */ -static int genpd_runtime_suspend(struct device *dev) -{ - struct generic_pm_domain *genpd; - bool (*suspend_ok)(struct device *__dev); - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; - bool runtime_pm = pm_runtime_enabled(dev); - ktime_t time_start; - s64 elapsed_ns; - int ret; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - /* - * A runtime PM centric subsystem/driver may re-use the runtime PM - * callbacks for other purposes than runtime PM. In those scenarios - * runtime PM is disabled. Under these circumstances, we shall skip - * validating/measuring the PM QoS latency. - */ - suspend_ok = genpd->gov ? genpd->gov->suspend_ok : NULL; - if (runtime_pm && suspend_ok && !suspend_ok(dev)) - return -EBUSY; - - /* Measure suspend latency. */ - time_start = 0; - if (runtime_pm) - time_start = ktime_get(); - - ret = __genpd_runtime_suspend(dev); - if (ret) - return ret; - - ret = genpd_stop_dev(genpd, dev); - if (ret) { - __genpd_runtime_resume(dev); - return ret; - } - - /* Update suspend latency value if the measured time exceeds it. */ - if (runtime_pm) { - elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns > td->suspend_latency_ns) { - td->suspend_latency_ns = elapsed_ns; - dev_dbg(dev, "suspend latency exceeded, %lld ns\n", - elapsed_ns); - genpd->max_off_time_changed = true; - td->constraint_changed = true; - } - } - - /* - * If power.irq_safe is set, this routine may be run with - * IRQs disabled, so suspend only if the PM domain also is irq_safe. - */ - if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) - return 0; - - genpd_lock(genpd); - genpd_power_off(genpd, true, 0); - genpd_unlock(genpd); - - return 0; -} - -/** - * genpd_runtime_resume - Resume a device belonging to I/O PM domain. - * @dev: Device to resume. - * - * Carry out a runtime resume of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a PM domain consisting of I/O devices. - */ -static int genpd_runtime_resume(struct device *dev) -{ - struct generic_pm_domain *genpd; - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; - bool runtime_pm = pm_runtime_enabled(dev); - ktime_t time_start; - s64 elapsed_ns; - int ret; - bool timed = true; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - /* - * As we don't power off a non IRQ safe domain, which holds - * an IRQ safe device, we don't need to restore power to it. - */ - if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) { - timed = false; - goto out; - } - - genpd_lock(genpd); - ret = genpd_power_on(genpd, 0); - genpd_unlock(genpd); - - if (ret) - return ret; - - out: - /* Measure resume latency. */ - time_start = 0; - if (timed && runtime_pm) - time_start = ktime_get(); - - ret = genpd_start_dev(genpd, dev); - if (ret) - goto err_poweroff; - - ret = __genpd_runtime_resume(dev); - if (ret) - goto err_stop; - - /* Update resume latency value if the measured time exceeds it. */ - if (timed && runtime_pm) { - elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); - if (elapsed_ns > td->resume_latency_ns) { - td->resume_latency_ns = elapsed_ns; - dev_dbg(dev, "resume latency exceeded, %lld ns\n", - elapsed_ns); - genpd->max_off_time_changed = true; - td->constraint_changed = true; - } - } - - return 0; - -err_stop: - genpd_stop_dev(genpd, dev); -err_poweroff: - if (!pm_runtime_is_irq_safe(dev) || - (pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) { - genpd_lock(genpd); - genpd_power_off(genpd, true, 0); - genpd_unlock(genpd); - } - - return ret; -} - -static bool pd_ignore_unused; -static int __init pd_ignore_unused_setup(char *__unused) -{ - pd_ignore_unused = true; - return 1; -} -__setup("pd_ignore_unused", pd_ignore_unused_setup); - -/** - * genpd_power_off_unused - Power off all PM domains with no devices in use. - */ -static int __init genpd_power_off_unused(void) -{ - struct generic_pm_domain *genpd; - - if (pd_ignore_unused) { - pr_warn("genpd: Not disabling unused power domains\n"); - return 0; - } - - mutex_lock(&gpd_list_lock); - - list_for_each_entry(genpd, &gpd_list, gpd_list_node) - genpd_queue_power_off_work(genpd); - - mutex_unlock(&gpd_list_lock); - - return 0; -} -late_initcall(genpd_power_off_unused); - -#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF) - -static bool genpd_present(const struct generic_pm_domain *genpd) -{ - const struct generic_pm_domain *gpd; - - if (IS_ERR_OR_NULL(genpd)) - return false; - - list_for_each_entry(gpd, &gpd_list, gpd_list_node) - if (gpd == genpd) - return true; - - return false; -} - -#endif - -#ifdef CONFIG_PM_SLEEP - -/** - * genpd_sync_power_off - Synchronously power off a PM domain and its masters. - * @genpd: PM domain to power off, if possible. - * @use_lock: use the lock. - * @depth: nesting count for lockdep. - * - * Check if the given PM domain can be powered off (during system suspend or - * hibernation) and do that if so. Also, in that case propagate to its masters. - * - * This function is only called in "noirq" and "syscore" stages of system power - * transitions. The "noirq" callbacks may be executed asynchronously, thus in - * these cases the lock must be held. - */ -static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, - unsigned int depth) -{ - struct gpd_link *link; - - if (!genpd_status_on(genpd) || genpd_is_always_on(genpd)) - return; - - if (genpd->suspended_count != genpd->device_count - || atomic_read(&genpd->sd_count) > 0) - return; - - /* Choose the deepest state when suspending */ - genpd->state_idx = genpd->state_count - 1; - if (_genpd_power_off(genpd, false)) - return; - - genpd->status = GPD_STATE_POWER_OFF; - - list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_dec(link->master); - - if (use_lock) - genpd_lock_nested(link->master, depth + 1); - - genpd_sync_power_off(link->master, use_lock, depth + 1); - - if (use_lock) - genpd_unlock(link->master); - } -} - -/** - * genpd_sync_power_on - Synchronously power on a PM domain and its masters. - * @genpd: PM domain to power on. - * @use_lock: use the lock. - * @depth: nesting count for lockdep. - * - * This function is only called in "noirq" and "syscore" stages of system power - * transitions. The "noirq" callbacks may be executed asynchronously, thus in - * these cases the lock must be held. - */ -static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock, - unsigned int depth) -{ - struct gpd_link *link; - - if (genpd_status_on(genpd)) - return; - - list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_inc(link->master); - - if (use_lock) - genpd_lock_nested(link->master, depth + 1); - - genpd_sync_power_on(link->master, use_lock, depth + 1); - - if (use_lock) - genpd_unlock(link->master); - } - - _genpd_power_on(genpd, false); - - genpd->status = GPD_STATE_ACTIVE; -} - -/** - * resume_needed - Check whether to resume a device before system suspend. - * @dev: Device to check. - * @genpd: PM domain the device belongs to. - * - * There are two cases in which a device that can wake up the system from sleep - * states should be resumed by genpd_prepare(): (1) if the device is enabled - * to wake up the system and it has to remain active for this purpose while the - * system is in the sleep state and (2) if the device is not enabled to wake up - * the system from sleep states and it generally doesn't generate wakeup signals - * by itself (those signals are generated on its behalf by other parts of the - * system). In the latter case it may be necessary to reconfigure the device's - * wakeup settings during system suspend, because it may have been set up to - * signal remote wakeup from the system's working state as needed by runtime PM. - * Return 'true' in either of the above cases. - */ -static bool resume_needed(struct device *dev, - const struct generic_pm_domain *genpd) -{ - bool active_wakeup; - - if (!device_can_wakeup(dev)) - return false; - - active_wakeup = genpd_is_active_wakeup(genpd); - return device_may_wakeup(dev) ? active_wakeup : !active_wakeup; -} - -/** - * genpd_prepare - Start power transition of a device in a PM domain. - * @dev: Device to start the transition of. - * - * Start a power transition of a device (during a system-wide power transition) - * under the assumption that its pm_domain field points to the domain member of - * an object of type struct generic_pm_domain representing a PM domain - * consisting of I/O devices. - */ -static int genpd_prepare(struct device *dev) -{ - struct generic_pm_domain *genpd; - int ret; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - /* - * If a wakeup request is pending for the device, it should be woken up - * at this point and a system wakeup event should be reported if it's - * set up to wake up the system from sleep states. - */ - if (resume_needed(dev, genpd)) - pm_runtime_resume(dev); - - genpd_lock(genpd); - - if (genpd->prepared_count++ == 0) - genpd->suspended_count = 0; - - genpd_unlock(genpd); - - ret = pm_generic_prepare(dev); - if (ret < 0) { - genpd_lock(genpd); - - genpd->prepared_count--; - - genpd_unlock(genpd); - } - - /* Never return 1, as genpd don't cope with the direct_complete path. */ - return ret >= 0 ? 0 : ret; -} - -/** - * genpd_finish_suspend - Completion of suspend or hibernation of device in an - * I/O pm domain. - * @dev: Device to suspend. - * @poweroff: Specifies if this is a poweroff_noirq or suspend_noirq callback. - * - * Stop the device and remove power from the domain if all devices in it have - * been stopped. - */ -static int genpd_finish_suspend(struct device *dev, bool poweroff) -{ - struct generic_pm_domain *genpd; - int ret = 0; - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - if (poweroff) - ret = pm_generic_poweroff_noirq(dev); - else - ret = pm_generic_suspend_noirq(dev); - if (ret) - return ret; - - if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd)) - return 0; - - if (genpd->dev_ops.stop && genpd->dev_ops.start && - !pm_runtime_status_suspended(dev)) { - ret = genpd_stop_dev(genpd, dev); - if (ret) { - if (poweroff) - pm_generic_restore_noirq(dev); - else - pm_generic_resume_noirq(dev); - return ret; - } - } - - genpd_lock(genpd); - genpd->suspended_count++; - genpd_sync_power_off(genpd, true, 0); - genpd_unlock(genpd); - - return 0; -} - -/** - * genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain. - * @dev: Device to suspend. - * - * Stop the device and remove power from the domain if all devices in it have - * been stopped. - */ -static int genpd_suspend_noirq(struct device *dev) -{ - dev_dbg(dev, "%s()\n", __func__); - - return genpd_finish_suspend(dev, false); -} - -/** - * genpd_resume_noirq - Start of resume of device in an I/O PM domain. - * @dev: Device to resume. - * - * Restore power to the device's PM domain, if necessary, and start the device. - */ -static int genpd_resume_noirq(struct device *dev) -{ - struct generic_pm_domain *genpd; - int ret; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd)) - return pm_generic_resume_noirq(dev); - - genpd_lock(genpd); - genpd_sync_power_on(genpd, true, 0); - genpd->suspended_count--; - genpd_unlock(genpd); - - if (genpd->dev_ops.stop && genpd->dev_ops.start && - !pm_runtime_status_suspended(dev)) { - ret = genpd_start_dev(genpd, dev); - if (ret) - return ret; - } - - return pm_generic_resume_noirq(dev); -} - -/** - * genpd_freeze_noirq - Completion of freezing a device in an I/O PM domain. - * @dev: Device to freeze. - * - * Carry out a late freeze of a device under the assumption that its - * pm_domain field points to the domain member of an object of type - * struct generic_pm_domain representing a power domain consisting of I/O - * devices. - */ -static int genpd_freeze_noirq(struct device *dev) -{ - const struct generic_pm_domain *genpd; - int ret = 0; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - ret = pm_generic_freeze_noirq(dev); - if (ret) - return ret; - - if (genpd->dev_ops.stop && genpd->dev_ops.start && - !pm_runtime_status_suspended(dev)) - ret = genpd_stop_dev(genpd, dev); - - return ret; -} - -/** - * genpd_thaw_noirq - Early thaw of device in an I/O PM domain. - * @dev: Device to thaw. - * - * Start the device, unless power has been removed from the domain already - * before the system transition. - */ -static int genpd_thaw_noirq(struct device *dev) -{ - const struct generic_pm_domain *genpd; - int ret = 0; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - if (genpd->dev_ops.stop && genpd->dev_ops.start && - !pm_runtime_status_suspended(dev)) { - ret = genpd_start_dev(genpd, dev); - if (ret) - return ret; - } - - return pm_generic_thaw_noirq(dev); -} - -/** - * genpd_poweroff_noirq - Completion of hibernation of device in an - * I/O PM domain. - * @dev: Device to poweroff. - * - * Stop the device and remove power from the domain if all devices in it have - * been stopped. - */ -static int genpd_poweroff_noirq(struct device *dev) -{ - dev_dbg(dev, "%s()\n", __func__); - - return genpd_finish_suspend(dev, true); -} - -/** - * genpd_restore_noirq - Start of restore of device in an I/O PM domain. - * @dev: Device to resume. - * - * Make sure the domain will be in the same power state as before the - * hibernation the system is resuming from and start the device if necessary. - */ -static int genpd_restore_noirq(struct device *dev) -{ - struct generic_pm_domain *genpd; - int ret = 0; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return -EINVAL; - - /* - * At this point suspended_count == 0 means we are being run for the - * first time for the given domain in the present cycle. - */ - genpd_lock(genpd); - if (genpd->suspended_count++ == 0) - /* - * The boot kernel might put the domain into arbitrary state, - * so make it appear as powered off to genpd_sync_power_on(), - * so that it tries to power it on in case it was really off. - */ - genpd->status = GPD_STATE_POWER_OFF; - - genpd_sync_power_on(genpd, true, 0); - genpd_unlock(genpd); - - if (genpd->dev_ops.stop && genpd->dev_ops.start && - !pm_runtime_status_suspended(dev)) { - ret = genpd_start_dev(genpd, dev); - if (ret) - return ret; - } - - return pm_generic_restore_noirq(dev); -} - -/** - * genpd_complete - Complete power transition of a device in a power domain. - * @dev: Device to complete the transition of. - * - * Complete a power transition of a device (during a system-wide power - * transition) under the assumption that its pm_domain field points to the - * domain member of an object of type struct generic_pm_domain representing - * a power domain consisting of I/O devices. - */ -static void genpd_complete(struct device *dev) -{ - struct generic_pm_domain *genpd; - - dev_dbg(dev, "%s()\n", __func__); - - genpd = dev_to_genpd(dev); - if (IS_ERR(genpd)) - return; - - pm_generic_complete(dev); - - genpd_lock(genpd); - - genpd->prepared_count--; - if (!genpd->prepared_count) - genpd_queue_power_off_work(genpd); - - genpd_unlock(genpd); -} - -/** - * genpd_syscore_switch - Switch power during system core suspend or resume. - * @dev: Device that normally is marked as "always on" to switch power for. - * - * This routine may only be called during the system core (syscore) suspend or - * resume phase for devices whose "always on" flags are set. - */ -static void genpd_syscore_switch(struct device *dev, bool suspend) -{ - struct generic_pm_domain *genpd; - - genpd = dev_to_genpd(dev); - if (!genpd_present(genpd)) - return; - - if (suspend) { - genpd->suspended_count++; - genpd_sync_power_off(genpd, false, 0); - } else { - genpd_sync_power_on(genpd, false, 0); - genpd->suspended_count--; - } -} - -void pm_genpd_syscore_poweroff(struct device *dev) -{ - genpd_syscore_switch(dev, true); -} -EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweroff); - -void pm_genpd_syscore_poweron(struct device *dev) -{ - genpd_syscore_switch(dev, false); -} -EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron); - -#else /* !CONFIG_PM_SLEEP */ - -#define genpd_prepare NULL -#define genpd_suspend_noirq NULL -#define genpd_resume_noirq NULL -#define genpd_freeze_noirq NULL -#define genpd_thaw_noirq NULL -#define genpd_poweroff_noirq NULL -#define genpd_restore_noirq NULL -#define genpd_complete NULL - -#endif /* CONFIG_PM_SLEEP */ - -static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, - struct gpd_timing_data *td) -{ - struct generic_pm_domain_data *gpd_data; - int ret; - - ret = dev_pm_get_subsys_data(dev); - if (ret) - return ERR_PTR(ret); - - gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); - if (!gpd_data) { - ret = -ENOMEM; - goto err_put; - } - - if (td) - gpd_data->td = *td; - - gpd_data->base.dev = dev; - gpd_data->td.constraint_changed = true; - gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; - gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; - - spin_lock_irq(&dev->power.lock); - - if (dev->power.subsys_data->domain_data) { - ret = -EINVAL; - goto err_free; - } - - dev->power.subsys_data->domain_data = &gpd_data->base; - - spin_unlock_irq(&dev->power.lock); - - return gpd_data; - - err_free: - spin_unlock_irq(&dev->power.lock); - kfree(gpd_data); - err_put: - dev_pm_put_subsys_data(dev); - return ERR_PTR(ret); -} - -static void genpd_free_dev_data(struct device *dev, - struct generic_pm_domain_data *gpd_data) -{ - spin_lock_irq(&dev->power.lock); - - dev->power.subsys_data->domain_data = NULL; - - spin_unlock_irq(&dev->power.lock); - - kfree(gpd_data); - dev_pm_put_subsys_data(dev); -} - -static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, - struct gpd_timing_data *td) -{ - struct generic_pm_domain_data *gpd_data; - int ret; - - dev_dbg(dev, "%s()\n", __func__); - - if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) - return -EINVAL; - - gpd_data = genpd_alloc_dev_data(dev, td); - if (IS_ERR(gpd_data)) - return PTR_ERR(gpd_data); - - genpd_lock(genpd); - - ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0; - if (ret) - goto out; - - dev_pm_domain_set(dev, &genpd->domain); - - genpd->device_count++; - genpd->max_off_time_changed = true; - - list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); - - out: - genpd_unlock(genpd); - - if (ret) - genpd_free_dev_data(dev, gpd_data); - else - dev_pm_qos_add_notifier(dev, &gpd_data->nb); - - return ret; -} - -/** - * pm_genpd_add_device - Add a device to an I/O PM domain. - * @genpd: PM domain to add the device to. - * @dev: Device to be added. - */ -int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) -{ - int ret; - - mutex_lock(&gpd_list_lock); - ret = genpd_add_device(genpd, dev, NULL); - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(pm_genpd_add_device); - -static int genpd_remove_device(struct generic_pm_domain *genpd, - struct device *dev) -{ - struct generic_pm_domain_data *gpd_data; - struct pm_domain_data *pdd; - int ret = 0; - - dev_dbg(dev, "%s()\n", __func__); - - pdd = dev->power.subsys_data->domain_data; - gpd_data = to_gpd_data(pdd); - dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - - genpd_lock(genpd); - - if (genpd->prepared_count > 0) { - ret = -EAGAIN; - goto out; - } - - genpd->device_count--; - genpd->max_off_time_changed = true; - - if (genpd->detach_dev) - genpd->detach_dev(genpd, dev); - - dev_pm_domain_set(dev, NULL); - - list_del_init(&pdd->list_node); - - genpd_unlock(genpd); - - genpd_free_dev_data(dev, gpd_data); - - return 0; - - out: - genpd_unlock(genpd); - dev_pm_qos_add_notifier(dev, &gpd_data->nb); - - return ret; -} - -/** - * pm_genpd_remove_device - Remove a device from an I/O PM domain. - * @dev: Device to be removed. - */ -int pm_genpd_remove_device(struct device *dev) -{ - struct generic_pm_domain *genpd = genpd_lookup_dev(dev); - - if (!genpd) - return -EINVAL; - - return genpd_remove_device(genpd, dev); -} -EXPORT_SYMBOL_GPL(pm_genpd_remove_device); - -static int genpd_add_subdomain(struct generic_pm_domain *genpd, - struct generic_pm_domain *subdomain) -{ - struct gpd_link *link, *itr; - int ret = 0; - - if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain) - || genpd == subdomain) - return -EINVAL; - - /* - * If the domain can be powered on/off in an IRQ safe - * context, ensure that the subdomain can also be - * powered on/off in that context. - */ - if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) { - WARN(1, "Parent %s of subdomain %s must be IRQ safe\n", - genpd->name, subdomain->name); - return -EINVAL; - } - - link = kzalloc(sizeof(*link), GFP_KERNEL); - if (!link) - return -ENOMEM; - - genpd_lock(subdomain); - genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); - - if (!genpd_status_on(genpd) && genpd_status_on(subdomain)) { - ret = -EINVAL; - goto out; - } - - list_for_each_entry(itr, &genpd->master_links, master_node) { - if (itr->slave == subdomain && itr->master == genpd) { - ret = -EINVAL; - goto out; - } - } - - link->master = genpd; - list_add_tail(&link->master_node, &genpd->master_links); - link->slave = subdomain; - list_add_tail(&link->slave_node, &subdomain->slave_links); - if (genpd_status_on(subdomain)) - genpd_sd_counter_inc(genpd); - - out: - genpd_unlock(genpd); - genpd_unlock(subdomain); - if (ret) - kfree(link); - return ret; -} - -/** - * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain. - * @genpd: Master PM domain to add the subdomain to. - * @subdomain: Subdomain to be added. - */ -int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, - struct generic_pm_domain *subdomain) -{ - int ret; - - mutex_lock(&gpd_list_lock); - ret = genpd_add_subdomain(genpd, subdomain); - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain); - -/** - * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain. - * @genpd: Master PM domain to remove the subdomain from. - * @subdomain: Subdomain to be removed. - */ -int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, - struct generic_pm_domain *subdomain) -{ - struct gpd_link *l, *link; - int ret = -EINVAL; - - if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) - return -EINVAL; - - genpd_lock(subdomain); - genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); - - if (!list_empty(&subdomain->master_links) || subdomain->device_count) { - pr_warn("%s: unable to remove subdomain %s\n", genpd->name, - subdomain->name); - ret = -EBUSY; - goto out; - } - - list_for_each_entry_safe(link, l, &genpd->master_links, master_node) { - if (link->slave != subdomain) - continue; - - list_del(&link->master_node); - list_del(&link->slave_node); - kfree(link); - if (genpd_status_on(subdomain)) - genpd_sd_counter_dec(genpd); - - ret = 0; - break; - } - -out: - genpd_unlock(genpd); - genpd_unlock(subdomain); - - return ret; -} -EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); - -static int genpd_set_default_power_state(struct generic_pm_domain *genpd) -{ - struct genpd_power_state *state; - - state = kzalloc(sizeof(*state), GFP_KERNEL); - if (!state) - return -ENOMEM; - - genpd->states = state; - genpd->state_count = 1; - genpd->free = state; - - return 0; -} - -static void genpd_lock_init(struct generic_pm_domain *genpd) -{ - if (genpd->flags & GENPD_FLAG_IRQ_SAFE) { - spin_lock_init(&genpd->slock); - genpd->lock_ops = &genpd_spin_ops; - } else { - mutex_init(&genpd->mlock); - genpd->lock_ops = &genpd_mtx_ops; - } -} - -/** - * pm_genpd_init - Initialize a generic I/O PM domain object. - * @genpd: PM domain object to initialize. - * @gov: PM domain governor to associate with the domain (may be NULL). - * @is_off: Initial value of the domain's power_is_off field. - * - * Returns 0 on successful initialization, else a negative error code. - */ -int pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off) -{ - int ret; - - if (IS_ERR_OR_NULL(genpd)) - return -EINVAL; - - INIT_LIST_HEAD(&genpd->master_links); - INIT_LIST_HEAD(&genpd->slave_links); - INIT_LIST_HEAD(&genpd->dev_list); - genpd_lock_init(genpd); - genpd->gov = gov; - INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn); - atomic_set(&genpd->sd_count, 0); - genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE; - genpd->device_count = 0; - genpd->max_off_time_ns = -1; - genpd->max_off_time_changed = true; - genpd->provider = NULL; - genpd->has_provider = false; - genpd->accounting_time = ktime_get(); - genpd->domain.ops.runtime_suspend = genpd_runtime_suspend; - genpd->domain.ops.runtime_resume = genpd_runtime_resume; - genpd->domain.ops.prepare = genpd_prepare; - genpd->domain.ops.suspend_noirq = genpd_suspend_noirq; - genpd->domain.ops.resume_noirq = genpd_resume_noirq; - genpd->domain.ops.freeze_noirq = genpd_freeze_noirq; - genpd->domain.ops.thaw_noirq = genpd_thaw_noirq; - genpd->domain.ops.poweroff_noirq = genpd_poweroff_noirq; - genpd->domain.ops.restore_noirq = genpd_restore_noirq; - genpd->domain.ops.complete = genpd_complete; - - if (genpd->flags & GENPD_FLAG_PM_CLK) { - genpd->dev_ops.stop = pm_clk_suspend; - genpd->dev_ops.start = pm_clk_resume; - } - - /* Always-on domains must be powered on at initialization. */ - if (genpd_is_always_on(genpd) && !genpd_status_on(genpd)) - return -EINVAL; - - /* Use only one "off" state if there were no states declared */ - if (genpd->state_count == 0) { - ret = genpd_set_default_power_state(genpd); - if (ret) - return ret; - } else if (!gov) { - pr_warn("%s : no governor for states\n", genpd->name); - } - - device_initialize(&genpd->dev); - dev_set_name(&genpd->dev, "%s", genpd->name); - - mutex_lock(&gpd_list_lock); - list_add(&genpd->gpd_list_node, &gpd_list); - mutex_unlock(&gpd_list_lock); - - return 0; -} -EXPORT_SYMBOL_GPL(pm_genpd_init); - -static int genpd_remove(struct generic_pm_domain *genpd) -{ - struct gpd_link *l, *link; - - if (IS_ERR_OR_NULL(genpd)) - return -EINVAL; - - genpd_lock(genpd); - - if (genpd->has_provider) { - genpd_unlock(genpd); - pr_err("Provider present, unable to remove %s\n", genpd->name); - return -EBUSY; - } - - if (!list_empty(&genpd->master_links) || genpd->device_count) { - genpd_unlock(genpd); - pr_err("%s: unable to remove %s\n", __func__, genpd->name); - return -EBUSY; - } - - list_for_each_entry_safe(link, l, &genpd->slave_links, slave_node) { - list_del(&link->master_node); - list_del(&link->slave_node); - kfree(link); - } - - list_del(&genpd->gpd_list_node); - genpd_unlock(genpd); - cancel_work_sync(&genpd->power_off_work); - kfree(genpd->free); - pr_debug("%s: removed %s\n", __func__, genpd->name); - - return 0; -} - -/** - * pm_genpd_remove - Remove a generic I/O PM domain - * @genpd: Pointer to PM domain that is to be removed. - * - * To remove the PM domain, this function: - * - Removes the PM domain as a subdomain to any parent domains, - * if it was added. - * - Removes the PM domain from the list of registered PM domains. - * - * The PM domain will only be removed, if the associated provider has - * been removed, it is not a parent to any other PM domain and has no - * devices associated with it. - */ -int pm_genpd_remove(struct generic_pm_domain *genpd) -{ - int ret; - - mutex_lock(&gpd_list_lock); - ret = genpd_remove(genpd); - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(pm_genpd_remove); - -#ifdef CONFIG_PM_GENERIC_DOMAINS_OF - -/* - * Device Tree based PM domain providers. - * - * The code below implements generic device tree based PM domain providers that - * bind device tree nodes with generic PM domains registered in the system. - * - * Any driver that registers generic PM domains and needs to support binding of - * devices to these domains is supposed to register a PM domain provider, which - * maps a PM domain specifier retrieved from the device tree to a PM domain. - * - * Two simple mapping functions have been provided for convenience: - * - genpd_xlate_simple() for 1:1 device tree node to PM domain mapping. - * - genpd_xlate_onecell() for mapping of multiple PM domains per node by - * index. - */ - -/** - * struct of_genpd_provider - PM domain provider registration structure - * @link: Entry in global list of PM domain providers - * @node: Pointer to device tree node of PM domain provider - * @xlate: Provider-specific xlate callback mapping a set of specifier cells - * into a PM domain. - * @data: context pointer to be passed into @xlate callback - */ -struct of_genpd_provider { - struct list_head link; - struct device_node *node; - genpd_xlate_t xlate; - void *data; -}; - -/* List of registered PM domain providers. */ -static LIST_HEAD(of_genpd_providers); -/* Mutex to protect the list above. */ -static DEFINE_MUTEX(of_genpd_mutex); - -/** - * genpd_xlate_simple() - Xlate function for direct node-domain mapping - * @genpdspec: OF phandle args to map into a PM domain - * @data: xlate function private data - pointer to struct generic_pm_domain - * - * This is a generic xlate function that can be used to model PM domains that - * have their own device tree nodes. The private data of xlate function needs - * to be a valid pointer to struct generic_pm_domain. - */ -static struct generic_pm_domain *genpd_xlate_simple( - struct of_phandle_args *genpdspec, - void *data) -{ - return data; -} - -/** - * genpd_xlate_onecell() - Xlate function using a single index. - * @genpdspec: OF phandle args to map into a PM domain - * @data: xlate function private data - pointer to struct genpd_onecell_data - * - * This is a generic xlate function that can be used to model simple PM domain - * controllers that have one device tree node and provide multiple PM domains. - * A single cell is used as an index into an array of PM domains specified in - * the genpd_onecell_data struct when registering the provider. - */ -static struct generic_pm_domain *genpd_xlate_onecell( - struct of_phandle_args *genpdspec, - void *data) -{ - struct genpd_onecell_data *genpd_data = data; - unsigned int idx = genpdspec->args[0]; - - if (genpdspec->args_count != 1) - return ERR_PTR(-EINVAL); - - if (idx >= genpd_data->num_domains) { - pr_err("%s: invalid domain index %u\n", __func__, idx); - return ERR_PTR(-EINVAL); - } - - if (!genpd_data->domains[idx]) - return ERR_PTR(-ENOENT); - - return genpd_data->domains[idx]; -} - -/** - * genpd_add_provider() - Register a PM domain provider for a node - * @np: Device node pointer associated with the PM domain provider. - * @xlate: Callback for decoding PM domain from phandle arguments. - * @data: Context pointer for @xlate callback. - */ -static int genpd_add_provider(struct device_node *np, genpd_xlate_t xlate, - void *data) -{ - struct of_genpd_provider *cp; - - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - return -ENOMEM; - - cp->node = of_node_get(np); - cp->data = data; - cp->xlate = xlate; - - mutex_lock(&of_genpd_mutex); - list_add(&cp->link, &of_genpd_providers); - mutex_unlock(&of_genpd_mutex); - pr_debug("Added domain provider from %pOF\n", np); - - return 0; -} - -/** - * of_genpd_add_provider_simple() - Register a simple PM domain provider - * @np: Device node pointer associated with the PM domain provider. - * @genpd: Pointer to PM domain associated with the PM domain provider. - */ -int of_genpd_add_provider_simple(struct device_node *np, - struct generic_pm_domain *genpd) -{ - int ret = -EINVAL; - - if (!np || !genpd) - return -EINVAL; - - mutex_lock(&gpd_list_lock); - - if (!genpd_present(genpd)) - goto unlock; - - genpd->dev.of_node = np; - - /* Parse genpd OPP table */ - if (genpd->set_performance_state) { - ret = dev_pm_opp_of_add_table(&genpd->dev); - if (ret) { - dev_err(&genpd->dev, "Failed to add OPP table: %d\n", - ret); - goto unlock; - } - - /* - * Save table for faster processing while setting performance - * state. - */ - genpd->opp_table = dev_pm_opp_get_opp_table(&genpd->dev); - WARN_ON(!genpd->opp_table); - } - - ret = genpd_add_provider(np, genpd_xlate_simple, genpd); - if (ret) { - if (genpd->set_performance_state) { - dev_pm_opp_put_opp_table(genpd->opp_table); - dev_pm_opp_of_remove_table(&genpd->dev); - } - - goto unlock; - } - - genpd->provider = &np->fwnode; - genpd->has_provider = true; - -unlock: - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(of_genpd_add_provider_simple); - -/** - * of_genpd_add_provider_onecell() - Register a onecell PM domain provider - * @np: Device node pointer associated with the PM domain provider. - * @data: Pointer to the data associated with the PM domain provider. - */ -int of_genpd_add_provider_onecell(struct device_node *np, - struct genpd_onecell_data *data) -{ - struct generic_pm_domain *genpd; - unsigned int i; - int ret = -EINVAL; - - if (!np || !data) - return -EINVAL; - - mutex_lock(&gpd_list_lock); - - if (!data->xlate) - data->xlate = genpd_xlate_onecell; - - for (i = 0; i < data->num_domains; i++) { - genpd = data->domains[i]; - - if (!genpd) - continue; - if (!genpd_present(genpd)) - goto error; - - genpd->dev.of_node = np; - - /* Parse genpd OPP table */ - if (genpd->set_performance_state) { - ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i); - if (ret) { - dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n", - i, ret); - goto error; - } - - /* - * Save table for faster processing while setting - * performance state. - */ - genpd->opp_table = dev_pm_opp_get_opp_table_indexed(&genpd->dev, i); - WARN_ON(!genpd->opp_table); - } - - genpd->provider = &np->fwnode; - genpd->has_provider = true; - } - - ret = genpd_add_provider(np, data->xlate, data); - if (ret < 0) - goto error; - - mutex_unlock(&gpd_list_lock); - - return 0; - -error: - while (i--) { - genpd = data->domains[i]; - - if (!genpd) - continue; - - genpd->provider = NULL; - genpd->has_provider = false; - - if (genpd->set_performance_state) { - dev_pm_opp_put_opp_table(genpd->opp_table); - dev_pm_opp_of_remove_table(&genpd->dev); - } - } - - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(of_genpd_add_provider_onecell); - -/** - * of_genpd_del_provider() - Remove a previously registered PM domain provider - * @np: Device node pointer associated with the PM domain provider - */ -void of_genpd_del_provider(struct device_node *np) -{ - struct of_genpd_provider *cp, *tmp; - struct generic_pm_domain *gpd; - - mutex_lock(&gpd_list_lock); - mutex_lock(&of_genpd_mutex); - list_for_each_entry_safe(cp, tmp, &of_genpd_providers, link) { - if (cp->node == np) { - /* - * For each PM domain associated with the - * provider, set the 'has_provider' to false - * so that the PM domain can be safely removed. - */ - list_for_each_entry(gpd, &gpd_list, gpd_list_node) { - if (gpd->provider == &np->fwnode) { - gpd->has_provider = false; - - if (!gpd->set_performance_state) - continue; - - dev_pm_opp_put_opp_table(gpd->opp_table); - dev_pm_opp_of_remove_table(&gpd->dev); - } - } - - list_del(&cp->link); - of_node_put(cp->node); - kfree(cp); - break; - } - } - mutex_unlock(&of_genpd_mutex); - mutex_unlock(&gpd_list_lock); -} -EXPORT_SYMBOL_GPL(of_genpd_del_provider); - -/** - * genpd_get_from_provider() - Look-up PM domain - * @genpdspec: OF phandle args to use for look-up - * - * Looks for a PM domain provider under the node specified by @genpdspec and if - * found, uses xlate function of the provider to map phandle args to a PM - * domain. - * - * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR() - * on failure. - */ -static struct generic_pm_domain *genpd_get_from_provider( - struct of_phandle_args *genpdspec) -{ - struct generic_pm_domain *genpd = ERR_PTR(-ENOENT); - struct of_genpd_provider *provider; - - if (!genpdspec) - return ERR_PTR(-EINVAL); - - mutex_lock(&of_genpd_mutex); - - /* Check if we have such a provider in our array */ - list_for_each_entry(provider, &of_genpd_providers, link) { - if (provider->node == genpdspec->np) - genpd = provider->xlate(genpdspec, provider->data); - if (!IS_ERR(genpd)) - break; - } - - mutex_unlock(&of_genpd_mutex); - - return genpd; -} - -/** - * of_genpd_add_device() - Add a device to an I/O PM domain - * @genpdspec: OF phandle args to use for look-up PM domain - * @dev: Device to be added. - * - * Looks-up an I/O PM domain based upon phandle args provided and adds - * the device to the PM domain. Returns a negative error code on failure. - */ -int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev) -{ - struct generic_pm_domain *genpd; - int ret; - - mutex_lock(&gpd_list_lock); - - genpd = genpd_get_from_provider(genpdspec); - if (IS_ERR(genpd)) { - ret = PTR_ERR(genpd); - goto out; - } - - ret = genpd_add_device(genpd, dev, NULL); - -out: - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(of_genpd_add_device); - -/** - * of_genpd_add_subdomain - Add a subdomain to an I/O PM domain. - * @parent_spec: OF phandle args to use for parent PM domain look-up - * @subdomain_spec: OF phandle args to use for subdomain look-up - * - * Looks-up a parent PM domain and subdomain based upon phandle args - * provided and adds the subdomain to the parent PM domain. Returns a - * negative error code on failure. - */ -int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, - struct of_phandle_args *subdomain_spec) -{ - struct generic_pm_domain *parent, *subdomain; - int ret; - - mutex_lock(&gpd_list_lock); - - parent = genpd_get_from_provider(parent_spec); - if (IS_ERR(parent)) { - ret = PTR_ERR(parent); - goto out; - } - - subdomain = genpd_get_from_provider(subdomain_spec); - if (IS_ERR(subdomain)) { - ret = PTR_ERR(subdomain); - goto out; - } - - ret = genpd_add_subdomain(parent, subdomain); - -out: - mutex_unlock(&gpd_list_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(of_genpd_add_subdomain); - -/** - * of_genpd_remove_last - Remove the last PM domain registered for a provider - * @provider: Pointer to device structure associated with provider - * - * Find the last PM domain that was added by a particular provider and - * remove this PM domain from the list of PM domains. The provider is - * identified by the 'provider' device structure that is passed. The PM - * domain will only be removed, if the provider associated with domain - * has been removed. - * - * Returns a valid pointer to struct generic_pm_domain on success or - * ERR_PTR() on failure. - */ -struct generic_pm_domain *of_genpd_remove_last(struct device_node *np) -{ - struct generic_pm_domain *gpd, *tmp, *genpd = ERR_PTR(-ENOENT); - int ret; - - if (IS_ERR_OR_NULL(np)) - return ERR_PTR(-EINVAL); - - mutex_lock(&gpd_list_lock); - list_for_each_entry_safe(gpd, tmp, &gpd_list, gpd_list_node) { - if (gpd->provider == &np->fwnode) { - ret = genpd_remove(gpd); - genpd = ret ? ERR_PTR(ret) : gpd; - break; - } - } - mutex_unlock(&gpd_list_lock); - - return genpd; -} -EXPORT_SYMBOL_GPL(of_genpd_remove_last); - -static void genpd_release_dev(struct device *dev) -{ - kfree(dev); -} - -static struct bus_type genpd_bus_type = { - .name = "genpd", -}; - -/** - * genpd_dev_pm_detach - Detach a device from its PM domain. - * @dev: Device to detach. - * @power_off: Currently not used - * - * Try to locate a corresponding generic PM domain, which the device was - * attached to previously. If such is found, the device is detached from it. - */ -static void genpd_dev_pm_detach(struct device *dev, bool power_off) -{ - struct generic_pm_domain *pd; - unsigned int i; - int ret = 0; - - pd = dev_to_genpd(dev); - if (IS_ERR(pd)) - return; - - dev_dbg(dev, "removing from PM domain %s\n", pd->name); - - for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) { - ret = genpd_remove_device(pd, dev); - if (ret != -EAGAIN) - break; - - mdelay(i); - cond_resched(); - } - - if (ret < 0) { - dev_err(dev, "failed to remove from PM domain %s: %d", - pd->name, ret); - return; - } - - /* Check if PM domain can be powered off after removing this device. */ - genpd_queue_power_off_work(pd); - - /* Unregister the device if it was created by genpd. */ - if (dev->bus == &genpd_bus_type) - device_unregister(dev); -} - -static void genpd_dev_pm_sync(struct device *dev) -{ - struct generic_pm_domain *pd; - - pd = dev_to_genpd(dev); - if (IS_ERR(pd)) - return; - - genpd_queue_power_off_work(pd); -} - -static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np, - unsigned int index, bool power_on) -{ - struct of_phandle_args pd_args; - struct generic_pm_domain *pd; - int ret; - - ret = of_parse_phandle_with_args(np, "power-domains", - "#power-domain-cells", index, &pd_args); - if (ret < 0) - return ret; - - mutex_lock(&gpd_list_lock); - pd = genpd_get_from_provider(&pd_args); - of_node_put(pd_args.np); - if (IS_ERR(pd)) { - mutex_unlock(&gpd_list_lock); - dev_dbg(dev, "%s() failed to find PM domain: %ld\n", - __func__, PTR_ERR(pd)); - return driver_deferred_probe_check_state(dev); - } - - dev_dbg(dev, "adding to PM domain %s\n", pd->name); - - ret = genpd_add_device(pd, dev, NULL); - mutex_unlock(&gpd_list_lock); - - if (ret < 0) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to add to PM domain %s: %d", - pd->name, ret); - return ret; - } - - dev->pm_domain->detach = genpd_dev_pm_detach; - dev->pm_domain->sync = genpd_dev_pm_sync; - - if (power_on) { - genpd_lock(pd); - ret = genpd_power_on(pd, 0); - genpd_unlock(pd); - } - - if (ret) - genpd_remove_device(pd, dev); - - return ret ? -EPROBE_DEFER : 1; -} - -/** - * genpd_dev_pm_attach - Attach a device to its PM domain using DT. - * @dev: Device to attach. - * - * Parse device's OF node to find a PM domain specifier. If such is found, - * attaches the device to retrieved pm_domain ops. - * - * Returns 1 on successfully attached PM domain, 0 when the device don't need a - * PM domain or when multiple power-domains exists for it, else a negative error - * code. Note that if a power-domain exists for the device, but it cannot be - * found or turned on, then return -EPROBE_DEFER to ensure that the device is - * not probed and to re-try again later. - */ -int genpd_dev_pm_attach(struct device *dev) -{ - if (!dev->of_node) - return 0; - - /* - * Devices with multiple PM domains must be attached separately, as we - * can only attach one PM domain per device. - */ - if (of_count_phandle_with_args(dev->of_node, "power-domains", - "#power-domain-cells") != 1) - return 0; - - return __genpd_dev_pm_attach(dev, dev->of_node, 0, true); -} -EXPORT_SYMBOL_GPL(genpd_dev_pm_attach); - -/** - * genpd_dev_pm_attach_by_id - Associate a device with one of its PM domains. - * @dev: The device used to lookup the PM domain. - * @index: The index of the PM domain. - * - * Parse device's OF node to find a PM domain specifier at the provided @index. - * If such is found, creates a virtual device and attaches it to the retrieved - * pm_domain ops. To deal with detaching of the virtual device, the ->detach() - * callback in the struct dev_pm_domain are assigned to genpd_dev_pm_detach(). - * - * Returns the created virtual device if successfully attached PM domain, NULL - * when the device don't need a PM domain, else an ERR_PTR() in case of - * failures. If a power-domain exists for the device, but cannot be found or - * turned on, then ERR_PTR(-EPROBE_DEFER) is returned to ensure that the device - * is not probed and to re-try again later. - */ -struct device *genpd_dev_pm_attach_by_id(struct device *dev, - unsigned int index) -{ - struct device *virt_dev; - int num_domains; - int ret; - - if (!dev->of_node) - return NULL; - - /* Deal only with devices using multiple PM domains. */ - num_domains = of_count_phandle_with_args(dev->of_node, "power-domains", - "#power-domain-cells"); - if (num_domains < 2 || index >= num_domains) - return NULL; - - /* Allocate and register device on the genpd bus. */ - virt_dev = kzalloc(sizeof(*virt_dev), GFP_KERNEL); - if (!virt_dev) - return ERR_PTR(-ENOMEM); - - dev_set_name(virt_dev, "genpd:%u:%s", index, dev_name(dev)); - virt_dev->bus = &genpd_bus_type; - virt_dev->release = genpd_release_dev; - - ret = device_register(virt_dev); - if (ret) { - kfree(virt_dev); - return ERR_PTR(ret); - } - - /* Try to attach the device to the PM domain at the specified index. */ - ret = __genpd_dev_pm_attach(virt_dev, dev->of_node, index, false); - if (ret < 1) { - device_unregister(virt_dev); - return ret ? ERR_PTR(ret) : NULL; - } - - pm_runtime_enable(virt_dev); - genpd_queue_power_off_work(dev_to_genpd(virt_dev)); - - return virt_dev; -} -EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id); - -/** - * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains. - * @dev: The device used to lookup the PM domain. - * @name: The name of the PM domain. - * - * Parse device's OF node to find a PM domain specifier using the - * power-domain-names DT property. For further description see - * genpd_dev_pm_attach_by_id(). - */ -struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name) -{ - int index; - - if (!dev->of_node) - return NULL; - - index = of_property_match_string(dev->of_node, "power-domain-names", - name); - if (index < 0) - return NULL; - - return genpd_dev_pm_attach_by_id(dev, index); -} - -static const struct of_device_id idle_state_match[] = { - { .compatible = "domain-idle-state", }, - { } -}; - -static int genpd_parse_state(struct genpd_power_state *genpd_state, - struct device_node *state_node) -{ - int err; - u32 residency; - u32 entry_latency, exit_latency; - - err = of_property_read_u32(state_node, "entry-latency-us", - &entry_latency); - if (err) { - pr_debug(" * %pOF missing entry-latency-us property\n", - state_node); - return -EINVAL; - } - - err = of_property_read_u32(state_node, "exit-latency-us", - &exit_latency); - if (err) { - pr_debug(" * %pOF missing exit-latency-us property\n", - state_node); - return -EINVAL; - } - - err = of_property_read_u32(state_node, "min-residency-us", &residency); - if (!err) - genpd_state->residency_ns = 1000 * residency; - - genpd_state->power_on_latency_ns = 1000 * exit_latency; - genpd_state->power_off_latency_ns = 1000 * entry_latency; - genpd_state->fwnode = &state_node->fwnode; - - return 0; -} - -static int genpd_iterate_idle_states(struct device_node *dn, - struct genpd_power_state *states) -{ - int ret; - struct of_phandle_iterator it; - struct device_node *np; - int i = 0; - - ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL); - if (ret <= 0) - return ret; - - /* Loop over the phandles until all the requested entry is found */ - of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) { - np = it.node; - if (!of_match_node(idle_state_match, np)) - continue; - if (states) { - ret = genpd_parse_state(&states[i], np); - if (ret) { - pr_err("Parsing idle state node %pOF failed with err %d\n", - np, ret); - of_node_put(np); - return ret; - } - } - i++; - } - - return i; -} - -/** - * of_genpd_parse_idle_states: Return array of idle states for the genpd. - * - * @dn: The genpd device node - * @states: The pointer to which the state array will be saved. - * @n: The count of elements in the array returned from this function. - * - * Returns the device states parsed from the OF node. The memory for the states - * is allocated by this function and is the responsibility of the caller to - * free the memory after use. If any or zero compatible domain idle states is - * found it returns 0 and in case of errors, a negative error code is returned. - */ -int of_genpd_parse_idle_states(struct device_node *dn, - struct genpd_power_state **states, int *n) -{ - struct genpd_power_state *st; - int ret; - - ret = genpd_iterate_idle_states(dn, NULL); - if (ret < 0) - return ret; - - if (!ret) { - *states = NULL; - *n = 0; - return 0; - } - - st = kcalloc(ret, sizeof(*st), GFP_KERNEL); - if (!st) - return -ENOMEM; - - ret = genpd_iterate_idle_states(dn, st); - if (ret <= 0) { - kfree(st); - return ret < 0 ? ret : -EINVAL; - } - - *states = st; - *n = ret; - - return 0; -} -EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states); - -/** - * pm_genpd_opp_to_performance_state - Gets performance state of the genpd from its OPP node. - * - * @genpd_dev: Genpd's device for which the performance-state needs to be found. - * @opp: struct dev_pm_opp of the OPP for which we need to find performance - * state. - * - * Returns performance state encoded in the OPP of the genpd. This calls - * platform specific genpd->opp_to_performance_state() callback to translate - * power domain OPP to performance state. - * - * Returns performance state on success and 0 on failure. - */ -unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev, - struct dev_pm_opp *opp) -{ - struct generic_pm_domain *genpd = NULL; - int state; - - genpd = container_of(genpd_dev, struct generic_pm_domain, dev); - - if (unlikely(!genpd->opp_to_performance_state)) - return 0; - - genpd_lock(genpd); - state = genpd->opp_to_performance_state(genpd, opp); - genpd_unlock(genpd); - - return state; -} -EXPORT_SYMBOL_GPL(pm_genpd_opp_to_performance_state); - -static int __init genpd_bus_init(void) -{ - return bus_register(&genpd_bus_type); -} -core_initcall(genpd_bus_init); - -#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */ - - -/*** debugfs support ***/ - -#ifdef CONFIG_DEBUG_FS -#include <linux/pm.h> -#include <linux/device.h> -#include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <linux/kobject.h> -static struct dentry *genpd_debugfs_dir; - -/* - * TODO: This function is a slightly modified version of rtpm_status_show - * from sysfs.c, so generalize it. - */ -static void rtpm_status_str(struct seq_file *s, struct device *dev) -{ - static const char * const status_lookup[] = { - [RPM_ACTIVE] = "active", - [RPM_RESUMING] = "resuming", - [RPM_SUSPENDED] = "suspended", - [RPM_SUSPENDING] = "suspending" - }; - const char *p = ""; - - if (dev->power.runtime_error) - p = "error"; - else if (dev->power.disable_depth) - p = "unsupported"; - else if (dev->power.runtime_status < ARRAY_SIZE(status_lookup)) - p = status_lookup[dev->power.runtime_status]; - else - WARN_ON(1); - - seq_puts(s, p); -} - -static int genpd_summary_one(struct seq_file *s, - struct generic_pm_domain *genpd) -{ - static const char * const status_lookup[] = { - [GPD_STATE_ACTIVE] = "on", - [GPD_STATE_POWER_OFF] = "off" - }; - struct pm_domain_data *pm_data; - const char *kobj_path; - struct gpd_link *link; - char state[16]; - int ret; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup))) - goto exit; - if (!genpd_status_on(genpd)) - snprintf(state, sizeof(state), "%s-%u", - status_lookup[genpd->status], genpd->state_idx); - else - snprintf(state, sizeof(state), "%s", - status_lookup[genpd->status]); - seq_printf(s, "%-30s %-15s ", genpd->name, state); - - /* - * Modifications on the list require holding locks on both - * master and slave, so we are safe. - * Also genpd->name is immutable. - */ - list_for_each_entry(link, &genpd->master_links, master_node) { - seq_printf(s, "%s", link->slave->name); - if (!list_is_last(&link->master_node, &genpd->master_links)) - seq_puts(s, ", "); - } - - list_for_each_entry(pm_data, &genpd->dev_list, list_node) { - kobj_path = kobject_get_path(&pm_data->dev->kobj, - genpd_is_irq_safe(genpd) ? - GFP_ATOMIC : GFP_KERNEL); - if (kobj_path == NULL) - continue; - - seq_printf(s, "\n %-50s ", kobj_path); - rtpm_status_str(s, pm_data->dev); - kfree(kobj_path); - } - - seq_puts(s, "\n"); -exit: - genpd_unlock(genpd); - - return 0; -} - -static int summary_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd; - int ret = 0; - - seq_puts(s, "domain status slaves\n"); - seq_puts(s, " /device runtime status\n"); - seq_puts(s, "----------------------------------------------------------------------\n"); - - ret = mutex_lock_interruptible(&gpd_list_lock); - if (ret) - return -ERESTARTSYS; - - list_for_each_entry(genpd, &gpd_list, gpd_list_node) { - ret = genpd_summary_one(s, genpd); - if (ret) - break; - } - mutex_unlock(&gpd_list_lock); - - return ret; -} - -static int status_show(struct seq_file *s, void *data) -{ - static const char * const status_lookup[] = { - [GPD_STATE_ACTIVE] = "on", - [GPD_STATE_POWER_OFF] = "off" - }; - - struct generic_pm_domain *genpd = s->private; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - if (WARN_ON_ONCE(genpd->status >= ARRAY_SIZE(status_lookup))) - goto exit; - - if (genpd->status == GPD_STATE_POWER_OFF) - seq_printf(s, "%s-%u\n", status_lookup[genpd->status], - genpd->state_idx); - else - seq_printf(s, "%s\n", status_lookup[genpd->status]); -exit: - genpd_unlock(genpd); - return ret; -} - -static int sub_domains_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - struct gpd_link *link; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - list_for_each_entry(link, &genpd->master_links, master_node) - seq_printf(s, "%s\n", link->slave->name); - - genpd_unlock(genpd); - return ret; -} - -static int idle_states_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - unsigned int i; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - seq_puts(s, "State Time Spent(ms)\n"); - - for (i = 0; i < genpd->state_count; i++) { - ktime_t delta = 0; - s64 msecs; - - if ((genpd->status == GPD_STATE_POWER_OFF) && - (genpd->state_idx == i)) - delta = ktime_sub(ktime_get(), genpd->accounting_time); - - msecs = ktime_to_ms( - ktime_add(genpd->states[i].idle_time, delta)); - seq_printf(s, "S%-13i %lld\n", i, msecs); - } - - genpd_unlock(genpd); - return ret; -} - -static int active_time_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - ktime_t delta = 0; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - if (genpd->status == GPD_STATE_ACTIVE) - delta = ktime_sub(ktime_get(), genpd->accounting_time); - - seq_printf(s, "%lld ms\n", ktime_to_ms( - ktime_add(genpd->on_time, delta))); - - genpd_unlock(genpd); - return ret; -} - -static int total_idle_time_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - ktime_t delta = 0, total = 0; - unsigned int i; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - for (i = 0; i < genpd->state_count; i++) { - - if ((genpd->status == GPD_STATE_POWER_OFF) && - (genpd->state_idx == i)) - delta = ktime_sub(ktime_get(), genpd->accounting_time); - - total = ktime_add(total, genpd->states[i].idle_time); - } - total = ktime_add(total, delta); - - seq_printf(s, "%lld ms\n", ktime_to_ms(total)); - - genpd_unlock(genpd); - return ret; -} - - -static int devices_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - struct pm_domain_data *pm_data; - const char *kobj_path; - int ret = 0; - - ret = genpd_lock_interruptible(genpd); - if (ret) - return -ERESTARTSYS; - - list_for_each_entry(pm_data, &genpd->dev_list, list_node) { - kobj_path = kobject_get_path(&pm_data->dev->kobj, - genpd_is_irq_safe(genpd) ? - GFP_ATOMIC : GFP_KERNEL); - if (kobj_path == NULL) - continue; - - seq_printf(s, "%s\n", kobj_path); - kfree(kobj_path); - } - - genpd_unlock(genpd); - return ret; -} - -static int perf_state_show(struct seq_file *s, void *data) -{ - struct generic_pm_domain *genpd = s->private; - - if (genpd_lock_interruptible(genpd)) - return -ERESTARTSYS; - - seq_printf(s, "%u\n", genpd->performance_state); - - genpd_unlock(genpd); - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(summary); -DEFINE_SHOW_ATTRIBUTE(status); -DEFINE_SHOW_ATTRIBUTE(sub_domains); -DEFINE_SHOW_ATTRIBUTE(idle_states); -DEFINE_SHOW_ATTRIBUTE(active_time); -DEFINE_SHOW_ATTRIBUTE(total_idle_time); -DEFINE_SHOW_ATTRIBUTE(devices); -DEFINE_SHOW_ATTRIBUTE(perf_state); - -static int __init genpd_debug_init(void) -{ - struct dentry *d; - struct generic_pm_domain *genpd; - - genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL); - - if (!genpd_debugfs_dir) - return -ENOMEM; - - d = debugfs_create_file("pm_genpd_summary", S_IRUGO, - genpd_debugfs_dir, NULL, &summary_fops); - if (!d) - return -ENOMEM; - - list_for_each_entry(genpd, &gpd_list, gpd_list_node) { - d = debugfs_create_dir(genpd->name, genpd_debugfs_dir); - if (!d) - return -ENOMEM; - - debugfs_create_file("current_state", 0444, - d, genpd, &status_fops); - debugfs_create_file("sub_domains", 0444, - d, genpd, &sub_domains_fops); - debugfs_create_file("idle_states", 0444, - d, genpd, &idle_states_fops); - debugfs_create_file("active_time", 0444, - d, genpd, &active_time_fops); - debugfs_create_file("total_idle_time", 0444, - d, genpd, &total_idle_time_fops); - debugfs_create_file("devices", 0444, - d, genpd, &devices_fops); - if (genpd->set_performance_state) - debugfs_create_file("perf_state", 0444, - d, genpd, &perf_state_fops); - } - - return 0; -} -late_initcall(genpd_debug_init); - -static void __exit genpd_debug_exit(void) -{ - debugfs_remove_recursive(genpd_debugfs_dir); -} -__exitcall(genpd_debug_exit); -#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c deleted file mode 100644 index 99896fbf18e4..000000000000 --- a/drivers/base/power/domain_governor.c +++ /dev/null @@ -1,259 +0,0 @@ -/* - * drivers/base/power/domain_governor.c - Governors for device PM domains. - * - * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp. - * - * This file is released under the GPLv2. - */ - -#include <linux/kernel.h> -#include <linux/pm_domain.h> -#include <linux/pm_qos.h> -#include <linux/hrtimer.h> - -static int dev_update_qos_constraint(struct device *dev, void *data) -{ - s64 *constraint_ns_p = data; - s64 constraint_ns; - - if (dev->power.subsys_data && dev->power.subsys_data->domain_data) { - /* - * Only take suspend-time QoS constraints of devices into - * account, because constraints updated after the device has - * been suspended are not guaranteed to be taken into account - * anyway. In order for them to take effect, the device has to - * be resumed and suspended again. - */ - constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns; - } else { - /* - * The child is not in a domain and there's no info on its - * suspend/resume latencies, so assume them to be negligible and - * take its current PM QoS constraint (that's the only thing - * known at this point anyway). - */ - constraint_ns = dev_pm_qos_read_value(dev); - constraint_ns *= NSEC_PER_USEC; - } - - if (constraint_ns < *constraint_ns_p) - *constraint_ns_p = constraint_ns; - - return 0; -} - -/** - * default_suspend_ok - Default PM domain governor routine to suspend devices. - * @dev: Device to check. - */ -static bool default_suspend_ok(struct device *dev) -{ - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; - unsigned long flags; - s64 constraint_ns; - - dev_dbg(dev, "%s()\n", __func__); - - spin_lock_irqsave(&dev->power.lock, flags); - - if (!td->constraint_changed) { - bool ret = td->cached_suspend_ok; - - spin_unlock_irqrestore(&dev->power.lock, flags); - return ret; - } - td->constraint_changed = false; - td->cached_suspend_ok = false; - td->effective_constraint_ns = 0; - constraint_ns = __dev_pm_qos_read_value(dev); - - spin_unlock_irqrestore(&dev->power.lock, flags); - - if (constraint_ns == 0) - return false; - - constraint_ns *= NSEC_PER_USEC; - /* - * We can walk the children without any additional locking, because - * they all have been suspended at this point and their - * effective_constraint_ns fields won't be modified in parallel with us. - */ - if (!dev->power.ignore_children) - device_for_each_child(dev, &constraint_ns, - dev_update_qos_constraint); - - if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS) { - /* "No restriction", so the device is allowed to suspend. */ - td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; - td->cached_suspend_ok = true; - } else if (constraint_ns == 0) { - /* - * This triggers if one of the children that don't belong to a - * domain has a zero PM QoS constraint and it's better not to - * suspend then. effective_constraint_ns is zero already and - * cached_suspend_ok is false, so bail out. - */ - return false; - } else { - constraint_ns -= td->suspend_latency_ns + - td->resume_latency_ns; - /* - * effective_constraint_ns is zero already and cached_suspend_ok - * is false, so if the computed value is not positive, return - * right away. - */ - if (constraint_ns <= 0) - return false; - - td->effective_constraint_ns = constraint_ns; - td->cached_suspend_ok = true; - } - - /* - * The children have been suspended already, so we don't need to take - * their suspend latencies into account here. - */ - return td->cached_suspend_ok; -} - -static bool __default_power_down_ok(struct dev_pm_domain *pd, - unsigned int state) -{ - struct generic_pm_domain *genpd = pd_to_genpd(pd); - struct gpd_link *link; - struct pm_domain_data *pdd; - s64 min_off_time_ns; - s64 off_on_time_ns; - - off_on_time_ns = genpd->states[state].power_off_latency_ns + - genpd->states[state].power_on_latency_ns; - - - min_off_time_ns = -1; - /* - * Check if subdomains can be off for enough time. - * - * All subdomains have been powered off already at this point. - */ - list_for_each_entry(link, &genpd->master_links, master_node) { - struct generic_pm_domain *sd = link->slave; - s64 sd_max_off_ns = sd->max_off_time_ns; - - if (sd_max_off_ns < 0) - continue; - - /* - * Check if the subdomain is allowed to be off long enough for - * the current domain to turn off and on (that's how much time - * it will have to wait worst case). - */ - if (sd_max_off_ns <= off_on_time_ns) - return false; - - if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0) - min_off_time_ns = sd_max_off_ns; - } - - /* - * Check if the devices in the domain can be off enough time. - */ - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - struct gpd_timing_data *td; - s64 constraint_ns; - - /* - * Check if the device is allowed to be off long enough for the - * domain to turn off and on (that's how much time it will - * have to wait worst case). - */ - td = &to_gpd_data(pdd)->td; - constraint_ns = td->effective_constraint_ns; - /* - * Zero means "no suspend at all" and this runs only when all - * devices in the domain are suspended, so it must be positive. - */ - if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS) - continue; - - if (constraint_ns <= off_on_time_ns) - return false; - - if (min_off_time_ns > constraint_ns || min_off_time_ns < 0) - min_off_time_ns = constraint_ns; - } - - /* - * If the computed minimum device off time is negative, there are no - * latency constraints, so the domain can spend arbitrary time in the - * "off" state. - */ - if (min_off_time_ns < 0) - return true; - - /* - * The difference between the computed minimum subdomain or device off - * time and the time needed to turn the domain on is the maximum - * theoretical time this domain can spend in the "off" state. - */ - genpd->max_off_time_ns = min_off_time_ns - - genpd->states[state].power_on_latency_ns; - return true; -} - -/** - * default_power_down_ok - Default generic PM domain power off governor routine. - * @pd: PM domain to check. - * - * This routine must be executed under the PM domain's lock. - */ -static bool default_power_down_ok(struct dev_pm_domain *pd) -{ - struct generic_pm_domain *genpd = pd_to_genpd(pd); - struct gpd_link *link; - - if (!genpd->max_off_time_changed) - return genpd->cached_power_down_ok; - - /* - * We have to invalidate the cached results for the masters, so - * use the observation that default_power_down_ok() is not - * going to be called for any master until this instance - * returns. - */ - list_for_each_entry(link, &genpd->slave_links, slave_node) - link->master->max_off_time_changed = true; - - genpd->max_off_time_ns = -1; - genpd->max_off_time_changed = false; - genpd->cached_power_down_ok = true; - genpd->state_idx = genpd->state_count - 1; - - /* Find a state to power down to, starting from the deepest. */ - while (!