From 4274521fabee05375d10bea0e36a806ed4ab7b45 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:35 +0000 Subject: [PATCH 01/24] PM: EM: Add missing newline for the message log Fix missing newline for the string long in the error code path. Reviewed-by: Hongyan Xia Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 7b44f5b89fa1..8b9dd4a39f63 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -250,7 +250,7 @@ static void em_cpufreq_update_efficiencies(struct device *dev) policy = cpufreq_cpu_get(cpumask_first(em_span_cpus(pd))); if (!policy) { - dev_warn(dev, "EM: Access to CPUFreq policy failed"); + dev_warn(dev, "EM: Access to CPUFreq policy failed\n"); return; } From e7b1cc9a7ea6d7862baac0fd7b145573618727dd Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:36 +0000 Subject: [PATCH 02/24] PM: EM: Extend em_cpufreq_update_efficiencies() argument list In order to prepare the code for the modifiable EM perf_state table, make em_cpufreq_update_efficiencies() take a pointer to the EM table as its second argument and modify it to use that new argument instead of the 'table' member of dev->em_pd. No functional impact. Reviewed-by: Hongyan Xia Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 8b9dd4a39f63..8c373b151875 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -237,15 +237,15 @@ static int em_create_pd(struct device *dev, int nr_states, return 0; } -static void em_cpufreq_update_efficiencies(struct device *dev) +static void +em_cpufreq_update_efficiencies(struct device *dev, struct em_perf_state *table) { struct em_perf_domain *pd = dev->em_pd; - struct em_perf_state *table; struct cpufreq_policy *policy; int found = 0; int i; - if (!_is_cpu_device(dev) || !pd) + if (!_is_cpu_device(dev)) return; policy = cpufreq_cpu_get(cpumask_first(em_span_cpus(pd))); @@ -254,8 +254,6 @@ static void em_cpufreq_update_efficiencies(struct device *dev) return; } - table = pd->table; - for (i = 0; i < pd->nr_perf_states; i++) { if (!(table[i].flags & EM_PERF_STATE_INEFFICIENT)) continue; @@ -397,7 +395,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, dev->em_pd->flags |= flags; - em_cpufreq_update_efficiencies(dev); + em_cpufreq_update_efficiencies(dev, dev->em_pd->table); em_debug_create_pd(dev); dev_info(dev, "EM: created perf domain\n"); From 99907d6054f2d39a625004f9f4e3fe9297838a3c Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:37 +0000 Subject: [PATCH 03/24] PM: EM: Find first CPU active while updating OPP efficiency The Energy Model might be updated at runtime and the energy efficiency for each OPP may change. Thus, there is a need to update also the cpufreq framework and make it aligned to the new values. In order to do that, use a first active CPU from the Performance Domain. This is needed since the first CPU in the cpumask might be offline when we run this code path. Reviewed-by: Hongyan Xia Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 8c373b151875..0c3220ff54f7 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -243,12 +243,19 @@ em_cpufreq_update_efficiencies(struct device *dev, struct em_perf_state *table) struct em_perf_domain *pd = dev->em_pd; struct cpufreq_policy *policy; int found = 0; - int i; + int i, cpu; if (!_is_cpu_device(dev)) return; - policy = cpufreq_cpu_get(cpumask_first(em_span_cpus(pd))); + /* Try to get a CPU which is active and in this PD */ + cpu = cpumask_first_and(em_span_cpus(pd), cpu_active_mask); + if (cpu >= nr_cpu_ids) { + dev_warn(dev, "EM: No online CPU for CPUFreq policy\n"); + return; + } + + policy = cpufreq_cpu_get(cpu); if (!policy) { dev_warn(dev, "EM: Access to CPUFreq policy failed\n"); return; From a3c78778f50c4db6cc0bb6aa2986c0174b1267d0 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:38 +0000 Subject: [PATCH 04/24] PM: EM: Refactor em_pd_get_efficient_state() to be more flexible The Energy Model (EM) is going to support runtime modification. There are going to be 2 EM tables which store information. This patch aims to prepare the code to be generic and use one of the tables. The function will no longer get a pointer to 'struct em_perf_domain' (the EM) but instead a pointer to 'struct em_perf_state' (which is one of the EM's tables). Prepare em_pd_get_efficient_state() for the upcoming changes and make it possible to be re-used. Return an index for the best performance state for a given EM table. The function arguments that are introduced should allow to work on different performance state arrays. The caller of em_pd_get_efficient_state() should be able to use the index either on the default or the modifiable EM table. Reviewed-by: Daniel Lezcano Reviewed-by: Hongyan Xia Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 88d91e087471..1dcd1645dde7 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -175,33 +175,35 @@ void em_dev_unregister_perf_domain(struct device *dev); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM - * @pd : Performance domain for which we want an efficient frequency - * @freq : Frequency to map with the EM + * @table: List of performance states, in ascending order + * @nr_perf_states: Number of performance states + * @freq: Frequency to map with the EM + * @pd_flags: Performance Domain flags * * It is called from the scheduler code quite frequently and as a consequence * doesn't implement any check. * - * Return: An efficient performance state, high enough to meet @freq + * Return: An efficient performance state id, high enough to meet @freq * requirement. */ -static inline -struct em_perf_state *em_pd_get_efficient_state(struct em_perf_domain *pd, - unsigned long freq) +static inline int +em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, + unsigned long freq, unsigned long pd_flags) { struct em_perf_state *ps; int i; - for (i = 0; i < pd->nr_perf_states; i++) { - ps = &pd->table[i]; + for (i = 0; i < nr_perf_states; i++) { + ps = &table[i]; if (ps->frequency >= freq) { - if (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && + if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && ps->flags & EM_PERF_STATE_INEFFICIENT) continue; - break; + return i; } } - return ps; + return nr_perf_states - 1; } /** @@ -226,7 +228,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, { unsigned long freq, ref_freq, scale_cpu; struct em_perf_state *ps; - int cpu; + int cpu, i; if (!sum_util) return 0; @@ -250,7 +252,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * Find the lowest performance state of the Energy Model above the * requested frequency. */ - ps = em_pd_get_efficient_state(pd, freq); + i = em_pd_get_efficient_state(pd->table, pd->nr_perf_states, freq, + pd->flags); + ps = &pd->table[i]; /* * The capacity of a CPU in the domain at the performance state (ps) From faf7075b79a259136e2b57ce52b48a7096270e8b Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:39 +0000 Subject: [PATCH 05/24] PM: EM: Introduce em_compute_costs() Move the EM costs computation code into a new dedicated function, em_compute_costs(), that can be reused in other places in the future. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 72 ++++++++++++++++++++++--------------- 1 file changed, 43 insertions(+), 29 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 0c3220ff54f7..5c47caaf270e 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -103,14 +103,52 @@ static void em_debug_create_pd(struct device *dev) {} static void em_debug_remove_pd(struct device *dev) {} #endif +static int em_compute_costs(struct device *dev, struct em_perf_state *table, + struct em_data_callback *cb, int nr_states, + unsigned long flags) +{ + unsigned long prev_cost = ULONG_MAX; + u64 fmax; + int i, ret; + + /* Compute the cost of each performance state. */ + fmax = (u64) table[nr_states - 1].frequency; + for (i = nr_states - 1; i >= 0; i--) { + unsigned long power_res, cost; + + if (flags & EM_PERF_DOMAIN_ARTIFICIAL) { + ret = cb->get_cost(dev, table[i].frequency, &cost); + if (ret || !cost || cost > EM_MAX_POWER) { + dev_err(dev, "EM: invalid cost %lu %d\n", + cost, ret); + return -EINVAL; + } + } else { + power_res = table[i].power; + cost = div64_u64(fmax * power_res, table[i].frequency); + } + + table[i].cost = cost; + + if (table[i].cost >= prev_cost) { + table[i].flags = EM_PERF_STATE_INEFFICIENT; + dev_dbg(dev, "EM: OPP:%lu is inefficient\n", + table[i].frequency); + } else { + prev_cost = table[i].cost; + } + } + + return 0; +} + static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, int nr_states, struct em_data_callback *cb, unsigned long flags) { - unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX; + unsigned long power, freq, prev_freq = 0; struct em_perf_state *table; int i, ret; - u64 fmax; table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL); if (!table) @@ -154,33 +192,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, table[i].frequency = prev_freq = freq; } - /* Compute the cost of each performance state. */ - fmax = (u64) table[nr_states - 1].frequency; - for (i = nr_states - 1; i >= 0; i--) { - unsigned long power_res, cost; - - if (flags & EM_PERF_DOMAIN_ARTIFICIAL) { - ret = cb->get_cost(dev, table[i].frequency, &cost); - if (ret || !cost || cost > EM_MAX_POWER) { - dev_err(dev, "EM: invalid cost %lu %d\n", - cost, ret); - goto free_ps_table; - } - } else { - power_res = table[i].power; - cost = div64_u64(fmax * power_res, table[i].frequency); - } - - table[i].cost = cost; - - if (table[i].cost >= prev_cost) { - table[i].flags = EM_PERF_STATE_INEFFICIENT; - dev_dbg(dev, "EM: OPP:%lu is inefficient\n", - table[i].frequency); - } else { - prev_cost = table[i].cost; - } - } + ret = em_compute_costs(dev, table, cb, nr_states, flags); + if (ret) + goto free_ps_table; pd->table = table; pd->nr_perf_states = nr_states; From 818867224d41725dcf4abe890d8f24e5d6bd9c67 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:40 +0000 Subject: [PATCH 06/24] PM: EM: Check if the get_cost() callback is present in em_compute_costs() Subsequent changes will introduce a case in which 'cb->get_cost' may not be set in em_compute_costs(), so add a check to ensure that it is not NULL before attempting to dereference it. