From c43198af05cffa5de8d4f356c40ce4bdca066272 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 17 Mar 2023 17:54:34 +0100 Subject: thermal: core: Introduce thermal_cooling_device_present() Introduce a helper function, thermal_cooling_device_present(), for checking if the given cooling device is in the list of registered cooling devices to avoid some code duplication in a subsequent patch. No expected functional impact. Signed-off-by: Rafael J. Wysocki Tested-by: Zhang Rui Reviewed-by: Zhang Rui --- drivers/thermal/thermal_core.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'drivers/thermal') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 55679fd86505..8894342540f1 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1045,6 +1045,18 @@ devm_thermal_of_cooling_device_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_thermal_of_cooling_device_register); +static bool thermal_cooling_device_present(struct thermal_cooling_device *cdev) +{ + struct thermal_cooling_device *pos = NULL; + + list_for_each_entry(pos, &thermal_cdev_list, node) { + if (pos == cdev) + return true; + } + + return false; +} + static void __unbind(struct thermal_zone_device *tz, int mask, struct thermal_cooling_device *cdev) { @@ -1067,20 +1079,17 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev) int i; const struct thermal_zone_params *tzp; struct thermal_zone_device *tz; - struct thermal_cooling_device *pos = NULL; if (!cdev) return; mutex_lock(&thermal_list_lock); - list_for_each_entry(pos, &thermal_cdev_list, node) - if (pos == cdev) - break; - if (pos != cdev) { - /* thermal cooling device not found */ + + if (!thermal_cooling_device_present(cdev)) { mutex_unlock(&thermal_list_lock); return; } + list_del(&cdev->node); /* Unbind all thermal zones associated with 'this' cdev */ -- cgit v1.2.3 From 790930f44289c8209c57461b2db499fcc702e0b3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 17 Mar 2023 18:01:26 +0100 Subject: thermal: core: Introduce thermal_cooling_device_update() Introduce a core thermal API function, thermal_cooling_device_update(), for updating the max_state value for a cooling device and rearranging its statistics in sysfs after a possible change of its ->get_max_state() callback return value. That callback is now invoked only once, during cooling device registration, to populate the max_state field in the cooling device object, so if its return value changes, it needs to be invoked again and the new return value needs to be stored as max_state. Moreover, the statistics presented in sysfs need to be rearranged in general, because there may not be enough room in them to store data for all of the possible states (in the case when max_state grows). The new function takes care of that (and some other minor things related to it), but some extra locking and lockdep annotations are added in several places too to protect against crashes in the cases when the statistics are not present or when a stale max_state value might be used by sysfs attributes. Note that the actual user of the new function will be added separately. Link: https://lore.kernel.org/linux-pm/53ec1f06f61c984100868926f282647e57ecfb2d.camel@intel.com/ Signed-off-by: Rafael J. Wysocki Tested-by: Zhang Rui Reviewed-by: Zhang Rui --- drivers/thermal/thermal_core.c | 83 ++++++++++++++++++++++++++++++++++++++++- drivers/thermal/thermal_core.h | 2 + drivers/thermal/thermal_sysfs.c | 74 +++++++++++++++++++++++++++++++----- 3 files changed, 149 insertions(+), 10 deletions(-) (limited to 'drivers/thermal') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 8894342540f1..cfd4c1afeae7 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -613,6 +613,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, struct thermal_instance *pos; struct thermal_zone_device *pos1; struct thermal_cooling_device *pos2; + bool upper_no_limit; int result; if (trip >= tz->num_trips || trip < 0) @@ -632,7 +633,13 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, /* lower default 0, upper default max_state */ lower = lower == THERMAL_NO_LIMIT ? 0 : lower; - upper = upper == THERMAL_NO_LIMIT ? cdev->max_state : upper; + + if (upper == THERMAL_NO_LIMIT) { + upper = cdev->max_state; + upper_no_limit = true; + } else { + upper_no_limit = false; + } if (lower > upper || upper > cdev->max_state) return -EINVAL; @@ -644,6 +651,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, dev->cdev = cdev; dev->trip = trip; dev->upper = upper; + dev->upper_no_limit = upper_no_limit; dev->lower = lower; dev->target = THERMAL_NO_TARGET; dev->weight = weight; @@ -1057,6 +1065,79 @@ static bool thermal_cooling_device_present(struct thermal_cooling_device *cdev) return false; } +/** + * thermal_cooling_device_update - Update a cooling device object + * @cdev: Target cooling device. + * + * Update @cdev to reflect a change of the underlying hardware or platform. + * + * Must be called when the maximum cooling state of @cdev becomes invalid and so + * its .get_max_state() callback needs to be run to produce the new maximum + * cooling state value. + */ +void thermal_cooling_device_update(struct thermal_cooling_device *cdev) +{ + struct thermal_instance *ti; + unsigned long state; + + if (IS_ERR_OR_NULL(cdev)) + return; + + /* + * Hold thermal_list_lock throughout the update to prevent the device + * from going away while being updated. + */ + mutex_lock(&thermal_list_lock); + + if (!thermal_cooling_device_present(cdev)) + goto unlock_list; + + /* + * Update under the cdev lock to prevent the state from being set beyond + * the new limit concurrently. + */ + mutex_lock(&cdev->lock); + + if (cdev->ops->get_max_state(cdev, &cdev->max_state)) + goto unlock; + + thermal_cooling_device_stats_reinit(cdev); + + list_for_each_entry(ti, &cdev->thermal_instances, cdev_node) { + if (ti->upper == cdev->max_state) + continue; + + if (ti->upper < cdev->max_state) { + if (ti->upper_no_limit) + ti->upper = cdev->max_state; + + continue; + } + + ti->upper = cdev->max_state; + if (ti->lower > ti->upper) + ti->lower = ti->upper; + + if (ti->target == THERMAL_NO_TARGET) + continue; + + if (ti->target > ti->upper) + ti->target = ti->upper; + } + + if (cdev->ops->get_cur_state(cdev, &state) || state > cdev->max_state) + goto unlock; + + thermal_cooling_device_stats_update(cdev, state); + +unlock: + mutex_unlock(&cdev->lock); + +unlock_list: + mutex_unlock(&thermal_list_lock); +} +EXPORT_SYMBOL_GPL(thermal_cooling_device_update); + static void __unbind(struct thermal_zone_device *tz, int mask, struct thermal_cooling_device *cdev) { diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index 7af54382e915..3d4a787c6b28 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -101,6 +101,7 @@ struct thermal_instance { struct list_head tz_node; /* node in tz->thermal_instances */ struct list_head cdev_node; /* node in cdev->thermal_instances */ unsigned int weight; /* The weight of the cooling device */ + bool upper_no_limit; }; #define to_thermal_zone(_dev) \ @@ -127,6 +128,7 @@ int thermal_zone_create_device_groups(struct thermal_zone_device *, int); void thermal_zone_destroy_device_groups(struct thermal_zone_device *); void thermal_cooling_device_setup_sysfs(struct thermal_cooling_device *); void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev); +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev); /* used only at binding time */ ssize_t trip_point_show(struct device *, struct device_attribute *, char *); ssize_t weight_show(struct device *, struct device_attribute *, char *); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index cef860deaf91..a4aba7b8bb8b 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -685,6 +685,8 @@ void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, { struct cooling_dev_stats *stats = cdev->stats; + lockdep_assert_held(&cdev->lock); + if (!stats) return; @@ -706,13 +708,22 @@ static ssize_t total_trans_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int ret; + struct cooling_dev_stats *stats; + int ret = 0; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; spin_lock(&stats->lock); ret = sprintf(buf, "%u\n", stats->total_trans); spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return ret; } @@ -721,11 +732,18 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + spin_lock(&stats->lock); + update_time_in_state(stats); for (i = 0; i <= cdev->max_state; i++) { @@ -734,6 +752,9 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, } spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -742,8 +763,16 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int i, states = cdev->max_state + 1; + struct cooling_dev_stats *stats; + int i, states; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + + states = cdev->max_state + 1; spin_lock(&stats->lock); @@ -757,6 +786,9 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return count; } @@ -764,10 +796,18 @@ static ssize_t trans_table_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i, j; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) { + len = -ENODATA; + goto unlock; + } + len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); len += snprintf(buf + len, PAGE_SIZE - len, " : "); for (i = 0; i <= cdev->max_state; i++) { @@ -775,8 +815,10 @@ static ssize_t trans_table_show(struct device *dev, break; len += snprintf(buf + len, PAGE_SIZE - len, "state%2u ", i); } - if (len >= PAGE_SIZE) - return PAGE_SIZE; + if (len >= PAGE_SIZE) { + len = PAGE_SIZE; + goto unlock; + } len += snprintf(buf + len, PAGE_SIZE - len, "\n"); @@ -799,8 +841,12 @@ static ssize_t trans_table_show(struct device *dev, if (len >= PAGE_SIZE) { pr_warn_once("Thermal transition table exceeds PAGE_SIZE. Disabling\n"); - return -EFBIG; + len = -EFBIG; } + +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -830,6 +876,8 @@ static void cooling_device_stats_setup(struct thermal_cooling_device *cdev) unsigned long states = cdev->max_state + 1; int var; + lockdep_assert_held(&cdev->lock); + var = sizeof(*stats); var += sizeof(*stats->time_in_state) * states; var += sizeof(*stats->trans_table) * states * states; @@ -855,6 +903,8 @@ out: static void cooling_device_stats_destroy(struct thermal_cooling_device *cdev) { + lockdep_assert_held(&cdev->lock); + kfree(cdev->stats); cdev->stats = NULL; } @@ -879,6 +929,12 @@ void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev) cooling_device_stats_destroy(cdev); } +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev) +{ + cooling_device_stats_destroy(cdev); + cooling_device_stats_setup(cdev); +} + /* these helper will be used only at the time of bindig */ ssize_t trip_point_show(struct device *dev, struct device_attribute *attr, char *buf) -- cgit v1.2.3 From f1b80a3878b2d76ced46a275fdfd7fb80b4f083b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 14 Mar 2023 17:50:10 +0200 Subject: thermal: core: Restore behavior regarding invalid trip points Commit 7c3d5c20dc16 ("thermal/core: Add a generic thermal_zone_get_trip() function") stopped marking trip points with a zero temperature as disabled, behavior that was originally introduced in commit 81ad4276b505 ("Thermal: Ignore invalid trip points"). When using the mlxsw driver we see that when such trip points are not disabled, the thermal subsystem repeatedly tries to set the state of the associated cooling devices to the maximum state. Address this by restoring the original behavior and mark trip points with a zero temperature as disabled. Fixes: 7c3d5c20dc16 ("thermal/core: Add a generic thermal_zone_get_trip() function") Signed-off-by: Ido Schimmel Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/thermal') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 55679fd86505..b50931f84aaa 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1309,7 +1309,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t struct thermal_trip trip; result = thermal_zone_get_trip(tz, count, &trip); - if (result) + if (result || !trip.temperature) set_bit(count, &tz->trips_disabled); } -- cgit v1.2.3