__default_power_down_ok(pd, genpd->state_idx)) { - if (genpd->state_idx == 0) { - genpd->cached_power_down_ok = false; - break; - } - genpd->state_idx--; - } - - return genpd->cached_power_down_ok; -} - -static bool always_on_power_down_ok(struct dev_pm_domain *domain) -{ - return false; -} - -struct dev_power_governor simple_qos_governor = { - .suspend_ok = default_suspend_ok, - .power_down_ok = default_power_down_ok, -}; - -/** - * pm_genpd_gov_always_on - A governor implementing an always-on policy - */ -struct dev_power_governor pm_domain_always_on_gov = { - .power_down_ok = always_on_power_down_ok, - .suspend_ok = default_suspend_ok, -}; diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c index b2ed606265a8..af99bbcf281c 100644 --- a/drivers/base/power/generic_ops.c +++ b/drivers/base/power/generic_ops.c @@ -1,15 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/generic_ops.c - Generic PM callbacks for subsystems * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. - * - * This file is released under the GPLv2. */ - #include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/export.h> +#define CALL_PM_OP(dev, op) \ +({ \ + struct device *_dev = (dev); \ + const struct dev_pm_ops *pm = _dev->driver ? _dev->driver->pm : NULL; \ + pm && pm->op ? pm->op(_dev) : 0; \ +}) + #ifdef CONFIG_PM /** * pm_generic_runtime_suspend - Generic runtime suspend callback for subsystems. @@ -21,12 +26,7 @@ */ int pm_generic_runtime_suspend(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int ret; - - ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0; - - return ret; + return CALL_PM_OP(dev, runtime_suspend); } EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend); @@ -40,12 +40,7 @@ EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend); */ int pm_generic_runtime_resume(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - int ret; - - ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0; - - return ret; + return CALL_PM_OP(dev, runtime_resume); } EXPORT_SYMBOL_GPL(pm_generic_runtime_resume); #endif /* CONFIG_PM */ @@ -74,9 +69,7 @@ int pm_generic_prepare(struct device *dev) */ int pm_generic_suspend_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend_noirq ? pm->suspend_noirq(dev) : 0; + return CALL_PM_OP(dev, suspend_noirq); } EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq); @@ -86,9 +79,7 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq); */ int pm_generic_suspend_late(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend_late ? pm->suspend_late(dev) : 0; + return CALL_PM_OP(dev, suspend_late); } EXPORT_SYMBOL_GPL(pm_generic_suspend_late); @@ -98,9 +89,7 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend_late); */ int pm_generic_suspend(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->suspend ? pm->suspend(dev) : 0; + return CALL_PM_OP(dev, suspend); } EXPORT_SYMBOL_GPL(pm_generic_suspend); @@ -110,33 +99,17 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend); */ int pm_generic_freeze_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->freeze_noirq ? pm->freeze_noirq(dev) : 0; + return CALL_PM_OP(dev, freeze_noirq); } EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq); /** - * pm_generic_freeze_late - Generic freeze_late callback for subsystems. - * @dev: Device to freeze. - */ -int pm_generic_freeze_late(struct device *dev) -{ - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->freeze_late ? pm->freeze_late(dev) : 0; -} -EXPORT_SYMBOL_GPL(pm_generic_freeze_late); - -/** * pm_generic_freeze - Generic freeze callback for subsystems. * @dev: Device to freeze. */ int pm_generic_freeze(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->freeze ? pm->freeze(dev) : 0; + return CALL_PM_OP(dev, freeze); } EXPORT_SYMBOL_GPL(pm_generic_freeze); @@ -146,9 +119,7 @@ EXPORT_SYMBOL_GPL(pm_generic_freeze); */ int pm_generic_poweroff_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff_noirq ? pm->poweroff_noirq(dev) : 0; + return CALL_PM_OP(dev, poweroff_noirq); } EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq); @@ -158,9 +129,7 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq); */ int pm_generic_poweroff_late(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff_late ? pm->poweroff_late(dev) : 0; + return CALL_PM_OP(dev, poweroff_late); } EXPORT_SYMBOL_GPL(pm_generic_poweroff_late); @@ -170,9 +139,7 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff_late); */ int pm_generic_poweroff(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->poweroff ? pm->poweroff(dev) : 0; + return CALL_PM_OP(dev, poweroff); } EXPORT_SYMBOL_GPL(pm_generic_poweroff); @@ -182,33 +149,17 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff); */ int pm_generic_thaw_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->thaw_noirq ? pm->thaw_noirq(dev) : 0; + return CALL_PM_OP(dev, thaw_noirq); } EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq); /** - * pm_generic_thaw_early - Generic thaw_early callback for subsystems. - * @dev: Device to thaw. - */ -int pm_generic_thaw_early(struct device *dev) -{ - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->thaw_early ? pm->thaw_early(dev) : 0; -} -EXPORT_SYMBOL_GPL(pm_generic_thaw_early); - -/** * pm_generic_thaw - Generic thaw callback for subsystems. * @dev: Device to thaw. */ int pm_generic_thaw(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->thaw ? pm->thaw(dev) : 0; + return CALL_PM_OP(dev, thaw); } EXPORT_SYMBOL_GPL(pm_generic_thaw); @@ -218,9 +169,7 @@ EXPORT_SYMBOL_GPL(pm_generic_thaw); */ int pm_generic_resume_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume_noirq ? pm->resume_noirq(dev) : 0; + return CALL_PM_OP(dev, resume_noirq); } EXPORT_SYMBOL_GPL(pm_generic_resume_noirq); @@ -230,9 +179,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume_noirq); */ int pm_generic_resume_early(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume_early ? pm->resume_early(dev) : 0; + return CALL_PM_OP(dev, resume_early); } EXPORT_SYMBOL_GPL(pm_generic_resume_early); @@ -242,9 +189,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume_early); */ int pm_generic_resume(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->resume ? pm->resume(dev) : 0; + return CALL_PM_OP(dev, resume); } EXPORT_SYMBOL_GPL(pm_generic_resume); @@ -254,9 +199,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume); */ int pm_generic_restore_noirq(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore_noirq ? pm->restore_noirq(dev) : 0; + return CALL_PM_OP(dev, restore_noirq); } EXPORT_SYMBOL_GPL(pm_generic_restore_noirq); @@ -266,9 +209,7 @@ EXPORT_SYMBOL_GPL(pm_generic_restore_noirq); */ int pm_generic_restore_early(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore_early ? pm->restore_early(dev) : 0; + return CALL_PM_OP(dev, restore_early); } EXPORT_SYMBOL_GPL(pm_generic_restore_early); @@ -278,9 +219,7 @@ EXPORT_SYMBOL_GPL(pm_generic_restore_early); */ int pm_generic_restore(struct device *dev) { - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - return pm && pm->restore ? pm->restore(dev) : 0; + return CALL_PM_OP(dev, restore); } EXPORT_SYMBOL_GPL(pm_generic_restore); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 0992e67e862b..97a8b4fcf471 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/main.c - Where the driver meets power management. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * - * This file is released under the GPLv2 - * - * * The driver model core calls device_pm_add() when a device is registered. * This will initialize the embedded device_pm_info object in the device * and add it to the list of power-controlled devices. sysfs entries for @@ -17,6 +15,9 @@ * subsystem list maintains. */ +#define pr_fmt(fmt) "PM: " fmt +#define dev_fmt pr_fmt + #include <linux/device.h> #include <linux/export.h> #include <linux/mutex.h> @@ -31,9 +32,9 @@ #include <linux/suspend.h> #include <trace/events/power.h> #include <linux/cpufreq.h> -#include <linux/cpuidle.h> #include <linux/devfreq.h> #include <linux/timer.h> +#include <linux/nmi.h> #include "../base.h" #include "power.h" @@ -56,12 +57,26 @@ static LIST_HEAD(dpm_suspended_list); static LIST_HEAD(dpm_late_early_list); static LIST_HEAD(dpm_noirq_list); -struct suspend_stats suspend_stats; static DEFINE_MUTEX(dpm_list_mtx); static pm_message_t pm_transition; +static DEFINE_MUTEX(async_wip_mtx); static int async_error; +/** + * pm_hibernate_is_recovering - if recovering from hibernate due to error. + * + * Used to query if dev_pm_ops.thaw() is called for normal hibernation case or + * recovering from some error. + * + * Return: true for error case, false for normal case. + */ +bool pm_hibernate_is_recovering(void) +{ + return pm_transition.event == PM_EVENT_RECOVER; +} +EXPORT_SYMBOL_GPL(pm_hibernate_is_recovering); + static const char *pm_verb(int event) { switch (event) { @@ -81,6 +96,8 @@ static const char *pm_verb(int event) return "restore"; case PM_EVENT_RECOVER: return "recover"; + case PM_EVENT_POWEROFF: + return "poweroff"; default: return "(unknown PM event)"; } @@ -124,7 +141,11 @@ void device_pm_unlock(void) */ void device_pm_add(struct device *dev) { - pr_debug("PM: Adding info for %s:%s\n", + /* Skip PM setup/initialization. */ + if (device_pm_not_required(dev)) + return; + + pr_debug("Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); device_pm_check_callbacks(dev); mutex_lock(&dpm_list_mtx); @@ -142,7 +163,10 @@ void device_pm_add(struct device *dev) */ void device_pm_remove(struct device *dev) { - pr_debug("PM: Removing info for %s:%s\n", + if (device_pm_not_required(dev)) + return; + + pr_debug("Removing info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); complete_all(&dev->power.completion); mutex_lock(&dpm_list_mtx); @@ -161,7 +185,7 @@ void device_pm_remove(struct device *dev) */ void device_pm_move_before(struct device *deva, struct device *devb) { - pr_debug("PM: Moving %s:%s before %s:%s\n", + pr_debug("Moving %s:%s before %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert before devb. */ @@ -175,7 +199,7 @@ void device_pm_move_before(struct device *deva, struct device *devb) */ void device_pm_move_after(struct device *deva, struct device *devb) { - pr_debug("PM: Moving %s:%s after %s:%s\n", + pr_debug("Moving %s:%s after %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert after devb. */ @@ -188,7 +212,7 @@ void device_pm_move_after(struct device *deva, struct device *devb) */ void device_pm_move_last(struct device *dev) { - pr_debug("PM: Moving %s:%s to end of list\n", + pr_debug("Moving %s:%s to end of list\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); list_move_tail(&dev->power.entry, &dpm_list); } @@ -198,7 +222,7 @@ static ktime_t initcall_debug_start(struct device *dev, void *cb) if (!pm_print_times_enabled) return 0; - dev_info(dev, "calling %pF @ %i, parent: %s\n", cb, + dev_info(dev, "calling %ps @ %i, parent: %s\n", cb, task_pid_nr(current), dev->parent ? dev_name(dev->parent) : "none"); return ktime_get(); @@ -208,16 +232,13 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime, void *cb, int error) { ktime_t rettime; - s64 nsecs; if (!pm_print_times_enabled) return; rettime = ktime_get(); - nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime)); - - dev_info(dev, "%pF returned %d after %Ld usecs\n", cb, error, - (unsigned long long)nsecs >> 10); + dev_info(dev, "%ps returned %d after %Ld usecs\n", cb, error, + (unsigned long long)ktime_us_delta(rettime, calltime)); } /** @@ -242,7 +263,7 @@ static int dpm_wait_fn(struct device *dev, void *async_ptr) static void dpm_wait_for_children(struct device *dev, bool async) { - device_for_each_child(dev, &async, dpm_wait_fn); + device_for_each_child(dev, &async, dpm_wait_fn); } static void dpm_wait_for_suppliers(struct device *dev, bool async) @@ -259,17 +280,46 @@ static void dpm_wait_for_suppliers(struct device *dev, bool async) * callbacks freeing the link objects for the links in the list we're * walking. */ - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dev_for_each_link_to_supplier(link, dev) + if (READ_ONCE(link->status) != DL_STATE_DORMANT && + !device_link_flag_is_sync_state_only(link->flags)) dpm_wait(link->supplier, async); device_links_read_unlock(idx); } -static void dpm_wait_for_superior(struct device *dev, bool async) +static bool dpm_wait_for_superior(struct device *dev, bool async) { - dpm_wait(dev->parent, async); + struct device *parent; + + /* + * If the device is resumed asynchronously and the parent's callback + * deletes both the device and the parent itself, the parent object may + * be freed while this function is running, so avoid that by reference + * counting the parent once more unless the device has been deleted + * already (in which case return right away). + */ + mutex_lock(&dpm_list_mtx); + + if (!device_pm_initialized(dev)) { + mutex_unlock(&dpm_list_mtx); + return false; + } + + parent = get_device(dev->parent); + + mutex_unlock(&dpm_list_mtx); + + dpm_wait(parent, async); + put_device(parent); + dpm_wait_for_suppliers(dev, async); + + /* + * If the parent's callback has deleted the device, attempting to resume + * it would be invalid, so avoid doing that then. + */ + return device_pm_initialized(dev); } static void dpm_wait_for_consumers(struct device *dev, bool async) @@ -288,8 +338,9 @@ static void dpm_wait_for_consumers(struct device *dev, bool async) * continue instead of trying to continue in parallel with its * unregistration). */ - list_for_each_entry_rcu(link, &dev->links.consumers, s_node) - if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dev_for_each_link_to_consumer(link, dev) + if (READ_ONCE(link->status) != DL_STATE_DORMANT && + !device_link_flag_is_sync_state_only(link->flags)) dpm_wait(link->consumer, async); device_links_read_unlock(idx); @@ -319,12 +370,12 @@ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state) case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw; - break; case PM_EVENT_RESTORE: return ops->restore; #endif /* CONFIG_HIBERNATE_CALLBACKS */ @@ -354,6 +405,7 @@ static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops, case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_late; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_late; case PM_EVENT_THAW: @@ -388,6 +440,7 @@ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t stat case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_noirq; + case PM_EVENT_POWEROFF: case PM_EVENT_HIBERNATE: return ops->poweroff_noirq; case PM_EVENT_THAW: @@ -403,16 +456,16 @@ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t stat static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info) { - dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event), + dev_dbg(dev, "%s%s%s driver flags: %x\n", info, pm_verb(state.event), ((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ? - ", may wakeup" : ""); + ", may wakeup" : "", dev->power.driver_flags); } static void pm_dev_err(struct device *dev, pm_message_t state, const char *info, int error) { - printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n", - dev_name(dev), pm_verb(state.event), info, error); + dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info, + error); } static void dpm_show_time(ktime_t starttime, pm_message_t state, int error, @@ -450,7 +503,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev, trace_device_pm_callback_start(dev, info, state.event); error = cb(dev); trace_device_pm_callback_end(dev, error); - suspend_report_result(cb, error); + suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); @@ -462,14 +515,20 @@ struct dpm_watchdog { struct device *dev; struct task_struct *tsk; struct timer_list timer; + bool fatal; }; #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ struct dpm_watchdog wd +static bool __read_mostly dpm_watchdog_all_cpu_backtrace; +module_param(dpm_watchdog_all_cpu_backtrace, bool, 0644); +MODULE_PARM_DESC(dpm_watchdog_all_cpu_backtrace, + "Backtrace all CPUs on DPM watchdog timeout"); + /** * dpm_watchdog_handler - Driver suspend / resume watchdog handler. - * @data: Watchdog object address. + * @t: The timer that PM watchdog depends on. * * Called when a driver has timed out suspending or resuming. * There's not much we can do here to recover so panic() to @@ -477,12 +536,28 @@ struct dpm_watchdog { */ static void dpm_watchdog_handler(struct timer_list *t) { - struct dpm_watchdog *wd = from_timer(wd, t, timer); + struct dpm_watchdog *wd = timer_container_of(wd, t, timer); + struct timer_list *timer = &wd->timer; + unsigned int time_left; + + if (wd->fatal) { + unsigned int this_cpu = smp_processor_id(); + + dev_emerg(wd->dev, "**** DPM device timeout ****\n"); + show_stack(wd->tsk, NULL, KERN_EMERG); + if (dpm_watchdog_all_cpu_backtrace) + trigger_allbutcpu_cpu_backtrace(this_cpu); + panic("%s %s: unrecoverable failure\n", + dev_driver_string(wd->dev), dev_name(wd->dev)); + } - dev_emerg(wd->dev, "**** DPM device timeout ****\n"); - show_stack(wd->tsk, NULL); - panic("%s %s: unrecoverable failure\n", - dev_driver_string(wd->dev), dev_name(wd->dev)); + time_left = CONFIG_DPM_WATCHDOG_TIMEOUT - CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; + dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n", + CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT, time_left); + show_stack(wd->tsk, NULL, KERN_WARNING); + + wd->fatal = true; + mod_timer(timer, jiffies + HZ * time_left); } /** @@ -496,10 +571,11 @@ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) wd->dev = dev; wd->tsk = current; + wd->fatal = CONFIG_DPM_WATCHDOG_TIMEOUT == CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ - timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; + timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT; add_timer(timer); } @@ -511,8 +587,8 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd) { struct timer_list *timer = &wd->timer; - del_timer_sync(timer); - destroy_timer_on_stack(timer); + timer_delete_sync(timer); + timer_destroy_on_stack(timer); } #else #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) @@ -523,86 +599,121 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd) /*------------------------- Resume routines -------------------------*/ /** - * dev_pm_skip_next_resume_phases - Skip next system resume phases for device. + * dev_pm_skip_resume - System-wide device resume optimization check. * @dev: Target device. * - * Make the core skip the "early resume" and "resume" phases for @dev. - * - * This function can be called by middle-layer code during the "noirq" phase of - * system resume if necessary, but not by device drivers. + * Return: + * - %false if the transition under way is RESTORE. + * - Return value of dev_pm_skip_suspend() if the transition under way is THAW. + * - The logical negation of %power.must_resume otherwise (that is, when the + * transition under way is RESUME). */ -void dev_pm_skip_next_resume_phases(struct device *dev) +bool dev_pm_skip_resume(struct device *dev) { - dev->power.is_late_suspended = false; - dev->power.is_suspended = false; + if (pm_transition.event == PM_EVENT_RESTORE) + return false; + + if (pm_transition.event == PM_EVENT_THAW) + return dev_pm_skip_suspend(dev); + + return !dev->power.must_resume; } -/** - * suspend_event - Return a "suspend" message for given "resume" one. - * @resume_msg: PM message representing a system-wide resume transition. - */ -static pm_message_t suspend_event(pm_message_t resume_msg) +static bool is_async(struct device *dev) { - switch (resume_msg.event) { - case PM_EVENT_RESUME: - return PMSG_SUSPEND; - case PM_EVENT_THAW: - case PM_EVENT_RESTORE: - return PMSG_FREEZE; - case PM_EVENT_RECOVER: - return PMSG_HIBERNATE; - } - return PMSG_ON; + return dev->power.async_suspend && pm_async_enabled + && !pm_trace_is_enabled(); } -/** - * dev_pm_may_skip_resume - System-wide device resume optimization check. - * @dev: Target device. - * - * Checks whether or not the device may be left in suspend after a system-wide - * transition to the working state. - */ -bool dev_pm_may_skip_resume(struct device *dev) +static bool __dpm_async(struct device *dev, async_func_t func) { - return !dev->power.must_resume && pm_transition.event != PM_EVENT_RESTORE; + if (dev->power.work_in_progress) + return true; + + if (!is_async(dev)) + return false; + + dev->power.work_in_progress = true; + + get_device(dev); + + if (async_schedule_dev_nocall(func, dev)) + return true; + + put_device(dev); + + return false; } -static pm_callback_t dpm_subsys_resume_noirq_cb(struct device *dev, - pm_message_t state, - const char **info_p) +static bool dpm_async_fn(struct device *dev, async_func_t func) { - pm_callback_t callback; - const char *info; + guard(mutex)(&async_wip_mtx); - if (dev->pm_domain) { - info = "noirq power domain "; - callback = pm_noirq_op(&dev->pm_domain->ops, state); - } else if (dev->type && dev->type->pm) { - info = "noirq type "; - callback = pm_noirq_op(dev->type->pm, state); - } else if (dev->class && dev->class->pm) { - info = "noirq class "; - callback = pm_noirq_op(dev->class->pm, state); - } else if (dev->bus && dev->bus->pm) { - info = "noirq bus "; - callback = pm_noirq_op(dev->bus->pm, state); - } else { - return NULL; - } + return __dpm_async(dev, func); +} + +static int dpm_async_with_cleanup(struct device *dev, void *fn) +{ + guard(mutex)(&async_wip_mtx); - if (info_p) - *info_p = info; + if (!__dpm_async(dev, fn)) + dev->power.work_in_progress = false; - return callback; + return 0; } -static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev, - pm_message_t state, - const char **info_p); +static void dpm_async_resume_children(struct device *dev, async_func_t func) +{ + /* + * Prevent racing with dpm_clear_async_state() during initial list + * walks in dpm_noirq_resume_devices(), dpm_resume_early(), and + * dpm_resume(). + */ + guard(mutex)(&dpm_list_mtx); -static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev, - pm_message_t state, - const char **info_p); + /* + * Start processing "async" children of the device unless it's been + * started already for them. + */ + device_for_each_child(dev, func, dpm_async_with_cleanup); +} + +static void dpm_async_resume_subordinate(struct device *dev, async_func_t func) +{ + struct device_link *link; + int idx; + + dpm_async_resume_children(dev, func); + + idx = device_links_read_lock(); + + /* Start processing the device's "async" consumers. */ + dev_for_each_link_to_consumer(link, dev) + if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dpm_async_with_cleanup(link->consumer, func); + + device_links_read_unlock(idx); +} + +static void dpm_clear_async_state(struct device *dev) +{ + reinit_completion(&dev->power.completion); + dev->power.work_in_progress = false; +} + +static bool dpm_root_device(struct device *dev) +{ + lockdep_assert_held(&dpm_list_mtx); + + /* + * Since this function is required to run under dpm_list_mtx, the + * list_empty() below will only return true if the device's list of + * consumers is actually empty before calling it. + */ + return !dev->parent && list_empty(&dev->links.suppliers); +} + +static void async_resume_noirq(void *data, async_cookie_t cookie); /** * device_resume_noirq - Execute a "noirq resume" callback for given device. @@ -613,10 +724,10 @@ static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev, * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_resume_noirq(struct device *dev, pm_message_t state, bool async) +static void device_resume_noirq(struct device *dev, pm_message_t state, bool async) { - pm_callback_t callback; - const char *info; + pm_callback_t callback = NULL; + const char *info = NULL; bool skip_resume; int error = 0; @@ -626,42 +737,59 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn if (dev->power.syscore || dev->power.direct_complete) goto Out; - if (!dev->power.is_noirq_suspended) + if (!dev->power.is_noirq_suspended) { + /* + * This means that system suspend has been aborted in the noirq + * phase before invoking the noirq suspend callback for the + * device, so if device_suspend_late() has left it in suspend, + * device_resume_early() should leave it in suspend either in + * case the early resume of it depends on the noirq resume that + * has not run. + */ + if (dev_pm_skip_suspend(dev)) + dev->power.must_resume = false; + goto Out; + } - dpm_wait_for_superior(dev, async); + if (!dpm_wait_for_superior(dev, async)) + goto Out; - skip_resume = dev_pm_may_skip_resume(dev); + skip_resume = dev_pm_skip_resume(dev); + /* + * If the driver callback is skipped below or by the middle layer + * callback and device_resume_early() also skips the driver callback for + * this device later, it needs to appear as "suspended" to PM-runtime, + * so change its status accordingly. + * + * Otherwise, the device is going to be resumed, so set its PM-runtime + * status to "active" unless its power.smart_suspend flag is clear, in + * which case it is not necessary to update its PM-runtime status. + */ + if (skip_resume) + pm_runtime_set_suspended(dev); + else if (dev_pm_smart_suspend(dev)) + pm_runtime_set_active(dev); - callback = dpm_subsys_resume_noirq_cb(dev, state, &info); + if (dev->pm_domain) { + info = "noirq power domain "; + callback = pm_noirq_op(&dev->pm_domain->ops, state); + } else if (dev->type && dev->type->pm) { + info = "noirq type "; + callback = pm_noirq_op(dev->type->pm, state); + } else if (dev->class && dev->class->pm) { + info = "noirq class "; + callback = pm_noirq_op(dev->class->pm, state); + } else if (dev->bus && dev->bus->pm) { + info = "noirq bus "; + callback = pm_noirq_op(dev->bus->pm, state); + } if (callback) goto Run; if (skip_resume) goto Skip; - if (dev_pm_smart_suspend_and_suspended(dev)) { - pm_message_t suspend_msg = suspend_event(state); - - /* - * If "freeze" callbacks have been skipped during a transition - * related to hibernation, the subsequent "thaw" callbacks must - * be skipped too or bad things may happen. Otherwise, resume - * callbacks are going to be run for the device, so its runtime - * PM status must be changed to reflect the new state after the - * transition under way. - */ - if (!dpm_subsys_suspend_late_cb(dev, suspend_msg, NULL) && - !dpm_subsys_suspend_noirq_cb(dev, suspend_msg, NULL)) { - if (state.event == PM_EVENT_THAW) { - skip_resume = true; - goto Skip; - } else { - pm_runtime_set_active(dev); - } - } - } - if (dev->driver && dev->driver->pm) { info = "noirq driver "; callback = pm_noirq_op(dev->driver->pm, state); @@ -673,96 +801,72 @@ Run: Skip: dev->power.is_noirq_suspended = false; - if (skip_resume) { - /* - * The device is going to be left in suspend, but it might not - * have been in runtime suspend before the system suspended, so - * its runtime PM status needs to be updated to avoid confusing - * the runtime PM framework when runtime PM is enabled for the - * device again. - */ - pm_runtime_set_suspended(dev); - dev_pm_skip_next_resume_phases(dev); - } - Out: complete_all(&dev->power.completion); TRACE_RESUME(error); - return error; -} -static bool is_async(struct device *dev) -{ - return dev->power.async_suspend && pm_async_enabled - && !pm_trace_is_enabled(); + if (error) { + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); + } + + dpm_async_resume_subordinate(dev, async_resume_noirq); } static void async_resume_noirq(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_noirq(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + device_resume_noirq(dev, pm_transition, true); put_device(dev); } -void dpm_noirq_resume_devices(pm_message_t state) +static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true); - mutex_lock(&dpm_list_mtx); + + async_error = 0; pm_transition = state; + mutex_lock(&dpm_list_mtx); + /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. + * Start processing "async" root devices upfront so they don't wait for + * the "sync" devices they