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 5c47caaf270e..21d761223255 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -116,7 +116,7 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, for (i = nr_states - 1; i >= 0; i--) { unsigned long power_res, cost; - if (flags & EM_PERF_DOMAIN_ARTIFICIAL) { + if ((flags & EM_PERF_DOMAIN_ARTIFICIAL) && cb->get_cost) { ret = cb->get_cost(dev, table[i].frequency, &cost); if (ret || !cost || cost > EM_MAX_POWER) { dev_err(dev, "EM: invalid cost %lu %d\n", From 8552d6820168d6508bd1f7cd49be248dcb74efb3 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:41 +0000 Subject: [PATCH 07/24] PM: EM: Split the allocation and initialization of the EM table Split the process of allocation and data initialization for the EM table. The upcoming changes for modifiable EM will use it. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 55 ++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 22 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 21d761223255..7468fa92134b 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -142,18 +142,26 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, return 0; } +static int em_allocate_perf_table(struct em_perf_domain *pd, + int nr_states) +{ + pd->table = kcalloc(nr_states, sizeof(struct em_perf_state), + GFP_KERNEL); + if (!pd->table) + return -ENOMEM; + + return 0; +} + static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, - int nr_states, struct em_data_callback *cb, + struct em_perf_state *table, + struct em_data_callback *cb, unsigned long flags) { unsigned long power, freq, prev_freq = 0; - struct em_perf_state *table; + int nr_states = pd->nr_perf_states; int i, ret; - table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; - /* Build the list of performance states for this performance domain */ for (i = 0, freq = 0; i < nr_states; i++, freq++) { /* @@ -165,7 +173,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (ret) { dev_err(dev, "EM: invalid perf. state: %d\n", ret); - goto free_ps_table; + return -EINVAL; } /* @@ -175,7 +183,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (freq <= prev_freq) { dev_err(dev, "EM: non-increasing freq: %lu\n", freq); - goto free_ps_table; + return -EINVAL; } /* @@ -185,7 +193,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (!power || power > EM_MAX_POWER) { dev_err(dev, "EM: invalid power: %lu\n", power); - goto free_ps_table; + return -EINVAL; } table[i].power = power; @@ -194,16 +202,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, ret = em_compute_costs(dev, table, cb, nr_states, flags); if (ret) - goto free_ps_table; - - pd->table = table; - pd->nr_perf_states = nr_states; + return -EINVAL; return 0; - -free_ps_table: - kfree(table); - return -EINVAL; } static int em_create_pd(struct device *dev, int nr_states, @@ -234,11 +235,15 @@ static int em_create_pd(struct device *dev, int nr_states, return -ENOMEM; } - ret = em_create_perf_table(dev, pd, nr_states, cb, flags); - if (ret) { - kfree(pd); - return ret; - } + pd->nr_perf_states = nr_states; + + ret = em_allocate_perf_table(pd, nr_states); + if (ret) + goto free_pd; + + ret = em_create_perf_table(dev, pd, pd->table, cb, flags); + if (ret) + goto free_pd_table; if (_is_cpu_device(dev)) for_each_cpu(cpu, cpus) { @@ -249,6 +254,12 @@ static int em_create_pd(struct device *dev, int nr_states, dev->em_pd = pd; return 0; + +free_pd_table: + kfree(pd->table); +free_pd: + kfree(pd); + return -EINVAL; } static void From ca0fc871f16f4bef746b5ba814b67afb59119700 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:42 +0000 Subject: [PATCH 08/24] PM: EM: Introduce runtime modifiable table The new runtime table can be populated with a new power data to better reflect the actual efficiency of the device e.g. CPU. The power can vary over time e.g. due to the SoC temperature change. Higher temperature can increase power values. For longer running scenarios, such as game or camera, when also other devices are used (e.g. GPU, ISP) the CPU power can change. The new EM framework is able to addresses this issue and change the EM data at runtime safely. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 12 ++++++++ kernel/power/energy_model.c | 53 ++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 1dcd1645dde7..8ddf1d8a9581 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -36,9 +36,20 @@ struct em_perf_state { */ #define EM_PERF_STATE_INEFFICIENT BIT(0) +/** + * struct em_perf_table - Performance states table + * @rcu: RCU used for safe access and destruction + * @state: List of performance states, in ascending order + */ +struct em_perf_table { + struct rcu_head rcu; + struct em_perf_state state[]; +}; + /** * struct em_perf_domain - Performance domain * @table: List of performance states, in ascending order + * @em_table: Pointer to the runtime modifiable em_perf_table * @nr_perf_states: Number of performance states * @flags: See "em_perf_domain flags" * @cpus: Cpumask covering the CPUs of the domain. It's here @@ -54,6 +65,7 @@ struct em_perf_state { */ struct em_perf_domain { struct em_perf_state *table; + struct em_perf_table __rcu *em_table; int nr_perf_states; unsigned long flags; unsigned long cpus[]; diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 7468fa92134b..131ff1d0dc5b 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -23,6 +23,9 @@ */ static DEFINE_MUTEX(em_pd_mutex); +static void em_cpufreq_update_efficiencies(struct device *dev, + struct em_perf_state *table); + static bool _is_cpu_device(struct device *dev) { return (dev->bus == &cpu_subsys); @@ -103,6 +106,31 @@ static void em_debug_create_pd(struct device *dev) {} static void em_debug_remove_pd(struct device *dev) {} #endif +static void em_destroy_table_rcu(struct rcu_head *rp) +{ + struct em_perf_table __rcu *table; + + table = container_of(rp, struct em_perf_table, rcu); + kfree(table); +} + +static void em_free_table(struct em_perf_table __rcu *table) +{ + call_rcu(&table->rcu, em_destroy_table_rcu); +} + +static struct em_perf_table __rcu * +em_allocate_table(struct em_perf_domain *pd) +{ + struct em_perf_table __rcu *table; + int table_size; + + table_size = sizeof(struct em_perf_state) * pd->nr_perf_states; + + table = kzalloc(sizeof(*table) + table_size, GFP_KERNEL); + return table; +} + static int em_compute_costs(struct device *dev, struct em_perf_state *table, struct em_data_callback *cb, int nr_states, unsigned long flags) @@ -153,6 +181,24 @@ static int em_allocate_perf_table(struct em_perf_domain *pd, return 0; } +static int em_create_runtime_table(struct em_perf_domain *pd) +{ + struct em_perf_table __rcu *table; + int table_size; + + table = em_allocate_table(pd); + if (!table) + return -ENOMEM; + + /* Initialize runtime table with existing data */ + table_size = sizeof(struct em_perf_state) * pd->nr_perf_states; + memcpy(table->state, pd->table, table_size); + + rcu_assign_pointer(pd->em_table, table); + + return 0; +} + static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, struct em_perf_state *table, struct em_data_callback *cb, @@ -245,6 +291,10 @@ static int em_create_pd(struct device *dev, int nr_states, if (ret) goto free_pd_table; + ret = em_create_runtime_table(pd); + if (ret) + goto free_pd_table; + if (_is_cpu_device(dev)) for_each_cpu(cpu, cpus) { cpu_dev = get_cpu_device(cpu); @@ -461,6 +511,9 @@ void em_dev_unregister_perf_domain(struct device *dev) em_debug_remove_pd(dev); kfree(dev->em_pd->table); + + em_free_table(dev->em_pd->em_table); + kfree(dev->em_pd); dev->em_pd = NULL; mutex_unlock(&em_pd_mutex); From aa11a7ebfd5d698f541641922beede1cb474bf70 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:43 +0000 Subject: [PATCH 09/24] PM: EM: Use runtime modified EM for CPUs energy estimation in EAS The new Energy Model (EM) supports runtime modification of the performance state table to better model the power used by the SoC. Use this new feature to improve energy estimation and therefore task placement in Energy Aware Scheduler (EAS). Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 8ddf1d8a9581..5f842da3bb0c 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -239,9 +239,14 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long allowed_cpu_cap) { unsigned long freq, ref_freq, scale_cpu; + struct em_perf_table *em_table; struct em_perf_state *ps; int cpu, i; +#ifdef CONFIG_SCHED_DEBUG + WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n"); +#endif + if (!sum_util) return 0; @@ -264,9 +269,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * Find the lowest performance state of the Energy Model above the * requested frequency. */ - i = em_pd_get_efficient_state(pd->table, pd->nr_perf_states, freq, - pd->flags); - ps = &pd->table[i]; + em_table = rcu_dereference(pd->em_table); + i = em_pd_get_efficient_state(em_table->state, pd->nr_perf_states, + freq, pd->flags); + ps = &em_table->state[i]; /* * The capacity of a CPU in the domain at the performance state (ps) From ffcf9bce7af02a21fb73738999de1e3d4fde5aca Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:44 +0000 Subject: [PATCH 10/24] PM: EM: Add functions for memory allocations for new EM tables The runtime modified EM table can be provided from drivers. Create mechanism which allows safely allocate and free the table for device drivers. The same table can be used by the EAS in task scheduler code paths, so make sure the memory is not freed when the device driver module is unloaded. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 11 +++++++++++ kernel/power/energy_model.c | 38 +++++++++++++++++++++++++++++++----- 2 files changed, 44 insertions(+), 5 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 5f842da3bb0c..27911dc1887e 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -39,10 +40,12 @@ struct em_perf_state { /** * struct em_perf_table - Performance states table * @rcu: RCU used for safe access and destruction + * @kref: Reference counter to track the users * @state: List of performance states, in ascending order */ struct em_perf_table { struct rcu_head rcu; + struct kref kref; struct em_perf_state state[]; }; @@ -184,6 +187,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); +void em_table_free(struct em_perf_table __rcu *table); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -365,6 +370,12 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { return 0; } +static inline +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) +{ + return NULL; +} +static inline void em_table_free(struct em_perf_table __rcu *table) {} #endif #endif diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 131ff1d0dc5b..16795743f969 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -114,13 +114,36 @@ static void em_destroy_table_rcu(struct rcu_head *rp) kfree(table); } -static void em_free_table(struct em_perf_table __rcu *table) +static void em_release_table_kref(struct kref *kref) { + struct em_perf_table __rcu *table; + + /* It was the last owner of this table so we can free */ + table = container_of(kref, struct em_perf_table, kref); + call_rcu(&table->rcu, em_destroy_table_rcu); } -static struct em_perf_table __rcu * -em_allocate_table(struct em_perf_domain *pd) +/** + * em_table_free() - Handles safe free of the EM table when needed + * @table : EM table which is going to be freed + * + * No return values. + */ +void em_table_free(struct em_perf_table __rcu *table) +{ + kref_put(&table->kref, em_release_table_kref); +} + +/** + * em_table_alloc() - Allocate a new EM table + * @pd : EM performance domain for which this must be done + * + * Allocate a new EM table and initialize its kref to indicate that it + * has a user. + * Returns allocated table or NULL. + */ +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) { struct em_perf_table __rcu *table; int table_size; @@ -128,6 +151,11 @@ em_allocate_table(struct em_perf_domain *pd) table_size = sizeof(struct em_perf_state) * pd->nr_perf_states; table = kzalloc(sizeof(*table) + table_size, GFP_KERNEL); + if (!table) + return NULL; + + kref_init(&table->kref); + return table; } @@ -186,7 +214,7 @@ static int em_create_runtime_table(struct em_perf_domain *pd) struct em_perf_table __rcu *table; int table_size; - table = em_allocate_table(pd); + table = em_table_alloc(pd); if (!table) return -ENOMEM; @@ -512,7 +540,7 @@ void em_dev_unregister_perf_domain(struct device *dev) kfree(dev->em_pd->table); - em_free_table(dev->em_pd->em_table); + em_table_free(dev->em_pd->em_table); kfree(dev->em_pd); dev->em_pd = NULL; From 977230d5d50314f9920d3ee6348773d8babbfb58 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:45 +0000 Subject: [PATCH 11/24] PM: EM: Introduce em_dev_update_perf_domain() for EM updates Add API function em_dev_update_perf_domain() which allows the EM to be changed safely. Concurrent updaters are serialized with a mutex and the removal of memory that will not be used any more is carried out with the help of RCU. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 8 +++++++ kernel/power/energy_model.c | 44 ++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 27911dc1887e..324a3a8e0a2d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -183,6 +183,8 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span, bool microwatts); @@ -376,6 +378,12 @@ struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) return NULL; } static inline void em_table_free(struct em_perf_table __rcu *table) {} +static inline +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table) +{ + return -EINVAL; +} #endif #endif diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 16795743f969..667619b70be7 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -209,6 +209,50 @@ static int em_allocate_perf_table(struct em_perf_domain *pd, return 0; } +/** + * em_dev_update_perf_domain() - Update runtime EM table for a device + * @dev : Device for which the EM is to be updated + * @new_table : The new EM table that is going to be used from now + * + * Update EM runtime modifiable table for the @dev using the provided @table. + * + * This function uses a mutex to serialize writers, so it must not be called + * from a non-sleeping context. + * + * Return 0 on success or an error code on failure. + */ +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table) +{ + struct em_perf_table __rcu *old_table; + struct em_perf_domain *pd; + + if (!dev) + return -EINVAL; + + /* Serialize update/unregister or concurrent updates */ + mutex_lock(&em_pd_mutex); + + if (!dev->em_pd) { + mutex_unlock(&em_pd_mutex); + return -EINVAL; + } + pd = dev->em_pd; + + kref_get(&new_table->kref); + + old_table = pd->em_table; + rcu_assign_pointer(pd->em_table, new_table); + + em_cpufreq_update_efficiencies(dev, new_table->state); + + em_table_free(old_table); + + mutex_unlock(&em_pd_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(em_dev_update_perf_domain); + static int em_create_runtime_table(struct em_perf_domain *pd) { struct em_perf_table __rcu *table; From ee1a19873ce1234a3c2e6f84af3624fc73bfbd9c Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:46 +0000 Subject: [PATCH 12/24] PM: EM: Add em_perf_state_from_pd() to get performance states table Introduce a wrapper to get the performance states table of the performance domain. The function should be called within the RCU read critical section. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 324a3a8e0a2d..158dad6ea313 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -338,6 +338,23 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) return pd->nr_perf_states; } +/** + * em_perf_state_from_pd() - Get the performance states table of perf. + * domain + * @pd : performance domain for which this must be done + * + * To use this function the rcu_read_lock() should be hold. After the usage + * of the performance states table is finished, the rcu_read_unlock() should + * be called. + * + * Return: the pointer to performance states table of the performance domain + */ +static inline +struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd) +{ + return rcu_dereference(pd->em_table)->state; +} + #else struct em_data_callback {}; #define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } @@ -384,6 +401,11 @@ int em_dev_update_perf_domain(struct device *dev, { return -EINVAL; } +static inline +struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd) +{ + return NULL; +} #endif #endif From 5a367f7b7014af86bd1ac0865a42db55187dbd3c Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:47 +0000 Subject: [PATCH 13/24] PM: EM: Add performance field to struct em_perf_state and optimize The performance doesn't scale linearly with the frequency. Also, it may be different in different workloads. Some CPUs are designed to be particularly good at some applications e.g. images or video processing and other CPUs in different. When those different types of CPUs are combined in one SoC they should be properly modeled to get max of the HW in Energy Aware Scheduler (EAS). The Energy Model (EM) provides the power vs. performance curves to the EAS, but assumes the CPUs capacity is fixed and scales linearly with the frequency. This patch allows to adjust the curve on the 'performance' axis as well. Code speed optimization: Removing map_util_freq() allows to avoid one division and one multiplication operations from the EAS hot code path. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 24 ++++++++++++------------ kernel/power/energy_model.c | 27 +++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 12 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 158dad6ea313..ce24ea3fe41c 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -13,6 +13,7 @@ /** * struct em_perf_state - Performance state of a performance domain + * @performance: CPU performance (capacity) at a given frequency * @frequency: The frequency in KHz, for consistency with CPUFreq * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. @@ -21,6 +22,7 @@ * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { + unsigned long performance; unsigned long frequency; unsigned long power; unsigned long cost; @@ -196,25 +198,25 @@ void em_table_free(struct em_perf_table __rcu *table); * em_pd_get_efficient_state() - Get an efficient performance state from the EM * @table: List of performance states, in ascending order * @nr_perf_states: Number of performance states - * @freq: Frequency to map with the EM + * @max_util: Max utilization to map with the EM * @pd_flags: Performance Domain flags * * It is called from the scheduler code quite frequently and as a consequence * doesn't implement any check. * - * Return: An efficient performance state id, high enough to meet @freq + * Return: An efficient performance state id, high enough to meet @max_util * requirement. */ static inline int em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, - unsigned long freq, unsigned long pd_flags) + unsigned long max_util, unsigned long pd_flags) { struct em_perf_state *ps; int i; for (i = 0; i < nr_perf_states; i++) { ps = &table[i]; - if (ps->frequency >= freq) { + if (ps->performance >= max_util) { if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && ps->flags & EM_PERF_STATE_INEFFICIENT) continue; @@ -245,9 +247,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util, unsigned long allowed_cpu_cap) { - unsigned long freq, ref_freq, scale_cpu; struct em_perf_table *em_table; struct em_perf_state *ps; + unsigned long scale_cpu; int cpu, i; #ifdef CONFIG_SCHED_DEBUG @@ -260,25 +262,23 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, /* * In order to predict the performance state, map the utilization of * the most utilized CPU of the performance domain to a requested - * frequency, like schedutil. Take also into account that the real - * frequency might be set lower (due to thermal capping). Thus, clamp + * performance, like schedutil. Take also into account that the real + * performance might be set lower (due to thermal capping). Thus, clamp * max utilization to the allowed CPU capacity before calculating - * effective frequency. + * effective performance. */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); - ref_freq = arch_scale_freq_ref(cpu); max_util = min(max_util, allowed_cpu_cap); - freq = map_util_freq(max_util, ref_freq, scale_cpu); /* * Find the lowest performance state of the Energy Model above the - * requested frequency. + * requested performance. */ em_table = rcu_dereference(pd->em_table); i = em_pd_get_efficient_state(em_table->state, pd->nr_perf_states, - freq, pd->flags); + max_util, pd->flags); ps = &em_table->state[i]; /* diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 667619b70be7..41418aa6daa6 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -46,6 +46,7 @@ static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd) debugfs_create_ulong("frequency", 0444, d, &ps->frequency); debugfs_create_ulong("power", 0444, d, &ps->power); debugfs_create_ulong("cost", 0444, d, &ps->cost); + debugfs_create_ulong("performance", 0444, d, &ps->performance); debugfs_create_ulong("inefficient", 0444, d, &ps->flags); } @@ -159,6 +160,30 @@ struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) return table; } +static void em_init_performance(struct device *dev, struct em_perf_domain *pd, + struct em_perf_state *table, int nr_states) +{ + u64 fmax, max_cap; + int i, cpu; + + /* This is needed only for CPUs and EAS skip other devices */ + if (!_is_cpu_device(dev)) + return; + + cpu = cpumask_first(em_span_cpus(pd)); + + /* + * Calculate the performance value for each frequency with + * linear relationship. The final CPU capacity might not be ready at + * boot time, but the EM will be updated a bit later with correct one. + */ + fmax = (u64) table[nr_states - 1].frequency; + max_cap = (u64) arch_scale_cpu_capacity(cpu); + for (i = 0; i < nr_states; i++) + table[i].performance = div64_u64(max_cap * table[i].frequency, + fmax); +} + static int em_compute_costs(struct device *dev, struct em_perf_state *table, struct em_data_callback *cb, int nr_states, unsigned long flags) @@ -318,6 +343,8 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, table[i].frequency = prev_freq = freq; } + em_init_performance(dev, pd, table, nr_states); + ret = em_compute_costs(dev, table, cb, nr_states, flags); if (ret) return -EINVAL; From e3f1164fc9ee8430b3a51e400abfa1b67664f538 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:48 +0000 Subject: [PATCH 14/24] PM: EM: Support late CPUs booting and capacity adjustment The patch adds needed infrastructure to handle the late CPUs boot, which might change the previous CPUs capacity values. With this changes the new CPUs which try to register EM will trigger the needed re-calculations for other CPUs EMs. Thanks to that the em_per_state::performance values will be aligned with the CPU capacity information after all CPUs finish the boot and EM registrations. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 124 ++++++++++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 41418aa6daa6..b192b0ac8c6e 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -25,6 +25,9 @@ static DEFINE_MUTEX(em_pd_mutex); static void em_cpufreq_update_efficiencies(struct device *dev, struct em_perf_state *table); +static void em_check_capacity_update(void); +static void em_update_workfn(struct work_struct *work); +static DECLARE_DELAYED_WORK(em_update_work, em_update_workfn); static bool _is_cpu_device(struct device *dev) { @@ -583,6 +586,10 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, unlock: mutex_unlock(&em_pd_mutex); + + if (_is_cpu_device(dev)) + em_check_capacity_update(); + return ret; } EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); @@ -618,3 +625,120 @@ void em_dev_unregister_perf_domain(struct device *dev) mutex_unlock(&em_pd_mutex); } EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain); + +/* + * Adjustment of CPU performance values after boot, when all CPUs capacites + * are correctly calculated. + */ +static void em_adjust_new_capacity(struct device *dev, + struct em_perf_domain *pd, + u64 max_cap) +{ + struct em_perf_table __rcu *em_table; + struct em_perf_state *ps, *new_ps; + int ret, ps_size; + + em_table = em_table_alloc(pd); + if (!em_table) { + dev_warn(dev, "EM: allocation failed\n"); + return; + } + + new_ps = em_table->state; + + rcu_read_lock(); + ps = em_perf_state_from_pd(pd); + /* Initialize data based on old table */ + ps_size = sizeof(struct em_perf_state) * pd->nr_perf_states; + memcpy(new_ps, ps, ps_size); + + rcu_read_unlock(); + + em_init_performance(dev, pd, new_ps, pd->nr_perf_states); + ret = em_compute_costs(dev, new_ps, NULL, pd->nr_perf_states, + pd->flags); + if (ret) { + dev_warn(dev, "EM: compute costs failed\n"); + return; + } + + ret = em_dev_update_perf_domain(dev, em_table); + if (ret) + dev_warn(dev, "EM: update failed %d\n", ret); + + /* + * This is one-time-update, so give up the ownership in this updater. + * The EM framework has incremented the usage counter and from now + * will keep the reference (then free the memory when needed). + */ + em_table_free(em_table); +} + +static void em_check_capacity_update(void) +{ + cpumask_var_t cpu_done_mask; + struct em_perf_state *table; + struct em_perf_domain *pd; + unsigned long cpu_capacity; + int cpu; + + if (!zalloc_cpumask_var(&cpu_done_mask, GFP_KERNEL)) { + pr_warn("no free memory\n"); + return; + } + + /* Check if CPUs capacity has changed than update EM */ + for_each_possible_cpu(cpu) { + struct cpufreq_policy *policy; + unsigned long em_max_perf; + struct device *dev; + int nr_states; + + if (cpumask_test_cpu(cpu, cpu_done_mask)) + continue; + + policy = cpufreq_cpu_get(cpu); + if (!policy) { + pr_debug("Accessing cpu%d policy failed\n", cpu); + schedule_delayed_work(&em_update_work, + msecs_to_jiffies(1000)); + break; + } + cpufreq_cpu_put(policy); + + pd = em_cpu_get(cpu); + if (!pd || em_is_artificial(pd)) + continue; + + cpumask_or(cpu_done_mask, cpu_done_mask, + em_span_cpus(pd)); + + nr_states = pd->nr_perf_states; + cpu_capacity = arch_scale_cpu_capacity(cpu); + + rcu_read_lock(); + table = em_perf_state_from_pd(pd); + em_max_perf = table[pd->nr_perf_states - 1].performance; + rcu_read_unlock(); + + /* + * Check if the CPU capacity has been adjusted during boot + * and trigger the update for new performance values. + */ + if (em_max_perf == cpu_capacity) + continue; + + pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n", + cpu, cpu_capacity, em_max_perf); + + dev = get_cpu_device(cpu); + em_adjust_new_capacity(dev, pd, cpu_capacity); + } + + free_cpumask_var(cpu_done_mask); +} + +static void em_update_workfn(struct work_struct *work) +{ + em_check_capacity_update(); +} From 1b600da510735a0f92c8b4140a7e2cb037a6a6c3 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:49 +0000 Subject: [PATCH 15/24] PM: EM: Optimize em_cpu_energy() and remove division The Energy Model (EM) can be modified at runtime which brings new possibilities. The em_cpu_energy() is called by the Energy Aware Scheduler (EAS) in its hot path. The energy calculation uses power value for a given performance state (ps) and the CPU busy time as percentage for that given frequency. It is possible to avoid the division by 'scale_cpu' at runtime, because EM is updated whenever new max capacity CPU is set in the system. Use that feature and do the needed division during the calculation of the coefficient 'ps->cost'. That enhanced 'ps->cost' value can be then just multiplied simply by utilization: pd_nrg = ps->cost * \Sum cpu_util to get the needed energy for whole Performance Domain (PD). With this optimization and earlier removal of map_util_freq(), the em_cpu_energy() should run faster on the Big CPU by 1.43x and on the Little CPU by 1.69x (RockPi 4B board). Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 55 ++++++++++-------------------------- kernel/power/energy_model.c | 7 ++--- 2 files changed, 18 insertions(+), 44 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index ce24ea3fe41c..aabfc26fcd31 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -115,27 +115,6 @@ struct em_perf_domain { #define EM_MAX_NUM_CPUS 16 #endif -/* - * To avoid an overflow on 32bit machines while calculating the energy - * use a different order in the operation. First divide by the 'cpu_scale' - * which would reduce big value stored in the 'cost' field, then multiply by - * the 'sum_util'. This would allow to handle existing platforms, which have - * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts. - * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util' - * could be 4096, then multiplication: 'cost' * 'sum_util' would overflow. - * This reordering of operations has some limitations, we lose small - * precision in the estimation (comparing to 64bit platform w/o reordering). - * - * We are safe on 64bit machine. - */ -#ifdef CONFIG_64BIT -#define em_estimate_energy(cost, sum_util, scale_cpu) \ - (((cost) * (sum_util)) / (scale_cpu)) -#else -#define em_estimate_energy(cost, sum_util, scale_cpu) \ - (((cost) / (scale_cpu)) * (sum_util)) -#endif - struct em_data_callback { /** * active_power() - Provide power at the next performance state of @@ -249,8 +228,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, { struct em_perf_table *em_table; struct em_perf_state *ps; - unsigned long scale_cpu; - int cpu, i; + int i; #ifdef CONFIG_SCHED_DEBUG WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n"); @@ -267,9 +245,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * max utilization to the allowed CPU capacity before calculating * effective performance. */ - cpu = cpumask_first(to_cpumask(pd->cpus)); - scale_cpu = arch_scale_cpu_capacity(cpu); - + max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); /* @@ -282,12 +258,12 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, ps = &em_table->state[i]; /* - * The capacity of a CPU in the domain at the performance state (ps) - * can be computed as: + * The performance (capacity) of a CPU in the domain at the performance + * state (ps) can be computed as: * - * ps->freq * scale_cpu - * ps->cap = -------------------- (1) - * cpu_max_freq + * ps->freq * scale_cpu + * ps->performance = -------------------- (1) + * cpu_max_freq * * So, ignoring the costs of idle states (which are not available in * the EM), the energy consumed by this CPU at that performance state @@ -295,9 +271,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * * ps->power * cpu_util * cpu_nrg = -------------------- (2) - * ps->cap + * ps->performance * - * since 'cpu_util / ps->cap' represents its percentage of busy time. + * since 'cpu_util / ps->performance' represents its percentage of busy + * time. * * NOTE: Although the result of this computation actually is in * units of power, it can be manipulated as an energy value @@ -307,9 +284,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product * of two terms: * - * ps->power * cpu_max_freq cpu_util - * cpu_nrg = ------------------------ * --------- (3) - * ps->freq scale_cpu + * ps->power * cpu_max_freq + * cpu_nrg = ------------------------ * cpu_util (3) + * ps->freq * scale_cpu * * The first term is static, and is stored in the em_perf_state struct * as 'ps->cost'. @@ -319,11 +296,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * total energy of the domain (which is the simple sum of the energy of * all of its CPUs) can be factorized as: * - * ps->cost * \Sum cpu_util - * pd_nrg = ------------------------ (4) - * scale_cpu + * pd_nrg = ps->cost * \Sum cpu_util (4) */ - return em_estimate_energy(ps->cost, sum_util, scale_cpu); + return ps->cost * sum_util; } /** diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index b192b0ac8c6e..a631d7d52c40 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -192,11 +192,9 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, unsigned long flags) { unsigned long prev_cost = ULONG_MAX; - u64 fmax; int i, ret; /* Compute the cost of each performance state. */ - fmax = (u64) table[nr_states - 1].frequency; for (i = nr_states - 1; i >= 0; i--) { unsigned long power_res, cost; @@ -208,8 +206,9 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, return -EINVAL; } } else { - power_res = table[i].power; - cost = div64_u64(fmax * power_res, table[i].frequency); + /* increase resolution of 'cost' precision */ + power_res = table[i].power * 10; + cost = power_res / table[i].performance; } table[i].cost = cost; From e20b7a8172b5f6fea82d063c8f1f4df881701759 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:50 +0000 Subject: [PATCH 16/24] powercap/dtpm_cpu: Use new Energy Model interface to get table Energy Model framework support modifications at runtime of the power values. Use the new EM table API which is protected with RCU. Align the code so that this RCU read section is short. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm_cpu.c | 39 +++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 9193c3b8edeb..ee0d1aa3e023 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -42,6 +42,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) { struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu); + struct em_perf_state *table; struct cpumask cpus; unsigned long freq; u64 power; @@ -50,20 +51,22 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); nr_cpus = cpumask_weight(&cpus); + rcu_read_lock(); + table = em_perf_state_from_pd(pd); for (i = 0; i < pd->nr_perf_states; i++) { - power = pd->table[i].power * nr_cpus; + power = table[i].power * nr_cpus; if (power > power_limit) break; } - freq = pd->table[i - 1].frequency; + freq = table[i - 1].frequency; + power_limit = table[i - 1].power * nr_cpus; + rcu_read_unlock(); freq_qos_update_request(&dtpm_cpu->qos_req, freq); - power_limit = pd->table[i - 1].power * nr_cpus; - return power_limit; } @@ -87,9 +90,11 @@ static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power) static u64 get_pd_power_uw(struct dtpm *dtpm) { struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); + struct em_perf_state *table; struct em_perf_domain *pd; struct cpumask *pd_mask; unsigned long freq; + u64 power = 0; int i; pd = em_cpu_get(dtpm_cpu->cpu); @@ -98,33 +103,43 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) freq = cpufreq_quick_get(dtpm_cpu->cpu); + rcu_read_lock(); + table = em_perf_state_from_pd(pd); for (i = 0; i < pd->nr_perf_states; i++) { - if (pd->table[i].frequency < freq) + if (table[i].frequency < freq) continue; - return scale_pd_power_uw(pd_mask, pd->table[i].power); + power = scale_pd_power_uw(pd_mask, table[i].power); + break; } + rcu_read_unlock(); - return 0; + return power; } static int update_pd_power_uw(struct dtpm *dtpm) { struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu); + struct em_perf_state *table; struct cpumask cpus; int nr_cpus; cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus)); nr_cpus = cpumask_weight(&cpus); - dtpm->power_min = em->table[0].power; + rcu_read_lock(); + table = em_perf_state_from_pd(em); + + dtpm->power_min = table[0].power; dtpm->power_min *= nr_cpus; - dtpm->power_max = em->table[em->nr_perf_states - 1].power; + dtpm->power_max = table[em->nr_perf_states - 1].power; dtpm->power_max *= nr_cpus; + rcu_read_unlock(); + return 0; } @@ -180,6 +195,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) { struct dtpm_cpu *dtpm_cpu; struct cpufreq_policy *policy; + struct em_perf_state *table; struct em_perf_domain *pd; char name[CPUFREQ_NAME_LEN]; int ret = -ENOMEM; @@ -216,9 +232,12 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) if (ret) goto out_kfree_dtpm_cpu; + rcu_read_lock(); + table = em_perf_state_from_pd(pd); ret = freq_qos_add_request(&policy->constraints, &dtpm_cpu->qos_req, FREQ_QOS_MAX, - pd->table[pd->nr_perf_states - 1].frequency); + table[pd->nr_perf_states - 1].frequency); + rcu_read_unlock(); if (ret) goto out_dtpm_unregister; From 27d2c37e7dea41801378c473089b80385ca65491 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:51 +0000 Subject: [PATCH 17/24] powercap/dtpm_devfreq: Use new Energy Model interface to get table Energy Model framework support modifications at runtime of the power values. Use the new EM table API which is protected with RCU. Align the code so that this RCU read section is short. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/powercap/dtpm_devfreq.c | 34 ++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c index 612c3b59dd5b..f40bce8176df 100644 --- a/drivers/powercap/dtpm_devfreq.c +++ b/drivers/powercap/dtpm_devfreq.c @@ -37,11 +37,16 @@ static int update_pd_power_uw(struct dtpm *dtpm) struct devfreq *devfreq = dtpm_devfreq->devfreq; struct device *dev = devfreq->dev.parent; struct em_perf_domain *pd = em_pd_get(dev); + struct em_perf_state *table; - dtpm->power_min = pd->table[0].power; + rcu_read_lock(); + table = em_perf_state_from_pd(pd); - dtpm->power_max = pd->table[pd->nr_perf_states - 1].power; + dtpm->power_min = table[0].power; + dtpm->power_max = table[pd->nr_perf_states - 1].power; + + rcu_read_unlock(); return 0; } @@ -51,20 +56,23 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) struct devfreq *devfreq = dtpm_devfreq->devfreq; struct device *dev = devfreq->dev.parent; struct em_perf_domain *pd = em_pd_get(dev); + struct em_perf_state *table; unsigned long freq; int i; + rcu_read_lock(); + table = em_perf_state_from_pd(pd); for (i = 0; i < pd->nr_perf_states; i++) { - if (pd->table[i].power > power_limit) + if (table[i].power > power_limit) break; } - freq = pd->table[i - 1].frequency; + freq = table[i - 1].frequency; + power_limit = table[i - 1].power; + rcu_read_unlock(); dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq); - power_limit = pd->table[i - 1].power; - return power_limit; } @@ -89,8 +97,9 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) struct device *dev = devfreq->dev.parent; struct em_perf_domain *pd = em_pd_get(dev); struct devfreq_dev_status status; + struct em_perf_state *table; unsigned long freq; - u64 power; + u64 power = 0; int i; mutex_lock(&devfreq->lock); @@ -100,19 +109,22 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) freq = DIV_ROUND_UP(status.current_frequency, HZ_PER_KHZ); _normalize_load(&status); + rcu_read_lock(); + table = em_perf_state_from_pd(pd); for (i = 0; i < pd->nr_perf_states; i++) { - if (pd->table[i].frequency < freq) + if (table[i].frequency < freq) continue; - power = pd->table[i].power; + power = table[i].power; power *= status.busy_time; power >>= 10; - return power; + break; } + rcu_read_unlock(); - return 0; + return power; } static void pd_release(struct dtpm *dtpm) From 207472b8ef715e8089424388c322e8b1633d5254 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:52 +0000 Subject: [PATCH 18/24] drivers/thermal/cpufreq_cooling: Use new Energy Model interface Energy Model framework support modifications at runtime of the power values. Use the new EM table which is protected with RCU. Align the code so that this RCU read section is short. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/thermal/cpufreq_cooling.c | 45 +++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index e2cc7bd30862..9d1b1459700d 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -91,12 +91,16 @@ struct cpufreq_cooling_device { static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, unsigned int freq) { + struct em_perf_state *table; int i; + rcu_read_lock(); + table = em_perf_state_from_pd(cpufreq_cdev->em); for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) { - if (freq > cpufreq_cdev->em->table[i].frequency) + if (freq > table[i].frequency) break; } + rcu_read_unlock(); return cpufreq_cdev->max_level - i - 1; } @@ -104,16 +108,20 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, u32 freq) { + struct em_perf_state *table; unsigned long power_mw; int i; + rcu_read_lock(); + table = em_perf_state_from_pd(cpufreq_cdev->em); for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) { - if (freq > cpufreq_cdev->em->table[i].frequency) + if (freq > table[i].frequency) break; } - power_mw = cpufreq_cdev->em->table[i + 1].power; + power_mw = table[i + 1].power; power_mw /= MICROWATT_PER_MILLIWATT; + rcu_read_unlock(); return power_mw; } @@ -121,18 +129,24 @@ static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, u32 power) { + struct em_perf_state *table; unsigned long em_power_mw; + u32 freq; int i; + rcu_read_lock(); + table = em_perf_state_from_pd(cpufreq_cdev->em); for (i = cpufreq_cdev->max_level; i > 0; i--) { /* Convert EM power to milli-Watts to make safe comparison */ - em_power_mw = cpufreq_cdev->em->table[i].power; + em_power_mw = table[i].power; em_power_mw /= MICROWATT_PER_MILLIWATT; if (power >= em_power_mw) break; } + freq = table[i].frequency; + rcu_read_unlock(); - return cpufreq_cdev->em->table[i].frequency; + return freq; } /** @@ -262,8 +276,9 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, static int cpufreq_state2power(struct thermal_cooling_device *cdev, unsigned long state, u32 *power) { - unsigned int freq, num_cpus, idx; struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + unsigned int freq, num_cpus, idx; + struct em_perf_state *table; /* Request state should be less than max_level */ if (state > cpufreq_cdev->max_level) @@ -272,7 +287,12 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus); idx = cpufreq_cdev->max_level - state; - freq = cpufreq_cdev->em->table[idx].frequency; + + rcu_read_lock(); + table = em_perf_state_from_pd(cpufreq_cdev->em); + freq = table[idx].frequency; + rcu_read_unlock(); + *power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus; return 0; @@ -378,8 +398,17 @@ static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev, #ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR /* Use the Energy Model table if available */ if (cpufreq_cdev->em) { + struct em_perf_state *table; + unsigned int freq; + idx = cpufreq_cdev->max_level - state; - return cpufreq_cdev->em->table[idx].frequency; + + rcu_read_lock(); + table = em_perf_state_from_pd(cpufreq_cdev->em); + freq = table[idx].frequency; + rcu_read_unlock(); + + return freq; } #endif From 9f5fb518c3c022c5c50883c9006f6f2cd00d51d7 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:53 +0000 Subject: [PATCH 19/24] drivers/thermal/devfreq_cooling: Use new Energy Model interface Energy Model framework support modifications at runtime of the power values. Use the new EM table which is protected with RCU. Align the code so that this RCU read section is short. This change is not expected to alter the general functionality. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- drivers/thermal/devfreq_cooling.c | 51 +++++++++++++++++++++++++------ 1 file changed, 41 insertions(+), 10 deletions(-) diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index 262e62ab6cf2..50dec24e967a 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -87,6 +87,7 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev, struct devfreq_cooling_device *dfc = cdev->devdata; struct devfreq *df = dfc->devfreq; struct device *dev = df->dev.parent; + struct em_perf_state *table; unsigned long freq; int perf_idx; @@ -100,7 +101,11 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev, if (dfc->em_pd) { perf_idx = dfc->max_state - state; - freq = dfc->em_pd->table[perf_idx].frequency * 1000; + + rcu_read_lock(); + table = em_perf_state_from_pd(dfc->em_pd); + freq = table[perf_idx].frequency * 1000; + rcu_read_unlock(); } else { freq = dfc->freq_table[state]; } @@ -123,14 +128,21 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev, */ static int get_perf_idx(struct em_perf_domain *em_pd, unsigned long freq) { - int i; + struct em_perf_state *table; + int i, idx = -EINVAL; + rcu_read_lock(); + table = em_perf_state_from_pd(em_pd); for (i = 0; i < em_pd->nr_perf_states; i++) { - if (em_pd->table[i].frequency == freq) - return i; - } + if (table[i].frequency != freq) + continue; - return -EINVAL; + idx = i; + break; + } + rcu_read_unlock(); + + return idx; } static unsigned long get_voltage(struct devfreq *df, unsigned long freq) @@ -181,6 +193,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd struct devfreq_cooling_device *dfc = cdev->devdata; struct devfreq *df = dfc->devfreq; struct devfreq_dev_status status; + struct em_perf_state *table; unsigned long state; unsigned long freq; unsigned long voltage; @@ -204,7 +217,11 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd state = dfc->capped_state; /* Convert EM power into milli-Watts first */ - dfc->res_util = dfc->em_pd->table[state].power; + rcu_read_lock(); + table = em_perf_state_from_pd(dfc->em_pd); + dfc->res_util = table[state].power; + rcu_read_unlock(); + dfc->res_util /= MICROWATT_PER_MILLIWATT; dfc->res_util *= SCALE_ERROR_MITIGATION; @@ -225,7 +242,11 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd _normalize_load(&status); /* Convert EM power into milli-Watts first */ - *power = dfc->em_pd->table[perf_idx].power; + rcu_read_lock(); + table = em_perf_state_from_pd(dfc->em_pd); + *power = table[perf_idx].power; + rcu_read_unlock(); + *power /= MICROWATT_PER_MILLIWATT; /* Scale power for utilization */ *power *= status.busy_time; @@ -245,13 +266,19 @@ static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev, unsigned long state, u32 *power) { struct devfreq_cooling_device *dfc = cdev->devdata; + struct em_perf_state *table; int perf_idx; if (state > dfc->max_state) return -EINVAL; perf_idx = dfc->max_state - state; - *power = dfc->em_pd->table[perf_idx].power; + + rcu_read_lock(); + table = em_perf_state_from_pd(dfc->em_pd); + *power = table[perf_idx].power; + rcu_read_unlock(); + *power /= MICROWATT_PER_MILLIWATT; return 0; @@ -264,6 +291,7 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev, struct devfreq *df = dfc->devfreq; struct devfreq_dev_status status; unsigned long freq, em_power_mw; + struct em_perf_state *table; s32 est_power; int i; @@ -288,13 +316,16 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev, * Find the first cooling state that is within the power * budget. The EM power table is sorted ascending. */ + rcu_read_lock(); + table = em_perf_state_from_pd(dfc->em_pd); for (i = dfc->max_state; i > 0; i--) { /* Convert EM power to milli-Watts to make safe comparison */ - em_power_mw = dfc->em_pd->table[i].power; + em_power_mw = table[i].power; em_power_mw /= MICROWATT_PER_MILLIWATT; if (est_power >= em_power_mw) break; } + rcu_read_unlock(); *state = dfc->max_state - i; dfc->capped_state = *state; From 09417e673cbd578a1eaf8aba34a668119622d79c Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:54 +0000 Subject: [PATCH 20/24] PM: EM: Change debugfs configuration to use runtime EM table data Dump the runtime EM table values which can be modified in time. In order to do that allocate chunk of debug memory which can be later freed automatically thanks to devm_kcalloc(). This design can handle the fact that the EM table memory can change after EM update, so debug code cannot use the pointer from initialization phase. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 67 ++++++++++++++++++++++++++++++++----- 1 file changed, 59 insertions(+), 8 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index a631d7d52c40..548908e686ed 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -37,20 +37,65 @@ static bool _is_cpu_device(struct device *dev) #ifdef CONFIG_DEBUG_FS static struct dentry *rootdir; -static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd) +struct em_dbg_info { + struct em_perf_domain *pd; + int ps_id; +}; + +#define DEFINE_EM_DBG_SHOW(name, fname) \ +static int em_debug_##fname##_show(struct seq_file *s, void *unused) \ +{ \ + struct em_dbg_info *em_dbg = s->private; \ + struct em_perf_state *table; \ + unsigned long val; \ + \ + rcu_read_lock(); \ + table = em_perf_state_from_pd(em_dbg->pd); \ + val = table[em_dbg->ps_id].name; \ + rcu_read_unlock(); \ + \ + seq_printf(s, "%lu\n", val); \ + return 0; \ +} \ +DEFINE_SHOW_ATTRIBUTE(em_debug_##fname) + +DEFINE_EM_DBG_SHOW(frequency, frequency); +DEFINE_EM_DBG_SHOW(power, power); +DEFINE_EM_DBG_SHOW(cost, cost); +DEFINE_EM_DBG_SHOW(performance, performance); +DEFINE_EM_DBG_SHOW(flags, inefficiency); + +static void em_debug_create_ps(struct em_perf_domain *em_pd, + struct em_dbg_info *em_dbg, int i, + struct dentry *pd) { + struct em_perf_state *table; + unsigned long freq; struct dentry *d; char name[24]; - snprintf(name, sizeof(name), "ps:%lu", ps->frequency); + em_dbg[i].pd = em_pd; + em_dbg[i].ps_id = i; + + rcu_read_lock(); + table = em_perf_state_from_pd(em_pd); + freq = table[i].frequency; + rcu_read_unlock(); + + snprintf(name, sizeof(name), "ps:%lu", freq); /* Create per-ps directory */ d = debugfs_create_dir(name, pd); - debugfs_create_ulong("frequency", 0444, d, &ps->frequency); - debugfs_create_ulong("power", 0444, d, &ps->power); - debugfs_create_ulong("cost", 0444, d, &ps->cost); - debugfs_create_ulong("performance", 0444, d, &ps->performance); - debugfs_create_ulong("inefficient", 0444, d, &ps->flags); + debugfs_create_file("frequency", 0444, d, &em_dbg[i], + &em_debug_frequency_fops); + debugfs_create_file("power", 0444, d, &em_dbg[i], + &em_debug_power_fops); + debugfs_create_file("cost", 0444, d, &em_dbg[i], + &em_debug_cost_fops); + debugfs_create_file("performance", 0444, d, &em_dbg[i], + &em_debug_performance_fops); + debugfs_create_file("inefficient", 0444, d, &em_dbg[i], + &em_debug_inefficiency_fops); } static int em_debug_cpus_show(struct seq_file *s, void *unused) @@ -73,6 +118,7 @@ DEFINE_SHOW_ATTRIBUTE(em_debug_flags); static void em_debug_create_pd(struct device *dev) { + struct em_dbg_info *em_dbg; struct dentry *d; int i; @@ -86,9 +132,14 @@ static void em_debug_create_pd(struct device *dev) debugfs_create_file("flags", 0444, d, dev->em_pd, &em_debug_flags_fops); + em_dbg = devm_kcalloc(dev, dev->em_pd->nr_perf_states, + sizeof(*em_dbg), GFP_KERNEL); + if (!em_dbg) + return; + /* Create a sub-directory for each performance state */ for (i = 0; i < dev->em_pd->nr_perf_states; i++) - em_debug_create_ps(&dev->em_pd->table[i], d); + em_debug_create_ps(dev->em_pd, em_dbg, i, d); } From 24e9fb635df2790eccb0e95ff65c6dee7a97fcb7 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:55 +0000 Subject: [PATCH 21/24] PM: EM: Remove old table Remove the old EM table which wasn't able to modify the data. Clean the unneeded function and refactor the code a bit. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 2 -- kernel/power/energy_model.c | 46 ++++++------------------------------ 2 files changed, 7 insertions(+), 41 deletions(-) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index aabfc26fcd31..92866a81abe4 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -53,7 +53,6 @@ struct em_perf_table { /** * struct em_perf_domain - Performance domain - * @table: List of performance states, in ascending order * @em_table: Pointer to the runtime modifiable em_perf_table * @nr_perf_states: Number of performance states * @flags: See "em_perf_domain flags" @@ -69,7 +68,6 @@ struct em_perf_table { * field is unused. */ struct em_perf_domain { - struct em_perf_state *table; struct em_perf_table __rcu *em_table; int nr_perf_states; unsigned long flags; diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 548908e686ed..57838d28af85 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -276,17 +276,6 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, return 0; } -static int em_allocate_perf_table(struct em_perf_domain *pd, - int nr_states) -{ - pd->table = kcalloc(nr_states, sizeof(struct em_perf_state), - GFP_KERNEL); - if (!pd->table) - return -ENOMEM; - - return 0; -} - /** * em_dev_update_perf_domain() - Update runtime EM table for a device * @dev : Device for which the EM is to be updated @@ -331,24 +320,6 @@ int em_dev_update_perf_domain(struct device *dev, } EXPORT_SYMBOL_GPL(em_dev_update_perf_domain); -static int em_create_runtime_table(struct em_perf_domain *pd) -{ - struct em_perf_table __rcu *table; - int table_size; - - table = em_table_alloc(pd); - if (!table) - return -ENOMEM; - - /* Initialize runtime table with existing data */ - table_size = sizeof(struct em_perf_state) * pd->nr_perf_states; - memcpy(table->state, pd->table, table_size); - - rcu_assign_pointer(pd->em_table, table); - - return 0; -} - static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, struct em_perf_state *table, struct em_data_callback *cb, @@ -409,6 +380,7 @@ static int em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, cpumask_t *cpus, unsigned long flags) { + struct em_perf_table __rcu *em_table; struct em_perf_domain *pd; struct device *cpu_dev; int cpu, ret, num_cpus; @@ -435,17 +407,15 @@ static int em_create_pd(struct device *dev, int nr_states, pd->nr_perf_states = nr_states; - ret = em_allocate_perf_table(pd, nr_states); - if (ret) + em_table = em_table_alloc(pd); + if (!em_table) goto free_pd; - ret = em_create_perf_table(dev, pd, pd->table, cb, flags); + ret = em_create_perf_table(dev, pd, em_table->state, cb, flags); if (ret) goto free_pd_table; - ret = em_create_runtime_table(pd); - if (ret) - goto free_pd_table; + rcu_assign_pointer(pd->em_table, em_table); if (_is_cpu_device(dev)) for_each_cpu(cpu, cpus) { @@ -458,7 +428,7 @@ static int em_create_pd(struct device *dev, int nr_states, return 0; free_pd_table: - kfree(pd->table); + kfree(em_table); free_pd: kfree(pd); return -EINVAL; @@ -629,7 +599,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, dev->em_pd->flags |= flags; - em_cpufreq_update_efficiencies(dev, dev->em_pd->table); + em_cpufreq_update_efficiencies(dev, dev->em_pd->em_table->state); em_debug_create_pd(dev); dev_info(dev, "EM: created perf domain\n"); @@ -666,8 +636,6 @@ void em_dev_unregister_perf_domain(struct device *dev) mutex_lock(&em_pd_mutex); em_debug_remove_pd(dev); - kfree(dev->em_pd->table); - em_table_free(dev->em_pd->em_table); kfree(dev->em_pd); From 22ea02848c07d1cbd15a5f442138ca429866300d Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:56 +0000 Subject: [PATCH 22/24] PM: EM: Add em_dev_compute_costs() The device drivers can modify EM at runtime by providing a new EM table. The EM is used by the EAS and the em_perf_state::cost stores pre-calculated value to avoid overhead. This patch provides the API for device drivers to calculate the cost values properly (and not duplicate the same code). Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 8 ++++++++ kernel/power/energy_model.c | 18 ++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 92866a81abe4..770755df852f 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -170,6 +170,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, void em_dev_unregister_perf_domain(struct device *dev); struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table __rcu *table); +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -379,6 +381,12 @@ struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd) { return NULL; } +static inline +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states) +{ + return -EINVAL; +} #endif #endif diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 57838d28af85..7101fa3fa0c0 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -276,6 +276,24 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, return 0; } +/** + * em_dev_compute_costs() - Calculate cost values for new runtime EM table + * @dev : Device for which the EM table is to be updated + * @table : The new EM table that is going to get the costs calculated + * + * Calculate the em_perf_state::cost values for new runtime EM table. The + * values are used for EAS during task placement. It also calculates and sets + * the efficiency flag for each performance state. When the function finish + * successfully the EM table is ready to be updated and used by EAS. + * + * Return 0 on success or a proper error in case of failure. + */ +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states) +{ + return em_compute_costs(dev, table, NULL, nr_states, 0); +} + /** * em_dev_update_perf_domain() - Update runtime EM table for a device * @dev : Device for which the EM is to be updated From eb1ad4d431674368bab4ef4e312f2e8c158294f9 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 8 Feb 2024 11:55:57 +0000 Subject: [PATCH 23/24] Documentation: EM: Update with runtime modification design Add a new description which covers the information about runtime EM. It contains the design decisions, describes models and how they reflect the reality. Remove description of the default EM. Add example driver code which modifies EM. Add API documentation for the new feature which allows to modify the EM in runtime. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- Documentation/power/energy-model.rst | 183 ++++++++++++++++++++++++++- 1 file changed, 179 insertions(+), 4 deletions(-) diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst index 13225965c9a4..ada4938c37e5 100644 --- a/Documentation/power/energy-model.rst +++ b/Documentation/power/energy-model.rst @@ -71,6 +71,31 @@ whose performance is scaled together. Performance domains generally have a required to have the same micro-architecture. CPUs in different performance domains can have different micro-architectures. +To better reflect power variation due to static power (leakage) the EM +supports runtime modifications of the power values. The mechanism relies on +RCU to free the modifiable EM perf_state table memory. Its user, the task +scheduler, also uses RCU to access this memory. The EM framework provides +API for allocating/freeing the new memory for the modifiable EM table. +The old memory is freed automatically using RCU callback mechanism when there +are no owners anymore for the given EM runtime table instance. This is tracked +using kref mechanism. The device driver which provided the new EM at runtime, +should call EM API to free it safely when it's no longer needed. The EM +framework will handle the clean-up when it's possible. + +The kernel code which want to modify the EM values is protected from concurrent +access using a mutex. Therefore, the device driver code must run in sleeping +context when it tries to modify the EM. + +With the runtime modifiable EM we switch from a 'single and during the entire +runtime static EM' (system property) design to a 'single EM which can be +changed during runtime according e.g. to the workload' (system and workload +property) design. + +It is possible also to modify the CPU performance values for each EM's +performance state. Thus, the full power and performance profile (which +is an exponential curve) can be changed according e.g. to the workload +or system property. + 2. Core APIs ------------ @@ -175,10 +200,82 @@ CPUfreq governor is in use in case of CPU device. Currently this calculation is not provided for other type of devices. More details about the above APIs can be found in ```` -or in Section 2.4 +or in Section 2.5 -2.4 Description details of this API +2.4 Runtime modifications +^^^^^^^^^^^^^^^^^^^^^^^^^ + +Drivers willing to update the EM at runtime should use the following dedicated +function to allocate a new instance of the modified EM. The API is listed +below:: + + struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); + +This allows to allocate a structure which contains the new EM table with +also RCU and kref needed by the EM framework. The 'struct em_perf_table' +contains array 'struct em_perf_state state[]' which is a list of performance +states in ascending order. That list must be populated by the device driver +which wants to update the EM. The list of frequencies can be taken from +existing EM (created during boot). The content in the 'struct em_perf_state' +must be populated by the driver as well. + +This is the API which does the EM update, using RCU pointers swap:: + + int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table); + +Drivers must provide a pointer to the allocated and initialized new EM +'struct em_perf_table'. That new EM will be safely used inside the EM framework +and will be visible to other sub-systems in the kernel (thermal, powercap). +The main design goal for this API is to be fast and avoid extra calculations +or memory allocations at runtime. When pre-computed EMs are available in the +device driver, than it should be possible to simply re-use them with low +performance overhead. + +In order to free the EM, provided earlier by the driver (e.g. when the module +is unloaded), there is a need to call the API:: + + void em_table_free(struct em_perf_table __rcu *table); + +It will allow the EM framework to safely remove the memory, when there is +no other sub-system using it, e.g. EAS. + +To use the power values in other sub-systems (like thermal, powercap) there is +a need to call API which protects the reader and provide consistency of the EM +table data:: + + struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd); + +It returns the 'struct em_perf_state' pointer which is an array of performance +states in ascending order. +This function must be called in the RCU read lock section (after the +rcu_read_lock()). When the EM table is not needed anymore there is a need to +call rcu_real_unlock(). In this way the EM safely uses the RCU read section +and protects the users. It also allows the EM framework to manage the memory +and free it. More details how to use it can be found in Section 3.2 in the +example driver. + +There is dedicated API for device drivers to calculate em_perf_state::cost +values:: + + int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states); + +These 'cost' values from EM are used in EAS. The new EM table should be passed +together with the number of entries and device pointer. When the computation +of the cost values is done properly the return value from the function is 0. +The function takes care for right setting of inefficiency for each performance +state as well. It updates em_perf_state::flags accordingly. +Then such prepared new EM can be passed to the em_dev_update_perf_domain() +function, which will allow to use it. + +More details about the above APIs can be found in ```` +or in Section 3.2 with an example code showing simple implementation of the +updating mechanism in a device driver. + + +2.5 Description details of this API ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ .. kernel-doc:: include/linux/energy_model.h :internal: @@ -187,8 +284,11 @@ or in Section 2.4 :export: -3. Example driver ------------------ +3. Examples +----------- + +3.1 Example driver with EM registration +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The CPUFreq framework supports dedicated callback for registering the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em(). @@ -242,3 +342,78 @@ EM framework:: 39 static struct cpufreq_driver foo_cpufreq_driver = { 40 .register_em = foo_cpufreq_register_em, 41 }; + + +3.2 Example driver with EM modification +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +This section provides a simple example of a thermal driver modifying the EM. +The driver implements a foo_thermal_em_update() function. The driver is woken +up periodically to check the temperature and modify the EM data:: + + -> drivers/soc/example/example_em_mod.c + + 01 static void foo_get_new_em(struct foo_context *ctx) + 02 { + 03 struct em_perf_table __rcu *em_table; + 04 struct em_perf_state *table, *new_table; + 05 struct device *dev = ctx->dev; + 06 struct em_perf_domain *pd; + 07 unsigned long freq; + 08 int i, ret; + 09 + 10 pd = em_pd_get(dev); + 11 if (!pd) + 12 return; + 13 + 14 em_table = em_table_alloc(pd); + 15 if (!em_table) + 16 return; + 17 + 18 new_table = em_table->state; + 19 + 20 rcu_read_lock(); + 21 table = em_perf_state_from_pd(pd); + 22 for (i = 0; i < pd->nr_perf_states; i++) { + 23 freq = table[i].frequency; + 24 foo_get_power_perf_values(dev, freq, &new_table[i]); + 25 } + 26 rcu_read_unlock(); + 27 + 28 /* Calculate 'cost' values for EAS */ + 29 ret = em_dev_compute_costs(dev, table, pd->nr_perf_states); + 30 if (ret) { + 31 dev_warn(dev, "EM: compute costs failed %d\n", ret); + 32 em_free_table(em_table); + 33 return; + 34 } + 35 + 36 ret = em_dev_update_perf_domain(dev, em_table); + 37 if (ret) { + 38 dev_warn(dev, "EM: update failed %d\n", ret); + 39 em_free_table(em_table); + 40 return; + 41 } + 42 + 43 /* + 44 * Since it's one-time-update drop the usage counter. + 45 * The EM framework will later free the table when needed. + 46 */ + 47 em_table_free(em_table); + 48 } + 49 + 50 /* + 51 * Function called periodically to check the temperature and + 52 * update the EM if needed + 53 */ + 54 static void foo_thermal_em_update(struct foo_context *ctx) + 55 { + 56 struct device *dev = ctx->dev; + 57 int cpu; + 58 + 59 ctx->temperature = foo_get_temp(dev, ctx); + 60 if (ctx->temperature < FOO_EM_UPDATE_TEMP_THRESHOLD) + 61 return; + 62 + 63 foo_get_new_em(ctx); + 64 } From 3a561ea2413ea5a740f3b1d6b5355d46f88a7456 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 21 Feb 2024 14:25:50 +0000 Subject: [PATCH 24/24] PM: EM: Fix nr_states warnings in static checks During the static checks nr_states has been mentioned by the kernel test robot. Fix the warning in those 2 places. Reported-by: kernel test robot Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- kernel/power/energy_model.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 7101fa3fa0c0..b686ac0345bd 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -280,6 +280,7 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, * em_dev_compute_costs() - Calculate cost values for new runtime EM table * @dev : Device for which the EM table is to be updated * @table : The new EM table that is going to get the costs calculated + * @nr_states : Number of performance states * * Calculate the em_perf_state::cost values for new runtime EM table. The * values are used for EAS during task placement. It also calculates and sets @@ -728,7 +729,6 @@ static void em_check_capacity_update(void) struct cpufreq_policy *policy; unsigned long em_max_perf; struct device *dev; - int nr_states; if (cpumask_test_cpu(cpu, cpu_done_mask)) continue; @@ -749,7 +749,6 @@ static void em_check_capacity_update(void) cpumask_or(cpu_done_mask, cpu_done_mask, em_span_cpus(pd)); - nr_states = pd->nr_perf_states; cpu_capacity = arch_scale_cpu_capacity(cpu); rcu_read_lock();