From 2ee5f8f05949735fa2f4c463a5e13fcb3660c719 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:42 +0100 Subject: [PATCH 01/14] units: Add Watt units As there are the temperature units, let's add the Watt macros definition. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/units.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/units.h b/include/linux/units.h index aaf716364ec3..92c234e71cab 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,10 @@ #include +#define MILLIWATT_PER_WATT 1000L +#define MICROWATT_PER_MILLIWATT 1000L +#define MICROWATT_PER_WATT 1000000L + #define ABSOLUTE_ZERO_MILLICELSIUS -273150 static inline long milli_kelvin_to_millicelsius(long t) From f5ad1c747956d501516610ee7900f4a6d57ee2f5 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:43 +0100 Subject: [PATCH 02/14] Documentation/powercap/dtpm: Add documentation for dtpm The dynamic thermal and power management is a technique to dynamically adjust the power consumption of different devices in order to ensure a global thermal constraint. An userspace daemon is usually monitoring the temperature and the power to take immediate action on the device. The DTPM framework provides an unified API to userspace to act on the power. Document this framework. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- Documentation/power/index.rst | 1 + Documentation/power/powercap/dtpm.rst | 212 ++++++++++++++++++++++++++ 2 files changed, 213 insertions(+) create mode 100644 Documentation/power/powercap/dtpm.rst diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index ced8a8007434..a0f5244fb427 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -30,6 +30,7 @@ Power Management userland-swsusp powercap/powercap + powercap/dtpm regulator/consumer regulator/design diff --git a/Documentation/power/powercap/dtpm.rst b/Documentation/power/powercap/dtpm.rst new file mode 100644 index 000000000000..a38dee3d815b --- /dev/null +++ b/Documentation/power/powercap/dtpm.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================== +Dynamic Thermal Power Management framework +========================================== + +On the embedded world, the complexity of the SoC leads to an +increasing number of hotspots which need to be monitored and mitigated +as a whole in order to prevent the temperature to go above the +normative and legally stated 'skin temperature'. + +Another aspect is to sustain the performance for a given power budget, +for example virtual reality where the user can feel dizziness if the +performance is capped while a big CPU is processing something else. Or +reduce the battery charging because the dissipated power is too high +compared with the power consumed by other devices. + +The user space is the most adequate place to dynamically act on the +different devices by limiting their power given an application +profile: it has the knowledge of the platform. + +The Dynamic Thermal Power Management (DTPM) is a technique acting on +the device power by limiting and/or balancing a power budget among +different devices. + +The DTPM framework provides an unified interface to act on the +device power. + +Overview +======== + +The DTPM framework relies on the powercap framework to create the +powercap entries in the sysfs directory and implement the backend +driver to do the connection with the power manageable device. + +The DTPM is a tree representation describing the power constraints +shared between devices, not their physical positions. + +The nodes of the tree are a virtual description aggregating the power +characteristics of the children nodes and their power limitations. + +The leaves of the tree are the real power manageable devices. + +For instance:: + + SoC + | + `-- pkg + | + |-- pd0 (cpu0-3) + | + `-- pd1 (cpu4-5) + +The pkg power will be the sum of pd0 and pd1 power numbers:: + + SoC (400mW - 3100mW) + | + `-- pkg (400mW - 3100mW) + | + |-- pd0 (100mW - 700mW) + | + `-- pd1 (300mW - 2400mW) + +When the nodes are inserted in the tree, their power characteristics are propagated to the parents:: + + SoC (600mW - 5900mW) + | + |-- pkg (400mW - 3100mW) + | | + | |-- pd0 (100mW - 700mW) + | | + | `-- pd1 (300mW - 2400mW) + | + `-- pd2 (200mW - 2800mW) + +Each node have a weight on a 2^10 basis reflecting the percentage of power consumption along the siblings:: + + SoC (w=1024) + | + |-- pkg (w=538) + | | + | |-- pd0 (w=231) + | | + | `-- pd1 (w=794) + | + `-- pd2 (w=486) + + Note the sum of weights at the same level are equal to 1024. + +When a power limitation is applied to a node, then it is distributed along the children given their weights. For example, if we set a power limitation of 3200mW at the 'SoC' root node, the resulting tree will be:: + + SoC (w=1024) <--- power_limit = 3200mW + | + |-- pkg (w=538) --> power_limit = 1681mW + | | + | |-- pd0 (w=231) --> power_limit = 378mW + | | + | `-- pd1 (w=794) --> power_limit = 1303mW + | + `-- pd2 (w=486) --> power_limit = 1519mW + + +Flat description +---------------- + +A root node is created and it is the parent of all the nodes. This +description is the simplest one and it is supposed to give to user +space a flat representation of all the devices supporting the power +limitation without any power limitation distribution. + +Hierarchical description +------------------------ + +The different devices supporting the power limitation are represented +hierarchically. There is one root node, all intermediate nodes are +grouping the child nodes which can be intermediate nodes also or real +devices. + +The intermediate nodes aggregate the power information and allows to +set the power limit given