don't depend on. */ list_for_each_entry(dev, &dpm_noirq_list, power.entry) { - reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule(async_resume_noirq, dev); - } + dpm_clear_async_state(dev); + if (dpm_root_device(dev)) + dpm_async_with_cleanup(dev, async_resume_noirq); } while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); - get_device(dev); list_move_tail(&dev->power.entry, &dpm_late_early_list); - mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; + if (!dpm_async_fn(dev, async_resume_noirq)) { + get_device(dev); - error = device_resume_noirq(dev, state, false); - if (error) { - suspend_stats.failed_resume_noirq++; - dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " noirq", error); - } - } + mutex_unlock(&dpm_list_mtx); - mutex_lock(&dpm_list_mtx); - put_device(dev); + device_resume_noirq(dev, state, false); + + put_device(dev); + + mutex_lock(&dpm_list_mtx); + } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "noirq"); - trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); -} + if (READ_ONCE(async_error)) + dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); -void dpm_noirq_end(void) -{ - resume_device_irqs(); - device_wakeup_disarm_wake_irqs(); - cpuidle_resume(); + trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); } /** @@ -775,38 +879,13 @@ void dpm_noirq_end(void) void dpm_resume_noirq(pm_message_t state) { dpm_noirq_resume_devices(state); - dpm_noirq_end(); -} -static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev, - pm_message_t state, - const char **info_p) -{ - pm_callback_t callback; - const char *info; - - if (dev->pm_domain) { - info = "early power domain "; - callback = pm_late_early_op(&dev->pm_domain->ops, state); - } else if (dev->type && dev->type->pm) { - info = "early type "; - callback = pm_late_early_op(dev->type->pm, state); - } else if (dev->class && dev->class->pm) { - info = "early class "; - callback = pm_late_early_op(dev->class->pm, state); - } else if (dev->bus && dev->bus->pm) { - info = "early bus "; - callback = pm_late_early_op(dev->bus->pm, state); - } else { - return NULL; - } - - if (info_p) - *info_p = info; - - return callback; + resume_device_irqs(); + device_wakeup_disarm_wake_irqs(); } +static void async_resume_early(void *data, async_cookie_t cookie); + /** * device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. @@ -815,50 +894,77 @@ static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev, * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_resume_early(struct device *dev, pm_message_t state, bool async) +static void device_resume_early(struct device *dev, pm_message_t state, bool async) { - pm_callback_t callback; - const char *info; + pm_callback_t callback = NULL; + const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); - if (dev->power.syscore || dev->power.direct_complete) + if (dev->power.direct_complete) goto Out; if (!dev->power.is_late_suspended) goto Out; - dpm_wait_for_superior(dev, async); + if (dev->power.syscore) + goto Skip; - callback = dpm_subsys_resume_early_cb(dev, state, &info); + if (!dpm_wait_for_superior(dev, async)) + goto Out; - if (!callback && dev->driver && dev->driver->pm) { + if (dev->pm_domain) { + info = "early power domain "; + callback = pm_late_early_op(&dev->pm_domain->ops, state); + } else if (dev->type && dev->type->pm) { + info = "early type "; + callback = pm_late_early_op(dev->type->pm, state); + } else if (dev->class && dev->class->pm) { + info = "early class "; + callback = pm_late_early_op(dev->class->pm, state); + } else if (dev->bus && dev->bus->pm) { + info = "early bus "; + callback = pm_late_early_op(dev->bus->pm, state); + } + if (callback) + goto Run; + + if (dev_pm_skip_resume(dev)) + goto Skip; + + if (dev->driver && dev->driver->pm) { info = "early driver "; callback = pm_late_early_op(dev->driver->pm, state); } +Run: error = dpm_run_callback(callback, dev, state, info); + +Skip: dev->power.is_late_suspended = false; + pm_runtime_enable(dev); - Out: +Out: TRACE_RESUME(error); - pm_runtime_enable(dev); complete_all(&dev->power.completion); - return error; + + if (error) { + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async early" : " early", error); + } + + dpm_async_resume_subordinate(dev, async_resume_early); } static void async_resume_early(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_early(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + device_resume_early(dev, pm_transition, true); put_device(dev); } @@ -872,45 +978,44 @@ void dpm_resume_early(pm_message_t state) ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_early"), state.event, true); - mutex_lock(&dpm_list_mtx); + + async_error = 0; pm_transition = state; + mutex_lock(&dpm_list_mtx); + /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. + * Start processing "async" root devices upfront so they don't wait for + * the "sync" devices they don't depend on. */ list_for_each_entry(dev, &dpm_late_early_list, power.entry) { - reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule(async_resume_early, dev); - } + dpm_clear_async_state(dev); + if (dpm_root_device(dev)) + dpm_async_with_cleanup(dev, async_resume_early); } while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); - get_device(dev); list_move_tail(&dev->power.entry, &dpm_suspended_list); - mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; + if (!dpm_async_fn(dev, async_resume_early)) { + get_device(dev); - error = device_resume_early(dev, state, false); - if (error) { - suspend_stats.failed_resume_early++; - dpm_save_failed_step(SUSPEND_RESUME_EARLY); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " early", error); - } + mutex_unlock(&dpm_list_mtx); + + device_resume_early(dev, state, false); + + put_device(dev); + + mutex_lock(&dpm_list_mtx); } - mutex_lock(&dpm_list_mtx); - put_device(dev); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "early"); + if (READ_ONCE(async_error)) + dpm_save_failed_step(SUSPEND_RESUME_EARLY); + trace_suspend_resume(TPS("dpm_resume_early"), state.event, false); } @@ -925,13 +1030,15 @@ void dpm_resume_start(pm_message_t state) } EXPORT_SYMBOL_GPL(dpm_resume_start); +static void async_resume(void *data, async_cookie_t cookie); + /** * device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ -static int device_resume(struct device *dev, pm_message_t state, bool async) +static void device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -944,13 +1051,27 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) if (dev->power.syscore) goto Complete; + if (!dev->power.is_suspended) + goto Complete; + + dev->power.is_suspended = false; + if (dev->power.direct_complete) { - /* Match the pm_runtime_disable() in __device_suspend(). */ + /* + * Allow new children to be added under the device after this + * point if it has no PM callbacks. + */ + if (dev->power.no_pm_callbacks) + dev->power.is_prepared = false; + + /* Match the pm_runtime_disable() in device_suspend(). */ pm_runtime_enable(dev); goto Complete; } - dpm_wait_for_superior(dev, async); + if (!dpm_wait_for_superior(dev, async)) + goto Complete; + dpm_watchdog_set(&wd, dev); device_lock(dev); @@ -960,9 +1081,6 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) */ dev->power.is_prepared = false; - if (!dev->power.is_suspended) - goto Unlock; - if (dev->pm_domain) { info = "power domain "; callback = pm_op(&dev->pm_domain->ops, state); @@ -1000,9 +1118,7 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) End: error = dpm_run_callback(callback, dev, state, info); - dev->power.is_suspended = false; - Unlock: device_unlock(dev); dpm_watchdog_clear(&wd); @@ -1011,17 +1127,20 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) TRACE_RESUME(error); - return error; + if (error) { + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } + + dpm_async_resume_subordinate(dev, async_resume); } static void async_resume(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; + struct device *dev = data; - error = device_resume(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + device_resume(dev, pm_transition, true); put_device(dev); } @@ -1038,45 +1157,43 @@ void dpm_resume(pm_message_t state) ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume"), state.event, true); - might_sleep(); - mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; + mutex_lock(&dpm_list_mtx); + + /* + * Start processing "async" root devices upfront so they don't wait for + * the "sync" devices they don't depend on. + */ list_for_each_entry(dev, &dpm_suspended_list, power.entry) { - reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule(async_resume, dev); - } + dpm_clear_async_state(dev); + if (dpm_root_device(dev)) + dpm_async_with_cleanup(dev, async_resume); } while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); - get_device(dev); - if (!is_async(dev)) { - int error; + list_move_tail(&dev->power.entry, &dpm_prepared_list); + + if (!dpm_async_fn(dev, async_resume)) { + get_device(dev); mutex_unlock(&dpm_list_mtx); - error = device_resume(dev, state, false); - if (error) { - suspend_stats.failed_resume++; - dpm_save_failed_step(SUSPEND_RESUME); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, "", error); - } + device_resume(dev, state, false); + + put_device(dev); mutex_lock(&dpm_list_mtx); } - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); - put_device(dev); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, NULL); + if (READ_ONCE(async_error)) + dpm_save_failed_step(SUSPEND_RESUME); cpufreq_resume(); devfreq_resume(); @@ -1094,7 +1211,7 @@ static void device_complete(struct device *dev, pm_message_t state) const char *info = NULL; if (dev->power.syscore) - return; + goto out; device_lock(dev); @@ -1124,6 +1241,9 @@ static void device_complete(struct device *dev, pm_message_t state) device_unlock(dev); +out: + /* If enabling runtime PM for the device is blocked, unblock it. */ + pm_runtime_unblock(dev); pm_runtime_put(dev); } @@ -1139,7 +1259,6 @@ void dpm_complete(pm_message_t state) struct list_head list; trace_suspend_resume(TPS("dpm_complete"), state.event, true); - might_sleep(); INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); @@ -1149,14 +1268,16 @@ void dpm_complete(pm_message_t state) get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); @@ -1176,6 +1297,7 @@ void dpm_complete(pm_message_t state) void dpm_resume_end(pm_message_t state) { dpm_resume(state); + pm_restore_gfp_mask(); dpm_complete(state); } EXPORT_SYMBOL_GPL(dpm_resume_end); @@ -1183,6 +1305,82 @@ EXPORT_SYMBOL_GPL(dpm_resume_end); /*------------------------- Suspend routines -------------------------*/ +static bool dpm_leaf_device(struct device *dev) +{ + struct device *child; + + lockdep_assert_held(&dpm_list_mtx); + + child = device_find_any_child(dev); + if (child) { + put_device(child); + + return false; + } + + /* + * Since this function is required to run under dpm_list_mtx, the + * list_empty() below will only return true if the device's list of + * consumers is actually empty before calling it. + */ + return list_empty(&dev->links.consumers); +} + +static bool dpm_async_suspend_parent(struct device *dev, async_func_t func) +{ + guard(mutex)(&dpm_list_mtx); + + /* + * If the device is suspended asynchronously and the parent's callback + * deletes both the device and the parent itself, the parent object may + * be freed while this function is running, so avoid that by checking + * if the device has been deleted already as the parent cannot be + * deleted before it. + */ + if (!device_pm_initialized(dev)) + return false; + + /* Start processing the device's parent if it is "async". */ + if (dev->parent) + dpm_async_with_cleanup(dev->parent, func); + + return true; +} + +static void dpm_async_suspend_superior(struct device *dev, async_func_t func) +{ + struct device_link *link; + int idx; + + if (!dpm_async_suspend_parent(dev, func)) + return; + + idx = device_links_read_lock(); + + /* Start processing the device's "async" suppliers. */ + dev_for_each_link_to_supplier(link, dev) + if (READ_ONCE(link->status) != DL_STATE_DORMANT) + dpm_async_with_cleanup(link->supplier, func); + + device_links_read_unlock(idx); +} + +static void dpm_async_suspend_complete_all(struct list_head *device_list) +{ + struct device *dev; + + guard(mutex)(&async_wip_mtx); + + list_for_each_entry_reverse(dev, device_list, power.entry) { + /* + * In case the device is being waited for and async processing + * has not started for it yet, let the waiters make progress. + */ + if (!dev->power.work_in_progress) + complete_all(&dev->power.completion); + } +} + /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. @@ -1214,69 +1412,16 @@ static void dpm_superior_set_must_resume(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) + dev_for_each_link_to_supplier(link, dev) link->supplier->power.must_resume = true; device_links_read_unlock(idx); } -static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev, - pm_message_t state, - const char **info_p) -{ - pm_callback_t callback; - const char *info; - - if (dev->pm_domain) { - info = "noirq power domain "; - callback = pm_noirq_op(&dev->pm_domain->ops, state); - } else if (dev->type && dev->type->pm) { - info = "noirq type "; - callback = pm_noirq_op(dev->type->pm, state); - } else if (dev->class && dev->class->pm) { - info = "noirq class "; - callback = pm_noirq_op(dev->class->pm, state); - } else if (dev->bus && dev->bus->pm) { - info = "noirq bus "; - callback = pm_noirq_op(dev->bus->pm, state); - } else { - return NULL; - } - - if (info_p) - *info_p = info; - - return callback; -} - -static bool device_must_resume(struct device *dev, pm_message_t state, - bool no_subsys_suspend_noirq) -{ - pm_message_t resume_msg = resume_event(state); - - /* - * If all of the device driver's "noirq", "late" and "early" callbacks - * are invoked directly by the core, the decision to allow the device to - * stay in suspend can be based on its current runtime PM status and its - * wakeup settings. - */ - if (no_subsys_suspend_noirq && - !dpm_subsys_suspend_late_cb(dev, state, NULL) && - !dpm_subsys_resume_early_cb(dev, resume_msg, NULL) && - !dpm_subsys_resume_noirq_cb(dev, resume_msg, NULL)) - return !pm_runtime_status_suspended(dev) && - (resume_msg.event != PM_EVENT_RESUME || - (device_can_wakeup(dev) && !device_may_wakeup(dev))); - - /* - * The only safe strategy here is to require that if the device may not - * be left in suspend, resume callbacks must be invoked for it. - */ - return !dev->power.may_skip_resume; -} +static void async_suspend_noirq(void *data, async_cookie_t cookie); /** - * __device_suspend_noirq - Execute a "noirq suspend" callback for given device. + * device_suspend_noirq - Execute a "noirq suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. @@ -1284,11 +1429,10 @@ static bool device_must_resume(struct device *dev, pm_message_t state, * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool async) +static void device_suspend_noirq(struct device *dev, pm_message_t state, bool async) { - pm_callback_t callback; - const char *info; - bool no_subsys_cb = false; + pm_callback_t callback = NULL; + const char *info = NULL; int error = 0; TRACE_DEVICE(dev); @@ -1296,24 +1440,29 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a dpm_wait_for_subordinate(dev, async); - if (async_error) + if (READ_ONCE(async_error)) goto Complete; - if (pm_wakeup_pending()) { - async_error = -EBUSY; - goto Complete; - } - if (dev->power.syscore || dev->power.direct_complete) goto Complete; - callback = dpm_subsys_suspend_noirq_cb(dev, state, &info); + if (dev->pm_domain) { + info = "noirq power domain "; + callback = pm_noirq_op(&dev->pm_domain->ops, state); + } else if (dev->type && dev->type->pm) { + info = "noirq type "; + callback = pm_noirq_op(dev->type->pm, state); + } else if (dev->class && dev->class->pm) { + info = "noirq class "; + callback = pm_noirq_op(dev->class->pm, state); + } else if (dev->bus && dev->bus->pm) { + info = "noirq bus "; + callback = pm_noirq_op(dev->bus->pm, state); + } if (callback) goto Run; - no_subsys_cb = !dpm_subsys_suspend_late_cb(dev, state, NULL); - - if (dev_pm_smart_suspend_and_suspended(dev) && no_subsys_cb) + if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { @@ -1324,20 +1473,24 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a Run: error = dpm_run_callback(callback, dev, state, info); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); goto Complete; } Skip: dev->power.is_noirq_suspended = true; - if (dev_pm_test_driver_flags(dev, DPM_FLAG_LEAVE_SUSPENDED)) { - dev->power.must_resume = dev->power.must_resume || - atomic_read(&dev->power.usage_count) > 1 || - device_must_resume(dev, state, no_subsys_cb); - } else { + /* + * Devices must be resumed unless they are explicitly allowed to be left + * in suspend, but even in that case skipping the resume of devices that + * were in use right before the system suspend (as indicated by their + * runtime PM usage counters and child counters) would be suboptimal. + */ + if (!(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) && + dev->power.may_skip_resume) || !pm_runtime_need_not_resume(dev)) dev->power.must_resume = true; - } if (dev->power.must_resume) dpm_superior_set_must_resume(dev); @@ -1345,83 +1498,81 @@ Skip: Complete: complete_all(&dev->power.completion); TRACE_SUSPEND(error); - return error; -} - -static void async_suspend_noirq(void *data, async_cookie_t cookie) -{ - struct device *dev = (struct device *)data; - int error; - error = __device_suspend_noirq(dev, pm_transition, true); - if (error) { - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, pm_transition, " async", error); - } + if (error || READ_ONCE(async_error)) + return; - put_device(dev); + dpm_async_suspend_superior(dev, async_suspend_noirq); } -static int device_suspend_noirq(struct device *dev) +static void async_suspend_noirq(void *data, async_cookie_t cookie) { - reinit_completion(&dev->power.completion); + struct device *dev = data; - if (is_async(dev)) { - get_device(dev); - async_schedule(async_suspend_noirq, dev); - return 0; - } - return __device_suspend_noirq(dev, pm_transition, false); -} - -void dpm_noirq_begin(void) -{ - cpuidle_pause(); - device_wakeup_arm_wake_irqs(); - suspend_device_irqs(); + device_suspend_noirq(dev, pm_transition, true); + put_device(dev); } -int dpm_noirq_suspend_devices(pm_message_t state) +static int dpm_noirq_suspend_devices(pm_message_t state) { ktime_t starttime = ktime_get(); - int error = 0; + struct device *dev; + int error; trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true); - mutex_lock(&dpm_list_mtx); + pm_transition = state; async_error = 0; + mutex_lock(&dpm_list_mtx); + + /* + * Start processing "async" leaf devices upfront so they don't need to + * wait for the "sync" devices they don't depend on. + */ + list_for_each_entry_reverse(dev, &dpm_late_early_list, power.entry) { + dpm_clear_async_state(dev); + if (dpm_leaf_device(dev)) + dpm_async_with_cleanup(dev, async_suspend_noirq); + } + while (!list_empty(&dpm_late_early_list)) { - struct device *dev = to_device(dpm_late_early_list.prev); + dev = to_device(dpm_late_early_list.prev); + + list_move(&dev->power.entry, &dpm_noirq_list); + + if (dpm_async_fn(dev, async_suspend_noirq)) + continue; get_device(dev); + mutex_unlock(&dpm_list_mtx); - error = device_suspend_noirq(dev); + device_suspend_noirq(dev, state, false); - mutex_lock(&dpm_list_mtx); - if (error) { - pm_dev_err(dev, state, " noirq", error); - dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_noirq_list); put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (READ_ONCE(async_error)) { + dpm_async_suspend_complete_all(&dpm_late_early_list); + /* + * Move all devices to the target list to resume them + * properly. + */ + list_splice_init(&dpm_late_early_list, &dpm_noirq_list); break; + } } + mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); - if (!error) - error = async_error; - if (error) { - suspend_stats.failed_suspend_noirq++; + error = READ_ONCE(async_error); + if (error) dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ); - } + dpm_show_time(starttime, state, error, "noirq"); trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false); return error; @@ -1438,7 +1589,9 @@ int dpm_suspend_noirq(pm_message_t state) { int ret; - dpm_noirq_begin(); + device_wakeup_arm_wake_irqs(); + suspend_device_irqs(); + ret = dpm_noirq_suspend_devices(state); if (ret) dpm_resume_noirq(resume_event(state)); @@ -1455,79 +1608,70 @@ static void dpm_propagate_wakeup_to_parent(struct device *dev) spin_lock_irq(&parent->power.lock); - if (dev->power.wakeup_path && !parent->power.ignore_children) + if (device_wakeup_path(dev) && !parent->power.ignore_children) parent->power.wakeup_path = true; spin_unlock_irq(&parent->power.lock); } -static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev, - pm_message_t state, - const char **info_p) -{ - pm_callback_t callback; - const char *info; - - if (dev->pm_domain) { - info = "late power domain "; - callback = pm_late_early_op(&dev->pm_domain->ops, state); - } else if (dev->type && dev->type->pm) { - info = "late type "; - callback = pm_late_early_op(dev->type->pm, state); - } else if (dev->class && dev->class->pm) { - info = "late class "; - callback = pm_late_early_op(dev->class->pm, state); - } else if (dev->bus && dev->bus->pm) { - info = "late bus "; - callback = pm_late_early_op(dev->bus->pm, state); - } else { - return NULL; - } - - if (info_p) - *info_p = info; - - return callback; -} +static void async_suspend_late(void *data, async_cookie_t cookie); /** - * __device_suspend_late - Execute a "late suspend" callback for given device. + * device_suspend_late - Execute a "late suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ -static int __device_suspend_late(struct device *dev, pm_message_t state, bool async) +static void device_suspend_late(struct device *dev, pm_message_t state, bool async) { - pm_callback_t callback; - const char *info; + pm_callback_t callback = NULL; + const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_SUSPEND(0); - __pm_runtime_disable(dev, false); - dpm_wait_for_subordinate(dev, async); - if (async_error) + if (READ_ONCE(async_error)) goto Complete; if (pm_wakeup_pending()) { - async_error = -EBUSY; + WRITE_ONCE(async_error, -EBUSY); goto Complete; } - if (dev->power.syscore || dev->power.direct_complete) + if (dev->power.direct_complete) goto Complete; - callback = dpm_subsys_suspend_late_cb(dev, state, &info); + /* + * Disable runtime PM for the device without checking if there is a + * pending resume request for it. + */ + __pm_runtime_disable(dev, false); + + if (dev->power.syscore) + goto Skip; + + if (dev->pm_domain) { + info = "late power domain "; + callback = pm_late_early_op(&dev->pm_domain->ops, state); + } else if (dev->type && dev->type->pm) { + info = "late type "; + callback = pm_late_early_op(dev->type->pm, state); + } else if (dev->class && dev->class->pm) { + info = "late class "; + callback = pm_late_early_op(dev->class->pm, state); + } else if (dev->bus && dev->bus->pm) { + info = "late bus "; + callback = pm_late_early_op(dev->bus->pm, state); + } if (callback) goto Run; - if (dev_pm_smart_suspend_and_suspended(dev) && - !dpm_subsys_suspend_noirq_cb(dev, state, NULL)) + if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { @@ -1538,7 +1682,10 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as Run: error = dpm_run_callback(callback, dev, state, info); if (error) { - async_error = error; + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async late" : " late", error); + pm_runtime_enable(dev); goto Complete; } dpm_propagate_wakeup_to_parent(dev); @@ -1549,33 +1696,19 @@ Skip: Complete: TRACE_SUSPEND(error); complete_all(&dev->power.completion); - return error; -} -static void async_suspend_late(void *data, async_cookie_t cookie) -{ - struct device *dev = (struct device *)data; - int error; + if (error || READ_ONCE(async_error)) + return; - error = __device_suspend_late(dev, pm_transition, true); - if (error) { - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, pm_transition, " async", error); - } - put_device(dev); + dpm_async_suspend_superior(dev, async_suspend_late); } -static int device_suspend_late(struct device *dev) +static void async_suspend_late(void *data, async_cookie_t cookie) { - reinit_completion(&dev->power.completion); - - if (is_async(dev)) { - get_device(dev); - async_schedule(async_suspend_late, dev); - return 0; - } + struct device *dev = data; - return __device_suspend_late(dev, pm_transition, false); + device_suspend_late(dev, pm_transition, true); + put_device(dev); } /** @@ -1585,42 +1718,63 @@ static int device_suspend_late(struct device *dev) int dpm_suspend_late(pm_message_t state) { ktime_t starttime = ktime_get(); - int error = 0; + struct device *dev; + int error; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); - mutex_lock(&dpm_list_mtx); + pm_transition = state; async_error = 0; + wake_up_all_idle_cpus(); + + mutex_lock(&dpm_list_mtx); + + /* + * Start processing "async" leaf devices upfront so they don't need to + * wait for the "sync" devices they don't depend on. + */ + list_for_each_entry_reverse(dev, &dpm_suspended_list, power.entry) { + dpm_clear_async_state(dev); + if (dpm_leaf_device(dev)) + dpm_async_with_cleanup(dev, async_suspend_late); + } + while (!list_empty(&dpm_suspended_list)) { - struct device *dev = to_device(dpm_suspended_list.prev); + dev = to_device(dpm_suspended_list.prev); + + list_move(&dev->power.entry, &dpm_late_early_list); + + if (dpm_async_fn(dev, async_suspend_late)) + continue; get_device(dev); + mutex_unlock(&dpm_list_mtx); - error = device_suspend_late(dev); + device_suspend_late(dev, state, false); + + put_device(dev); mutex_lock(&dpm_list_mtx); - if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_late_early_list); - if (error) { - pm_dev_err(dev, state, " late", error); - dpm_save_failed_dev(dev_name(dev)); - put_device(dev); + if (READ_ONCE(async_error)) { + dpm_async_suspend_complete_all(&dpm_suspended_list); + /* + * Move all devices to the target list to resume them + * properly. + */ + list_splice_init(&dpm_suspended_list, &dpm_late_early_list); break; } - put_device(dev); - - if (async_error) - break; } + mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); - if (!error) - error = async_error; + + error = READ_ONCE(async_error); if (error) { - suspend_stats.failed_suspend_late++; dpm_save_failed_step(SUSPEND_SUSPEND_LATE); dpm_resume_early(resume_event(state)); } @@ -1635,17 +1789,20 @@ int dpm_suspend_late(pm_message_t state) */ int dpm_suspend_end(pm_message_t state) { - int error = dpm_suspend_late(state); + ktime_t starttime = ktime_get(); + int error; + + error = dpm_suspend_late(state); if (error) - return error; + goto out; error = dpm_suspend_noirq(state); - if (error) { + if (error) dpm_resume_early(resume_event(state)); - return error; - } - return 0; +out: + dpm_show_time(starttime, state, error, "end"); + return error; } EXPORT_SYMBOL_GPL(dpm_suspend_end); @@ -1668,7 +1825,7 @@ static int legacy_suspend(struct device *dev, pm_message_t state, trace_device_pm_callback_start(dev, info, state.event); error = cb(dev, state); trace_device_pm_callback_end(dev, error); - suspend_report_result(cb, error); + suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); @@ -1688,7 +1845,7 @@ static void dpm_clear_superiors_direct_complete(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + dev_for_each_link_to_supplier(link, dev) { spin_lock_irq(&link->supplier->power.lock); link->supplier->power.direct_complete = false; spin_unlock_irq(&link->supplier->power.lock); @@ -1697,13 +1854,15 @@ static void dpm_clear_superiors_direct_complete(struct device *dev) device_links_read_unlock(idx); } +static void async_suspend(void *data, async_cookie_t cookie); + /** - * __device_suspend - Execute "suspend" callbacks for given device. + * device_suspend - Execute "suspend" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. */ -static int __device_suspend(struct device *dev, pm_message_t state, bool async) +static void device_suspend(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -1715,42 +1874,53 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_subordinate(dev, async); - if (async_error) { + if (READ_ONCE(async_error)) { dev->power.direct_complete = false; goto Complete; } /* - * If a device configured to wake up the system from sleep states - * has been suspended at run time and there's a resume request pending - * for it, this is equivalent to the device signaling wakeup, so the - * system suspend operation should be aborted. + * Wait for possible runtime PM transitions of the device in progress + * to complete and if there's a runtime resume request pending for it, + * resume it before proceeding with invoking the system-wide suspend + * callbacks for it. + * + * If the system-wide suspend callbacks below change the configuration + * of the device, they must disable runtime PM for it or otherwise + * ensure that its runtime-resume callbacks will not be confused by that + * change in case they are invoked going forward. */ - if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) - pm_wakeup_event(dev, 0); + pm_runtime_barrier(dev); if (pm_wakeup_pending()) { dev->power.direct_complete = false; - async_error = -EBUSY; + WRITE_ONCE(async_error, -EBUSY); goto Complete; } if (dev->power.syscore) goto Complete; + /* Avoid direct_complete to let wakeup_path propagate. */ + if (device_may_wakeup(dev) || device_wakeup_path(dev)) + dev->power.direct_complete = false; + if (dev->power.direct_complete) { if (pm_runtime_status_suspended(dev)) { pm_runtime_disable(dev); - if (pm_runtime_status_suspended(dev)) + if (pm_runtime_status_suspended(dev)) { + pm_dev_dbg(dev, state, "direct-complete "); + dev->power.is_suspended = true; goto Complete; + } pm_runtime_enable(dev); } dev->power.direct_complete = false; } - dev->power.may_skip_resume = false; - dev->power.must_resume = false; + dev->power.may_skip_resume = true; + dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME); dpm_watchdog_set(&wd, dev); device_lock(dev); @@ -1807,39 +1977,27 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_watchdog_clear(&wd); Complete: - if (error) - async_error = error; + if (error) { + WRITE_ONCE(async_error, error); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } complete_all(&dev->power.completion); TRACE_SUSPEND(error); - return error; -} - -static void async_suspend(void *data, async_cookie_t cookie) -{ - struct device *dev = (struct device *)data; - int error; - error = __device_suspend(dev, pm_transition, true); - if (error) { - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, pm_transition, " async", error); - } + if (error || READ_ONCE(async_error)) + return; - put_device(dev); + dpm_async_suspend_superior(dev, async_suspend); } -static int device_suspend(struct device *dev) +static void async_suspend(void *data, async_cookie_t cookie) { - reinit_completion(&dev->power.completion); - - if (is_async(dev)) { - get_device(dev); - async_schedule(async_suspend, dev); - return 0; - } + struct device *dev = data; - return __device_suspend(dev, pm_transition, false); + device_suspend(dev, pm_transition, true); + put_device(dev); } /** @@ -1849,7 +2007,8 @@ static int device_suspend(struct device *dev) int dpm_suspend(pm_message_t state) { ktime_t starttime = ktime_get(); - int error = 0; + struct device *dev; + int error; trace_suspend_resume(TPS("dpm_suspend"), state.event, true); might_sleep(); @@ -1857,43 +2016,103 @@ int dpm_suspend(pm_message_t state) devfreq_suspend(); cpufreq_suspend(); - mutex_lock(&dpm_list_mtx); pm_transition = state; async_error = 0; + + mutex_lock(&dpm_list_mtx); + + /* + * Start processing "async" leaf devices upfront so they don't need to + * wait for the "sync" devices they don't depend on. + */ + list_for_each_entry_reverse(dev, &dpm_prepared_list, power.entry) { + dpm_clear_async_state(dev); + if (dpm_leaf_device(dev)) + dpm_async_with_cleanup(dev, async_suspend); + } + while (!list_empty(&dpm_prepared_list)) { - struct device *dev = to_device(dpm_prepared_list.prev); + dev = to_device(dpm_prepared_list.prev); + + list_move(&dev->power.entry, &dpm_suspended_list); + + if (dpm_async_fn(dev, async_suspend)) + continue; get_device(dev); + mutex_unlock(&dpm_list_mtx); - error = device_suspend(dev); + device_suspend(dev, state, false); + + put_device(dev); mutex_lock(&dpm_list_mtx); - if (error) { - pm_dev_err(dev, state, "", error); - dpm_save_failed_dev(dev_name(dev)); - put_device(dev); + + if (READ_ONCE(async_error)) { + dpm_async_suspend_complete_all(&dpm_prepared_list); + /* + * Move all devices to the target list to resume them + * properly. + */ + list_splice_init(&dpm_prepared_list, &dpm_suspended_list); break; } - if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_suspended_list); - put_device(dev); - if (async_error) - break; } + mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); - if (!error) - error = async_error; - if (error) { - suspend_stats.failed_suspend++; + + error = READ_ONCE(async_error); + if (error) dpm_save_failed_step(SUSPEND_SUSPEND); - } + dpm_show_time(starttime, state, error, NULL); trace_suspend_resume(TPS("dpm_suspend"), state.event, false); return error; } +static bool device_prepare_smart_suspend(struct device *dev) +{ + struct device_link *link; + bool ret = true; + int idx; + + /* + * The "smart suspend" feature is enabled for devices whose drivers ask + * for it and for devices without PM callbacks. + * + * However, if "smart suspend" is not enabled for the device's parent + * or any of its suppliers that take runtime PM into account, it cannot + * be enabled for the device either. + */ + if (!dev->power.no_pm_callbacks && + !dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) + return false; + + if (dev->parent && !dev_pm_smart_suspend(dev->parent) && + !dev->parent->power.ignore_children && !pm_runtime_blocked(dev->parent)) + return false; + + idx = device_links_read_lock(); + + dev_for_each_link_to_supplier(link, dev) { + if (!device_link_test(link, DL_FLAG_PM_RUNTIME)) + continue; + + if (!dev_pm_smart_suspend(link->supplier) && + !pm_runtime_blocked(link->supplier)) { + ret = false; + break; + } + } + + device_links_read_unlock(idx); + + return ret; +} + /** * device_prepare - Prepare a device for system power transition. * @dev: Device to handle. @@ -1905,15 +2124,9 @@ int dpm_suspend(pm_message_t state) static int device_prepare(struct device *dev, pm_message_t state) { int (*callback)(struct device *) = NULL; + bool smart_suspend; int ret = 0; - if (dev->power.syscore) - return 0; - - WARN_ON(!pm_runtime_enabled(dev) && - dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND | - DPM_FLAG_LEAVE_SUSPENDED)); - /* * If a device's parent goes into runtime suspend at the wrong time, * it won't be possible to resume the device. To prevent this we @@ -1921,10 +2134,21 @@ static int device_prepare(struct device *dev, pm_message_t state) * it again during the complete phase. */ pm_runtime_get_noresume(dev); + /* + * If runtime PM is disabled for the device at this point and it has + * never been enabled so far, it should not be enabled until this system + * suspend-resume cycle is complete, so prepare to trigger a warning on + * subsequent attempts to enable it. + */ + smart_suspend = !pm_runtime_block_if_disabled(dev); + + if (dev->power.syscore) + return 0; device_lock(dev); dev->power.wakeup_path = false; + dev->power.out_band_wakeup = false; if (dev->power.no_pm_callbacks) goto unlock; @@ -1948,10 +2172,17 @@ unlock: device_unlock(dev); if (ret < 0) { - suspend_report_result(callback, ret); + suspend_report_result(dev, callback, ret); pm_runtime_put(dev); return ret; } + /* Do not enable "smart suspend" for devices with disabled runtime PM. */ + if (smart_suspend) + smart_suspend = device_prepare_smart_suspend(dev); + + spin_lock_irq(&dev->power.lock); + + dev->power.smart_suspend = smart_suspend; /* * A positive return value from ->prepare() means "this device appears * to be runtime-suspended and its state is fine, so if it really is @@ -1959,12 +2190,12 @@ unlock: * will do the same thing with all of its descendants". This only * applies to suspend transitions, however. */ - spin_lock_irq(&dev->power.lock); dev->power.direct_complete = state.event == PM_EVENT_SUSPEND && - ((pm_runtime_suspended(dev) && ret > 0) || - dev->power.no_pm_callbacks) && - !dev_pm_test_driver_flags(dev, DPM_FLAG_NEVER_SKIP); + (ret > 0 || dev->power.no_pm_callbacks) && + !dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE); + spin_unlock_irq(&dev->power.lock); + return 0; } @@ -1979,7 +2210,6 @@ int dpm_prepare(pm_message_t state) int error = 0; trace_suspend_resume(TPS("dpm_prepare"), state.event, true); - might_sleep(); /* * Give a chance for the known devices to complete their probes, before @@ -1996,10 +2226,11 @@ int dpm_prepare(pm_message_t state) device_block_probing(); mutex_lock(&dpm_list_mtx); - while (!list_empty(&dpm_list)) { + while (!list_empty(&dpm_list) && !error) { struct device *dev = to_device(dpm_list.next); get_device(dev); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); @@ -2007,22 +2238,23 @@ int dpm_prepare(pm_message_t state) trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); - if (error) { - if (error == -EAGAIN) { - put_device(dev); - error = 0; - continue; - } - printk(KERN_INFO "PM: Device %s not prepared " - "for power transition: code %d\n", - dev_name(dev), error); - put_device(dev); - break; + + if (!error) { + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + } else if (error == -EAGAIN) { + error = 0; + } else { + dev_info(dev, "not prepared for power transition: code %d\n", + error); } - dev->power.is_prepared = true; - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); @@ -2038,29 +2270,33 @@ int dpm_prepare(pm_message_t state) */ int dpm_suspend_start(pm_message_t state) { + ktime_t starttime = ktime_get(); int error; error = dpm_prepare(state); - if (error) { - suspend_stats.failed_prepare++; + if (error) dpm_save_failed_step(SUSPEND_PREPARE); - } else + else { + pm_restrict_gfp_mask(); error = dpm_suspend(state); + } + + dpm_show_time(starttime, state, error, "start"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_start); -void __suspend_report_result(const char *function, void *fn, int ret) +void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret) { if (ret) - printk(KERN_ERR "%s(): %pF returns %d\n", function, fn, ret); + dev_err(dev, "%s(): %ps returns %d\n", function, fn, ret); } EXPORT_SYMBOL_GPL(__suspend_report_result); /** * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete. - * @dev: Device to wait for. * @subordinate: Device that needs to wait for @dev. + * @dev: Device to wait for. */ int device_pm_wait_for_dev(struct device *subordinate, struct device *dev) { @@ -2108,7 +2344,9 @@ static bool pm_ops_is_empty(const struct dev_pm_ops *ops) void device_pm_check_callbacks(struct device *dev) { - spin_lock_irq(&dev->power.lock); + unsigned long flags; + + spin_lock_irqsave(&dev->power.lock, flags); dev->power.no_pm_callbacks = (!dev->bus || (pm_ops_is_empty(dev->bus->pm) && !dev->bus->suspend && !dev->bus->resume)) && @@ -2117,11 +2355,10 @@ void device_pm_check_callbacks(struct device *dev) (!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) && (!dev->driver || (pm_ops_is_empty(dev->driver->pm) && !dev->driver->suspend && !dev->driver->resume)); - spin_unlock_irq(&dev->power.lock); + spin_unlock_irqrestore(&dev->power.lock, flags); } -bool dev_pm_smart_suspend_and_suspended(struct device *dev) +bool dev_pm_skip_suspend(struct device *dev) { - return dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) && - pm_runtime_status_suspended(dev); + return dev_pm_smart_suspend(dev) && pm_runtime_status_suspended(dev); } diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index c511def48b48..922ed457db19 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -21,11 +21,15 @@ static inline void pm_runtime_early_init(struct device *dev) extern void pm_runtime_init(struct device *dev); extern void pm_runtime_reinit(struct device *dev); extern void pm_runtime_remove(struct device *dev); +extern u64 pm_runtime_active_time(struct device *dev); #define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) #define WAKE_IRQ_DEDICATED_MANAGED BIT(1) +#define WAKE_IRQ_DEDICATED_REVERSE BIT(2) #define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ - WAKE_IRQ_DEDICATED_MANAGED) + WAKE_IRQ_DEDICATED_MANAGED | \ + WAKE_IRQ_DEDICATED_REVERSE) +#define WAKE_IRQ_DEDICATED_ENABLED BIT(3) struct wake_irq { struct device *dev; @@ -38,7 +42,8 @@ extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); extern void dev_pm_enable_wake_irq_check(struct device *dev, bool can_change_status); -extern void dev_pm_disable_wake_irq_check(struct device *dev); +extern void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable); +extern void dev_pm_enable_wake_irq_complete(struct device *dev); #ifdef CONFIG_PM_SLEEP @@ -73,6 +78,7 @@ extern int pm_qos_sysfs_add_flags(struct device *dev); extern void pm_qos_sysfs_remove_flags(struct device *dev); extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev); extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev); +extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); #else /* CONFIG_PM */ @@ -87,6 +93,8 @@ static inline void pm_runtime_remove(struct device *dev) {} static inline int dpm_sysfs_add(struct device *dev) { return 0; } static inline void dpm_sysfs_remove(struct device *dev) {} +static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) { return 0; } #endif @@ -116,6 +124,13 @@ static inline bool device_pm_initialized(struct device *dev) return dev->power.in_dpm_list; } +/* drivers/base/power/wakeup_stats.c */ +extern int wakeup_source_sysfs_add(struct device *parent, + struct wakeup_source *ws); +extern void wakeup_source_sysfs_remove(struct wakeup_source *ws); + +extern int pm_wakeup_source_sysfs_add(struct device *parent); + #else /* !CONFIG_PM_SLEEP */ static inline void device_pm_sleep_init(struct device *dev) {} @@ -140,6 +155,11 @@ static inline bool device_pm_initialized(struct device *dev) return device_is_registered(dev); } +static inline int pm_wakeup_source_sysfs_add(struct device *parent) +{ + return 0; +} + #endif /* !CONFIG_PM_SLEEP */ static inline void device_pm_init(struct device *dev) diff --git a/drivers/base/power/qos-test.c b/drivers/base/power/qos-test.c new file mode 100644 index 000000000000..79fc6c4418da --- /dev/null +++ b/drivers/base/power/qos-test.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 NXP + */ +#include <kunit/test.h> +#include <linux/pm_qos.h> + +/* Basic test for aggregating two "min" requests */ +static void freq_qos_test_min(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req1, req2; + int ret; + + freq_constraints_init(&qos); + memset(&req1, 0, sizeof(req1)); + memset(&req2, 0, sizeof(req2)); + + ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MIN, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MIN, 2000); + KUNIT_EXPECT_EQ(test, ret, 1); + + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000); + + ret = freq_qos_remove_request(&req2); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000); + + ret = freq_qos_remove_request(&req1); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); +} + +/* Test that requests for MAX_DEFAULT_VALUE have no effect */ +static void freq_qos_test_maxdef(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req1, req2; + int ret; + + freq_constraints_init(&qos); + memset(&req1, 0, sizeof(req1)); + memset(&req2, 0, sizeof(req2)); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), + FREQ_QOS_MAX_DEFAULT_VALUE); + + ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + KUNIT_EXPECT_EQ(test, ret, 0); + ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + KUNIT_EXPECT_EQ(test, ret, 0); + + /* Add max 1000 */ + ret = freq_qos_update_request(&req1, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000); + + /* Add max 2000, no impact */ + ret = freq_qos_update_request(&req2, 2000); + KUNIT_EXPECT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000); + + /* Remove max 1000, new max 2000 */ + ret = freq_qos_remove_request(&req1); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 2000); +} + +/* + * Test that a freq_qos_request can be added again after removal + * + * This issue was solved by commit 05ff1ba412fd ("PM: QoS: Invalidate frequency + * QoS requests after removal") + */ +static void freq_qos_test_readd(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req; + int ret; + + freq_constraints_init(&qos); + memset(&req, 0, sizeof(req)); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); + + /* Add */ + ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000); + + /* Remove */ + ret = freq_qos_remove_request(&req); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); + + /* Add again */ + ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 2000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000); +} + +static struct kunit_case pm_qos_test_cases[] = { + KUNIT_CASE(freq_qos_test_min), + KUNIT_CASE(freq_qos_test_maxdef), + KUNIT_CASE(freq_qos_test_readd), + {}, +}; + +static struct kunit_suite pm_qos_test_module = { + .name = "qos-kunit-test", + .test_cases = pm_qos_test_cases, +}; +kunit_test_suites(&pm_qos_test_module); diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 3382542b39b7..ff393cba7649 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Devices PM QoS constraints management * * Copyright (C) 2011 Texas Instruments, Inc. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * * This module exposes the interface to kernel space for specifying * per-device PM QoS dependencies. It provides infrastructure for registration * of: @@ -22,7 +18,7 @@ * per-device constraint data struct. * * Note about the per-device constraint data struct allocation: - * . The per-device constraints data struct ptr is tored into the device + * . The per-device constraints data struct ptr is stored into the device * dev_pm_info. * . To minimize the data usage by the per-device constraints, the data struct * is only allocated at the first call to dev_pm_qos_add_request. @@ -94,33 +90,54 @@ enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) EXPORT_SYMBOL_GPL(dev_pm_qos_flags); /** - * __dev_pm_qos_read_value - Get PM QoS constraint for a given device. + * __dev_pm_qos_resume_latency - Get resume latency constraint for a given device. * @dev: Device to get the PM QoS constraint value for. * * This routine must be called with dev->power.lock held. */ -s32 __dev_pm_qos_read_value(struct device *dev) +s32 __dev_pm_qos_resume_latency(struct device *dev) { lockdep_assert_held(&dev->power.lock); - return dev_pm_qos_raw_read_value(dev); + return dev_pm_qos_raw_resume_latency(dev); } /** * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked). * @dev: Device to get the PM QoS constraint value for. + * @type: QoS request type. */ -s32 dev_pm_qos_read_value(struct device *dev) +s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) { + struct dev_pm_qos *qos = dev->power.qos; unsigned long flags; s32 ret; spin_lock_irqsave(&dev->power.lock, flags); - ret = __dev_pm_qos_read_value(dev); + + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT + : pm_qos_read_value(&qos->resume_latency); + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); + break; + default: + WARN_ON(1); + ret = 0; + } + spin_unlock_irqrestore(&dev->power.lock, flags); return ret; } +EXPORT_SYMBOL_GPL(dev_pm_qos_read_value); /** * apply_constraint - Add/modify/remove device PM QoS request. @@ -153,6 +170,10 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_apply(&req->data.freq, action, value); + break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -181,12 +202,11 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) if (!qos) return -ENOMEM; - n = kzalloc(sizeof(*n), GFP_KERNEL); + n = kcalloc(3, sizeof(*n), GFP_KERNEL); if (!n) { kfree(qos); return -ENOMEM; } - BLOCKING_INIT_NOTIFIER_HEAD(n); c = &qos->resume_latency; plist_head_init(&c->list); @@ -195,6 +215,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; c->type = PM_QOS_MIN; c->notifiers = n; + BLOCKING_INIT_NOTIFIER_HEAD(n); c = &qos->latency_tolerance; plist_head_init(&c->list); @@ -203,6 +224,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; + freq_constraints_init(&qos->freq); + INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -256,11 +279,27 @@ void dev_pm_qos_constraints_destroy(struct device *dev) apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } + c = &qos->latency_tolerance; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } + + c = &qos->freq.min_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + + c = &qos->freq.max_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -306,11 +345,22 @@ static int __dev_pm_qos_add_request(struct device *dev, ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); - if (!ret) { - req->dev = dev; - req->type = type; + if (ret) + return ret; + + req->dev = dev; + req->type = type; + if (req->type == DEV_PM_QOS_MIN_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MIN, value); + else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MAX, value); + else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); - } + return ret; } @@ -374,6 +424,10 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + curr_value = req->data.freq.pnode.prio; + break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; @@ -471,6 +525,7 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); * * @dev: target device for the constraint * @notifier: notifier block managed by caller. + * @type: request type. * * Will register the notifier into a notification chain that gets called * upon changes to the target value for the device. @@ -478,7 +533,8 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); * If the device's constraints object doesn't exist when this routine is called, * it will be created (or error code will be returned if that fails). */ -int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier) +int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, + enum dev_pm_qos_req_type type) { int ret = 0; @@ -489,10 +545,28 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier) else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); - if (!ret) + if (ret) + goto unlock; + + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; + default: + WARN_ON(1); + ret = -EINVAL; + } +unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } @@ -504,24 +578,44 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier); * * @dev: target device for the constraint * @notifier: notifier block to be removed. + * @type: request type. * * Will remove the notifier from the notification chain that gets called * upon changes to the target value. */ int dev_pm_qos_remove_notifier(struct device *dev, - struct notifier_block *notifier) + struct notifier_block *notifier, + enum dev_pm_qos_req_type type) { - int retval = 0; + int ret = 0; mutex_lock(&dev_pm_qos_mtx); /* Silently return if the constraints object is not present. */ - if (!IS_ERR_OR_NULL(dev->power.qos)) - retval = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, - notifier); + if (IS_ERR_OR_NULL(dev->power.qos)) + goto unlock; + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: + ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, + notifier); + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; + default: + WARN_ON(1); + ret = -EINVAL; + } + +unlock: mutex_unlock(&dev_pm_qos_mtx); - return retval; + return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier); @@ -581,6 +675,9 @@ static void __dev_pm_qos_drop_user_request(struct device *dev, req = dev->power.qos->flags_req; dev->power.qos->flags_req = NULL; break; + default: + WARN_ON(1); + return; } __dev_pm_qos_remove_request(req); kfree(req); diff --git a/drivers/base/power/runtime-test.c b/drivers/base/power/runtime-test.c new file mode 100644 index 000000000000..1535ad2b0264 --- /dev/null +++ b/drivers/base/power/runtime-test.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2025 Google, Inc. + */ + +#include <linux/cleanup.h> +#include <linux/pm_runtime.h> +#include <kunit/device.h> +#include <kunit/test.h> + +#define DEVICE_NAME "pm_runtime_test_device" + +static void pm_runtime_depth_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + pm_runtime_enable(dev); + + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + KUNIT_EXPECT_EQ(test, 1, pm_runtime_get_sync(dev)); /* "already active" */ + KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev)); + KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); +} + +/* Test pm_runtime_put() and friends when already suspended. */ +static void pm_runtime_already_suspended_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + pm_runtime_enable(dev); + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + + pm_runtime_get_noresume(dev); + KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync(dev)); + + KUNIT_EXPECT_EQ(test, 1, pm_runtime_suspend(dev)); + KUNIT_EXPECT_EQ(test, 1, pm_runtime_autosuspend(dev)); + KUNIT_EXPECT_EQ(test, 1, pm_request_autosuspend(dev)); + + pm_runtime_get_noresume(dev); + KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync_autosuspend(dev)); + + pm_runtime_get_noresume(dev); + pm_runtime_put_autosuspend(dev); + + /* Grab 2 refcounts */ + pm_runtime_get_noresume(dev); + pm_runtime_get_noresume(dev); + /* The first put() sees usage_count 1 */ + KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync_autosuspend(dev)); + /* The second put() sees usage_count 0 but tells us "already suspended". */ + KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync_autosuspend(dev)); + + /* Should have remained suspended the whole time. */ + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); +} + +static void pm_runtime_idle_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + pm_runtime_enable(dev); + + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + pm_runtime_put_noidle(dev); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + KUNIT_EXPECT_EQ(test, 0, pm_runtime_idle(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_idle(dev)); +} + +static void pm_runtime_disabled_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + /* Never called pm_runtime_enable() */ + KUNIT_EXPECT_FALSE(test, pm_runtime_enabled(dev)); + + /* "disabled" is treated as "active" */ + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + KUNIT_EXPECT_FALSE(test, pm_runtime_suspended(dev)); + + /* + * Note: these "fail", but they still acquire/release refcounts, so + * keep them balanced. + */ + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get(dev)); + pm_runtime_put(dev); + + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get_sync(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_put_sync(dev)); + + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get(dev)); + pm_runtime_put_autosuspend(dev); + + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_resume_and_get(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_idle(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_request_idle(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_request_resume(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_request_autosuspend(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_suspend(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_resume(dev)); + KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_autosuspend(dev)); + + /* Still disabled */ + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + KUNIT_EXPECT_FALSE(test, pm_runtime_enabled(dev)); +} + +static void pm_runtime_error_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + pm_runtime_enable(dev); + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + + /* Fake a .runtime_resume() error */ + dev->power.runtime_error = -EIO; + + /* + * Note: these "fail", but they still acquire/release refcounts, so + * keep them balanced. + */ + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev)); + pm_runtime_put(dev); + + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get_sync(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_put_sync(dev)); + + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev)); + pm_runtime_put_autosuspend(dev); + + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_put_sync_autosuspend(dev)); + + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_resume_and_get(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_idle(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_idle(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_resume(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_autosuspend(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_suspend(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_resume(dev)); + KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_autosuspend(dev)); + + /* Error is still pending */ + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + KUNIT_EXPECT_EQ(test, -EIO, dev->power.runtime_error); + /* Clear error */ + KUNIT_EXPECT_EQ(test, 0, pm_runtime_set_suspended(dev)); + KUNIT_EXPECT_EQ(test, 0, dev->power.runtime_error); + /* Still suspended */ + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_get(dev)); + pm_runtime_barrier(dev); + pm_runtime_put(dev); + pm_runtime_suspend(dev); /* flush the put(), to suspend */ + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev)); + KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev)); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev)); + pm_runtime_put_autosuspend(dev); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_resume_and_get(dev)); + + /* + * The following should all return -EAGAIN (usage is non-zero) or 1 + * (already resumed). + */ + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_idle(dev)); + KUNIT_EXPECT_EQ(test, 1, pm_request_resume(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_autosuspend(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_suspend(dev)); + KUNIT_EXPECT_EQ(test, 1, pm_runtime_resume(dev)); + KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_autosuspend(dev)); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev)); + + /* Suspended again */ + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); +} + +/* + * Explore a typical probe() sequence in which a device marks itself powered, + * but doesn't hold any runtime PM reference, so it suspends as soon as it goes + * idle. + */ +static void pm_runtime_probe_active_test(struct kunit *test) +{ + struct device *dev = kunit_device_register(test, DEVICE_NAME); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + KUNIT_EXPECT_TRUE(test, pm_runtime_status_suspended(dev)); + + KUNIT_EXPECT_EQ(test, 0, pm_runtime_set_active(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + + pm_runtime_enable(dev); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + + /* Nothing to flush. We stay active. */ + pm_runtime_barrier(dev); + KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev)); + + /* Ask for idle? Now we suspend. */ + KUNIT_EXPECT_EQ(test, 0, pm_runtime_idle(dev)); + KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev)); +} + +static struct kunit_case pm_runtime_test_cases[] = { + KUNIT_CASE(pm_runtime_depth_test), + KUNIT_CASE(pm_runtime_already_suspended_test), + KUNIT_CASE(pm_runtime_idle_test), + KUNIT_CASE(pm_runtime_disabled_test), + KUNIT_CASE(pm_runtime_error_test), + KUNIT_CASE(pm_runtime_probe_active_test), + {} +}; + +static struct kunit_suite pm_runtime_test_suite = { + .name = "pm_runtime_test_cases", + .test_cases = pm_runtime_test_cases, +}; + +kunit_test_suite(pm_runtime_test_suite); +MODULE_DESCRIPTION("Runtime power management unit test suite"); +MODULE_LICENSE("GPL"); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..84676cc24221 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1,18 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/runtime.c - Helper functions for device runtime PM * * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> - * - * This file is released under the GPLv2. */ - #include <linux/sched/mm.