diff options
| -rw-r--r-- | Documentation/kernel-parameters.txt | 9 | ||||
| -rw-r--r-- | arch/arm/Kconfig | 85 | ||||
| -rw-r--r-- | arch/arm/include/asm/hw_breakpoint.h | 3 | ||||
| -rw-r--r-- | arch/arm/include/asm/topology.h | 31 | ||||
| -rw-r--r-- | arch/arm/kernel/hw_breakpoint.c | 56 | ||||
| -rw-r--r-- | arch/arm/kernel/topology.c | 105 | ||||
| -rw-r--r-- | drivers/cpufreq/cpufreq.c | 25 | ||||
| -rw-r--r-- | include/linux/sched.h | 12 | ||||
| -rw-r--r-- | include/trace/events/sched.h | 153 | ||||
| -rw-r--r-- | kernel/irq/irqdesc.c | 21 | ||||
| -rw-r--r-- | kernel/sched/core.c | 4 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 3 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 1021 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 13 | ||||
| -rw-r--r-- | linaro/configs/big-LITTLE-MP.conf | 13 |
15 files changed, 1534 insertions, 20 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6c723811c0a..21516d189f1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1177,6 +1177,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. See comment before ip2_setup() in drivers/char/ip2/ip2base.c. + irqaffinity= [SMP] Set the default irq affinity mask + Format: + <cpu number>,...,<cpu number> + or + <cpu number>-<cpu number> + (must be a positive range in ascending order) + or a mixture + <cpu number>,...,<cpu number>-<cpu number> + irqfixup [HW] When an interrupt is not handled search all handlers for it. Intended to get systems with badly broken diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 67874b82a4e..67ac812f733 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1567,6 +1567,91 @@ config SCHED_SMT MultiThreading at a cost of slightly increased overhead in some places. If unsure say N here. +config DISABLE_CPU_SCHED_DOMAIN_BALANCE + bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing" + help + Disables scheduler load-balancing at CPU sched domain level. + +config SCHED_HMP + bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling" + depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP + help + Experimental scheduler optimizations for heterogeneous platforms. + Attempts to introspectively select task affinity to optimize power + and performance. Basic support for multiple (>2) cpu types is in place, + but it has only been tested with two types of cpus. + There is currently no support for migration of task groups, hence + !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled + between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE). + +config SCHED_HMP_PRIO_FILTER + bool "(EXPERIMENTAL) Filter HMP migrations by task priority" + depends on SCHED_HMP + default y + help + Enables task priority based HMP migration filter. Any task with + a NICE value above the threshold will always be on low-power cpus + with less compute capacity. + +config SCHED_HMP_PRIO_FILTER_VAL + int "NICE priority threshold" + default 5 + depends on SCHED_HMP_PRIO_FILTER + +config HMP_FAST_CPU_MASK + string "HMP scheduler fast CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the fast CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_SLOW_CPU_MASK + string "HMP scheduler slow CPU mask" + depends on SCHED_HMP + help + Leave empty to use device tree information. + Specify the cpuids of the slow CPUs in the system as a list string, + e.g. cpuid 0+1 should be specified as 0-1. + +config HMP_VARIABLE_SCALE + bool "Allows changing the load tracking scale through sysfs" + depends on SCHED_HMP + help + When turned on, this option exports the thresholds and load average + period value for the load tracking patches through sysfs. + The values can be modified to change the rate of load accumulation + and the thresholds used for HMP migration. + The load_avg_period_ms is the time in ms to reach a load average of + 0.5 for an idle task of 0 load average ratio that start a busy loop. + The up_threshold and down_threshold is the value to go to a faster + CPU or to go back to a slower cpu. + The {up,down}_threshold are devided by 1024 before being compared + to the load average. + For examples, with load_avg_period_ms = 128 and up_threshold = 512, + a running task with a load of 0 will be migrated to a bigger CPU after + 128ms, because after 128ms its load_avg_ratio is 0.5 and the real + up_threshold is 0.5. + This patch has the same behavior as changing the Y of the load + average computation to + (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms) + but it remove intermadiate overflows in computation. + +config HMP_FREQUENCY_INVARIANT_SCALE + bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP" + depends on HMP_VARIABLE_SCALE && CPU_FREQ + help + Scales the current load contribution in line with the frequency + of the CPU that the task was executed on. + In this version, we use a simple linear scale derived from the + maximum frequency reported by CPUFreq. + Restricting tracked load to be scaled by the CPU's frequency + represents the consumption of possible compute capacity + (rather than consumption of actual instantaneous capacity as + normal) and allows the HMP migration's simple threshold + migration strategy to interact more predictably with CPUFreq's + asynchronous compute capacity changes. + config HAVE_ARM_SCU bool help diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index 01169dd723f..eef55ea9ef0 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -85,6 +85,9 @@ static inline void decode_ctrl_reg(u32 reg, #define ARM_DSCR_HDBGEN (1 << 14) #define ARM_DSCR_MDBGEN (1 << 15) +/* OSLSR os lock model bits */ +#define ARM_OSLSR_OSLM0 (1 << 0) + /* opcode2 numbers for the co-processor instructions. */ #define ARM_OP2_BVR 4 #define ARM_OP2_BCR 5 diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 611edefaeaf..983fa7c153a 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -28,6 +28,37 @@ void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask); +#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE +/* Common values for CPUs */ +#ifndef SD_CPU_INIT +#define SD_CPU_INIT (struct sched_domain) { \ + .min_interval = 1, \ + .max_interval = 4, \ + .busy_factor = 64, \ + .imbalance_pct = 125, \ + .cache_nice_tries = 1, \ + .busy_idx = 2, \ + .idle_idx = 1, \ + .newidle_idx = 0, \ + .wake_idx = 0, \ + .forkexec_idx = 0, \ + \ + .flags = 0*SD_LOAD_BALANCE \ + | 1*SD_BALANCE_NEWIDLE \ + | 1*SD_BALANCE_EXEC \ + | 1*SD_BALANCE_FORK \ + | 0*SD_BALANCE_WAKE \ + | 1*SD_WAKE_AFFINE \ + | 0*SD_SHARE_CPUPOWER \ + | 0*SD_SHARE_PKG_RESOURCES \ + | 0*SD_SERIALIZE \ + , \ + .last_balance = jiffies, \ + .balance_interval = 1, \ +} +#endif +#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */ + #else static inline void init_cpu_topology(void) { } diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 5ff2e77782b..f031a4f8293 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -28,6 +28,7 @@ #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/smp.h> +#include <linux/cpu_pm.h> #include <asm/cacheflush.h> #include <asm/cputype.h> @@ -49,6 +50,9 @@ static int core_num_wrps; /* Debug architecture version. */ static u8 debug_arch; +/* Does debug architecture support