the weight of the nodes. + +User space API +============== + +As stated in the overview, the DTPM framework is built on top of the +powercap framework. Thus the sysfs interface is the same, please refer +to the powercap documentation for further details. + + * power_uw: Instantaneous power consumption. If the node is an + intermediate node, then the power consumption will be the sum of all + children power consumption. + + * max_power_range_uw: The power range resulting of the maximum power + minus the minimum power. + + * name: The name of the node. This is implementation dependent. Even + if it is not recommended for the user space, several nodes can have + the same name. + + * constraint_X_name: The name of the constraint. + + * constraint_X_max_power_uw: The maximum power limit to be applicable + to the node. + + * constraint_X_power_limit_uw: The power limit to be applied to the + node. If the value contained in constraint_X_max_power_uw is set, + the constraint will be removed. + + * constraint_X_time_window_us: The meaning of this file will depend + on the constraint number. + +Constraints +----------- + + * Constraint 0: The power limitation is immediately applied, without + limitation in time. + +Kernel API +========== + +Overview +-------- + +The DTPM framework has no power limiting backend support. It is +generic and provides a set of API to let the different drivers to +implement the backend part for the power limitation and create the +power constraints tree. + +It is up to the platform to provide the initialization function to +allocate and link the different nodes of the tree. + +A special macro has the role of declaring a node and the corresponding +initialization function via a description structure. This one contains +an optional parent field allowing to hook different devices to an +already existing tree at boot time. + +For instance:: + + struct dtpm_descr my_descr = { + .name = "my_name", + .init = my_init_func, + }; + + DTPM_DECLARE(my_descr); + +The nodes of the DTPM tree are described with dtpm structure. The +steps to add a new power limitable device is done in three steps: + + * Allocate the dtpm node + * Set the power number of the dtpm node + * Register the dtpm node + +The registration of the dtpm node is done with the powercap +ops. Basically, it must implements the callbacks to get and set the +power and the limit. + +Alternatively, if the node to be inserted is an intermediate one, then +a simple function to insert it as a future parent is available. + +If a device has its power characteristics changing, then the tree must +be updated with the new power numbers and weights. + +Nomenclature +------------ + + * dtpm_alloc() : Allocate and initialize a dtpm structure + + * dtpm_register() : Add the dtpm node to the tree + + * dtpm_unregister() : Remove the dtpm node from the tree + + * dtpm_update_power() : Update the power characteristics of the dtpm node From a20d0ef97abf486a917aff066c457bdb930425af Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:44 +0100 Subject: [PATCH 03/14] powercap/drivers/dtpm: Add API for dynamic thermal power management On the embedded world, the complexity of the SoC leads to an increasing number of hotspots which need to be monitored and mitigated as a whole in order to prevent the temperature to go above the normative and legally stated 'skin temperature'. Another aspect is to sustain the performance for a given power budget, for example virtual reality where the user can feel dizziness if the GPU performance is capped while a big CPU is processing something else. Or reduce the battery charging because the dissipated power is too high compared with the power consumed by other devices. The userspace is the most adequate place to dynamically act on the different devices by limiting their power given an application profile: it has the knowledge of the platform. These userspace daemons are in charge of the Dynamic Thermal Power Management (DTPM). Nowadays, the dtpm daemons are abusing the thermal framework as they act on the cooling device state to force a specific and arbitrary state without taking care of the governor decisions. Given the closed loop of some governors that can confuse the logic or directly enter in a decision conflict. As the number of cooling device support is limited today to the CPU and the GPU, the dtpm daemons have little control on the power dissipation of the system. The out of tree solutions are hacking around here and there in the drivers, in the frameworks to have control on the devices. The common solution is to declare them as cooling devices. There is no unification of the power limitation unit, opaque states are used. This patch provides a way to create a hierarchy of constraints using the powercap framework. The devices which are registered as power limit-able devices are represented in this hierarchy as a tree. They are linked together with intermediate nodes which are just there to propagate the constraint to the children. The leaves of the tree are the real devices, the intermediate nodes are virtual, aggregating the children constraints and power characteristics. Each node have a weight on a 2^10 basis, in order to reflect the percentage of power distribution of the children's node. This percentage is used to dispatch the power limit to the children. The weight is computed against the max power of the siblings. This simple approach allows to do a fair distribution of the power limit. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/powercap/Kconfig | 6 + drivers/powercap/Makefile | 1 + drivers/powercap/dtpm.c | 473 ++++++++++++++++++++++++++++++ include/asm-generic/vmlinux.lds.h | 11 + include/linux/dtpm.h | 75 +++++ 5 files changed, 566 insertions(+) create mode 100644 drivers/powercap/dtpm.c create mode 100644 include/linux/dtpm.h diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index bc228725346b..cc1953bd8bed 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -43,4 +43,10 @@ config IDLE_INJECT CPUs for power capping. Idle period can be injected synchronously on a set of specified CPUs or alternatively on a per CPU basis. + +config DTPM + bool "Power capping for Dynamic Thermal Power Management" + help + This enables support for the power capping for the dynamic + thermal power management userspace engine. endif diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile index 7255c94ec61c..6482ac52054d 100644 --- a/drivers/powercap/Makefile +++ b/drivers/powercap/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DTPM) += dtpm.o obj-$(CONFIG_POWERCAP) += powercap_sys.o obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c new file mode 100644 index 000000000000..5b6857e9b064 --- /dev/null +++ b/drivers/powercap/dtpm.c @@ -0,0 +1,473 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Linaro Limited + * + * Author: Daniel Lezcano + * + * The powercap based Dynamic Thermal Power Management framework + * provides to the userspace a consistent API to set the power limit + * on some devices. + * + * DTPM defines the functions to create a tree of constraints. Each + * parent node is a virtual description of the aggregation of the + * children. It propagates the constraints set at its level to its + * children and collect the children power information. The leaves of + * the tree are the real devices which have the ability to get their + * current power consumption and set their power limit. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +#define DTPM_POWER_LIMIT_FLAG BIT(0) + +static const char *constraint_name[] = { + "Instantaneous", +}; + +static DEFINE_MUTEX(dtpm_lock); +static struct powercap_control_type *pct; +static struct dtpm *root; + +static int get_time_window_us(struct powercap_zone *pcz, int cid, u64 *window) +{ + return -ENOSYS; +} + +static int set_time_window_us(struct powercap_zone *pcz, int cid, u64 window) +{ + return -ENOSYS; +} + +static int get_max_power_range_uw(struct powercap_zone *pcz, u64 *max_power_uw) +{ + struct dtpm *dtpm = to_dtpm(pcz); + + mutex_lock(&dtpm_lock); + *max_power_uw = dtpm->power_max - dtpm->power_min; + mutex_unlock(&dtpm_lock); + + return 0; +} + +static int __get_power_uw(struct dtpm *dtpm, u64 *power_uw) +{ + struct dtpm *child; + u64 power; + int ret = 0; + + if (dtpm->ops) { + *power_uw = dtpm->ops->get_power_uw(dtpm); + return 0; + } + + *power_uw = 0; + + list_for_each_entry(child, &dtpm->children, sibling) { + ret = __get_power_uw(child, &power); + if (ret) + break; + *power_uw += power; + } + + return ret; +} + +static int get_power_uw(struct powercap_zone *pcz, u64 *power_uw) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + ret = __get_power_uw(dtpm, power_uw); + mutex_unlock(&dtpm_lock); + + return ret; +} + +static void __dtpm_rebalance_weight(struct dtpm *dtpm) +{ + struct dtpm *child; + + list_for_each_entry(child, &dtpm->children, sibling) { + + pr_debug("Setting weight '%d' for '%s'\n", + child->weight, child->zone.name); + + child->weight = DIV_ROUND_CLOSEST(child->power_max * 1024, + dtpm->power_max); + + __dtpm_rebalance_weight(child); + } +} + +static void __dtpm_sub_power(struct dtpm *dtpm) +{ + struct dtpm *parent = dtpm->parent; + + while (parent) { + parent->power_min -= dtpm->power_min; + parent->power_max -= dtpm->power_max; + parent->power_limit -= dtpm->power_limit; + parent = parent->parent; + } + + __dtpm_rebalance_weight(root); +} + +static void __dtpm_add_power(struct dtpm *dtpm) +{ + struct dtpm *parent = dtpm->parent; + + while (parent) { + parent->power_min += dtpm->power_min; + parent->power_max += dtpm->power_max; + parent->power_limit += dtpm->power_limit; + parent = parent->parent; + } + + __dtpm_rebalance_weight(root); +} + +/** + * dtpm_update_power - Update the power on the dtpm + * @dtpm: a pointer to a dtpm structure to update + * @power_min: a u64 representing the new power_min value + * @power_max: a u64 representing the new power_max value + * + * Function to update the power values of the dtpm node specified in + * parameter. These new values will be propagated to the tree. + * + * Return: zero on success, -EINVAL if the values are inconsistent + */ +int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max) +{ + mutex_lock(&dtpm_lock); + + if (power_min == dtpm->power_min && power_max == dtpm->power_max) + return 0; + + if (power_max < power_min) + return -EINVAL; + + __dtpm_sub_power(dtpm); + + dtpm->power_min = power_min; + dtpm->power_max = power_max; + if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags)) + dtpm->power_limit = power_max; + + __dtpm_add_power(dtpm); + + mutex_unlock(&dtpm_lock); + + return 0; +} + +/** + * dtpm_release_zone - Cleanup when the node is released + * @pcz: a pointer to a powercap_zone structure + * + * Do some housecleaning and update the weight on the tree. The + * release will be denied if the node has children. This function must + * be called by the specific release callback of the different + * backends. + * + * Return: 0 on success, -EBUSY if there are children + */ +int dtpm_release_zone(struct powercap_zone *pcz) +{ + struct dtpm *dtpm = to_dtpm(pcz); + struct dtpm *parent = dtpm->parent; + + mutex_lock(&dtpm_lock); + + if (!list_empty(&dtpm->children)) + return -EBUSY; + + if (parent) + list_del(&dtpm->sibling); + + __dtpm_sub_power(dtpm); + + mutex_unlock(&dtpm_lock); + + if (dtpm->ops) + dtpm->ops->release(dtpm); + + kfree(dtpm); + + return 0; +} + +static int __get_power_limit_uw(struct dtpm *dtpm, int cid, u64 *power_limit) +{ + *power_limit = dtpm->power_limit; + return 0; +} + +static int get_power_limit_uw(struct powercap_zone *pcz, + int cid, u64 *power_limit) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + ret = __get_power_limit_uw(dtpm, cid, power_limit); + mutex_unlock(&dtpm_lock); + + return ret; +} + +/* + * Set the power limit on the nodes, the power limit is distributed + * given the weight of the children. + * + * The dtpm node lock must be held when calling this function. + */ +static int __set_power_limit_uw(struct dtpm *dtpm, int cid, u64 power_limit) +{ + struct dtpm *child; + int ret = 0; + u64 power; + + /* + * A max power limitation means we remove the power limit, + * otherwise we set a constraint and flag the dtpm node. + */ + if (power_limit == dtpm->power_max) { + clear_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags); + } else { + set_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags); + } + + pr_debug("Setting power limit for '%s': %llu uW\n", + dtpm->zone.name, power_limit); + + /* + * Only leaves of the dtpm tree has ops to get/set the power + */ + if (dtpm->ops) { + dtpm->power_limit = dtpm->ops->set_power_uw(dtpm, power_limit); + } else { + dtpm->power_limit = 0; + + list_for_each_entry(child, &dtpm->children, sibling) { + + /* + * Integer division rounding will inevitably + * lead to a different min or max value when + * set several times. In order to restore the + * initial value, we force the child's min or + * max power every time if the constraint is + * at the boundaries. + */ + if (power_limit == dtpm->power_max) { + power = child->power_max; + } else if (power_limit == dtpm->power_min) { + power = child->power_min; + } else { + power = DIV_ROUND_CLOSEST( + power_limit * child->weight, 1024); + } + + pr_debug("Setting power limit for '%s': %llu uW\n", + child->zone.name, power); + + ret = __set_power_limit_uw(child, cid, power); + if (!ret) + ret = __get_power_limit_uw(child, cid, &power); + + if (ret) + break; + + dtpm->power_limit += power; + } + } + + return ret; +} + +static int set_power_limit_uw(struct powercap_zone *pcz, + int cid, u64 power_limit) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + + /* + * Don't allow values outside of the power range previously + * set when initializing the power numbers. + */ + power_limit = clamp_val(power_limit, dtpm->power_min, dtpm->power_max); + + ret = __set_power_limit_uw(dtpm, cid, power_limit); + + pr_debug("%s: power limit: %llu uW, power max: %llu uW\n", + dtpm->zone.name, dtpm->power_limit, dtpm->power_max); + + mutex_unlock(&dtpm_lock); + + return ret; +} + +static const char *get_constraint_name(struct powercap_zone *pcz, int cid) +{ + return constraint_name[cid]; +} + +static int get_max_power_uw(struct powercap_zone *pcz, int id, u64 *max_power) +{ + struct dtpm *dtpm = to_dtpm(pcz); + + mutex_lock(&dtpm_lock); + *max_power = dtpm->power_max; + mutex_unlock(&dtpm_lock); + + return 0; +} + +static struct powercap_zone_constraint_ops constraint_ops = { + .set_power_limit_uw = set_power_limit_uw, + .get_power_limit_uw = get_power_limit_uw, + .set_time_window_us = set_time_window_us, + .get_time_window_us = get_time_window_us, + .get_max_power_uw = get_max_power_uw, + .get_name = get_constraint_name, +}; + +static struct powercap_zone_ops zone_ops = { + .get_max_power_range_uw = get_max_power_range_uw, + .get_power_uw = get_power_uw, + .release = dtpm_release_zone, +}; + +/** + * dtpm_alloc - Allocate and initialize a dtpm struct + * @name: a string specifying the name of the node + * + * Return: a struct dtpm pointer, NULL in case of error + */ +struct dtpm *dtpm_alloc(struct dtpm_ops *ops) +{ + struct dtpm *dtpm; + + dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL); + if (dtpm) { + INIT_LIST_HEAD(&dtpm->children); + INIT_LIST_HEAD(&dtpm->sibling); + dtpm->weight = 1024; + dtpm->ops = ops; + } + + return dtpm; +} + +/** + * dtpm_unregister - Unregister a dtpm node from the hierarchy tree + * @dtpm: a pointer to a dtpm structure corresponding to the node to be removed + * + * Call the underlying powercap unregister function. That will call + * the release callback of the powercap zone. + */ +void dtpm_unregister(struct dtpm *dtpm) +{ + powercap_unregister_zone(pct, &dtpm->zone); + + pr_info("Unregistered dtpm node '%s'\n", dtpm->zone.name); +} + +/** + * dtpm_register - Register a dtpm node in the hierarchy tree + * @name: a string specifying the name of the node + * @dtpm: a pointer to a dtpm structure corresponding to the new node + * @parent: a pointer to a dtpm structure corresponding to the parent node + * + * Create a dtpm node in the tree. If no parent is specified, the node + * is the root node of the hierarchy. If the root node already exists, + * then the registration will fail. The powercap controller must be + * initialized before calling this function. + * + * The dtpm structure must be initialized with the power numbers + * before calling this function. + * + * Return: zero on success, a negative value in case of error: + * -EAGAIN: the function is called before the framework is initialized. + * -EBUSY: the root node is already inserted + * -EINVAL: * there is no root node yet and @parent is specified + * * no all ops are defined + * * parent have ops which are reserved for leaves + * Other negative values are reported back from the powercap framework + */ +int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) +{ + struct powercap_zone *pcz; + + if (!pct) + return -EAGAIN; + + if (root && !parent) + return -EBUSY; + + if (!root && parent) + return -EINVAL; + + if (parent && parent->ops) + return -EINVAL; + + if (!dtpm) + return -EINVAL; + + if (dtpm->ops && !