diff options
Diffstat (limited to 'arch')
| -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 | 93 |
5 files changed, 263 insertions, 5 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index f95ba14ae3d..e165235fc2d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1562,6 +1562,91 @@ 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..17a01a00d35 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -287,6 +287,99 @@ 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 = 0; + + 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"))) { + + if (cpu >= num_possible_cpus()) + break; + + if (is_little_cpu(cn)) + cpumask_set_cpu(cpu, slow); + else + cpumask_set_cpu(cpu, fast); + + cpu++; + } + + 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 |