OS Save and Restore? */ +static bool has_ossr; + /* Maximum supported watchpoint length. */ static u8 max_watchpoint_len; @@ -903,6 +907,23 @@ static struct undef_hook debug_reg_hook = { .fn = debug_reg_trap, }; +/* Does this core support OS Save and Restore? */ +static bool core_has_os_save_restore(void) +{ + u32 oslsr; + + switch (get_debug_arch()) { + case ARM_DEBUG_ARCH_V7_1: + return true; + case ARM_DEBUG_ARCH_V7_ECP14: + ARM_DBG_READ(c1, c1, 4, oslsr); + if (oslsr & ARM_OSLSR_OSLM0) + return true; + default: + return false; + } +} + static void reset_ctrl_regs(void *unused) { int i, raw_num_brps, err = 0, cpu = smp_processor_id(); @@ -930,11 +951,7 @@ static void reset_ctrl_regs(void *unused) if ((val & 0x1) == 0) err = -EPERM; - /* - * Check whether we implement OS save and restore. - */ - ARM_DBG_READ(c1, c1, 4, val); - if ((val & 0x9) == 0) + if (!has_ossr) goto clear_vcr; break; case ARM_DEBUG_ARCH_V7_1: @@ -1015,6 +1032,31 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = { .notifier_call = dbg_reset_notify, }; +#ifdef CONFIG_CPU_PM +static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, + void *v) +{ + if (action == CPU_PM_EXIT) + reset_ctrl_regs(NULL); + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { + .notifier_call = dbg_cpu_pm_notify, +}; + +static void __init pm_init(void) +{ + if (has_ossr) + cpu_pm_register_notifier(&dbg_cpu_pm_nb); +} +#else +static inline void pm_init(void) +{ +} +#endif + static int __init arch_hw_breakpoint_init(void) { debug_arch = get_debug_arch(); @@ -1024,6 +1066,8 @@ static int __init arch_hw_breakpoint_init(void) return 0; } + has_ossr = core_has_os_save_restore(); + /* Determine how many BRPs/WRPs are available. */ core_num_brps = get_num_brps(); core_num_wrps = get_num_wrps(); @@ -1064,6 +1108,8 @@ static int __init arch_hw_breakpoint_init(void) /* Register hotplug notifier. */ register_cpu_notifier(&dbg_reset_nb); + + pm_init(); return 0; } arch_initcall(arch_hw_breakpoint_init); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 4239ab2e87c..fa45fb43a62 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <asm/cputype.h> +#include <asm/smp_plat.h> #include <asm/topology.h> /* @@ -287,6 +288,110 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } + +#ifdef CONFIG_SCHED_HMP + +static const char * const little_cores[] = { + "arm,cortex-a7", + NULL, +}; + +static bool is_little_cpu(struct device_node *cn) +{ + const char * const *lc; + for (lc = little_cores; *lc; lc++) + if (of_device_is_compatible(cn, *lc)) + return true; + return false; +} + +void __init arch_get_fast_and_slow_cpus(struct cpumask *fast, + struct cpumask *slow) +{ + struct device_node *cn = NULL; + int cpu; + + cpumask_clear(fast); + cpumask_clear(slow); + + /* + * Use the config options if they are given. This helps testing + * HMP scheduling on systems without a big.LITTLE architecture. + */ + if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) { + if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast)) + WARN(1, "Failed to parse HMP fast cpu mask!\n"); + if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow)) + WARN(1, "Failed to parse HMP slow cpu mask!\n"); + return; + } + + /* + * Else, parse device tree for little cores. + */ + while ((cn = of_find_node_by_type(cn, "cpu"))) { + + const u32 *mpidr; + int len; + + mpidr = of_get_property(cn, "reg", &len); + if (!mpidr || len != 4) { + pr_err("* %s missing reg property\n", cn->full_name); + continue; + } + + cpu = get_logical_index(be32_to_cpup(mpidr)); + if (cpu == -EINVAL) { + pr_err("couldn't get logical index for mpidr %x\n", + be32_to_cpup(mpidr)); + break; + } + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + } + + if (!cpumask_empty(fast) && !cpumask_empty(slow)) + return; + + /* + * We didn't find both big and little cores so let's call all cores + * fast as this will keep the system running, with all cores being + * treated equal. + */ + cpumask_setall(fast); + cpumask_clear(slow); +} + +void __init arch_get_hmp_domains(struct list_head *hmp_domains_list) +{ + struct cpumask hmp_fast_cpu_mask; + struct cpumask hmp_slow_cpu_mask; + struct hmp_domain *domain; + + arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask); + + /* + * Initialize hmp_domains + * Must be ordered with respect to compute capacity. + * Fastest domain at head of list. + */ + if(!cpumask_empty(&hmp_slow_cpu_mask)) { + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->cpus, &hmp_slow_cpu_mask); + list_add(&domain->hmp_domains, hmp_domains_list); + } + domain = (struct hmp_domain *) + kmalloc(sizeof(struct hmp_domain), GFP_KERNEL); + cpumask_copy(&domain->cpus, &hmp_fast_cpu_mask); + list_add(&domain->hmp_domains, hmp_domains_list); +} +#endif /* CONFIG_SCHED_HMP */ + + /* * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster * @socket_id: cluster HW identifier diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1f93dbd7235..034d1836884 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -47,6 +47,9 @@ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); #endif static DEFINE_SPINLOCK(cpufreq_driver_lock); +/* Used when we unregister cpufreq driver */ +static struct cpumask cpufreq_online_mask; + /* * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure * all cpufreq/hotplug/workqueue/etc related lock issues. @@ -751,11 +754,16 @@ static int cpufreq_add_dev_policy(unsigned int cpu, return -EBUSY; } + __cpufreq_governor(managed_policy, CPUFREQ_GOV_STOP); + spin_lock_irqsave(&cpufreq_driver_lock, flags); cpumask_copy(managed_policy->cpus, policy->cpus); per_cpu(cpufreq_cpu_data, cpu) = managed_policy; spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + __cpufreq_governor(managed_policy, CPUFREQ_GOV_START); + __cpufreq_governor(managed_policy, CPUFREQ_GOV_LIMITS); + pr_debug("CPU already managed, adding link\n"); ret = sysfs_create_link(&dev->kobj, &managed_policy->kobj, @@ -970,6 +978,14 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) pr_debug("initialization failed\n"); goto err_unlock_policy; } + + /* + * affected cpus must always be the one, which are online. We aren't + * managing offline cpus here. + */ + cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); + cpumask_and(policy->cpus, policy->cpus, &cpufreq_online_mask); + policy->user_policy.min = policy->min; policy->user_policy.max = policy->max; @@ -1052,15 +1068,19 @@ static int __cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif } per_cpu(cpufreq_cpu_data, cpu) = NULL; - #ifdef CONFIG_SMP /* if this isn't the CPU which is the parent of the kobj, we * only need to unlink, put and exit */ if (unlikely(cpu != data->cpu)) { pr_debug("removing link\n"); + __cpufreq_governor(data, CPUFREQ_GOV_STOP); cpumask_clear_cpu(cpu, data->cpus); spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + + __cpufreq_governor(data, CPUFREQ_GOV_START); + __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + kobj = &dev->kobj; cpufreq_cpu_put(data); unlock_policy_rwsem_write(cpu); @@ -1168,6 +1188,7 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) if (unlikely(lock_policy_rwsem_write(cpu))) BUG(); + cpumask_clear_cpu(cpu, &cpufreq_online_mask); retval = __cpufreq_remove_dev(dev, sif); return retval; } @@ -1886,6 +1907,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) cpufreq_driver = driver_data; spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + cpumask_setall(&cpufreq_online_mask); + ret = subsys_interface_register(&cpufreq_interface); if (ret) goto err_null_driver; diff --git a/include/linux/sched.h b/include/linux/sched.h index d2112477ff5..1a8e5ddb4ed 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1020,6 +1020,12 @@ unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); bool cpus_share_cache(int this_cpu, int that_cpu); +#ifdef CONFIG_SCHED_HMP +struct hmp_domain { + struct cpumask cpus; + struct list_head hmp_domains; +}; +#endif /* CONFIG_SCHED_HMP */ #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1132,6 +1138,12 @@ struct sched_avg { u64 last_runnable_update; s64 decay_count; unsigned long load_avg_contrib; + unsigned long load_avg_ratio; +#ifdef CONFIG_SCHED_HMP + u64 hmp_last_up_migration; + u64 hmp_last_down_migration; +#endif + u32 usage_avg_sum; }; #ifdef CONFIG_SCHEDSTATS diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 5a8671e8a67..501aa32eb2f 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -430,6 +430,159 @@ TRACE_EVENT(sched_pi_setprio, __entry->oldprio, __entry->newprio) ); +/* + * Tracepoint for showing tracked load contribution. + */ +TRACE_EVENT(sched_task_load_contrib, + + TP_PROTO(struct task_struct *tsk, unsigned long load_contrib), + + TP_ARGS(tsk, load_contrib), + + TP_STRUCT__entry( + __array(char, comm, TASK_COMM_LEN) + __field(pid_t, pid) + __field(unsigned long, load_contrib) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->load_contrib = load_contrib; + ), + + TP_printk("comm=%s pid=%d load_contrib=%lu", + __entry->comm, __entry->pid, + __entry->load_contrib) +); + +/* + * Tracepoint for showing tracked task runnable ratio [0..1023]. + */ +TRACE_EVENT(sched_task_runnable_ratio, + + TP_PROTO(struct task_struct *tsk, unsigned long ratio), + + TP_ARGS(tsk, ratio), + + TP_STRUCT__entry( + __array(char, comm, TASK_COMM_LEN) + __field(pid_t, pid) + __field(unsigned long, ratio) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->ratio = ratio; + ), + + TP_printk("comm=%s pid=%d ratio=%lu", + __entry->comm, __entry->pid, + __entry->ratio) +); + +/* + * Tracepoint for showing tracked rq runnable ratio [0..1023]. + */ +TRACE_EVENT(sched_rq_runnable_ratio, + + TP_PROTO(int cpu, unsigned long ratio), + + TP_ARGS(cpu, ratio), + + TP_STRUCT__entry( + __field(int, cpu) + __field(unsigned long, ratio) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->ratio = ratio; + ), + + TP_printk("cpu=%d ratio=%lu", + __entry->cpu, + __entry->ratio) +); + +/* + * Tracepoint for showing tracked rq runnable load. + */ +TRACE_EVENT(sched_rq_runnable_load, + + TP_PROTO(int cpu, u64 load), + + TP_ARGS(cpu, load), + + TP_STRUCT__entry( + __field(int, cpu) + __field(u64, load) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->load = load; + ), + + TP_printk("cpu=%d load=%llu", + __entry->cpu, + __entry->load) +); + +/* + * Tracepoint for showing tracked task cpu usage ratio [0..1023]. + */ +TRACE_EVENT(sched_task_usage_ratio, + + TP_PROTO(struct task_struct *tsk, unsigned long ratio), + + TP_ARGS(tsk, ratio), + + TP_STRUCT__entry( + __array(char, comm, TASK_COMM_LEN) + __field(pid_t, pid) + __field(unsigned long, ratio) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->ratio = ratio; + ), + + TP_printk("comm=%s pid=%d ratio=%lu", + __entry->comm, __entry->pid, + __entry->ratio) +); + +/* + * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations. + */ +TRACE_EVENT(sched_hmp_migrate, + + TP_PROTO(struct task_struct *tsk, int dest, int force), + + TP_ARGS(tsk, dest, force), + + TP_STRUCT__entry( + __array(char, comm, TASK_COMM_LEN) + __field(pid_t, pid) + __field(int, dest) + __field(int, force) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->dest = dest; + __entry->force = force; + ), + + TP_printk("comm=%s pid=%d dest=%d force=%d", + __entry->comm, __entry->pid, + __entry->dest, __entry->force) +); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 192a302d6cf..473b2b6eccb 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -23,10 +23,27 @@ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) +static int __init irq_affinity_setup(char *str) +{ + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + cpulist_parse(str, irq_default_affinity); + /* + * Set at least the boot cpu. We don't want to end up with + * bugreports caused by random comandline masks + */ + cpumask_set_cpu(smp_processor_id(), irq_default_affinity); + return 1; +} +__setup("irqaffinity=", irq_affinity_setup); + static void __init init_irq_default_affinity(void) { - alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); - cpumask_setall(irq_default_affinity); +#ifdef CONFIG_CPUMASK_OFFSTACK + if (!irq_default_affinity) + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); +#endif + if (cpumask_empty(irq_default_affinity)) + cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 26058d0bebb..cf00316e342 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1559,6 +1559,10 @@ static void __sched_fork(struct task_struct *p) #if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED) p->se.avg.runnable_avg_period = 0; p->se.avg.runnable_avg_sum = 0; +#ifdef CONFIG_SCHED_HMP + p->se.avg.hmp_last_up_migration = 0; + p->se.avg.hmp_last_down_migration = 0; +#endif #endif #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 7ae4c4c5420..4a429ad01fd 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -94,6 +94,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group #ifdef CONFIG_SMP P(se->avg.runnable_avg_sum); P(se->avg.runnable_avg_period); + P(se->avg.usage_avg_sum); P(se->avg.load_avg_contrib); P(se->avg.decay_count); #endif @@ -230,6 +231,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->tg_runnable_contrib); SEQ_printf(m, " .%-30s: %d\n", "tg->runnable_avg", atomic_read(&cfs_rq->tg->runnable_avg)); + SEQ_printf(m, " .%-30s: %d\n", "tg->usage_avg", + atomic_read(&cfs_rq->tg->usage_avg)); #endif print_cfs_group_stats(m, cpu, cfs_rq->tg); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 81fa5364340..6baa8c84aa8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -31,9 +31,20 @@ #include <linux/task_work.h> #include <trace/events/sched.h> +#ifdef CONFIG_HMP_VARIABLE_SCALE +#include <linux/sysfs.h> +#include <linux/vmalloc.h> +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE +/* Include cpufreq header to add a notifier so that cpu frequency + * scaling can track the current CPU frequency + */ +#include <linux/cpufreq.h> +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ +#endif /* CONFIG_HMP_VARIABLE_SCALE */ #include "sched.h" + /* * Targeted preemption latency for CPU-bound tasks: * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) @@ -1200,8 +1211,95 @@ static u32 __compute_runnable_contrib(u64 n) return contrib + runnable_avg_yN_sum[n]; } -/* - * We can represent the historical contribution to runnable average as the +#ifdef CONFIG_HMP_VARIABLE_SCALE + +#define HMP_VARIABLE_SCALE_SHIFT 16ULL +struct hmp_global_attr { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, + struct attribute *attr, char *buf); + ssize_t (*store)(struct kobject *a, struct attribute *b, + const char *c, size_t count); + int *value; + int (*to_sysfs)(int); + int (*from_sysfs)(int); +}; + +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE +#define HMP_DATA_SYSFS_MAX 4 +#else +#define HMP_DATA_SYSFS_MAX 3 +#endif + +struct hmp_data_struct { +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + int freqinvar_load_scale_enabled; +#endif + int multiplier; /* used to scale the time delta */ + struct attribute_group attr_group; + struct attribute *attributes[HMP_DATA_SYSFS_MAX + 1]; + struct hmp_global_attr attr[HMP_DATA_SYSFS_MAX]; +} hmp_data; + +static u64 hmp_variable_scale_convert(u64 delta); +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE +/* Frequency-Invariant Load Modification: + * Loads are calculated as in PJT's patch however we also scale the current + * contribution in line with the frequency of the CPU that the task was + * executed on. + * In this version, we use a simple linear scale derived from the maximum + * frequency reported by CPUFreq. As an example: + * + * Consider that we ran a task for 100% of the previous interval. + * + * Our CPU was under asynchronous frequency control through one of the + * CPUFreq governors. + * + * The CPUFreq governor reports that it is able to scale the CPU between + * 500MHz and 1GHz. + * + * During the period, the CPU was running at 1GHz. + * + * In this case, our load contribution for that period is calculated as + * 1 * (number_of_active_microseconds) + * + * This results in our task being able to accumulate maximum load as normal. + * + * + * Consider now that our CPU was executing at 500MHz. + * + * We now scale the load contribution such that it is calculated as + * 0.5 * (number_of_active_microseconds) + * + * Our task can only record 50% maximum load during this period. + * + * This represents the task consuming 50% of the CPU's *possible* compute + * capacity. However the task did consume 100% of the CPU's *available* + * compute capacity which is the value seen by the CPUFreq governor and + * user-side CPU Utilization tools. + * + * Restricting tracked load to be scaled by the CPU's frequency accurately + * represents the consumption of possible compute capacity and allows the + * HMP migration's simple threshold migration strategy to interact more + * predictably with CPUFreq's asynchronous compute capacity changes. + */ +#define SCHED_FREQSCALE_SHIFT 10 +struct cpufreq_extents { + u32 curr_scale; + u32 min; + u32 max; + u32 flags; +}; +/* Flag set when the governor in use only allows one frequency. + * Disables scaling. + */ +#define SCHED_LOAD_FREQINVAR_SINGLEFREQ 0x01 + +static struct cpufreq_extents freq_scale[CONFIG_NR_CPUS]; +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ +#endif /* CONFIG_HMP_VARIABLE_SCALE */ + +/* We can represent the historical contribution to runnable average as the * coefficients of a geometric series. To do this we sub-divide our runnable * history into segments of approximately 1ms (1024us); label the segment that * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. @@ -1230,13 +1328,24 @@ static u32 __compute_runnable_contrib(u64 n) */ static __always_inline int __update_entity_runnable_avg(u64 now, struct sched_avg *sa, - int runnable) + int runnable, + int running, + int cpu) { u64 delta, periods; u32 runnable_contrib; int delta_w, decayed = 0; +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + u64 scaled_delta; + u32 scaled_runnable_contrib; + int scaled_delta_w; + u32 curr_scale = 1024; +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ delta = now - sa->last_runnable_update; +#ifdef CONFIG_HMP_VARIABLE_SCALE + delta = hmp_variable_scale_convert(delta); +#endif /* * This should only happen when time goes backwards, which it * unfortunately does during sched clock init when we swap over to TSC. @@ -1255,6 +1364,12 @@ static __always_inline int __update_entity_runnable_avg(u64 now, return 0; sa->last_runnable_update = now; +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + /* retrieve scale factor for load */ + if (hmp_data.freqinvar_load_scale_enabled) + curr_scale = freq_scale[cpu].curr_scale; +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ + /* delta_w is the amount already accumulated against our next period */ delta_w = sa->runnable_avg_period % 1024; if (delta + delta_w >= 1024) { @@ -1267,8 +1382,20 @@ static __always_inline int __update_entity_runnable_avg(u64 now, * period and accrue it. */ delta_w = 1024 - delta_w; + /* scale runnable time if necessary */ +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + scaled_delta_w = (delta_w * curr_scale) + >> SCHED_FREQSCALE_SHIFT; + if (runnable) + sa->runnable_avg_sum += scaled_delta_w; + if (running) + sa->usage_avg_sum += scaled_delta_w; +#else if (runnable) sa->runnable_avg_sum += delta_w; + if (running) + sa->usage_avg_sum += delta_w; +#endif /* #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ sa->runnable_avg_period += delta_w; delta -= delta_w; @@ -1276,22 +1403,49 @@ static __always_inline int __update_entity_runnable_avg(u64 now, /* Figure out how many additional periods this update spans */ periods = delta / 1024; delta %= 1024; - + /* decay the load we have accumulated so far */ sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, periods + 1); sa->runnable_avg_period = decay_load(sa->runnable_avg_period, periods + 1); - + sa->usage_avg_sum = decay_load(sa->usage_avg_sum, periods + 1); + /* add the contribution from this period */ /* Efficiently calculate \sum (1..n_period) 1024*y^i */ runnable_contrib = __compute_runnable_contrib(periods); + /* Apply load scaling if necessary. + * Note that multiplying the whole series is same as + * multiplying all terms + */ +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + scaled_runnable_contrib = (runnable_contrib * curr_scale) + >> SCHED_FREQSCALE_SHIFT; + if (runnable) + sa->runnable_avg_sum += scaled_runnable_contrib; + if (running) + sa->usage_avg_sum += scaled_runnable_contrib; +#else if (runnable) sa->runnable_avg_sum += runnable_contrib; + if (running) + sa->usage_avg_sum += runnable_contrib; +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ sa->runnable_avg_period += runnable_contrib; } /* Remainder of delta accrued against u_0` */ + /* scale if necessary */ +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + scaled_delta = ((delta * curr_scale) >> SCHED_FREQSCALE_SHIFT); + if (runnable) + sa->runnable_avg_sum += scaled_delta; + if (running) + sa->usage_avg_sum += scaled_delta; +#else if (runnable) sa->runnable_avg_sum += delta; + if (running) + sa->usage_avg_sum += delta; +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ sa->runnable_avg_period += delta; return decayed; @@ -1337,16 +1491,28 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa, struct cfs_rq *cfs_rq) { struct task_group *tg = cfs_rq->tg; - long contrib; + long contrib, usage_contrib; /* The fraction of a cpu used by this