(dtpm->ops->set_power_uw && + dtpm->ops->get_power_uw && + dtpm->ops->release)) + return -EINVAL; + + pcz = powercap_register_zone(&dtpm->zone, pct, name, + parent ? &parent->zone : NULL, + &zone_ops, MAX_DTPM_CONSTRAINTS, + &constraint_ops); + if (IS_ERR(pcz)) + return PTR_ERR(pcz); + + mutex_lock(&dtpm_lock); + + if (parent) { + list_add_tail(&dtpm->sibling, &parent->children); + dtpm->parent = parent; + } else { + root = dtpm; + } + + __dtpm_add_power(dtpm); + + pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n", + dtpm->zone.name, dtpm->power_min, dtpm->power_max); + + mutex_unlock(&dtpm_lock); + + return 0; +} + +static int __init dtpm_init(void) +{ + struct dtpm_descr **dtpm_descr; + + pct = powercap_register_control_type(NULL, "dtpm", NULL); + if (!pct) { + pr_err("Failed to register control type\n"); + return -EINVAL; + } + + for_each_dtpm_table(dtpm_descr) + (*dtpm_descr)->init(*dtpm_descr); + + return 0; +} +late_initcall(dtpm_init); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b2b3d81b1535..b3e4e0740089 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -316,6 +316,16 @@ #define THERMAL_TABLE(name) #endif +#ifdef CONFIG_DTPM +#define DTPM_TABLE() \ + . = ALIGN(8); \ + __dtpm_table = .; \ + KEEP(*(__dtpm_table)) \ + __dtpm_table_end = .; +#else +#define DTPM_TABLE() +#endif + #define KERNEL_DTB() \ STRUCT_ALIGN(); \ __dtb_start = .; \ @@ -733,6 +743,7 @@ ACPI_PROBE_TABLE(irqchip) \ ACPI_PROBE_TABLE(timer) \ THERMAL_TABLE(governor) \ + DTPM_TABLE() \ EARLYCON_TABLE() \ LSM_TABLE() \ EARLY_LSM_TABLE() \ diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h new file mode 100644 index 000000000000..7a1d0b50e334 --- /dev/null +++ b/include/linux/dtpm.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Linaro Ltd + * + * Author: Daniel Lezcano + */ +#ifndef ___DTPM_H__ +#define ___DTPM_H__ + +#include + +#define MAX_DTPM_DESCR 8 +#define MAX_DTPM_CONSTRAINTS 1 + +struct dtpm { + struct powercap_zone zone; + struct dtpm *parent; + struct list_head sibling; + struct list_head children; + struct dtpm_ops *ops; + unsigned long flags; + u64 power_limit; + u64 power_max; + u64 power_min; + int weight; + void *private; +}; + +struct dtpm_ops { + u64 (*set_power_uw)(struct dtpm *, u64); + u64 (*get_power_uw)(struct dtpm *); + void (*release)(struct dtpm *); +}; + +struct dtpm_descr; + +typedef int (*dtpm_init_t)(struct dtpm_descr *); + +struct dtpm_descr { + struct dtpm *parent; + const char *name; + dtpm_init_t init; +}; + +/* Init section thermal table */ +extern struct dtpm_descr *__dtpm_table[]; +extern struct dtpm_descr *__dtpm_table_end[]; + +#define DTPM_TABLE_ENTRY(name) \ + static typeof(name) *__dtpm_table_entry_##name \ + __used __section("__dtpm_table") = &name + +#define DTPM_DECLARE(name) DTPM_TABLE_ENTRY(name) + +#define for_each_dtpm_table(__dtpm) \ + for (__dtpm = __dtpm_table; \ + __dtpm < __dtpm_table_end; \ + __dtpm++) + +static inline struct dtpm *to_dtpm(struct powercap_zone *zone) +{ + return container_of(zone, struct dtpm, zone); +} + +int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max); + +int dtpm_release_zone(struct powercap_zone *pcz); + +struct dtpm *dtpm_alloc(struct dtpm_ops *ops); + +void dtpm_unregister(struct dtpm *dtpm); + +int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); + +#endif From 0e8f68d7f04856a9e2ad4817b477fa35124888bd Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:45 +0100 Subject: [PATCH 04/14] powercap/drivers/dtpm: Add CPU energy model based support With the powercap dtpm controller, we are able to plug devices with power limitation features in the tree. The following patch introduces the CPU power limitation based on the energy model and the performance states. The power limitation is done at the performance domain level. If some CPUs are unplugged, the corresponding power will be subtracted from the performance domain total power. It is up to the platform to initialize the dtpm tree and add the CPU. Here is an example to create a simple tree with one root node called "pkg" and the CPU's performance domains. static int dtpm_register_pkg(struct dtpm_descr *descr) { struct dtpm *pkg; int ret; pkg = dtpm_alloc(NULL); if (!pkg) return -ENOMEM; ret = dtpm_register(descr->name, pkg, descr->parent); if (ret) return ret; return dtpm_register_cpu(pkg); } static struct dtpm_descr descr = { .name = "pkg", .init = dtpm_register_pkg, }; DTPM_DECLARE(descr); Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/powercap/Kconfig | 7 + drivers/powercap/Makefile | 1 + drivers/powercap/dtpm_cpu.c | 257 ++++++++++++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + include/linux/dtpm.h | 2 + 5 files changed, 268 insertions(+) create mode 100644 drivers/powercap/dtpm_cpu.c diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index cc1953bd8bed..20b4325c6161 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -49,4 +49,11 @@ config DTPM help This enables support for the power capping for the dynamic thermal power management userspace engine. + +config DTPM_CPU + bool "Add CPU power capping based on the energy model" + depends on DTPM && ENERGY_MODEL + help + This enables support for CPU power limitation based on + energy model. endif diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile index 6482ac52054d..fabcf388a8d3 100644 --- a/drivers/powercap/Makefile +++ b/drivers/powercap/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DTPM) += dtpm.o +obj-$(CONFIG_DTPM_CPU) += dtpm_cpu.o obj-$(CONFIG_POWERCAP) += powercap_sys.o obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c new file mode 100644 index 000000000000..6933c783c6b4 --- /dev/null +++ b/drivers/powercap/dtpm_cpu.