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> +#include <linux/rculist.h> #include <trace/events/rpm.h> #include "../base.h" @@ -20,10 +19,24 @@ typedef int (*pm_callback_t)(struct device *); +static inline pm_callback_t get_callback_ptr(const void *start, size_t offset) +{ + return *(pm_callback_t *)(start + offset); +} + +static pm_callback_t __rpm_get_driver_callback(struct device *dev, + size_t cb_offset) +{ + if (dev->driver && dev->driver->pm) + return get_callback_ptr(dev->driver->pm, cb_offset); + + return NULL; +} + static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { - pm_callback_t cb; const struct dev_pm_ops *ops; + pm_callback_t cb = NULL; if (dev->pm_domain) ops = &dev->pm_domain->ops; @@ -37,12 +50,10 @@ static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) ops = NULL; if (ops) - cb = *(pm_callback_t *)((void *)ops + cb_offset); - else - cb = NULL; + cb = get_callback_ptr(ops, cb_offset); - if (!cb && dev->driver && dev->driver->pm) - cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); + if (!cb) + cb = __rpm_get_driver_callback(dev, cb_offset); return cb; } @@ -64,30 +75,67 @@ static int rpm_suspend(struct device *dev, int rpmflags); * runtime_status field is updated, to account the time in the old state * correctly. */ -void update_pm_runtime_accounting(struct device *dev) +static void update_pm_runtime_accounting(struct device *dev) { - unsigned long now = jiffies; - unsigned long delta; + u64 now, last, delta; + + if (dev->power.disable_depth > 0) + return; - delta = now - dev->power.accounting_timestamp; + last = dev->power.accounting_timestamp; + now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; - if (dev->power.disable_depth > 0) + /* + * Because ktime_get_mono_fast_ns() is not monotonic during + * timekeeping updates, ensure that 'now' is after the last saved + * timestamp. + */ + if (now < last) return; + delta = now - last; + if (dev->power.runtime_status == RPM_SUSPENDED) - dev->power.suspended_jiffies += delta; + dev->power.suspended_time += delta; else - dev->power.active_jiffies += delta; + dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) { update_pm_runtime_accounting(dev); + trace_rpm_status(dev, status); dev->power.runtime_status = status; } +static u64 rpm_get_accounted_time(struct device *dev, bool suspended) +{ + u64 time; + unsigned long flags; + + spin_lock_irqsave(&dev->power.lock, flags); + + update_pm_runtime_accounting(dev); + time = suspended ? dev->power.suspended_time : dev->power.active_time; + + spin_unlock_irqrestore(&dev->power.lock, flags); + + return time; +} + +u64 pm_runtime_active_time(struct device *dev) +{ + return rpm_get_accounted_time(dev, false); +} + +u64 pm_runtime_suspended_time(struct device *dev) +{ + return rpm_get_accounted_time(dev, true); +} +EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); + /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. @@ -95,7 +143,7 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { - hrtimer_cancel(&dev->power.suspend_timer); + hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } @@ -129,24 +177,21 @@ static void pm_runtime_cancel_pending(struct device *dev) u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; - u64 last_busy, expires = 0; - u64 now = ktime_to_ns(ktime_get()); + u64 expires; if (!dev->power.use_autosuspend) - goto out; + return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) - goto out; - - last_busy = READ_ONCE(dev->power.last_busy); + return 0; - expires = last_busy + (u64)autosuspend_delay * NSEC_PER_MSEC; - if (expires <= now) - expires = 0; /* Already expired. */ + expires = READ_ONCE(dev->power.last_busy); + expires += (u64)autosuspend_delay * NSEC_PER_MSEC; + if (expires > ktime_get_mono_fast_ns()) + return expires; /* Expires in the future */ - out: - return expires; + return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); @@ -172,7 +217,7 @@ static int dev_memalloc_noio(struct device *dev, void *data) * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block - * device becomes active and the involed page I/O finishes. The + * device becomes active and the involved page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * @@ -212,8 +257,7 @@ void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) * flag was set by any one of the descendants. */ if (!dev || (!enable && - device_for_each_child(dev, NULL, - dev_memalloc_noio))) + device_for_each_child(dev, NULL, dev_memalloc_noio))) break; } mutex_unlock(&dev_hotplug_mutex); @@ -232,19 +276,17 @@ static int rpm_check_suspend_allowed(struct device *dev) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; - else if (atomic_read(&dev->power.usage_count) > 0) + else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; - else if (!dev->power.ignore_children && - atomic_read(&dev->power.child_count)) + else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ - else if ((dev->power.deferred_resume - && dev->power.runtime_status == RPM_SUSPENDING) - || (dev->power.request_pending - && dev->power.request == RPM_REQ_RESUME)) + else if ((dev->power.deferred_resume && + dev->power.runtime_status == RPM_SUSPENDING) || + (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME)) retval = -EAGAIN; - else if (__dev_pm_qos_read_value(dev) == 0) + else if (__dev_pm_qos_resume_latency(dev) == 0) retval = -EPERM; else if (dev->power.runtime_status == RPM_SUSPENDED) retval = 1; @@ -256,14 +298,11 @@ static int rpm_get_suppliers(struct device *dev) { struct device_link *link; - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) { int retval; - if (!(link->flags & DL_FLAG_PM_RUNTIME)) - continue; - - if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND || - link->rpm_active) + if (!device_link_test(link, DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); @@ -272,21 +311,59 @@ static int rpm_get_suppliers(struct device *dev) pm_runtime_put_noidle(link->supplier); return retval; } - link->rpm_active = true; + refcount_inc(&link->rpm_active); } return 0; } +/** + * pm_runtime_release_supplier - Drop references to device link's supplier. + * @link: Target device link. + * + * Drop all runtime PM references associated with @link to its supplier device. + */ +void pm_runtime_release_supplier(struct device_link *link) +{ + struct device *supplier = link->supplier; + + /* + * The additional power.usage_count check is a safety net in case + * the rpm_active refcount becomes saturated, in which case + * refcount_dec_not_one() would return true forever, but it is not + * strictly necessary. + */ + while (refcount_dec_not_one(&link->rpm_active) && + atomic_read(&supplier->power.usage_count) > 0) + pm_runtime_put_noidle(supplier); +} + +static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) +{ + struct device_link *link; + + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) { + pm_runtime_release_supplier(link); + if (try_to_suspend) + pm_request_idle(link->supplier); + } +} + static void rpm_put_suppliers(struct device *dev) { + __rpm_put_suppliers(dev, true); +} + +static void rpm_suspend_suppliers(struct device *dev) +{ struct device_link *link; + int idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (link->rpm_active && - READ_ONCE(link->status) != DL_STATE_SUPPLIER_UNBIND) { - pm_runtime_put(link->supplier); - link->rpm_active = false; - } + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) + pm_request_idle(link->supplier); + + device_links_read_unlock(idx); } /** @@ -297,7 +374,7 @@ static void rpm_put_suppliers(struct device *dev) static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { - int retval, idx; + int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { @@ -316,14 +393,17 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); - if (retval) + if (retval) { + rpm_put_suppliers(dev); goto fail; + } device_links_read_unlock(idx); } } - retval = cb(dev); + if (cb) + retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); @@ -335,14 +415,14 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) * * Do that if resume fails too. */ - if (use_links - && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) - || (dev->power.runtime_status == RPM_RESUMING && retval))) { + if (use_links && + ((dev->power.runtime_status == RPM_SUSPENDING && !retval) || + (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); - fail: - rpm_put_suppliers(dev); + __rpm_put_suppliers(dev, false); +fail: device_links_read_unlock(idx); } @@ -353,6 +433,49 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) } /** + * rpm_callback - Run a given runtime PM callback for a given device. + * @cb: Runtime PM callback to run. + * @dev: Device to run the callback for. + */ +static int rpm_callback(int (*cb)(struct device *), struct device *dev) +{ + int retval; + + if (dev->power.memalloc_noio) { + unsigned int noio_flag; + + /* + * Deadlock might be caused if memory allocation with + * GFP_KERNEL happens inside runtime_suspend and + * runtime_resume callbacks of one block device's + * ancestor or the block device itself. Network + * device might be thought as part of iSCSI block + * device, so network device and its ancestor should + * be marked as memalloc_noio too. + */ + noio_flag = memalloc_noio_save(); + retval = __rpm_callback(cb, dev); + memalloc_noio_restore(noio_flag); + } else { + retval = __rpm_callback(cb, dev); + } + + /* + * Since -EACCES means that runtime PM is disabled for the given device, + * it should not be returned by runtime PM callbacks. If it is returned + * nevertheless, assume it to be a transient error and convert it to + * -EAGAIN. + */ + if (retval == -EACCES) + retval = -EAGAIN; + + if (retval != -EAGAIN && retval != -EBUSY) + dev->power.runtime_error = retval; + + return retval; +} + +/** * rpm_idle - Notify device bus type if the device can be suspended. * @dev: Device to notify the bus type about. * @rpmflags: Flag bits. @@ -370,11 +493,14 @@ static int rpm_idle(struct device *dev, int rpmflags) int (*callback)(struct device *); int retval; - trace_rpm_idle_rcuidle(dev, rpmflags); + trace_rpm_idle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ + else if ((rpmflags & RPM_GET_PUT) && retval == 1) + ; /* put() is allowed in RPM_SUSPENDED */ + /* Idle notifications are allowed only in the RPM_ACTIVE state. */ else if (dev->power.runtime_status != RPM_ACTIVE) retval = -EAGAIN; @@ -390,13 +516,17 @@ static int rpm_idle(struct device *dev, int rpmflags) /* Act as though RPM_NOWAIT is always set. */ else if (dev->power.idle_notification) retval = -EINPROGRESS; + if (retval) goto out; /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; - if (dev->power.no_callbacks) + callback = RPM_GET_CALLBACK(dev, runtime_idle); + + /* If no callback assume success. */ + if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ @@ -406,61 +536,33 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } - trace_rpm_return_int_rcuidle(dev, _THIS_IP_, 0); + trace_rpm_return_int(dev, _THIS_IP_, 0); return 0; } dev->power.idle_notification = true; - callback = RPM_GET_CALLBACK(dev, runtime_idle); + if (dev->power.irq_safe) + spin_unlock(&dev->power.lock); + else + spin_unlock_irq(&dev->power.lock); + + retval = callback(dev); - if (callback) - retval = __rpm_callback(callback, dev); + if (dev->power.irq_safe) + spin_lock(&dev->power.lock); + else + spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: - trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); + trace_rpm_return_int(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } /** - * rpm_callback - Run a given runtime PM callback for a given device. - * @cb: Runtime PM callback to run. - * @dev: Device to run the callback for. - */ -static int rpm_callback(int (*cb)(struct device *), struct device *dev) -{ - int retval; - - if (!cb) - return -ENOSYS; - - if (dev->power.memalloc_noio) { - unsigned int noio_flag; - - /* - * Deadlock might be caused if memory allocation with - * GFP_KERNEL happens inside runtime_suspend and - * runtime_resume callbacks of one block device's - * ancestor or the block device itself. Network - * device might be thought as part of iSCSI block - * device, so network device and its ancestor should - * be marked as memalloc_noio too. - */ - noio_flag = memalloc_noio_save(); - retval = __rpm_callback(cb, dev); - memalloc_noio_restore(noio_flag); - } else { - retval = __rpm_callback(cb, dev); - } - - dev->power.runtime_error = retval; - return retval != -EACCES ? retval : -EIO; -} - -/** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. * @rpmflags: Flag bits. @@ -488,24 +590,22 @@ static int rpm_suspend(struct device *dev, int rpmflags) struct device *parent = NULL; int retval; - trace_rpm_suspend_rcuidle(dev, rpmflags); + trace_rpm_suspend(dev, rpmflags); repeat: retval = rpm_check_suspend_allowed(dev); - if (retval < 0) - ; /* Conditions are wrong. */ + goto out; /* Conditions are wrong. */ /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ - else if (dev->power.runtime_status == RPM_RESUMING && - !(rpmflags & RPM_ASYNC)) + if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC)) retval = -EAGAIN; + if (retval) goto out; /* If the autosuspend_delay time hasn't expired yet, reschedule. */ - if ((rpmflags & RPM_AUTO) - && dev->power.runtime_status != RPM_SUSPENDING) { + if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) { u64 expires = pm_runtime_autosuspend_expiration(dev); if (expires != 0) { @@ -520,7 +620,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) * rest. */ if (!(dev->power.timer_expires && - dev->power.timer_expires <= expires)) { + dev->power.timer_expires <= expires)) { /* * We add a slack of 25% to gather wakeups * without sacrificing the granularity. @@ -530,9 +630,9 @@ static int rpm_suspend(struct device *dev, int rpmflags) dev->power.timer_expires = expires; hrtimer_start_range_ns(&dev->power.suspend_timer, - ns_to_ktime(expires), - slack, - HRTIMER_MODE_ABS); + ns_to_ktime(expires), + slack, + HRTIMER_MODE_ABS); } dev->power.timer_autosuspends = 1; goto out; @@ -599,6 +699,8 @@ static int rpm_suspend(struct device *dev, int rpmflags) if (retval) goto fail; + dev_pm_enable_wake_irq_complete(dev); + no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); @@ -616,8 +718,11 @@ static int rpm_suspend(struct device *dev, int rpmflags) goto out; } + if (dev->power.irq_safe) + goto out; + /* Maybe the parent is now able to suspend. */ - if (parent && !parent->power.ignore_children && !dev->power.irq_safe) { + if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); @@ -626,33 +731,38 @@ static int rpm_suspend(struct device *dev, int rpmflags) spin_lock(&dev->power.lock); } + /* Maybe the suppliers are now able to suspend. */ + if (dev->power.links_count > 0) { + spin_unlock_irq(&dev->power.lock); + + rpm_suspend_suppliers(dev); + + spin_lock_irq(&dev->power.lock); + } out: - trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); + trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; fail: - dev_pm_disable_wake_irq_check(dev); + dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); - if (retval == -EAGAIN || retval == -EBUSY) { - dev->power.runtime_error = 0; + /* + * On transient errors, if the callback routine failed an autosuspend, + * and if the last_busy time has been updated so that there is a new + * autosuspend expiration time, automatically reschedule another + * autosuspend. + */ + if (!dev->power.runtime_error && (rpmflags & RPM_AUTO) && + pm_runtime_autosuspend_expiration(dev) != 0) + goto repeat; + + pm_runtime_cancel_pending(dev); - /* - * If the callback routine failed an autosuspend, and - * if the last_busy time has been updated so that there - * is a new autosuspend expiration time, automatically - * reschedule another autosuspend. - */ - if ((rpmflags & RPM_AUTO) && - pm_runtime_autosuspend_expiration(dev) != 0) - goto repeat; - } else { - pm_runtime_cancel_pending(dev); - } goto out; } @@ -680,16 +790,20 @@ static int rpm_resume(struct device *dev, int rpmflags) struct device *parent = NULL; int retval = 0; - trace_rpm_resume_rcuidle(dev, rpmflags); + trace_rpm_resume(dev, rpmflags); repeat: - if (dev->power.runtime_error) + if (dev->power.runtime_error) { retval = -EINVAL; - else if (dev->power.disable_depth == 1 && dev->power.is_suspended - && dev->power.runtime_status == RPM_ACTIVE) - retval = 1; - else if (dev->power.disable_depth > 0) - retval = -EACCES; + } else if (dev->power.disable_depth > 0) { + if (dev->power.runtime_status == RPM_ACTIVE && + dev->power.last_status == RPM_ACTIVE) + retval = 1; + else if (rpmflags & RPM_TRANSPARENT) + goto out; + else + retval = -EACCES; + } if (retval) goto out; @@ -708,15 +822,18 @@ static int rpm_resume(struct device *dev, int rpmflags) goto out; } - if (dev->power.runtime_status == RPM_RESUMING - || dev->power.runtime_status == RPM_SUSPENDING) { + if (dev->power.runtime_status == RPM_RESUMING || + dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { - if (dev->power.runtime_status == RPM_SUSPENDING) + if (dev->power.runtime_status == RPM_SUSPENDING) { dev->power.deferred_resume = true; - else + if (rpmflags & RPM_NOWAIT) + retval = -EINPROGRESS; + } else { retval = -EINPROGRESS; + } goto out; } @@ -733,8 +850,8 @@ static int rpm_resume(struct device *dev, int rpmflags) for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); - if (dev->power.runtime_status != RPM_RESUMING - && dev->power.runtime_status != RPM_SUSPENDING) + if (dev->power.runtime_status != RPM_RESUMING && + dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); @@ -754,9 +871,9 @@ static int rpm_resume(struct device *dev, int rpmflags) */ if (dev->power.no_callbacks && !parent && dev->parent) { spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); - if (dev->parent->power.disable_depth > 0 - || dev->parent->power.ignore_children - || dev->parent->power.runtime_status == RPM_ACTIVE) { + if (dev->parent->power.disable_depth > 0 || + dev->parent->power.ignore_children || + dev->parent->power.runtime_status == RPM_ACTIVE) { atomic_inc(&dev->parent->power.child_count); spin_unlock(&dev->parent->power.lock); retval = 1; @@ -785,6 +902,7 @@ static int rpm_resume(struct device *dev, int rpmflags) parent = dev->parent; if (dev->power.irq_safe) goto skip_parent; + spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); @@ -794,8 +912,8 @@ static int rpm_resume(struct device *dev, int rpmflags) * Resume the parent if it has runtime PM enabled and not been * set to ignore its children. */ - if (!parent->power.disable_depth - && !parent->power.ignore_children) { + if (!parent->power.disable_depth && + !parent->power.ignore_children) { rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; @@ -805,6 +923,7 @@ static int rpm_resume(struct device *dev, int rpmflags) spin_lock(&dev->power.lock); if (retval) goto out; + goto repeat; } skip_parent: @@ -816,7 +935,7 @@ static int rpm_resume(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_resume); - dev_pm_disable_wake_irq_check(dev); + dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); @@ -843,7 +962,7 @@ static int rpm_resume(struct device *dev, int rpmflags) spin_lock_irq(&dev->power.lock); } - trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); + trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; } @@ -892,7 +1011,7 @@ static void pm_runtime_work(struct work_struct *work) /** * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). - * @data: Device pointer passed by pm_schedule_suspend(). + * @timer: hrtimer used by pm_schedule_suspend(). * * Check if the time is right and queue a suspend request. */ @@ -909,7 +1028,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) * If 'expires' is after the current time, we've been called * too early. */ - if (expires > 0 && expires < ktime_to_ns(ktime_get())) { + if (expires > 0 && expires <= ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); @@ -928,7 +1047,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; - ktime_t expires; + u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); @@ -945,8 +1064,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); - expires = ktime_add(ktime_get(), ms_to_ktime(delay)); - dev->power.timer_expires = ktime_to_ns(expires); + expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; + dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); @@ -957,13 +1076,33 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) } EXPORT_SYMBOL_GPL(pm_schedule_suspend); +static int rpm_drop_usage_count(struct device *dev) +{ + int ret; + + ret = atomic_sub_return(1, &dev->power.usage_count); + if (ret >= 0) + return ret; + + /* + * Because rpm_resume() does not check the usage counter, it will resume + * the device even if the usage counter is 0 or negative, so it is + * sufficient to increment the usage counter here to reverse the change + * made above. + */ + atomic_inc(&dev->power.usage_count); + dev_warn(dev, "Runtime PM usage count underflow!\n"); + return -EINVAL; +} + /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and - * return immediately if it is larger than zero. Then carry out an idle + * return immediately if it is larger than zero (if it becomes negative, log a + * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, @@ -975,8 +1114,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags) int retval; if (rpmflags & RPM_GET_PUT) { - if (!atomic_dec_and_test(&dev->power.usage_count)) + retval = rpm_drop_usage_count(dev); + if (retval < 0) { + return retval; + } else if (retval > 0) { + trace_rpm_usage(dev, rpmflags); return 0; + } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); @@ -995,7 +1139,8 @@ EXPORT_SYMBOL_GPL(__pm_runtime_idle); * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and - * return immediately if it is larger than zero. Then carry out a suspend, + * return immediately if it is larger than zero (if it becomes negative, log a + * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, @@ -1007,8 +1152,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags) int retval; if (rpmflags & RPM_GET_PUT) { - if (!atomic_dec_and_test(&dev->power.usage_count)) + retval = rpm_drop_usage_count(dev); + if (retval < 0) { + return retval; + } else if (retval > 0) { + trace_rpm_usage(dev, rpmflags); return 0; + } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); @@ -1052,27 +1202,88 @@ int __pm_runtime_resume(struct device *dev, int rpmflags) EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** - * pm_runtime_get_if_in_use - Conditionally bump up the device's usage counter. + * pm_runtime_get_conditional - Conditionally bump up device usage counter. * @dev: Device to handle. + * @ign_usage_count: Whether or not to look at the current usage counter value. * - * Return -EINVAL if runtime PM is disabled for the device. + * Return -EINVAL if runtime PM is disabled for @dev. * - * If that's not the case and if the device's runtime PM status is RPM_ACTIVE - * and the runtime PM usage counter is nonzero, increment the counter and - * return 1. Otherwise return 0 without changing the counter. + * Otherwise, if its runtime PM status is %RPM_ACTIVE and (1) @ign_usage_count + * is set, or (2) @dev is not ignoring children and its active child count is + * nonzero, or (3) the runtime PM usage counter of @dev is not zero, increment + * the usage counter of @dev and return 1. + * + * Otherwise, return 0 without changing the usage counter. + * + * If @ign_usage_count is %true, this function can be used to prevent suspending + * the device when its runtime PM status is %RPM_ACTIVE. + * + * If @ign_usage_count is %false, this function can be used to prevent + * suspending the device when both its runtime PM status is %RPM_ACTIVE and its + * runtime PM usage counter is not zero. + * + * The caller is responsible for decrementing the runtime PM usage counter of + * @dev after this function has returned a positive value for it. */ -int pm_runtime_get_if_in_use(struct device *dev) +static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count) { unsigned long flags; int retval; spin_lock_irqsave(&dev->power.lock, flags); - retval = dev->power.disable_depth > 0 ? -EINVAL : - dev->power.runtime_status == RPM_ACTIVE - && atomic_inc_not_zero(&dev->power.usage_count); + if (dev->power.disable_depth > 0) { + retval = -EINVAL; + } else if (dev->power.runtime_status != RPM_ACTIVE) { + retval = 0; + } else if (ign_usage_count || (!dev->power.ignore_children && + atomic_read(&dev->power.child_count) > 0)) { + retval = 1; + atomic_inc(&dev->power.usage_count); + } else { + retval = atomic_inc_not_zero(&dev->power.usage_count); + } + trace_rpm_usage(dev, 0); spin_unlock_irqrestore(&dev->power.lock, flags); + return retval; } + +/** + * pm_runtime_get_if_active - Bump up runtime PM usage counter if the device is + * in active state + * @dev: Target device. + * + * Increment the runtime PM usage counter of @dev if its runtime PM status is + * %RPM_ACTIVE, in which case it returns 1. If the device is in a different + * state, 0 is returned. -EINVAL is returned if runtime PM is disabled for the + * device, in which case also the usage_count will remain unmodified. + */ +int pm_runtime_get_if_active(struct device *dev) +{ + return pm_runtime_get_conditional(dev, true); +} +EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); + +/** + * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. + * @dev: Target device. + * + * Increment the runtime PM usage counter of @dev if its runtime PM status is + * %RPM_ACTIVE and its runtime PM usage counter is greater than 0 or it is not + * ignoring children and its active child count is nonzero. 1 is returned in + * this case. + * + * If @dev is in a different state or it is not in use (that is, its usage + * counter is 0, or it is ignoring children, or its active child count is 0), + * 0 is returned. + * + * -EINVAL is returned if runtime PM is disabled for the device, in which case + * also the usage counter of @dev is not updated. + */ +int pm_runtime_get_if_in_use(struct device *dev) +{ + return pm_runtime_get_conditional(dev, false); +} EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); /** @@ -1091,12 +1302,19 @@ EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. + * + * If @dev has any suppliers (as reflected by device links to them), and @status + * is RPM_ACTIVE, they will be activated upfront and if the activation of one + * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead + * of the @status value) and the suppliers will be deacticated on exit. The + * error returned by the failing supplier activation will be returned in that + * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; - unsigned long flags; bool notify_parent = false; + unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) @@ -1104,11 +1322,38 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) spin_lock_irqsave(&dev->power.lock, flags); - if (!dev->power.runtime_error && !dev->power.disable_depth) { + /* + * Prevent PM-runtime from being enabled for the device or return an + * error if it is enabled already and working. + */ + if (dev->power.runtime_error || dev->power.disable_depth) + dev->power.disable_depth++; + else error = -EAGAIN; - goto out; + + spin_unlock_irqrestore(&dev->power.lock, flags); + + if (error) + return error; + + /* + * If the new status is RPM_ACTIVE, the suppliers can be activated + * upfront regardless of the current status, because next time + * rpm_put_suppliers() runs, the rpm_active refcounts of the links + * involved will be dropped down to one anyway. + */ + if (status == RPM_ACTIVE) { + int idx = device_links_read_lock(); + + error = rpm_get_suppliers(dev); + if (error) + status = RPM_SUSPENDED; + + device_links_read_unlock(idx); } + spin_lock_irqsave(&dev->power.lock, flags); + if (dev->power.runtime_status == status || !parent) goto out_set; @@ -1123,9 +1368,9 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) * not active, has runtime PM enabled and the * 'power.ignore_children' flag unset. */ - if (!parent->power.disable_depth - && !parent->power.ignore_children - && parent->power.runtime_status != RPM_ACTIVE) { + if (!parent->power.disable_depth && + !parent->power.ignore_children && + parent->power.runtime_status != RPM_ACTIVE) { dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", dev_name(dev), dev_name(parent)); @@ -1136,19 +1381,33 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) spin_unlock(&parent->power.lock); - if (error) + if (error) { + status = RPM_SUSPENDED; goto out; + } } out_set: __update_runtime_status(dev, status); - dev->power.runtime_error = 0; + if (!error) + dev->power.runtime_error = 0; + out: spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); + if (status == RPM_SUSPENDED) { + int idx = device_links_read_lock(); + + rpm_put_suppliers(dev); + + device_links_read_unlock(idx); + } + + pm_runtime_enable(dev); + return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); @@ -1176,9 +1435,9 @@ static void __pm_runtime_barrier(struct device *dev) dev->power.request_pending = false; } - if (dev->power.runtime_status == RPM_SUSPENDING - || dev->power.runtime_status == RPM_RESUMING - || dev->power.idle_notification) { + if (dev->power.runtime_status == RPM_SUSPENDING || + dev->power.runtime_status == RPM_RESUMING || + dev->power.idle_notification) { DEFINE_WAIT(wait); /* Suspend, wake-up or idle notification in progress. */ @@ -1208,47 +1467,48 @@ static void __pm_runtime_barrier(struct device *dev) * Next, make sure that all pending requests for the device have been flushed * from pm_wq and wait for all runtime PM operations involving the device in * progress to complete. - * - * Return value: - * 1, if there was a resume request pending and the device had to be woken up, - * 0, otherwise */ -int pm_runtime_barrier(struct device *dev) +void pm_runtime_barrier(struct device *dev) { - int retval = 0; - pm_runtime_get_noresume(dev); spin_lock_irq(&dev->power.lock); if (dev->power.request_pending - && dev->power.request == RPM_REQ_RESUME) { + && dev->power.request == RPM_REQ_RESUME) rpm_resume(dev, 0); - retval = 1; - } __pm_runtime_barrier(dev); spin_unlock_irq(&dev->power.lock); pm_runtime_put_noidle(dev); - - return retval; } EXPORT_SYMBOL_GPL(pm_runtime_barrier); -/** - * __pm_runtime_disable - Disable runtime PM of a device. - * @dev: Device to handle. - * @check_resume: If set, check if there's a resume request for the device. - * - * Increment power.disable_depth for the device and if it was zero previously, - * cancel all pending runtime PM requests for the device and wait for all - * operations in