cfs_rq */ contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT, sa->runnable_avg_period + 1); contrib -= cfs_rq->tg_runnable_contrib; - if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { + usage_contrib = div_u64(sa->usage_avg_sum << NICE_0_SHIFT, + sa->runnable_avg_period + 1); + usage_contrib -= cfs_rq->tg_usage_contrib; + + /* + * contrib/usage at this point represent deltas, only update if they + * are substantive. + */ + if ((abs(contrib) > cfs_rq->tg_runnable_contrib / 64) || + (abs(usage_contrib) > cfs_rq->tg_usage_contrib / 64)) { atomic_add(contrib, &tg->runnable_avg); cfs_rq->tg_runnable_contrib += contrib; + + atomic_add(usage_contrib, &tg->usage_avg); + cfs_rq->tg_usage_contrib += usage_contrib; } } @@ -1407,6 +1573,11 @@ static inline void __update_task_entity_contrib(struct sched_entity *se) contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); contrib /= (se->avg.runnable_avg_period + 1); se->avg.load_avg_contrib = scale_load(contrib); + trace_sched_task_load_contrib(task_of(se), se->avg.load_avg_contrib); + contrib = se->avg.runnable_avg_sum * scale_load_down(NICE_0_LOAD); + contrib /= (se->avg.runnable_avg_period + 1); + se->avg.load_avg_ratio = scale_load(contrib); + trace_sched_task_runnable_ratio(task_of(se), se->avg.load_avg_ratio); } /* Compute the current contribution to load_avg by se, return any delta */ @@ -1442,7 +1613,11 @@ static inline void update_entity_load_avg(struct sched_entity *se, struct cfs_rq *cfs_rq = cfs_rq_of(se); long contrib_delta; u64 now; + int cpu = -1; /* not used in normal case */ +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + cpu = cfs_rq->rq->cpu; +#endif /* * For a group entity we need to use their owned cfs_rq_clock_task() in * case they are the parent of a throttled hierarchy. @@ -1452,7 +1627,8 @@ static inline void update_entity_load_avg(struct sched_entity *se, else now = cfs_rq_clock_task(group_cfs_rq(se)); - if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq)) + if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq, + cfs_rq->curr == se, cpu)) return; contrib_delta = __update_entity_load_avg_contrib(se); @@ -1496,8 +1672,19 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) static inline void update_rq_runnable_avg(struct rq *rq, int runnable) { - __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable); + u32 contrib; + int cpu = -1; /* not used in normal case */ + +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + cpu = rq->cpu; +#endif + __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable, + runnable, cpu); __update_tg_runnable_avg(&rq->avg, &rq->cfs); + contrib = rq->avg.runnable_avg_sum * scale_load_down(1024); + contrib /= (rq->avg.runnable_avg_period + 1); + trace_sched_rq_runnable_ratio(cpu_of(rq), scale_load(contrib)); + trace_sched_rq_runnable_load(cpu_of(rq), rq->cfs.runnable_load_avg); } /* Add the load generated by se into cfs_rq's child load-average */ @@ -1866,6 +2053,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); + update_entity_load_avg(se, 1); } update_stats_curr_start(cfs_rq, se); @@ -3301,6 +3489,387 @@ done: return target; } +#ifdef CONFIG_SCHED_HMP +/* + * Heterogenous multiprocessor (HMP) optimizations + * + * The cpu types are distinguished using a list of hmp_domains + * which each represent one cpu type using a cpumask. + * The list is assumed ordered by compute capacity with the + * fastest domain first. + */ +DEFINE_PER_CPU(struct hmp_domain *, hmp_cpu_domain); + +extern void __init arch_get_hmp_domains(struct list_head *hmp_domains_list); + +/* Setup hmp_domains */ +static int __init hmp_cpu_mask_setup(void) +{ + char buf[64]; + struct hmp_domain *domain; + struct list_head *pos; + int dc, cpu; + + pr_debug("Initializing HMP scheduler:\n"); + + /* Initialize hmp_domains using platform code */ + arch_get_hmp_domains(&hmp_domains); + if (list_empty(&hmp_domains)) { + pr_debug("HMP domain list is empty!\n"); + return 0; + } + + /* Print hmp_domains */ + dc = 0; + list_for_each(pos, &hmp_domains) { + domain = list_entry(pos, struct hmp_domain, hmp_domains); + cpulist_scnprintf(buf, 64, &domain->cpus); + pr_debug(" HMP domain %d: %s\n", dc, buf); + + for_each_cpu_mask(cpu, domain->cpus) { + per_cpu(hmp_cpu_domain, cpu) = domain; + } + dc++; + } + + return 1; +} + +/* + * Migration thresholds should be in the range [0..1023] + * hmp_up_threshold: min. load required for migrating tasks to a faster cpu + * hmp_down_threshold: max. load allowed for tasks migrating to a slower cpu + * The default values (512, 256) offer good responsiveness, but may need + * tweaking suit particular needs. + * + * hmp_up_prio: Only up migrate task with high priority (<hmp_up_prio) + * hmp_next_up_threshold: Delay before next up migration (1024 ~= 1 ms) + * hmp_next_down_threshold: Delay before next down migration (1024 ~= 1 ms) + */ +unsigned int hmp_up_threshold = 512; +unsigned int hmp_down_threshold = 256; +#ifdef CONFIG_SCHED_HMP_PRIO_FILTER +unsigned int hmp_up_prio = NICE_TO_PRIO(CONFIG_SCHED_HMP_PRIO_FILTER_VAL); +#endif +unsigned int hmp_next_up_threshold = 4096; +unsigned int hmp_next_down_threshold = 4096; + +static unsigned int hmp_up_migration(int cpu, struct sched_entity *se); +static unsigned int hmp_down_migration(int cpu, struct sched_entity *se); + +/* Check if cpu is in fastest hmp_domain */ +static inline unsigned int hmp_cpu_is_fastest(int cpu) +{ + struct list_head *pos; + + pos = &hmp_cpu_domain(cpu)->hmp_domains; + return pos == hmp_domains.next; +} + +/* Check if cpu is in slowest hmp_domain */ +static inline unsigned int hmp_cpu_is_slowest(int cpu) +{ + struct list_head *pos; + + pos = &hmp_cpu_domain(cpu)->hmp_domains; + return list_is_last(pos, &hmp_domains); +} + +/* Next (slower) hmp_domain relative to cpu */ +static inline struct hmp_domain *hmp_slower_domain(int cpu) +{ + struct list_head *pos; + + pos = &hmp_cpu_domain(cpu)->hmp_domains; + return list_entry(pos->next, struct hmp_domain, hmp_domains); +} + +/* Previous (faster) hmp_domain relative to cpu */ +static inline struct hmp_domain *hmp_faster_domain(int cpu) +{ + struct list_head *pos; + + pos = &hmp_cpu_domain(cpu)->hmp_domains; + return list_entry(pos->prev, struct hmp_domain, hmp_domains); +} + +/* + * Selects a cpu in previous (faster) hmp_domain + * Note that cpumask_any_and() returns the first cpu in the cpumask + */ +static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk, + int cpu) +{ + return cpumask_any_and(&hmp_faster_domain(cpu)->cpus, + tsk_cpus_allowed(tsk)); +} + +/* + * Selects a cpu in next (slower) hmp_domain + * Note that cpumask_any_and() returns the first cpu in the cpumask + */ +static inline unsigned int hmp_select_slower_cpu(struct task_struct *tsk, + int cpu) +{ + return cpumask_any_and(&hmp_slower_domain(cpu)->cpus, + tsk_cpus_allowed(tsk)); +} + +static inline void hmp_next_up_delay(struct sched_entity *se, int cpu) +{ + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + + se->avg.hmp_last_up_migration = cfs_rq_clock_task(cfs_rq); + se->avg.hmp_last_down_migration = 0; +} + +static inline void hmp_next_down_delay(struct sched_entity *se, int cpu) +{ + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + + se->avg.hmp_last_down_migration = cfs_rq_clock_task(cfs_rq); + se->avg.hmp_last_up_migration = 0; +} + +#ifdef CONFIG_HMP_VARIABLE_SCALE +/* + * Heterogenous multiprocessor (HMP) optimizations + * + * These functions allow to change the growing speed of the load_avg_ratio + * by default it goes from 0 to 0.5 in LOAD_AVG_PERIOD = 32ms + * This can now be changed with /sys/kernel/hmp/load_avg_period_ms. + * + * These functions also allow to change the up and down threshold of HMP + * using /sys/kernel/hmp/{up,down}_threshold. + * Both must be between 0 and 1023. The threshold that is compared + * to the load_avg_ratio is up_threshold/1024 and down_threshold/1024. + * + * For instance, if load_avg_period = 64 and up_threshold = 512, an idle + * task with a load of 0 will reach the threshold after 64ms of busy loop. + * + * Changing load_avg_periods_ms has the same effect than changing the + * default scaling factor Y=1002/1024 in the load_avg_ratio computation to + * (1002/1024.0)^(LOAD_AVG_PERIOD/load_avg_period_ms), but the last one + * could trigger overflows. + * For instance, with Y = 1023/1024 in __update_task_entity_contrib() + * "contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);" + * could be overflowed for a weight > 2^12 even is the load_avg_contrib + * should still be a 32bits result. This would not happen by multiplicating + * delta time by 1/22 and setting load_avg_period_ms = 706. + */ + +/* + * By scaling the delta time it end-up increasing or decrease the + * growing speed of the per entity load_avg_ratio + * The scale factor hmp_data.multiplier is a fixed point + * number: (32-HMP_VARIABLE_SCALE_SHIFT).HMP_VARIABLE_SCALE_SHIFT + */ +static u64 hmp_variable_scale_convert(u64 delta) +{ + u64 high = delta >> 32ULL; + u64 low = delta & 0xffffffffULL; + low *= hmp_data.multiplier; + high *= hmp_data.multiplier; + return (low >> HMP_VARIABLE_SCALE_SHIFT) + + (high << (32ULL - HMP_VARIABLE_SCALE_SHIFT)); +} + +static ssize_t hmp_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + ssize_t ret = 0; + struct hmp_global_attr *hmp_attr = + container_of(attr, struct hmp_global_attr, attr); + int temp = *(hmp_attr->value); + if (hmp_attr->to_sysfs != NULL) + temp = hmp_attr->to_sysfs(temp); + ret = sprintf(buf, "%d\n", temp); + return ret; +} + +static ssize_t hmp_store(struct kobject *a, struct attribute *attr, + const char *buf, size_t count) +{ + int temp; + ssize_t ret = count; + struct hmp_global_attr *hmp_attr = + container_of(attr, struct hmp_global_attr, attr); + char *str = vmalloc(count + 1); + if (str == NULL) + return -ENOMEM; + memcpy(str, buf, count); + str[count] = 0; + if (sscanf(str, "%d", &temp) < 1) + ret = -EINVAL; + else { + if (hmp_attr->from_sysfs != NULL) + temp = hmp_attr->from_sysfs(temp); + if (temp < 0) + ret = -EINVAL; + else + *(hmp_attr->value) = temp; + } + vfree(str); + return ret; +} + +static int hmp_period_tofrom_sysfs(int value) +{ + return (LOAD_AVG_PERIOD << HMP_VARIABLE_SCALE_SHIFT) / value; +} + +/* max value for threshold is 1024 */ +static int hmp_theshold_from_sysfs(int value) +{ + if (value > 1024) + return -1; + return value; +} +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE +/* freqinvar control is only 0,1 off/on */ +static int hmp_freqinvar_from_sysfs(int value) +{ + if (value < 0 || value > 1) + return -1; + return value; +} +#endif +static void hmp_attr_add( + const char *name, + int *value, + int (*to_sysfs)(int), + int (*from_sysfs)(int)) +{ + int i = 0; + while (hmp_data.attributes[i] != NULL) { + i++; + if (i >= HMP_DATA_SYSFS_MAX) + return; + } + hmp_data.attr[i].attr.mode = 0644; + hmp_data.attr[i].show = hmp_show; + hmp_data.attr[i].store = hmp_store; + hmp_data.attr[i].attr.name = name; + hmp_data.attr[i].value = value; + hmp_data.attr[i].to_sysfs = to_sysfs; + hmp_data.attr[i].from_sysfs = from_sysfs; + hmp_data.attributes[i] = &hmp_data.attr[i].attr; + hmp_data.attributes[i + 1] = NULL; +} + +static int hmp_attr_init(void) +{ + int ret; + memset(&hmp_data, sizeof(hmp_data), 0); + /* by default load_avg_period_ms == LOAD_AVG_PERIOD + * meaning no change + */ + hmp_data.multiplier = hmp_period_tofrom_sysfs(LOAD_AVG_PERIOD); + + hmp_attr_add("load_avg_period_ms", + &hmp_data.multiplier, + hmp_period_tofrom_sysfs, + hmp_period_tofrom_sysfs); + hmp_attr_add("up_threshold", + &hmp_up_threshold, + NULL, + hmp_theshold_from_sysfs); + hmp_attr_add("down_threshold", + &hmp_down_threshold, + NULL, + hmp_theshold_from_sysfs); +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE + /* default frequency-invariant scaling ON */ + hmp_data.freqinvar_load_scale_enabled = 1; + hmp_attr_add("frequency_invariant_load_scale", + &hmp_data.freqinvar_load_scale_enabled, + NULL, + hmp_freqinvar_from_sysfs); +#endif + hmp_data.attr_group.name = "hmp"; + hmp_data.attr_group.attrs = hmp_data.attributes; + ret = sysfs_create_group(kernel_kobj, + &hmp_data.attr_group); + return 0; +} +late_initcall(hmp_attr_init); +#endif /* CONFIG_HMP_VARIABLE_SCALE */ + +static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd, + int *min_cpu) +{ + int cpu; + int min_load = INT_MAX; + int min_cpu_temp = NR_CPUS; + + for_each_cpu_mask(cpu, hmpd->cpus) { + if (cpu_rq(cpu)->cfs.tg_load_contrib < min_load) { + min_load = cpu_rq(cpu)->cfs.tg_load_contrib; + min_cpu_temp = cpu; + } + } + + if (min_cpu) + *min_cpu = min_cpu_temp; + + return min_load; +} + +/* + * Calculate the task starvation + * This is the ratio of actually running time vs. runnable time. + * If the two are equal the task is getting the cpu time it needs or + * it is alone on the cpu and the cpu is fully utilized. + */ +static inline unsigned int hmp_task_starvation(struct sched_entity *se) +{ + u32 starvation; + + starvation = se->avg.usage_avg_sum * scale_load_down(NICE_0_LOAD); + starvation /= (se->avg.runnable_avg_sum + 1); + + return scale_load(starvation); +} + +static inline unsigned int hmp_offload_down(int cpu, struct sched_entity *se) +{ + int min_usage; + int dest_cpu = NR_CPUS; + + if (hmp_cpu_is_slowest(cpu)) + return NR_CPUS; + + /* Is the current domain fully loaded? */ + /* load < ~94% */ + min_usage = hmp_domain_min_load(hmp_cpu_domain(cpu), NULL); + if (min_usage < NICE_0_LOAD-64) + return NR_CPUS; + + /* Is the cpu oversubscribed? */ + /* load < ~194% */ + if (cpu_rq(cpu)->cfs.tg_load_contrib < 2*NICE_0_LOAD-64) + return NR_CPUS; + + /* Is the task alone on the cpu? */ + if (cpu_rq(cpu)->cfs.nr_running < 2) + return NR_CPUS; + + /* Is the task actually starving? */ + if (hmp_task_starvation(se) > 768) /* <25% waiting */ + return NR_CPUS; + + /* Does the slower domain have spare cycles? */ + min_usage = hmp_domain_min_load(hmp_slower_domain(cpu), &dest_cpu); + /* load > 50% */ + if (min_usage > NICE_0_LOAD/2) + return NR_CPUS; + + if (cpumask_test_cpu(dest_cpu, &hmp_slower_domain(cpu)->cpus)) + return dest_cpu; + return NR_CPUS; +} +#endif /* CONFIG_SCHED_HMP */ + /* * sched_balance_self: balance the current task (running on cpu) in domains * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and @@ -3399,6 +3968,24 