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Linaro Limited + * + * Author: Daniel Lezcano + * + * The DTPM CPU is based on the energy model. It hooks the CPU in the + * DTPM tree which in turns update the power number by propagating the + * power number from the CPU energy model information to the parents. + * + * The association between the power and the performance state, allows + * to set the power of the CPU at the OPP granularity. + * + * The CPU hotplug is supported and the power numbers will be updated + * if a CPU is hot plugged / unplugged. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +static struct dtpm *__parent; + +static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu); + +struct dtpm_cpu { + struct freq_qos_request qos_req; + int cpu; +}; + +/* + * When a new CPU is inserted at hotplug or boot time, add the power + * contribution and update the dtpm tree. + */ +static int power_add(struct dtpm *dtpm, struct em_perf_domain *em) +{ + u64 power_min, power_max; + + power_min = em->table[0].power; + power_min *= MICROWATT_PER_MILLIWATT; + power_min += dtpm->power_min; + + power_max = em->table[em->nr_perf_states - 1].power; + power_max *= MICROWATT_PER_MILLIWATT; + power_max += dtpm->power_max; + + return dtpm_update_power(dtpm, power_min, power_max); +} + +/* + * When a CPU is unplugged, remove its power contribution from the + * dtpm tree. + */ +static int power_sub(struct dtpm *dtpm, struct em_perf_domain *em) +{ + u64 power_min, power_max; + + power_min = em->table[0].power; + power_min *= MICROWATT_PER_MILLIWATT; + power_min = dtpm->power_min - power_min; + + power_max = em->table[em->nr_perf_states - 1].power; + power_max *= MICROWATT_PER_MILLIWATT; + power_max = dtpm->power_max - power_max; + + return dtpm_update_power(dtpm, power_min, power_max); +} + +static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct em_perf_domain *pd; + struct cpumask cpus; + unsigned long freq; + u64 power; + int i, nr_cpus; + + pd = em_cpu_get(dtpm_cpu->cpu); + + cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); + + nr_cpus = cpumask_weight(&cpus); + + for (i = 0; i < pd->nr_perf_states; i++) { + + power = pd->table[i].power * MICROWATT_PER_MILLIWATT * nr_cpus; + + if (power > power_limit) + break; + } + + freq = pd->table[i - 1].frequency; + + freq_qos_update_request(&dtpm_cpu->qos_req, freq); + + power_limit = pd->table[i - 1].power * + MICROWATT_PER_MILLIWATT * nr_cpus; + + return power_limit; +} + +static u64 get_pd_power_uw(struct dtpm *dtpm) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct em_perf_domain *pd; + struct cpumask cpus; + unsigned long freq; + int i, nr_cpus; + + pd = em_cpu_get(dtpm_cpu->cpu); + freq = cpufreq_quick_get(dtpm_cpu->cpu); + cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); + nr_cpus = cpumask_weight(&cpus); + + for (i = 0; i < pd->nr_perf_states; i++) { + + if (pd->table[i].frequency < freq) + continue; + + return pd->table[i].power * + MICROWATT_PER_MILLIWATT * nr_cpus; + } + + return 0; +} + +static void pd_release(struct dtpm *dtpm) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + + if (freq_qos_request_active(&dtpm_cpu->qos_req)) + freq_qos_remove_request(&dtpm_cpu->qos_req); + + kfree(dtpm_cpu); +} + +static struct dtpm_ops dtpm_ops = { + .set_power_uw = set_pd_power_limit, + .get_power_uw = get_pd_power_uw, + .release = pd_release, +}; + +static int cpuhp_dtpm_cpu_offline(unsigned int cpu) +{ + struct cpufreq_policy *policy; + struct em_perf_domain *pd; + struct dtpm *dtpm; + + policy = cpufreq_cpu_get(cpu); + + if (!policy) + return 0; + + pd = em_cpu_get(cpu); + if (!pd) + return -EINVAL; + + dtpm = per_cpu(dtpm_per_cpu, cpu); + + power_sub(dtpm, pd); + + if (cpumask_weight(policy->cpus) != 1) + return 0; + + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = NULL; + + dtpm_unregister(dtpm); + + return 0; +} + +static int cpuhp_dtpm_cpu_online(unsigned int cpu) +{ + struct dtpm *dtpm; + struct dtpm_cpu *dtpm_cpu; + struct cpufreq_policy *policy; + struct em_perf_domain *pd; + char name[CPUFREQ_NAME_LEN]; + int ret = -ENOMEM; + + policy = cpufreq_cpu_get(cpu); + + if (!policy) + return 0; + + pd = em_cpu_get(cpu); + if (!pd) + return -EINVAL; + + dtpm = per_cpu(dtpm_per_cpu, cpu); + if (dtpm) + return power_add(dtpm, pd); + + dtpm = dtpm_alloc(&dtpm_ops); + if (!dtpm) + return -EINVAL; + + dtpm_cpu = kzalloc(sizeof(dtpm_cpu), GFP_KERNEL); + if (!dtpm_cpu) + goto out_kfree_dtpm; + + dtpm->private = dtpm_cpu; + dtpm_cpu->cpu = cpu; + + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = dtpm; + + sprintf(name, "cpu%d", dtpm_cpu->cpu); + + ret = dtpm_register(name, dtpm, __parent); + if (ret) + goto out_kfree_dtpm_cpu; + + ret = power_add(dtpm, pd); + if (ret) + goto out_dtpm_unregister; + + ret = freq_qos_add_request(&policy->constraints, + &dtpm_cpu->qos_req, FREQ_QOS_MAX, + pd->table[pd->nr_perf_states - 1].frequency); + if (ret) + goto out_power_sub; + + return 0; + +out_power_sub: + power_sub(dtpm, pd); + +out_dtpm_unregister: + dtpm_unregister(dtpm); + dtpm_cpu = NULL; + dtpm = NULL; + +out_kfree_dtpm_cpu: + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = NULL; + kfree(dtpm_cpu); + +out_kfree_dtpm: + kfree(dtpm); + return ret; +} + +int dtpm_register_cpu(struct dtpm *parent) +{ + __parent = parent; + + return