progress to complete. The device can be either active or - * suspended after its runtime PM has been disabled. - * - * If @check_resume is set and there's a resume request pending when - * __pm_runtime_disable() is called and power.disable_depth is zero, the - * function will wake up the device before disabling its runtime PM. - */ +bool pm_runtime_block_if_disabled(struct device *dev) +{ + bool ret; + + spin_lock_irq(&dev->power.lock); + + ret = !pm_runtime_enabled(dev); + if (ret && dev->power.last_status == RPM_INVALID) + dev->power.last_status = RPM_BLOCKED; + + spin_unlock_irq(&dev->power.lock); + + return ret; +} + +void pm_runtime_unblock(struct device *dev) +{ + spin_lock_irq(&dev->power.lock); + + if (dev->power.last_status == RPM_BLOCKED) + dev->power.last_status = RPM_INVALID; + + spin_unlock_irq(&dev->power.lock); +} + void __pm_runtime_disable(struct device *dev, bool check_resume) { spin_lock_irq(&dev->power.lock); @@ -1263,8 +1523,8 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) * means there probably is some I/O to process and disabling runtime PM * shouldn't prevent the device from processing the I/O. */ - if (check_resume && dev->power.request_pending - && dev->power.request == RPM_REQ_RESUME) { + if (check_resume && dev->power.request_pending && + dev->power.request == RPM_REQ_RESUME) { /* * Prevent suspends and idle notifications from being carried * out after we have woken up the device. @@ -1276,8 +1536,13 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) pm_runtime_put_noidle(dev); } - if (!dev->power.disable_depth++) + /* Update time accounting before disabling PM-runtime. */ + update_pm_runtime_accounting(dev); + + if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); + dev->power.last_status = dev->power.runtime_status; + } out: spin_unlock_irq(&dev->power.lock); @@ -1294,29 +1559,107 @@ void pm_runtime_enable(struct device *dev) spin_lock_irqsave(&dev->power.lock, flags); - if (dev->power.disable_depth > 0) - dev->power.disable_depth--; - else + if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); + goto out; + } - WARN(!dev->power.disable_depth && - dev->power.runtime_status == RPM_SUSPENDED && - !dev->power.ignore_children && - atomic_read(&dev->power.child_count) > 0, - "Enabling runtime PM for inactive device (%s) with active children\n", - dev_name(dev)); + if (--dev->power.disable_depth > 0) + goto out; + if (dev->power.last_status == RPM_BLOCKED) { + dev_warn(dev, "Attempt to enable runtime PM when it is blocked\n"); + dump_stack(); + } + dev->power.last_status = RPM_INVALID; + dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); + + if (dev->power.runtime_status == RPM_SUSPENDED && + !dev->power.ignore_children && + atomic_read(&dev->power.child_count) > 0) + dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); + +out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); +static void pm_runtime_set_suspended_action(void *data) +{ + pm_runtime_set_suspended(data); +} + +/** + * devm_pm_runtime_set_active_enabled - set_active version of devm_pm_runtime_enable. + * + * @dev: Device to handle. + */ +int devm_pm_runtime_set_active_enabled(struct device *dev) +{ + int err; + + err = pm_runtime_set_active(dev); + if (err) + return err; + + err = devm_add_action_or_reset(dev, pm_runtime_set_suspended_action, dev); + if (err) + return err; + + return devm_pm_runtime_enable(dev); +} +EXPORT_SYMBOL_GPL(devm_pm_runtime_set_active_enabled); + +static void pm_runtime_disable_action(void *data) +{ + pm_runtime_dont_use_autosuspend(data); + pm_runtime_disable(data); +} + +/** + * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. + * + * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for + * you at driver exit time if needed. + * + * @dev: Device to handle. + */ +int devm_pm_runtime_enable(struct device *dev) +{ + pm_runtime_enable(dev); + + return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); + +static void pm_runtime_put_noidle_action(void *data) +{ + pm_runtime_put_noidle(data); +} + +/** + * devm_pm_runtime_get_noresume - devres-enabled version of pm_runtime_get_noresume. + * + * @dev: Device to handle. + */ +int devm_pm_runtime_get_noresume(struct device *dev) +{ + pm_runtime_get_noresume(dev); + + return devm_add_action_or_reset(dev, pm_runtime_put_noidle_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_runtime_get_noresume); + /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * - * Increase the device's usage count and clear its power.runtime_auto flag, - * so that it cannot be suspended at run time until pm_runtime_allow() is called - * for it. + * Resume @dev if already suspended and block runtime suspend of @dev in such + * a way that it can be unblocked via the /sys/devices/.../power/control + * interface, or otherwise by calling pm_runtime_allow(). + * + * Calling this function many times in a row has the same effect as calling it + * once. */ void pm_runtime_forbid(struct device *dev) { @@ -1337,17 +1680,28 @@ EXPORT_SYMBOL_GPL(pm_runtime_forbid); * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * - * Decrease the device's usage count and set its power.runtime_auto flag. + * Unblock runtime suspend of @dev after it has been blocked by + * pm_runtime_forbid() (for instance, if it has been blocked via the + * /sys/devices/.../power/control interface), check if @dev can be + * suspended and suspend it in that case. + * + * Calling this function many times in a row has the same effect as calling it + * once. */ void pm_runtime_allow(struct device *dev) { + int ret; + spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; - if (atomic_dec_and_test(&dev->power.usage_count)) + ret = rpm_drop_usage_count(dev); + if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); + else if (ret > 0) + trace_rpm_usage(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); @@ -1387,6 +1741,7 @@ void pm_runtime_irq_safe(struct device *dev) { if (dev->parent) pm_runtime_get_sync(dev->parent); + spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 1; spin_unlock_irq(&dev->power.lock); @@ -1415,6 +1770,8 @@ static void update_autosuspend(struct device *dev, int old_delay, int old_use) if (!old_use || old_delay >= 0) { atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); + } else { + trace_rpm_usage(dev, 0); } } @@ -1480,6 +1837,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; + dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; @@ -1494,12 +1852,12 @@ void pm_runtime_init(struct device *dev) dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; - dev->power.accounting_timestamp = jiffies; + dev->power.needs_force_resume = false; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; - hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - dev->power.suspend_timer.function = pm_suspend_timer_fn; + hrtimer_setup(&dev->power.suspend_timer, pm_suspend_timer_fn, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); init_waitqueue_head(&dev->power.wait_queue); } @@ -1521,6 +1879,11 @@ void pm_runtime_reinit(struct device *dev) pm_runtime_put(dev->parent); } } + /* + * Clear power.needs_force_resume in case it has been set by + * pm_runtime_force_suspend() invoked from a driver remove callback. + */ + dev->power.needs_force_resume = false; } /** @@ -1534,43 +1897,6 @@ void pm_runtime_remove(struct device *dev) } /** - * pm_runtime_clean_up_links - Prepare links to consumers for driver removal. - * @dev: Device whose driver is going to be removed. - * - * Check links from this device to any consumers and if any of them have active - * runtime PM references to the device, drop the usage counter of the device - * (once per link). - * - * Links with the DL_FLAG_STATELESS flag set are ignored. - * - * Since the device is guaranteed to be runtime-active at the point this is - * called, nothing else needs to be done here. - * - * Moreover, this is called after device_links_busy() has returned 'false', so - * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and - * therefore rpm_active can't be manipulated concurrently. - */ -void pm_runtime_clean_up_links(struct device *dev) -{ - struct device_link *link; - int idx; - - idx = device_links_read_lock(); - - list_for_each_entry_rcu(link, &dev->links.consumers, s_node) { - if (link->flags & DL_FLAG_STATELESS) - continue; - - if (link->rpm_active) { - pm_runtime_put_noidle(dev); - link->rpm_active = false; - } - } - - device_links_read_unlock(idx); -} - -/** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ @@ -1581,9 +1907,11 @@ void pm_runtime_get_suppliers(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (link->flags & DL_FLAG_PM_RUNTIME) + dev_for_each_link_to_supplier(link, dev) + if (device_link_test(link, DL_FLAG_PM_RUNTIME)) { + link->supplier_preactivated = true; pm_runtime_get_sync(link->supplier); + } device_links_read_unlock(idx); } @@ -1599,9 +1927,12 @@ void pm_runtime_put_suppliers(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) - if (link->flags & DL_FLAG_PM_RUNTIME) + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) + if (link->supplier_preactivated) { + link->supplier_preactivated = false; pm_runtime_put(link->supplier); + } device_links_read_unlock(idx); } @@ -1613,23 +1944,49 @@ void pm_runtime_new_link(struct device *dev) spin_unlock_irq(&dev->power.lock); } -void pm_runtime_drop_link(struct device *dev) +static void pm_runtime_drop_link_count(struct device *dev) { - rpm_put_suppliers(dev); - spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; spin_unlock_irq(&dev->power.lock); } -static bool pm_runtime_need_not_resume(struct device *dev) +/** + * pm_runtime_drop_link - Prepare for device link removal. + * @link: Device link going away. + * + * Drop the link count of the consumer end of @link and decrement the supplier + * device's runtime PM usage counter as many times as needed to drop all of the + * PM runtime reference to it from the consumer. + */ +void pm_runtime_drop_link(struct device_link *link) { - return atomic_read(&dev->power.usage_count) <= 1 && - (atomic_read(&dev->power.child_count) == 0 || - dev->power.ignore_children); + if (!device_link_test(link, DL_FLAG_PM_RUNTIME)) + return; + + pm_runtime_drop_link_count(link->consumer); + pm_runtime_release_supplier(link); + pm_request_idle(link->supplier); +} + +static pm_callback_t get_callback(struct device *dev, size_t cb_offset) +{ + /* + * Setting power.strict_midlayer means that the middle layer + * code does not want its runtime PM callbacks to be invoked via + * pm_runtime_force_suspend() and pm_runtime_force_resume(), so + * return a direct pointer to the driver callback in that case. + */ + if (dev_pm_strict_midlayer_is_set(dev)) + return __rpm_get_driver_callback(dev, cb_offset); + + return __rpm_get_callback(dev, cb_offset); } +#define GET_CALLBACK(dev, callback) \ + get_callback(dev, offsetof(struct dev_pm_ops, callback)) + /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. @@ -1653,71 +2010,106 @@ int pm_runtime_force_suspend(struct device *dev) int ret; pm_runtime_disable(dev); - if (pm_runtime_status_suspended(dev)) + if (pm_runtime_status_suspended(dev) || dev->power.needs_force_resume) return 0; - callback = RPM_GET_CALLBACK(dev, runtime_suspend); + callback = GET_CALLBACK(dev, runtime_suspend); + dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; + dev_pm_enable_wake_irq_complete(dev); + /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of - * its parent, but set its status to RPM_SUSPENDED anyway in case this - * function will be called again for it in the meantime. + * its parent and the usage counters of its suppliers. Otherwise, set + * power.needs_force_resume to let pm_runtime_force_resume() know that + * the device needs to be taken care of and to prevent this function + * from handling the device again in case the device is passed to it + * once more subsequently. */ if (pm_runtime_need_not_resume(dev)) pm_runtime_set_suspended(dev); else - __update_runtime_status(dev, RPM_SUSPENDED); + dev->power.needs_force_resume = true; return 0; err: + dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); +#ifdef CONFIG_PM_SLEEP + /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * - * Prior invoking this function we expect the user to have brought the device - * into low power state by a call to pm_runtime_force_suspend(). Here we reverse - * those actions and bring the device into full power, if it is expected to be - * used on system resume. In the other case, we defer the resume to be managed - * via runtime PM. + * This function expects that either pm_runtime_force_suspend() has put the + * device into a low-power state prior to calling it, or the device had been + * runtime-suspended before the preceding system-wide suspend transition and it + * was left in suspend during that transition. * - * Typically this function may be invoked from a system resume callback. + * The actions carried out by pm_runtime_force_suspend(), or by a runtime + * suspend in general, are reversed and the device is brought back into full + * power if it is expected to be used on system resume, which is the case when + * its needs_force_resume flag is set or when its smart_suspend flag is set and + * its runtime PM status is "active". + * + * In other cases, the resume is deferred to be managed via runtime PM. + * + * Typically, this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; - if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev)) + if (!dev->power.needs_force_resume && (!dev_pm_smart_suspend(dev) || + pm_runtime_status_suspended(dev))) goto out; - /* - * The value of the parent's children counter is correct already, so - * just update the status of the device. - */ - __update_runtime_status(dev, RPM_ACTIVE); - - callback = RPM_GET_CALLBACK(dev, runtime_resume); + callback = GET_CALLBACK(dev, runtime_resume); + dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); + dev_pm_enable_wake_irq_check(dev, false); goto out; } pm_runtime_mark_last_busy(dev); + out: + /* + * The smart_suspend flag can be cleared here because it is not going + * to be necessary until the next system-wide suspend transition that + * will update it again. + */ + dev->power.smart_suspend = false; + /* + * Also clear needs_force_resume to make this function skip devices that + * have been seen by it once. + */ + dev->power.needs_force_resume = false; + pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); + +bool pm_runtime_need_not_resume(struct device *dev) +{ + return atomic_read(&dev->power.usage_count) <= 1 && + (atomic_read(&dev->power.child_count) == 0 || + dev->power.ignore_children); +} + +#endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d713738ce796..13b31a3adc77 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -1,8 +1,7 @@ -/* - * drivers/base/power/sysfs.c - sysfs entries for device PM - */ - +// SPDX-License-Identifier: GPL-2.0 +/* sysfs entries for device PM */ #include <linux/device.h> +#include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/pm_qos.h> @@ -101,8 +100,8 @@ static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", - dev->power.runtime_auto ? ctrl_auto : ctrl_on); + return sysfs_emit(buf, "%s\n", + dev->power.runtime_auto ? ctrl_auto : ctrl_on); } static ssize_t control_store(struct device * dev, struct device_attribute *attr, @@ -122,70 +121,71 @@ static ssize_t control_store(struct device * dev, struct device_attribute *attr, static DEVICE_ATTR_RW(control); static ssize_t runtime_active_time_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, + char *buf) { - int ret; - spin_lock_irq(&dev->power.lock); - update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies)); - spin_unlock_irq(&dev->power.lock); - return ret; + u64 tmp = pm_runtime_active_time(dev); + + do_div(tmp, NSEC_PER_MSEC); + + return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_active_time); static ssize_t runtime_suspended_time_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, + char *buf) { - int ret; - spin_lock_irq(&dev->power.lock); - update_pm_runtime_accounting(dev); - ret = sprintf(buf, "%i\n", - jiffies_to_msecs(dev->power.suspended_jiffies)); - spin_unlock_irq(&dev->power.lock); - return ret; + u64 tmp = pm_runtime_suspended_time(dev); + + do_div(tmp, NSEC_PER_MSEC); + + return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_suspended_time); static ssize_t runtime_status_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, char *buf) { - const char *p; + const char *output; if (dev->power.runtime_error) { - p = "error\n"; + output = "error"; } else if (dev->power.disable_depth) { - p = "unsupported\n"; + output = "unsupported"; } else { switch (dev->power.runtime_status) { case RPM_SUSPENDED: - p = "suspended\n"; + output = "suspended"; break; case RPM_SUSPENDING: - p = "suspending\n"; + output = "suspending"; break; case RPM_RESUMING: - p = "resuming\n"; + output = "resuming"; break; case RPM_ACTIVE: - p = "active\n"; + output = "active"; break; default: return -EIO; } } - return sprintf(buf, p); + return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_status); static ssize_t autosuspend_delay_ms_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, + char *buf) { if (!dev->power.use_autosuspend) return -EIO; - return sprintf(buf, "%d\n", dev->power.autosuspend_delay); + + return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, @@ -214,11 +214,11 @@ static ssize_t pm_qos_resume_latency_us_show(struct device *dev, s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) - return sprintf(buf, "n/a\n"); + return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; - return sprintf(buf, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, @@ -258,11 +258,11 @@ static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) - return sprintf(buf, "auto\n"); + return sysfs_emit(buf, "%s\n", "auto"); if (value == PM_QOS_LATENCY_ANY) - return sprintf(buf, "any\n"); + return sysfs_emit(buf, "%s\n", "any"); - return sprintf(buf, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, @@ -294,8 +294,8 @@ static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) - & PM_QOS_FLAG_NO_POWER_OFF)); + return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) + & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, @@ -323,9 +323,9 @@ static const char _disabled[] = "disabled"; static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", device_can_wakeup(dev) - ? (device_may_wakeup(dev) ? _enabled : _disabled) - : ""); + return sysfs_emit(buf, "%s\n", device_can_wakeup(dev) + ? (device_may_wakeup(dev) ? _enabled : _disabled) + : ""); } static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr, @@ -348,7 +348,7 @@ static DEVICE_ATTR_RW(wakeup); static ssize_t wakeup_count_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long count = 0; + unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -357,7 +357,10 @@ static ssize_t wakeup_count_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_count); @@ -366,7 +369,7 @@ static ssize_t wakeup_active_count_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long count = 0; + unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -375,7 +378,10 @@ static ssize_t wakeup_active_count_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_active_count); @@ -384,7 +390,7 @@ static ssize_t wakeup_abort_count_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long count = 0; + unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -393,7 +399,10 @@ static ssize_t wakeup_abort_count_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_abort_count); @@ -402,7 +411,7 @@ static ssize_t wakeup_expire_count_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long count = 0; + unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -411,7 +420,10 @@ static ssize_t wakeup_expire_count_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_expire_count); @@ -419,7 +431,7 @@ static DEVICE_ATTR_RO(wakeup_expire_count); static ssize_t wakeup_active_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned int active = 0; + unsigned int active; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -428,7 +440,10 @@ static ssize_t wakeup_active_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%u\n", active); } static DEVICE_ATTR_RO(wakeup_active); @@ -437,7 +452,7 @@ static ssize_t wakeup_total_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { - s64 msec = 0; + s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -446,7 +461,10 @@ static ssize_t wakeup_total_time_ms_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_total_time_ms); @@ -454,7 +472,7 @@ static DEVICE_ATTR_RO(wakeup_total_time_ms); static ssize_t wakeup_max_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { - s64 msec = 0; + s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -463,7 +481,10 @@ static ssize_t wakeup_max_time_ms_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_max_time_ms); @@ -472,7 +493,7 @@ static ssize_t wakeup_last_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { - s64 msec = 0; + s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -481,7 +502,10 @@ static ssize_t wakeup_last_time_ms_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_last_time_ms); @@ -491,7 +515,7 @@ static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { - s64 msec = 0; + s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); @@ -500,18 +524,36 @@ static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, enabled = true; } spin_unlock_irq(&dev->power.lock); - return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); + + if (!enabled) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ -#endif /* CONFIG_PM_SLEEP */ + +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + if (dev->power.wakeup && dev->power.wakeup->dev) + return device_change_owner(dev->power.wakeup->dev, kuid, kgid); + return 0; +} + +#else /* CONFIG_PM_SLEEP */ +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} +#endif #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count)); + return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count)); } static DEVICE_ATTR_RO(runtime_usage); @@ -519,21 +561,26 @@ static ssize_t runtime_active_kids_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", dev->power.ignore_children ? - 0 : atomic_read(&dev->power.child_count)); + return sysfs_emit(buf, "%d\n", dev->power.ignore_children ? + 0 : atomic_read(&dev->power.child_count)); } static DEVICE_ATTR_RO(runtime_active_kids); static ssize_t runtime_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (dev->power.disable_depth && (dev->power.runtime_auto == false)) - return sprintf(buf, "disabled & forbidden\n"); - if (dev->power.disable_depth) - return sprintf(buf, "disabled\n"); - if (dev->power.runtime_auto == false) - return sprintf(buf, "forbidden\n"); - return sprintf(buf, "enabled\n"); + const char *output; + + if (dev->power.disable_depth && !dev->power.runtime_auto) + output = "disabled & forbidden"; + else if (dev->power.disable_depth) + output = "disabled"; + else if (!dev->power.runtime_auto) + output = "forbidden"; + else + output = "enabled"; + + return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_enabled); @@ -541,9 +588,9 @@ static DEVICE_ATTR_RO(runtime_enabled); static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", - device_async_suspend_enabled(dev) ? - _enabled : _disabled); + return sysfs_emit(buf, "%s\n", + device_async_suspend_enabled(dev) ? + _enabled : _disabled); } static ssize_t async_store(struct device *dev, struct device_attribute *attr, @@ -564,15 +611,9 @@ static DEVICE_ATTR_RW(async); #endif /* CONFIG_PM_ADVANCED_DEBUG */ static struct attribute *power_attrs[] = { -#ifdef CONFIG_PM_ADVANCED_DEBUG -#ifdef CONFIG_PM_SLEEP +#if defined(CONFIG_PM_ADVANCED_DEBUG) && defined(CONFIG_PM_SLEEP) &dev_attr_async.attr, #endif - &dev_attr_runtime_status.attr, - &dev_attr_runtime_usage.attr, - &dev_attr_runtime_active_kids.attr, - &dev_attr_runtime_enabled.attr, -#endif /* CONFIG_PM_ADVANCED_DEBUG */ NULL, }; static const struct attribute_group pm_attr_group = { @@ -603,13 +644,16 @@ static const struct attribute_group pm_wakeup_attr_group = { }; static struct attribute *runtime_attrs[] = { -#ifndef CONFIG_PM_ADVANCED_DEBUG &dev_attr_runtime_status.attr, -#endif &dev_attr_control.attr, &dev_attr_runtime_suspended_time.attr, &dev_attr_runtime_active_time.attr, &dev_attr_autosuspend_delay_ms.attr, +#ifdef CONFIG_PM_ADVANCED_DEBUG + &dev_attr_runtime_usage.attr, + &dev_attr_runtime_active_kids.attr, + &dev_attr_runtime_enabled.attr, +#endif NULL, }; static const struct attribute_group pm_runtime_attr_group = { @@ -648,11 +692,15 @@ int dpm_sysfs_add(struct device *dev) { int rc; + /* No need to create PM sysfs if explicitly disabled. */ + if (device_pm_not_required(dev)) + return 0; + rc = sysfs_create_group(&dev->kobj, &pm_attr_group); if (rc) return rc; - if (pm_runtime_callbacks_present(dev)) { + if (!pm_runtime_has_no_callbacks(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group); if (rc) goto err_out; @@ -668,8 +716,13 @@ int dpm_sysfs_add(struct device *dev) if (rc) goto err_wakeup; } + rc = pm_wakeup_source_sysfs_add(dev); + if (rc) + goto err_latency; return 0; + err_latency: + sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); err_wakeup: sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); err_runtime: @@ -679,14 +732,59 @@ int dpm_sysfs_add(struct device *dev) return rc; } +int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) +{ + int rc; + + if (device_pm_not_required(dev)) + return 0; + + rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid); + if (rc) + return rc; + + if (!pm_runtime_has_no_callbacks(dev)) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_runtime_attr_group, kuid, kgid); + if (rc) + return rc; + } + + if (device_can_wakeup(dev)) { + rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group, + kuid, kgid); + if (rc) + return rc; + + rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid); + if (rc) + return rc; + } + + if (dev->power.set_latency_tolerance) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid, + kgid); + if (rc) + return rc; + } + return 0; +} + int wakeup_sysfs_add(struct device *dev) { - return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); + int ret = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); + + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_CHANGE); + + return ret; } void wakeup_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); + kobject_uevent(&dev->kobj, KOBJ_CHANGE); } int pm_qos_sysfs_add_resume_latency(struct device *dev) @@ -727,6 +825,8 @@ void rpm_sysfs_remove(struct device *dev) void dpm_sysfs_remove(struct device *dev) { + if (device_pm_not_required(dev)) + return; sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); dev_pm_qos_constraints_destroy(dev); rpm_sysfs_remove(dev); diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index b11f47a1e819..d8da7195bb00 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/trace.c * @@ -6,11 +7,13 @@ * Trace facility for suspend/resume problems, when none of the * devices may be working. */ +#define pr_fmt(fmt) "PM: " fmt #include <linux/pm-trace.h> #include <linux/export.h> #include <linux/rtc.h> #include <linux/suspend.h> +#include <linux/init.h> #include <linux/mc146818rtc.h> @@ -117,7 +120,11 @@ static unsigned int read_magic_time(void) struct rtc_time time; unsigned int val; - mc146818_get_time(&time); + if (mc146818_get_time(&time, 1000) < 0) { + pr_err("Unable to read current time from RTC\n"); + return 0; + } + pr_info("RTC time: %ptRt, date: %ptRd\n", &time, &time); val = time.tm_year; /* 100 years */ if (val > 100) @@ -163,6 +170,9 @@ void generate_pm_trace(const void *tracedata, unsigned int user) const char *file = *(const char **)(tracedata + 2); unsigned int user_hash_value, file_hash_value; + if (!x86_platform.legacy.rtc) + return; + user_hash_value = user % USERHASH; file_hash_value = hash_string(lineno, file, FILEHASH); set_magic_time(user_hash_value, file_hash_value, dev_hash_value); @@ -228,10 +238,8 @@ int show_trace_dev_match(char *buf, size_t size) unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH); if (hash == value) { - int len = snprintf(buf, size, "%s\n", + int len = scnprintf(buf, size, "%s\n", dev_driver_string(dev)); - if (len > size) - len = size; buf += len; ret += len; size -= len; @@ -263,18 +271,24 @@ static struct notifier_block pm_trace_nb = { .notifier_call = pm_trace_notify, }; -static int early_resume_init(void) +static int __init early_resume_init(void) { + if (!x86_platform.legacy.rtc) + return 0; + hash_value_early_read = read_magic_time(); register_pm_notifier(&pm_trace_nb); return 0; } -static int late_resume_init(void) +static int __init late_resume_init(void) { unsigned int val = hash_value_early_read; unsigned int user, file, dev; + if (!x86_platform.legacy.rtc) + return 0; + user = val % USERHASH; val = val / USERHASH; file = val % FILEHASH; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index b8fa5c0f2d13..8aa28c08b289 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -1,16 +1,5 @@ -/* - * wakeirq.c - Device wakeirq helper functions - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - +// SPDX-License-Identifier: GPL-2.0 +/* Device wakeirq helper functions */ #include <linux/device.h> #include <linux/interrupt.h> #include <linux/irq.h> @@ -23,14 +12,11 @@ /** * dev_pm_attach_wake_irq - Attach device interrupt as a wake IRQ * @dev: Device entry - * @irq: Device wake-up capable interrupt * @wirq: Wake irq specific data * - * Internal function to attach either a device IO interrupt or a - * dedicated wake-up interrupt as a wake IRQ. + * Internal function to attach a dedicated wake-up interrupt as a wake IRQ. */ -static int dev_pm_attach_wake_irq(struct device *dev, int irq, - struct wake_irq *wirq) +static int dev_pm_attach_wake_irq(struct device *dev, struct wake_irq *wirq) { unsigned long flags; @@ -76,7 +62,7 @@ int dev_pm_set_wake_irq(struct device *dev, int irq) wirq->dev = dev; wirq->irq = irq; - err = dev_pm_attach_wake_irq(dev, irq, wirq); + err = dev_pm_attach_wake_irq(dev, wirq); if (err) kfree(wirq); @@ -117,6 +103,32 @@ void dev_pm_clear_wake_irq(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); +static void devm_pm_clear_wake_irq(void *dev) +{ + dev_pm_clear_wake_irq(dev); +} + +/** + * devm_pm_set_wake_irq - device-managed variant of dev_pm_set_wake_irq + * @dev: Device entry + * @irq: Device IO interrupt + * + * + * Attach a device IO interrupt as a wake IRQ, same with dev_pm_set_wake_irq, + * but the device will be auto clear wake capability on driver detach. + */ +int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + int ret; + + ret = dev_pm_set_wake_irq(dev, irq); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_pm_clear_wake_irq, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_set_wake_irq); + /** * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts * @irq: Device specific dedicated wake-up interrupt @@ -156,24 +168,7 @@ static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq) return IRQ_HANDLED; } -/** - * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt - * @dev: Device entry - * @irq: Device wake-up interrupt - * - * Unless your hardware has separate wake-up interrupts in addition - * to the device IO interrupts, you don't need this. - * - * Sets up a threaded interrupt handler for a device that has - * a dedicated wake-up interrupt in addition to the device IO - * interrupt. - * - * The interrupt starts disabled, and needs to be managed for - * the device by the bus code or the device driver using - * dev_pm_enable_wake_irq() and dev_pm_disable_wake_irq() - * functions. - */ -int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) +static int __dev_pm_set_dedicated_wake_irq(struct device *dev, int irq, unsigned int flag) { struct wake_irq *wirq; int err; @@ -193,7 +188,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) wirq->dev = dev; wirq->irq = irq; - irq_set_status_flags(irq, IRQ_NOAUTOEN); /* Prevent deferred spurious wakeirqs with disable_irq_nosync() */ irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY); @@ -203,15 +197,16 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) * so we use a threaded irq. */ err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq, - IRQF_ONESHOT, wirq->name, wirq); + IRQF_ONESHOT | IRQF_NO_AUTOEN, + wirq->name, wirq); if (err) goto err_free_name; - err = dev_pm_attach_wake_irq(dev, irq, wirq); + err = dev_pm_attach_wake_irq(dev, wirq); if (err) goto err_free_irq; - wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED; + wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED | flag; return err; @@ -224,45 +219,45 @@ err_free: return err; } -EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq); /** - * dev_pm_enable_wake_irq - Enable device wake-up interrupt - * @dev: Device + * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt + * @dev: Device entry + * @irq: Device wake-up interrupt * - * Optionally called from the bus code or the device driver for - * runtime_resume() to override the PM runtime core managed wake-up - * interrupt handling to enable the wake-up interrupt. + * Unless your hardware has separate wake-up interrupts in addition + * to the device IO interrupts, you don't need this. * - * Note that for runtime_suspend()) the wake-up interrupts - * should be unconditionally enabled unlike for suspend() - * that is conditional. + * Sets up a threaded interrupt handler for a device that has + * a dedicated wake-up interrupt in addition to the device IO + * interrupt. */ -void dev_pm_enable_wake_irq(struct device *dev) +int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) { - struct wake_irq *wirq = dev->power.wakeirq; - - if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) - enable_irq(wirq->irq); + return __dev_pm_set_dedicated_wake_irq(dev, irq, 0); } -EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq); +EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq); /** - * dev_pm_disable_wake_irq - Disable device wake-up interrupt - * @dev: Device + * dev_pm_set_dedicated_wake_irq_reverse - Request a dedicated wake-up interrupt + * with reverse enable ordering + * @dev: Device entry + * @irq: Device wake-up interrupt * - * Optionally called from the bus code or the device driver for - * runtime_suspend() to override the PM runtime core managed wake-up - * interrupt handling to disable the wake-up interrupt. + * Unless your hardware has separate wake-up interrupts in addition + * to the device IO interrupts, you don't need this. + * + * Sets up a threaded interrupt handler for a device that has a dedicated + * wake-up interrupt in addition to the device IO interrupt. It sets + * the status of WAKE_IRQ_DEDICATED_REVERSE to tell rpm_suspend() + * to enable dedicated wake-up interrupt after running the runtime suspend + * callback for @dev. */ -void dev_pm_disable_wake_irq(struct device *dev) +int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq) { - struct wake_irq *wirq = dev->power.wakeirq; - - if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) - disable_irq_nosync(wirq->irq); + return __dev_pm_set_dedicated_wake_irq(dev, irq, WAKE_IRQ_DEDICATED_REVERSE); } -EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq); +EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq_reverse); /** * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt @@ -271,7 +266,7 @@ EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq); * * Enables wakeirq conditionally. We need to enable wake-up interrupt * lazily on the first rpm_suspend(). This is needed as the consumer device - * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would + * starts in RPM_SUSPENDED state, and the first pm_runtime_get() would * otherwise try to disable already disabled wakeirq. The wake-up interrupt * starts disabled with IRQ_NOAUTOEN set. * @@ -283,7 +278,7 @@ void dev_pm_enable_wake_irq_check(struct device *dev, { struct wake_irq *wirq = dev->power.wakeirq; - if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK)) return; if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) { @@ -296,25 +291,58 @@ void dev_pm_enable_wake_irq_check(struct device *dev, return; enable: - enable_irq(wirq->irq); + if (!can_change_status || !(wirq->status & WAKE_IRQ_DEDICATED_REVERSE)) { + enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt * @dev: Device + * @cond_disable: if set, also check WAKE_IRQ_DEDICATED_REVERSE * * Disables wake-up interrupt conditionally based on status. * Should be only called from rpm_suspend() and rpm_resume() path. */ -void dev_pm_disable_wake_irq_check(struct device *dev) +void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable) { struct wake_irq *wirq = dev->power.wakeirq; - if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK)) return; - if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) + if (cond_disable && (wirq->status & WAKE_IRQ_DEDICATED_REVERSE)) + return; + + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) { + wirq->status &= ~WAKE_IRQ_DEDICATED_ENABLED; disable_irq_nosync(wirq->irq); + } +} + +/** + * dev_pm_enable_wake_irq_complete - enable wake IRQ not enabled before + * @dev: Device using the wake IRQ + * + * Enable wake IRQ conditionally based on status, mainly used if want to + * enable wake IRQ after running ->runtime_suspend() which depends on + * WAKE_IRQ_DEDICATED_REVERSE. + * + * Should be only called from rpm_suspend() path. + */ +void dev_pm_enable_wake_irq_complete(struct device *dev) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK)) + return; + + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { + enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** @@ -331,7 +359,7 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq) if (device_may_wakeup(wirq->dev)) { if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && - !pm_runtime_status_suspended(wirq->dev)) + !(wirq->status & WAKE_IRQ_DEDICATED_ENABLED)) enable_irq(wirq->irq); enable_irq_wake(wirq->irq); @@ -354,7 +382,7 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq) disable_irq_wake(wirq->irq); if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && - !pm_runtime_status_suspended(wirq->dev)) + !(wirq->status & WAKE_IRQ_DEDICATED_ENABLED)) disable_irq_nosync(wirq->irq); } } diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5fa1898755a3..1e1a0e7eeac5 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -1,10 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. - * - * This file is released under the GPLv2. */ +#define pr_fmt(fmt) "PM: " fmt #include <linux/device.h> #include <linux/slab.h> @@ -19,11 +19,9 @@ #include "power.h" -#ifndef CONFIG_SUSPEND -suspend_state_t pm_suspend_target_state; -#define pm_suspend_target_state (PM_SUSPEND_ON) -#endif - +#define list_for_each_entry_rcu_locked(pos, head, member) \ + list_for_each_entry_rcu(pos, head, member, \ + srcu_read_lock_held(&wakeup_srcu)) /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. @@ -31,7 +29,8 @@ suspend_state_t pm_suspend_target_state; bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ -unsigned int pm_wakeup_irq __read_mostly; +static unsigned int wakeup_irq[2] __read_mostly; +static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; @@ -72,56 +71,41 @@ static struct wakeup_source deleted_ws = { .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), }; -/** - * wakeup_source_prepare - Prepare a new wakeup source for initialization. - * @ws: Wakeup source to prepare. - * @name: Pointer to the name of the new wakeup source. - * - * Callers must ensure that the @name string won't be freed when @ws is still in - * use. - */ -void wakeup_source_prepare(struct wakeup_source *ws, const char *name) -{ - if (ws) { - memset(ws, 0, sizeof(*ws)); - ws->name = name; - } -} -EXPORT_SYMBOL_GPL(wakeup_source_prepare); +static DEFINE_IDA(wakeup_ida); /** * wakeup_source_create - Create a struct wakeup_source object. * @name: Name of the new wakeup source. */ -struct wakeup_source *wakeup_source_create(const char *name) +static struct wakeup_source *wakeup_source_create(const char *name) { struct wakeup_source *ws; + const char *ws_name; + int id; - ws = kmalloc(sizeof(*ws), GFP_KERNEL); + ws = kzalloc(sizeof(*ws), GFP_KERNEL); if (!ws) - return NULL; + goto err_ws; - wakeup_source_prepare(ws, name ? kstrdup_const(name, GFP_KERNEL) : NULL); - return ws; -} -EXPORT_SYMBOL_GPL(wakeup_source_create); + ws_name = kstrdup_const(name, GFP_KERNEL); + if (!ws_name) + goto err_name; + ws->name = ws_name; -/** - * wakeup_source_drop - Prepare a struct wakeup_source object for destruction. - * @ws: Wakeup source to prepare for destruction. - * - * Callers must ensure that __pm_stay_awake() or __pm_wakeup_event() will never - * be run in parallel with this function for the same wakeup source object. - */ -void wakeup_source_drop(struct wakeup_source *ws) -{ - if (!ws) - return; + id = ida_alloc(&wakeup_ida, GFP_KERNEL); + if (id < 0) + goto err_id; + ws->id = id; - del_timer_sync(&ws->timer); - __pm_relax(ws); + return ws; + +err_id: + kfree_const(ws->name); +err_name: + kfree(ws); +err_ws: + return NULL; } -EXPORT_SYMBOL_GPL(wakeup_source_drop); /* * Record wakeup_source statistics being deleted into a dummy wakeup_source. @@ -151,29 +135,34 @@ static void wakeup_source_record(struct wakeup_source *ws) spin_unlock_irqrestore(&deleted_ws.lock, flags); } +static void wakeup_source_free(struct wakeup_source *ws) +{ + ida_free(&wakeup_ida, ws->id); + kfree_const(ws->name); + kfree(ws); +} + /** * wakeup_source_destroy - Destroy a struct wakeup_source object. * @ws: Wakeup source to destroy. * * Use only for wakeup source objects created with wakeup_source_create(). */ -void wakeup_source_destroy(struct wakeup_source *ws) +static void wakeup_source_destroy(struct wakeup_source *ws) { if (!ws) return; - wakeup_source_drop(ws); + __pm_relax(ws); wakeup_source_record(ws); - kfree_const(ws->name); - kfree(ws); + wakeup_source_free(ws); } -EXPORT_SYMBOL_GPL(wakeup_source_destroy); /** * wakeup_source_add - Add given object to the list of wakeup sources. * @ws: Wakeup source object to add to the list. */ -void wakeup_source_add(struct wakeup_source *ws) +static void wakeup_source_add(struct wakeup_source *ws) { unsigned long flags; @@ -188,38 +177,52 @@ void wakeup_source_add(struct wakeup_source *ws) list_add_rcu(&ws->entry, &wakeup_sources); raw_spin_unlock_irqrestore(&events_lock, flags); } -EXPORT_SYMBOL_GPL(wakeup_source_add); /** * wakeup_source_remove - Remove given object from the wakeup sources list. * @ws: Wakeup source object to remove from the list. */ -void wakeup_source_remove(struct wakeup_source *ws) +static void wakeup_source_remove(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; + /* + * After shutting down the timer, wakeup_source_activate() will warn if + * the given wakeup source is passed to it. + */ + timer_shutdown_sync(&ws->timer); + raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); } -EXPORT_SYMBOL_GPL(wakeup_source_remove); /** * wakeup_source_register - Create wakeup source and add it to the list. + * @dev: Device this wakeup source is associated with (or NULL if virtual). * @name: Name of the wakeup source to register. */ -struct wakeup_source *wakeup_source_register(const char *name) +struct wakeup_source *wakeup_source_register(struct device *dev, + const char *name) { struct wakeup_source *ws; + int ret; ws = wakeup_source_create(name); - if (ws) + if (ws) { + if (!dev || device_is_registered(dev)) { + ret = wakeup_source_sysfs_add(dev, ws); + if (ret) { + wakeup_source_free(ws); + return NULL; + } + } wakeup_source_add(ws); - + } return ws; } EXPORT_SYMBOL_GPL(wakeup_source_register); @@ -232,12 +235,69 @@ void wakeup_source_unregister(struct wakeup_source *ws) { if (ws) { wakeup_source_remove(ws); + if (ws->dev) + wakeup_source_sysfs_remove(ws); + wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** + * wakeup_sources_read_lock - Lock wakeup source list for read. + * + * Returns an index of srcu lock for struct wakeup_srcu. + * This index must be passed to the matching wakeup_sources_read_unlock(). + */ +int wakeup_sources_read_lock(void) +{ + return srcu_read_lock(&wakeup_srcu); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); + +/** + * wakeup_sources_read_unlock - Unlock wakeup source list. + * @idx: return value from corresponding wakeup_sources_read_lock() + */ +void wakeup_sources_read_unlock(int idx) +{ + srcu_read_unlock(&wakeup_srcu, idx); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); + +/** + * wakeup_sources_walk_start - Begin a walk on wakeup source list + * + * Returns first object of the list of wakeup sources. + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_start(void) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_entry_rcu(ws_head->next, struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); + +/** + * wakeup_sources_walk_next - Get next wakeup source from the list + * @ws: Previous wakeup source object + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_next_or_null_rcu(ws_head, &ws->entry, + struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); + +/** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. * @ws: Wakeup source object to attach to @dev. @@ -272,10 +332,10 @@ int device_wakeup_enable(struct device *dev) if (!dev || !dev->power.can_wakeup) return -EINVAL; - if (pm_suspend_target_state != PM_SUSPEND_ON) + if (pm_sleep_transition_in_progress()) dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__); - ws = wakeup_source_register(dev_name(dev)); + ws = wakeup_source_register(dev, dev_name(dev)); if (!ws) return -ENOMEM; @@ -331,9 +391,9 @@ void device_wakeup_detach_irq(struct device *dev) } /** - * device_wakeup_arm_wake_irqs(void) + * device_wakeup_arm_wake_irqs - * - * Itereates over the list of device wakeirqs to arm them. + * Iterates over the list of device wakeirqs to arm them. */ void device_wakeup_arm_wake_irqs(void) { @@ -341,15 +401,15 @@ void device_wakeup_arm_wake_irqs(void) int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) + list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** - * device_wakeup_disarm_wake_irqs(void) + * device_wakeup_disarm_wake_irqs - * - * Itereates over the list of device wakeirqs to disarm them. + * Iterates over the list of device wakeirqs to disarm them. */ void device_wakeup_disarm_wake_irqs(void) { @@ -357,7 +417,7 @@ void device_wakeup_disarm_wake_irqs(void) int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) + list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_disarm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } @@ -386,16 +446,15 @@ static struct wakeup_source *device_wakeup_detach(struct device *dev) * Detach the @dev's wakeup source object from it, unregister this wakeup source * object and destroy it. */ -int device_wakeup_disable(struct device *dev) +void device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) - return -EINVAL; + return; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); - return 0; } EXPORT_SYMBOL_GPL(device_wakeup_disable); @@ -431,54 +490,29 @@ void device_set_wakeup_capable(struct device *dev, bool capable) EXPORT_SYMBOL_GPL(device_set_wakeup_capable); /** - * device_init_wakeup - Device wakeup initialization. - * @dev: Device to handle. - * @enable: Whether or not to enable @dev as a wakeup device. - * - * By default, most devices should leave wakeup disabled. The exceptions are - * devices that everyone expects to be wakeup sources: keyboards, power buttons, - * possibly network interfaces, etc. Also, devices that don't generate their - * own wakeup requests but merely forward requests from one bus to another - * (like PCI bridges) should have wakeup enabled by default. - */ -int device_init_wakeup(struct device *dev, bool enable) -{ - int ret = 0; - - if (!dev) - return -EINVAL; - - if (enable) { - device_set_wakeup_capable(dev, true); - ret = device_wakeup_enable(dev); - } else { - device_wakeup_disable(dev); - device_set_wakeup_capable(dev, false); - } - - return ret; -} -EXPORT_SYMBOL_GPL(device_init_wakeup); - -/** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. + * @enable: enable/disable flag */ int device_set_wakeup_enable(struct device *dev, bool enable) { - return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev); + if (enable) + return device_wakeup_enable(dev); + + device_wakeup_disable(dev); + return 0; } EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** - * wakeup_source_not_registered - validate the given wakeup source. + * wakeup_source_not_usable - validate the given wakeup source. * @ws: Wakeup source to be validated. */ -static bool wakeup_source_not_registered(struct wakeup_source *ws) +static bool wakeup_source_not_usable(struct wakeup_source *ws) { /* - * Use timer struct to check if the given source is initialized - * by wakeup_source_add. + * Use the timer struct to check if the given wakeup source has been + * initialized by wakeup_source_add() and it is not going away. */ return ws->timer.function != pm_wakeup_timer_fn; } @@ -512,19 +546,18 @@ static bool wakeup_source_not_registered(struct wakeup_source *ws) */ /** - * wakup_source_activate - Mark given wakeup source as active. + * wakeup_source_activate - Mark given wakeup source as active. * @ws: Wakeup source to handle. * * Update the @ws' statistics and, if @ws has just been activated, notify the PM - * core of the event by incrementing the counter of of wakeup events being + * core of the event by incrementing the counter of the wakeup events being * processed. */ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; - if (WARN_ONCE(wakeup_source_not_registered(ws), - "unregistered wakeup source\n")) + if (WARN_ONCE(wakeup_source_not_usable(ws), "unusable wakeup source\n")) return; ws->active = true; @@ -574,7 +607,7 @@ void __pm_stay_awake(struct wakeup_source *ws) spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, false); - del_timer(&ws->timer); + timer_delete(&ws->timer); ws->timer_expires = 0; spin_unlock_irqrestore(&ws->lock, flags); @@ -617,7 +650,7 @@ static inline void update_prevent_sleep_time(struct wakeup_source *ws, #endif /** - * wakup_source_deactivate - Mark given wakeup source as inactive. + * wakeup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. * * Update the @ws' statistics and notify the PM core that the wakeup source has @@ -654,7 +687,7 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) ws->max_time = duration; ws->last_time = now; - del_timer(&ws->timer); + timer_delete(&ws->timer); ws->timer_expires = 0; if (ws->autosleep_enabled) @@ -662,7 +695,7 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) /* * Increment the counter of registered wakeup events and decrement the - * couter of wakeup events in progress simultaneously. + * counter of wakeup events in progress simultaneously. */ cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); trace_wakeup_source_deactivate(ws->name, cec); @@ -716,7 +749,7 @@ EXPORT_SYMBOL_GPL(pm_relax); /** * pm_wakeup_timer_fn - Delayed finalization of a wakeup event. - * @data: Address of the wakeup source object associated with the event source. + * @t: timer list * * Call wakeup_source_deactivate() for the wakeup source whose address is stored * in @data if it is currently active and its timer has not been canceled and @@ -724,7 +757,7 @@ EXPORT_SYMBOL_GPL(pm_relax); */ static void pm_wakeup_timer_fn(struct timer_list *t) { - struct wakeup_source *ws = from_timer(ws, t, timer); + struct wakeup_source *ws = timer_container_of(ws, t, timer); unsigned long flags; spin_lock_irqsave(&ws->lock, flags); @@ -783,7 +816,7 @@ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** - * pm_wakeup_event - Notify the PM core of a wakeup event. + * pm_wakeup_dev_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. @@ -810,9 +843,9 @@ void pm_print_active_wakeup_sources(void) struct wakeup_source *last_activity_ws = NULL; srcuidx = srcu_read_lock(&wakeup_srcu); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (ws->active) { - pr_debug("active wakeup source: %s\n", ws->name); + pm_pr_dbg("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || @@ -823,7 +856,7 @@ void pm_print_active_wakeup_sources(void) } if (!active && last_activity_ws) - pr_debug("last active wakeup source: %s\n", + pm_pr_dbg("last active wakeup source: %s\n", last_activity_ws->name); srcu_read_unlock(&wakeup_srcu, srcuidx); } @@ -853,12 +886,13 @@ bool pm_wakeup_pending(void) raw_spin_unlock_irqrestore(&events_lock, flags); if (ret) { - pr_debug("PM: Wakeup pending, aborting suspend\n"); + pm_pr_dbg("Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); } return ret || atomic_read(&pm_abort_suspend) > 0; } +EXPORT_SYMBOL_GPL(pm_wakeup_pending); void pm_system_wakeup(void) { @@ -869,22 +903,50 @@ EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_system_cancel_wakeup(void) { - atomic_dec(&pm_abort_suspend); + atomic_dec_if_positive(&pm_abort_suspend); } -void pm_wakeup_clear(bool reset) +void pm_wakeup_clear(unsigned int irq_number) { - pm_wakeup_irq = 0; - if (reset) + raw_spin_lock_irq(&wakeup_irq_lock); + + if (irq_number && wakeup_irq[0] == irq_number) + wakeup_irq[0] = wakeup_irq[1]; + else + wakeup_irq[0] = 0; + + wakeup_irq[1] = 0; + + raw_spin_unlock_irq(&wakeup_irq_lock); + + if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { - if (pm_wakeup_irq == 0) { - pm_wakeup_irq = irq_number; + unsigned long flags; + + raw_spin_lock_irqsave(&wakeup_irq_lock, flags); + + if (wakeup_irq[0] == 0) + wakeup_irq[0] = irq_number; + else if (wakeup_irq[1] == 0) + wakeup_irq[1] = irq_number; + else + irq_number = 0; + + pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number); + + raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); + + if (irq_number) pm_system_wakeup(); - } +} + +unsigned int pm_wakeup_irq(void) +{ + return wakeup_irq[0]; } /** @@ -952,7 +1014,7 @@ bool pm_save_wakeup_count(unsigned int count) #ifdef CONFIG_PM_AUTOSLEEP /** * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. - * @enabled: Whether to set or to clear the autosleep_enabled flags. + * @set: Whether to set or to clear the autosleep_enabled flags. */ void pm_wakep_autosleep_enabled(bool set) { @@ -961,7 +1023,7 @@ void pm_wakep_autosleep_enabled(bool set) int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { ws->autosleep_enabled = set; @@ -978,8 +1040,6 @@ void pm_wakep_autosleep_enabled(bool set) } #endif /* CONFIG_PM_AUTOSLEEP */ -static struct dentry *wakeup_sources_stats_dentry; - /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. @@ -1042,7 +1102,7 @@ static void *wakeup_sources_stats_seq_start(struct seq_file *m, } *srcuidx = srcu_read_lock(&wakeup_srcu); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (n-- <= 0) return ws; } @@ -1063,6 +1123,9 @@ static void *wakeup_sources_stats_seq_next(struct seq_file *m, break; } + if (!next_ws) + print_wakeup_source_stats(m, &deleted_ws); + return next_ws; } @@ -1109,8 +1172,8 @@ static const struct file_operations wakeup_sources_stats_fops = { static int __init wakeup_sources_debugfs_init(void) { - wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources", - S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops); + debugfs_create_file("wakeup_sources", 0444, NULL, NULL, + &wakeup_sources_stats_fops); return 0; } diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c new file mode 100644 index 000000000000..3ffd427248e8 --- /dev/null +++ b/drivers/base/power/wakeup_stats.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Wakeup statistics in sysfs + * + * Copyright (c) 2019 Linux Foundation + * Copyright (c) 2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2019 Google Inc. + */ + +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/init.h> +#include <linux/kdev_t.h> +#include <linux/kernel.h> +#include <linux/kobject.h> +#include <linux/slab.h> +#include <linux/timekeeping.h> + +#include "power.h" + +static struct class *wakeup_class; + +#define wakeup_attr(_name) \ +static ssize_t _name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct wakeup_source *ws = dev_get_drvdata(dev); \ + \ + return sysfs_emit(buf, "%lu\n", ws->_name); \ +} \ +static DEVICE_ATTR_RO(_name) + +wakeup_attr(active_count); +wakeup_attr(event_count); +wakeup_attr(wakeup_count); +wakeup_attr(expire_count); +wakeup_attr(relax_count); + +static ssize_t active_time_ms_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + ktime_t active_time = + ws->active ? ktime_sub(ktime_get(), ws->last_time) : 0; + + return sysfs_emit(buf, "%lld\n", ktime_to_ms(active_time)); +} +static DEVICE_ATTR_RO(active_time_ms); + +static ssize_t total_time_ms_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + ktime_t active_time; + ktime_t total_time = ws->total_time; + + if (ws->active) { + active_time = ktime_sub(ktime_get(), ws->last_time); + total_time = ktime_add(total_time, active_time); + } + + return sysfs_emit(buf, "%lld\n", ktime_to_ms(total_time)); +} +static DEVICE_ATTR_RO(total_time_ms); + +static ssize_t max_time_ms_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + ktime_t active_time; + ktime_t max_time = ws->max_time; + + if (ws->active) { + active_time = ktime_sub(ktime_get(), ws->last_time); + if (active_time > max_time) + max_time = active_time; + } + + return sysfs_emit(buf, "%lld\n", ktime_to_ms(max_time)); +} +static DEVICE_ATTR_RO(max_time_ms); + +static ssize_t last_change_ms_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%lld\n", ktime_to_ms(ws->last_time)); +} +static DEVICE_ATTR_RO(last_change_ms); + +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ws->name); +} +static DEVICE_ATTR_RO(name); + +static ssize_t prevent_suspend_time_ms_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct wakeup_source *ws = dev_get_drvdata(dev); + ktime_t prevent_sleep_time = ws->prevent_sleep_time; + + if (ws->active && ws->autosleep_enabled) { + prevent_sleep_time = ktime_add(prevent_sleep_time, + ktime_sub(ktime_get(), ws->start_prevent_time)); + } + + return sysfs_emit(buf, "%lld\n", ktime_to_ms(prevent_sleep_time)); +} +static DEVICE_ATTR_RO(prevent_suspend_time_ms); + +static struct attribute *wakeup_source_attrs[] = { + &dev_attr_name.attr, + &dev_attr_active_count.attr, + &dev_attr_event_count.attr, + &dev_attr_wakeup_count.attr, + &dev_attr_expire_count.attr, + &dev_attr_relax_count.attr, + &dev_attr_active_time_ms.attr, + &dev_attr_total_time_ms.attr, + &dev_attr_max_time_ms.attr, + &dev_attr_last_change_ms.attr, + &dev_attr_prevent_suspend_time_ms.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wakeup_source); + +static void device_create_release(struct device *dev) +{ + kfree(dev); +} + +static struct device *wakeup_source_device_create(struct device *parent, + struct wakeup_source *ws) +{ + struct device *dev = NULL; + int retval; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + retval = -ENOMEM; + goto error; + } + + device_initialize(dev); + dev->devt = MKDEV(0, 0); + dev->class = wakeup_class; + dev->parent = parent; + dev->groups = wakeup_source_groups; + dev->release = device_create_release; + dev_set_drvdata(dev, ws); + device_set_pm_not_required(dev); + + retval = dev_set_name(dev, "wakeup%d", ws->id); + if (retval) + goto error; + + retval = device_add(dev); + if (retval) + goto error; + + return dev; + +error: + put_device(dev); + return ERR_PTR(retval); +} + +/** + * wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs. + * @parent: Device given wakeup source is associated with (or NULL if virtual). + * @ws: Wakeup source to be added in sysfs. + */ +int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws) +{ + struct device *dev; + + dev = wakeup_source_device_create(parent, ws); + if (IS_ERR(dev)) + return PTR_ERR(dev); + ws->dev = dev; + + return 0; +} + +/** + * pm_wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs + * for a device if they're missing. + * @parent: Device given wakeup source is associated with + */ +int pm_wakeup_source_sysfs_add(struct device *parent) +{ + if (!parent->power.wakeup || parent->power.wakeup->dev) + return 0; + + return wakeup_source_sysfs_add(parent, parent->power.wakeup); +} + +/** + * wakeup_source_sysfs_remove - Remove wakeup_source attributes from sysfs. + * @ws: Wakeup source to be removed from sysfs. + */ +void wakeup_source_sysfs_remove(struct wakeup_source *ws) +{ + device_unregister(ws->dev); +} + +static int __init wakeup_sources_sysfs_init(void) +{ + wakeup_class = class_create("wakeup"); + + return PTR_ERR_OR_ZERO(wakeup_class); +} +postcore_initcall(wakeup_sources_sysfs_init); |