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) unlock: rcu_read_unlock(); +#ifdef CONFIG_SCHED_HMP + if (hmp_up_migration(prev_cpu, &p->se)) { + new_cpu = hmp_select_faster_cpu(p, prev_cpu); + hmp_next_up_delay(&p->se, new_cpu); + trace_sched_hmp_migrate(p, new_cpu, 0); + return new_cpu; + } + if (hmp_down_migration(prev_cpu, &p->se)) { + new_cpu = hmp_select_slower_cpu(p, prev_cpu); + hmp_next_down_delay(&p->se, new_cpu); + trace_sched_hmp_migrate(p, new_cpu, 0); + return new_cpu; + } + /* Make sure that the task stays in its previous hmp domain */ + if (!cpumask_test_cpu(new_cpu, &hmp_cpu_domain(prev_cpu)->cpus)) + return prev_cpu; +#endif + return new_cpu; } @@ -3925,7 +4512,6 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 1) task is cache cold, or * 2) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { @@ -5659,6 +6245,286 @@ need_kick: static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { } #endif +#ifdef CONFIG_SCHED_HMP +/* Check if task should migrate to a faster cpu */ +static unsigned int hmp_up_migration(int cpu, struct sched_entity *se) +{ + struct task_struct *p = task_of(se); + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + u64 now; + + if (hmp_cpu_is_fastest(cpu)) + return 0; + +#ifdef CONFIG_SCHED_HMP_PRIO_FILTER + /* Filter by task priority */ + if (p->prio >= hmp_up_prio) + return 0; +#endif + + /* Let the task load settle before doing another up migration */ + now = cfs_rq_clock_task(cfs_rq); + if (((now - se->avg.hmp_last_up_migration) >> 10) + < hmp_next_up_threshold) + return 0; + + if (se->avg.load_avg_ratio > hmp_up_threshold) { + /* Target domain load < ~94% */ + if (hmp_domain_min_load(hmp_faster_domain(cpu), NULL) + > NICE_0_LOAD-64) + return 0; + if (cpumask_intersects(&hmp_faster_domain(cpu)->cpus, + tsk_cpus_allowed(p))) + return 1; + } + return 0; +} + +/* Check if task should migrate to a slower cpu */ +static unsigned int hmp_down_migration(int cpu, struct sched_entity *se) +{ + struct task_struct *p = task_of(se); + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + u64 now; + + if (hmp_cpu_is_slowest(cpu)) + return 0; + +#ifdef CONFIG_SCHED_HMP_PRIO_FILTER + /* Filter by task priority */ + if ((p->prio >= hmp_up_prio) && + cpumask_intersects(&hmp_slower_domain(cpu)->cpus, + tsk_cpus_allowed(p))) { + return 1; + } +#endif + + /* Let the task load settle before doing another down migration */ + now = cfs_rq_clock_task(cfs_rq); + if (((now - se->avg.hmp_last_down_migration) >> 10) + < hmp_next_down_threshold) + return 0; + + if (cpumask_intersects(&hmp_slower_domain(cpu)->cpus, + tsk_cpus_allowed(p)) + && se->avg.load_avg_ratio < hmp_down_threshold) { + return 1; + } + return 0; +} + +/* + * hmp_can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + * Ideally this function should be merged with can_migrate_task() to avoid + * redundant code. + */ +static int hmp_can_migrate_task(struct task_struct *p, struct lb_env *env) +{ + int tsk_cache_hot = 0; + + /* + * We do not migrate tasks that are: + * 1) running (obviously), or + * 2) cannot be migrated to this CPU due to cpus_allowed + */ + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { + schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + return 0; + } + env->flags &= ~LBF_ALL_PINNED; + + if (task_running(env->src_rq, p)) { + schedstat_inc(p, se.statistics.nr_failed_migrations_running); + return 0; + } + + /* + * Aggressive migration if: + * 1) task is cache cold, or + * 2) too many balance attempts have failed. + */ + + tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); + if (!tsk_cache_hot || + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { +#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { + schedstat_inc(env->sd, lb_hot_gained[env->idle]); + schedstat_inc(p, se.statistics.nr_forced_migrations); + } +#endif + return 1; + } + + return 1; +} + +/* + * move_specific_task tries to move a specific task. + * Returns 1 if successful and 0 otherwise. + * Called with both runqueues locked. + */ +static int move_specific_task(struct lb_env *env, struct task_struct *pm) +{ + struct task_struct *p, *n; + + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + if (throttled_lb_pair(task_group(p), env->src_rq->cpu, + env->dst_cpu)) + continue; + + if (!hmp_can_migrate_task(p, env)) + continue; + /* Check if we found the right task */ + if (p != pm) + continue; + + move_task(p, env); + /* + * Right now, this is only the third place move_task() + * is called, so we can safely collect move_task() + * stats here rather than inside move_task(). + */ + schedstat_inc(env->sd, lb_gained[env->idle]); + return 1; + } + return 0; +} + +/* + * hmp_active_task_migration_cpu_stop is run by cpu stopper and used to + * migrate a specific task from one runqueue to another. + * hmp_force_up_migration uses this to push a currently running task + * off a runqueue. + * Based on active_load_balance_stop_cpu and can potentially be merged. + */ +static int hmp_active_task_migration_cpu_stop(void *data) +{ + struct rq *busiest_rq = data; + struct task_struct *p = busiest_rq->migrate_task; + int busiest_cpu = cpu_of(busiest_rq); + int target_cpu = busiest_rq->push_cpu; + struct rq *target_rq = cpu_rq(target_cpu); + struct sched_domain *sd; + + raw_spin_lock_irq(&busiest_rq->lock); + /* make sure the requested cpu hasn't gone down in the meantime */ + if (unlikely(busiest_cpu != smp_processor_id() || + !busiest_rq->active_balance)) { + goto out_unlock; + } + /* Is there any task to move? */ + if (busiest_rq->nr_running <= 1) + goto out_unlock; + /* Task has migrated meanwhile, abort forced migration */ + if (task_rq(p) != busiest_rq) + goto out_unlock; + /* + * This condition is "impossible", if it occurs + * we need to fix it. Originally reported by + * Bjorn Helgaas on a 128-cpu setup. + */ + BUG_ON(busiest_rq == target_rq); + + /* move a task from busiest_rq to target_rq */ + double_lock_balance(busiest_rq, target_rq); + + /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); + for_each_domain(target_cpu, sd) { + if (cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) + break; + } + + if (likely(sd)) { + struct lb_env env = { + .sd = sd, + .dst_cpu = target_cpu, + .dst_rq = target_rq, + .src_cpu = busiest_rq->cpu, + .src_rq = busiest_rq, + .idle = CPU_IDLE, + }; + + schedstat_inc(sd, alb_count); + + if (move_specific_task(&env, p)) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } + rcu_read_unlock(); + double_unlock_balance(busiest_rq, target_rq); +out_unlock: + busiest_rq->active_balance = 0; + raw_spin_unlock_irq(&busiest_rq->lock); + return 0; +} + +static DEFINE_SPINLOCK(hmp_force_migration); + +/* + * hmp_force_up_migration checks runqueues for tasks that need to + * be actively migrated to a faster cpu. + */ +static void hmp_force_up_migration(int this_cpu) +{ + int cpu; + struct sched_entity *curr; + struct rq *target; + unsigned long flags; + unsigned int force; + struct task_struct *p; + + if (!spin_trylock(&hmp_force_migration)) + return; + for_each_online_cpu(cpu) { + force = 0; + target = cpu_rq(cpu); + raw_spin_lock_irqsave(&target->lock, flags); + curr = target->cfs.curr; + if (!curr || !entity_is_task(curr)) { + raw_spin_unlock_irqrestore(&target->lock, flags); + continue; + } + p = task_of(curr); + if (hmp_up_migration(cpu, curr)) { + if (!target->active_balance) { + target->active_balance = 1; + target->push_cpu = hmp_select_faster_cpu(p, cpu); + target->migrate_task = p; + force = 1; + trace_sched_hmp_migrate(p, target->push_cpu, 1); + hmp_next_up_delay(&p->se, target->push_cpu); + } + } + if (!force && !target->active_balance) { + /* + * For now we just check the currently running task. + * Selecting the lightest task for offloading will + * require extensive book keeping. + */ + target->push_cpu = hmp_offload_down(cpu, curr); + if (target->push_cpu < NR_CPUS) { + target->active_balance = 1; + target->migrate_task = p; + force = 1; + trace_sched_hmp_migrate(p, target->push_cpu, 2); + hmp_next_down_delay(&p->se, target->push_cpu); + } + } + raw_spin_unlock_irqrestore(&target->lock, flags); + if (force) + stop_one_cpu_nowait(cpu_of(target), + hmp_active_task_migration_cpu_stop, + target, &target->active_balance_work); + } + spin_unlock(&hmp_force_migration); +} +#else +static void hmp_force_up_migration(int this_cpu) { } +#endif /* CONFIG_SCHED_HMP */ + /* * run_rebalance_domains is triggered when needed from the scheduler tick. * Also triggered for nohz idle balancing (with nohz_balancing_kick set). @@ -5670,6 +6536,8 @@ static void run_rebalance_domains(struct softirq_action *h) enum cpu_idle_type idle = this_rq->idle_balance ? CPU_IDLE : CPU_NOT_IDLE; + hmp_force_up_migration(this_cpu); + rebalance_domains(this_cpu, idle); /* @@ -6169,6 +7037,139 @@ __init void init_sched_fair_class(void) zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); #endif + +#ifdef CONFIG_SCHED_HMP + hmp_cpu_mask_setup(); +#endif #endif /* SMP */ } + +#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE +static u32 cpufreq_calc_scale(u32 min, u32 max, u32 curr) +{ + u32 result = curr / max; + return result; +} + +/* Called when the CPU Frequency is changed. + * Once for each CPU. + */ +static int cpufreq_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct cpufreq_freqs *freq = data; + int cpu = freq->cpu; + struct cpufreq_extents *extents; + + if (freq->flags & CPUFREQ_CONST_LOOPS) + return NOTIFY_OK; + + if (val != CPUFREQ_POSTCHANGE) + return NOTIFY_OK; + + /* if dynamic load scale is disabled, set the load scale to 1.0 */ + if (!hmp_data.freqinvar_load_scale_enabled) { + freq_scale[cpu].curr_scale = 1024; + return NOTIFY_OK; + } + + extents = &freq_scale[cpu]; + if (extents->flags & SCHED_LOAD_FREQINVAR_SINGLEFREQ) { + /* If our governor was recognised as a single-freq governor, + * use 1.0 + */ + extents->curr_scale = 1024; + } else { + extents->curr_scale = cpufreq_calc_scale(extents->min, + extents->max, freq->new); + } + + return NOTIFY_OK; +} + +/* Called when the CPUFreq governor is changed. + * Only called for the CPUs which are actually changed by the + * userspace. + */ +static int cpufreq_policy_callback(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct cpufreq_policy *policy = data; + struct cpufreq_extents *extents; + int cpu, singleFreq = 0; + static const char performance_governor[] = "performance"; + static const char powersave_governor[] = "powersave"; + + if (event == CPUFREQ_START) + return 0; + + if (event != CPUFREQ_INCOMPATIBLE) + return 0; + + /* CPUFreq governors do not accurately report the range of + * CPU Frequencies they will choose from. + * We recognise performance and powersave governors as + * single-frequency only. + */ + if (!strncmp(policy->governor->name, performance_governor, + strlen(performance_governor)) || + !strncmp(policy->governor->name, powersave_governor, + strlen(powersave_governor))) + singleFreq = 1; + + /* Make sure that all CPUs impacted by this policy are + * updated since we will only get a notification when the + * user explicitly changes the policy on a CPU. + */ + for_each_cpu(cpu, policy->cpus) { + extents = &freq_scale[cpu]; + extents->max = policy->max >> SCHED_FREQSCALE_SHIFT; + extents->min = policy->min >> SCHED_FREQSCALE_SHIFT; + if (!hmp_data.freqinvar_load_scale_enabled) { + extents->curr_scale = 1024; + } else if (singleFreq) { + extents->flags |= SCHED_LOAD_FREQINVAR_SINGLEFREQ; + extents->curr_scale = 1024; + } else { + extents->flags &= ~SCHED_LOAD_FREQINVAR_SINGLEFREQ; + extents->curr_scale = cpufreq_calc_scale(extents->min, + extents->max, policy->cur); + } + } + + return 0; +} + +static struct notifier_block cpufreq_notifier = { + .notifier_call = cpufreq_callback, +}; +static struct notifier_block cpufreq_policy_notifier = { + .notifier_call = cpufreq_policy_callback, +}; + +static int __init register_sched_cpufreq_notifier(void) +{ + int ret = 0; + + /* init safe defaults since there are no policies at registration */ + for (ret = 0; ret < CONFIG_NR_CPUS; ret++) { + /* safe defaults */ + freq_scale[ret].max = 1024; + freq_scale[ret].min = 1024; + freq_scale[ret].curr_scale = 1024; + } + + pr_info("sched: registering cpufreq notifiers for scale-invariant loads\n"); + ret = cpufreq_register_notifier(&cpufreq_policy_notifier, + CPUFREQ_POLICY_NOTIFIER); + + if (ret != -EINVAL) + ret = cpufreq_register_notifier(&cpufreq_notifier, + CPUFREQ_TRANSITION_NOTIFIER); + + return ret; +} + +core_initcall(register_sched_cpufreq_notifier); +#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index fc886441436..6a95904661e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -113,7 +113,7 @@ struct task_group { atomic_t load_weight; atomic64_t load_avg; - atomic_t runnable_avg; + atomic_t runnable_avg, usage_avg; #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -243,7 +243,7 @@ struct cfs_rq { #endif /* CONFIG_FAIR_GROUP_SCHED */ /* These always depend on CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED - u32 tg_runnable_contrib; + u32 tg_runnable_contrib, tg_usage_contrib; u64 tg_load_contrib; #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -425,6 +425,9 @@ struct rq { int active_balance; int push_cpu; struct cpu_stop_work active_balance_work; +#ifdef CONFIG_SCHED_HMP + struct task_struct *migrate_task; +#endif /* cpu of this runqueue: */ int cpu; int online; @@ -547,6 +550,12 @@ DECLARE_PER_CPU(int, sd_llc_id); extern int group_balance_cpu(struct sched_group *sg); +#ifdef CONFIG_SCHED_HMP +static LIST_HEAD(hmp_domains); +DECLARE_PER_CPU(struct hmp_domain *, hmp_cpu_domain); +#define hmp_cpu_domain(cpu) (per_cpu(hmp_cpu_domain, (cpu))) +#endif /* CONFIG_SCHED_HMP */ + #endif /* CONFIG_SMP */ #include "stats.h" diff --git a/linaro/configs/big-LITTLE-MP.conf b/linaro/configs/big-LITTLE-MP.conf new file mode 100644 index 00000000000..8cc2be049a4 --- /dev/null +++ b/linaro/configs/big-LITTLE-MP.conf @@ -0,0 +1,13 @@ +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +CONFIG_NO_HZ=y +CONFIG_SCHED_MC=y +CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE=y +CONFIG_SCHED_HMP=y +CONFIG_HMP_FAST_CPU_MASK="" +CONFIG_HMP_SLOW_CPU_MASK="" +CONFIG_HMP_VARIABLE_SCALE=y +CONFIG_HMP_FREQUENCY_INVARIANT_SCALE=y +CONFIG_SCHED_HMP_PRIO_FILTER=y +CONFIG_SCHED_HMP_PRIO_FILTER_VAL=5 |