cpuhp_setup_state(CPUHP_AP_DTPM_CPU_ONLINE, + "dtpm_cpu:online", + cpuhp_dtpm_cpu_online, + cpuhp_dtpm_cpu_offline); +} diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0042ef362511..ee09a39627d6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -193,6 +193,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, + CPUHP_AP_DTPM_CPU_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 7a1d0b50e334..e80a332e3d8a 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -72,4 +72,6 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); +int dtpm_register_cpu(struct dtpm *parent); + #endif From 8f50db4b5c79af2ba54f5fbe8a5173fd7f37a493 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 30 Dec 2020 16:37:44 +0100 Subject: [PATCH 05/14] powercap/drivers/dtpm: Fix __udivdi3 and __aeabi_uldivmod unresolved symbols 32-bit architectures do not support u64 divisions, so the macro DIV_ROUND_CLOSEST is not adequate as the compiler will replace the call to an unexisting function for the platform, leading to unresolved references to symbols. Fix this by using the compatible macros: DIV64_U64_ROUND_CLOSEST and DIV_ROUND_CLOSEST_ULL. Fixes: a20d0ef97abf ("powercap/drivers/dtpm: Add API for dynamic thermal power management") Reported-by: kernel test robot Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 5b6857e9b064..0abcc439d728 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -99,8 +99,8 @@ static void __dtpm_rebalance_weight(struct dtpm *dtpm) pr_debug("Setting weight '%d' for '%s'\n", child->weight, child->zone.name); - child->weight = DIV_ROUND_CLOSEST(child->power_max * 1024, - dtpm->power_max); + child->weight = DIV64_U64_ROUND_CLOSEST( + child->power_max * 1024, dtpm->power_max); __dtpm_rebalance_weight(child); } @@ -272,7 +272,7 @@ static int __set_power_limit_uw(struct dtpm *dtpm, int cid, u64 power_limit) } else if (power_limit == dtpm->power_min) { power = child->power_min; } else { - power = DIV_ROUND_CLOSEST( + power = DIV_ROUND_CLOSEST_ULL( power_limit * child->weight, 1024); } From 2185c23071e2c1f26fbccb323aa831732540cfcc Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Jan 2021 11:36:35 +0300 Subject: [PATCH 06/14] powercap/drivers/dtpm: Fix a double shift bug The DTPM_POWER_LIMIT_FLAG is used for test_bit() etc which take a bit number so it should be bit 0. But currently it's set to BIT(0) then that is double shifted equivalent to BIT(BIT(0)). This doesn't cause a run time problem because it's done consistently. Fixes: a20d0ef97abf ("powercap/drivers/dtpm: Add API for dynamic thermal power management") Signed-off-by: Dan Carpenter Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 0abcc439d728..d49df0569cd4 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -24,7 +24,7 @@ #include #include -#define DTPM_POWER_LIMIT_FLAG BIT(0) +#define DTPM_POWER_LIMIT_FLAG 0 static const char *constraint_name[] = { "Instantaneous", From 0fe1329b7b518f67c8f1760711eb0eaf90433fd3 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Jan 2021 11:41:09 +0300 Subject: [PATCH 07/14] powercap/drivers/dtpm: Fix some missing unlock bugs We need to unlock on these paths before returning. Fixes: a20d0ef97abf ("powercap/drivers/dtpm: Add API for dynamic thermal power management") Signed-off-by: Dan Carpenter Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index d49df0569cd4..470a1182b868 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -147,13 +147,17 @@ static void __dtpm_add_power(struct dtpm *dtpm) */ int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max) { + int ret = 0; + mutex_lock(&dtpm_lock); if (power_min == dtpm->power_min && power_max == dtpm->power_max) - return 0; + goto unlock; - if (power_max < power_min) - return -EINVAL; + if (power_max < power_min) { + ret = -EINVAL; + goto unlock; + } __dtpm_sub_power(dtpm); @@ -164,9 +168,10 @@ int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max) __dtpm_add_power(dtpm); +unlock: mutex_unlock(&dtpm_lock); - return 0; + return ret; } /** @@ -187,8 +192,10 @@ int dtpm_release_zone(struct powercap_zone *pcz) mutex_lock(&dtpm_lock); - if (!list_empty(&dtpm->children)) + if (!list_empty(&dtpm->children)) { + mutex_unlock(&dtpm_lock); return -EBUSY; + } if (parent) list_del(&dtpm->sibling); From f8f706ad75abbc65fee365853e7b24731223fd6d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Jan 2021 12:03:08 +0300 Subject: [PATCH 08/14] powercap/drivers/dtpm: Fix an IS_ERR() vs NULL check The powercap_register_control_type() function never returns NULL, it returns error pointers on error so update this check. Fixes: a20d0ef97abf ("powercap/drivers/dtpm: Add API for dynamic thermal power management") Signed-off-by: Dan Carpenter Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 470a1182b868..5a51cd34a7e8 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -467,9 +467,9 @@ static int __init dtpm_init(void) struct dtpm_descr **dtpm_descr; pct = powercap_register_control_type(NULL, "dtpm", NULL); - if (!pct) { + if (IS_ERR(pct)) { pr_err("Failed to register control type\n"); - return -EINVAL; + return PTR_ERR(pct); } for_each_dtpm_table(dtpm_descr) From 66e713fbbbc6c259559d4937a3b016d36ab529ff Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 4 Jan 2021 12:10:53 +0000 Subject: [PATCH 09/14] powercap/drivers/dtpm: Fix size of object being allocated The kzalloc allocation for dtpm_cpu is currently allocating the size of the pointer and not the size of the structure. Fix this by using the correct sizeof argument. Addresses-Coverity: ("Wrong sizeof argument") Fixes: 0e8f68d7f048 ("powercap/drivers/dtpm: Add CPU energy model based support") Signed-off-by: Colin Ian King Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm_cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 6933c783c6b4..51c366938acd 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -200,7 +200,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) if (!dtpm) return -EINVAL; - dtpm_cpu = kzalloc(sizeof(dtpm_cpu), GFP_KERNEL); + dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL); if (!dtpm_cpu) goto out_kfree_dtpm; From cca26b66efc1e92c10701087aca4895530660b85 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 27 Jan 2021 13:42:27 +0800 Subject: [PATCH 10/14] powercap/intel_rapl: add support for AlderLake Mobile Add intel_rapl support for the AlderLake Mobile platform. Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index c9e57237d778..f0799837c2dd 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1049,6 +1049,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), From 3af2f0aa2ed04f07975ba1242002b66cd53e6290 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 9 Feb 2021 10:54:34 +0000 Subject: [PATCH 11/14] PM: EM: update Kconfig description and drop "default n" option Energy Model supports now other devices like GPUs, DSPs, not only CPUs. Thus, update the description in the config option. Remove also unneeded "default n". If the "default" line is removed, it defaults to 'n'. Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/Kconfig | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index a7320f07689d..56dbc2616d5c 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -322,15 +322,14 @@ config CPU_PM bool config ENERGY_MODEL - bool "Energy Model for CPUs" + bool "Energy Model for devices with DVFS (CPUs, GPUs, etc)" depends on SMP depends on CPU_FREQ - default n help Several subsystems (thermal and/or the task scheduler for example) - can leverage information about the energy consumed by CPUs to make - smarter decisions. This config option enables the framework from - which subsystems can access the energy models. + can leverage information about the energy consumed by devices to + make smarter decisions. This config option enables the framework + from which subsystems can access the energy models. The exact usage of the energy model is subsystem-dependent. From c4cc3141b6f8e0097a03f6885cafac957421df9e Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 9 Feb 2021 10:54:35 +0000 Subject: [PATCH 12/14] PM: Kconfig: remove unneeded "default n" options Remove "default n" options. If the "default" line is removed, it defaults to 'n'. Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/Kconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 56dbc2616d5c..6bfe3ead10ad 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -139,7 +139,6 @@ config PM_SLEEP_SMP_NONZERO_CPU config PM_AUTOSLEEP bool "Opportunistic sleep" depends on PM_SLEEP - default n help Allow the kernel to trigger a system transition into a global sleep state automatically whenever there are no active wakeup sources. @@ -147,7 +146,6 @@ config PM_AUTOSLEEP config PM_WAKELOCKS bool "User space wakeup sources interface" depends on PM_SLEEP - default n help Allow user space to create, activate and deactivate wakeup source objects with the help of a sysfs-based interface. @@ -293,7 +291,6 @@ config PM_GENERIC_DOMAINS config WQ_POWER_EFFICIENT_DEFAULT bool "Enable workqueue power-efficient mode by default" depends on PM - default n help Per-cpu workqueues are generally preferred because they show better performance thanks to cache locality; unfortunately, From 88ffce95764603e13eda4be003ec919e124ec365 Mon Sep 17 00:00:00 2001 From: Yunfeng Ye Date: Sat, 23 Jan 2021 05:06:07 -0500 Subject: [PATCH 13/14] powercap: intel_rapl: Use topology interface in rapl_add_package() It's not a good idea to access phys_proc_id and cpu_die_id directly. Use topology_physical_package_id(cpu) and topology_die_id(cpu) instead. Signed-off-by: Yunfeng Ye [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index f0799837c2dd..b6c7bedf517e 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1310,7 +1310,6 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) { int id = topology_logical_die_id(cpu); struct rapl_package *rp; - struct cpuinfo_x86 *c = &cpu_data(cpu); int ret; if (!rapl_defaults) @@ -1327,10 +1326,11 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) if (topology_max_die_per_package() > 1) snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, - "package-%d-die-%d", c->phys_proc_id, c->cpu_die_id); + "package-%d-die-%d", + topology_physical_package_id(cpu), topology_die_id(cpu)); else snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d", - c->phys_proc_id); + topology_physical_package_id(cpu)); /* check if the package contains valid domains */ if (rapl_detect_domains(rp, cpu) || rapl_defaults->check_unit(rp, cpu)) { From 65348ba259e27ad4b69459ef477facd4c702bbf6 Mon Sep 17 00:00:00 2001 From: Yunfeng Ye Date: Sat, 23 Jan 2021 05:06:08 -0500 Subject: [PATCH 14/14] powercap: intel_rapl: Use topology interface in rapl_init_domains() It's not a good idea to access the phys_proc_id of cpuinfo directly. Use topology_physical_package_id(cpu) instead. Signed-off-by: Yunfeng Ye [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index b6c7bedf517e..fdda2a737186 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -547,7 +547,7 @@ static void rapl_init_domains(struct rapl_package *rp) if (i == RAPL_DOMAIN_PLATFORM && rp->id > 0) { snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "psys-%d", - cpu_data(rp->lead_cpu).phys_proc_id); + topology_physical_package_id(rp->lead_cpu)); } else snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "%s", rapl_domain_names[i]);