diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 26 | ||||
| -rw-r--r-- | kernel/sched/auto_group.c | 253 | ||||
| -rw-r--r-- | kernel/sched/auto_group.h | 64 | ||||
| -rw-r--r-- | kernel/sched/bfs.c | 7429 | ||||
| -rw-r--r-- | kernel/sched/bfs_sched.h | 172 | ||||
| -rw-r--r-- | kernel/sched/clock.c | 435 | ||||
| -rw-r--r-- | kernel/sched/completion.c | 317 | ||||
| -rw-r--r-- | kernel/sched/core.c | 8381 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.c | 283 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.h | 17 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.c | 246 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.h | 32 | ||||
| -rw-r--r-- | kernel/sched/cpupri.c | 248 | ||||
| -rw-r--r-- | kernel/sched/cpupri.h | 31 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 852 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 1818 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 674 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 8310 | ||||
| -rw-r--r-- | kernel/sched/features.h | 98 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 302 | ||||
| -rw-r--r-- | kernel/sched/idle_task.c | 109 | ||||
| -rw-r--r-- | kernel/sched/proc.c | 584 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 2346 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 1736 | ||||
| -rw-r--r-- | kernel/sched/stats.c | 142 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 267 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 136 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 624 |
28 files changed, 35932 insertions, 0 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile new file mode 100644 index 000000000..54b88a1c0 --- /dev/null +++ b/kernel/sched/Makefile @@ -0,0 +1,26 @@ +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) +endif + +ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) +# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is +# needed for x86 only. Why this used to be enabled for all architectures is beyond +# me. I suspect most platforms don't need this, but until we know that for sure +# I turn this off for IA-64 only. Andreas Schwab says it's also needed on m68k +# to get a correct value for the wait-channel (WCHAN in ps). --davidm +CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer +endif + +ifdef CONFIG_SCHED_BFS +obj-y += bfs.o clock.o +else +obj-y += core.o proc.o clock.o cputime.o +obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +obj-$(CONFIG_SMP) += cpudeadline.o +obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o +obj-$(CONFIG_SCHED_DEBUG) += debug.o +obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o +endif +obj-y += wait.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o +obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c new file mode 100644 index 000000000..eae160dd6 --- /dev/null +++ b/kernel/sched/auto_group.c @@ -0,0 +1,253 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include "sched.h" + +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/kallsyms.h> +#include <linux/utsname.h> +#include <linux/security.h> +#include <linux/export.h> + +unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; +static struct autogroup autogroup_default; +static atomic_t autogroup_seq_nr; + +void __init autogroup_init(struct task_struct *init_task) +{ + autogroup_default.tg = &root_task_group; + kref_init(&autogroup_default.kref); + init_rwsem(&autogroup_default.lock); + init_task->signal->autogroup = &autogroup_default; +} + +void autogroup_free(struct task_group *tg) +{ + kfree(tg->autogroup); +} + +static inline void autogroup_destroy(struct kref *kref) +{ + struct autogroup *ag = container_of(kref, struct autogroup, kref); + +#ifdef CONFIG_RT_GROUP_SCHED + /* We've redirected RT tasks to the root task group... */ + ag->tg->rt_se = NULL; + ag->tg->rt_rq = NULL; +#endif + sched_offline_group(ag->tg); + sched_destroy_group(ag->tg); +} + +static inline void autogroup_kref_put(struct autogroup *ag) +{ + kref_put(&ag->kref, autogroup_destroy); +} + +static inline struct autogroup *autogroup_kref_get(struct autogroup *ag) +{ + kref_get(&ag->kref); + return ag; +} + +static inline struct autogroup *autogroup_task_get(struct task_struct *p) +{ + struct autogroup *ag; + unsigned long flags; + + if (!lock_task_sighand(p, &flags)) + return autogroup_kref_get(&autogroup_default); + + ag = autogroup_kref_get(p->signal->autogroup); + unlock_task_sighand(p, &flags); + + return ag; +} + +static inline struct autogroup *autogroup_create(void) +{ + struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL); + struct task_group *tg; + + if (!ag) + goto out_fail; + + tg = sched_create_group(&root_task_group); + + if (IS_ERR(tg)) + goto out_free; + + kref_init(&ag->kref); + init_rwsem(&ag->lock); + ag->id = atomic_inc_return(&autogroup_seq_nr); + ag->tg = tg; +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Autogroup RT tasks are redirected to the root task group + * so we don't have to move tasks around upon policy change, + * or flail around trying to allocate bandwidth on the fly. + * A bandwidth exception in __sched_setscheduler() allows + * the policy change to proceed. + */ + free_rt_sched_group(tg); + tg->rt_se = root_task_group.rt_se; + tg->rt_rq = root_task_group.rt_rq; +#endif + tg->autogroup = ag; + + sched_online_group(tg, &root_task_group); + return ag; + +out_free: + kfree(ag); +out_fail: + if (printk_ratelimit()) { + printk(KERN_WARNING "autogroup_create: %s failure.\n", + ag ? "sched_create_group()" : "kmalloc()"); + } + + return autogroup_kref_get(&autogroup_default); +} + +bool task_wants_autogroup(struct task_struct *p, struct task_group *tg) +{ + if (tg != &root_task_group) + return false; + + /* + * We can only assume the task group can't go away on us if + * autogroup_move_group() can see us on ->thread_group list. + */ + if (p->flags & PF_EXITING) + return false; + + return true; +} + +static void +autogroup_move_group(struct task_struct *p, struct autogroup *ag) +{ + struct autogroup *prev; + struct task_struct *t; + unsigned long flags; + + BUG_ON(!lock_task_sighand(p, &flags)); + + prev = p->signal->autogroup; + if (prev == ag) { + unlock_task_sighand(p, &flags); + return; + } + + p->signal->autogroup = autogroup_kref_get(ag); + + if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled)) + goto out; + + for_each_thread(p, t) + sched_move_task(t); +out: + unlock_task_sighand(p, &flags); + autogroup_kref_put(prev); +} + +/* Allocates GFP_KERNEL, cannot be called under any spinlock */ +void sched_autogroup_create_attach(struct task_struct *p) +{ + struct autogroup *ag = autogroup_create(); + + autogroup_move_group(p, ag); + /* drop extra reference added by autogroup_create() */ + autogroup_kref_put(ag); +} +EXPORT_SYMBOL(sched_autogroup_create_attach); + +/* Cannot be called under siglock. Currently has no users */ +void sched_autogroup_detach(struct task_struct *p) +{ + autogroup_move_group(p, &autogroup_default); +} +EXPORT_SYMBOL(sched_autogroup_detach); + +void sched_autogroup_fork(struct signal_struct *sig) +{ + sig->autogroup = autogroup_task_get(current); +} + +void sched_autogroup_exit(struct signal_struct *sig) +{ + autogroup_kref_put(sig->autogroup); +} + +static int __init setup_autogroup(char *str) +{ + sysctl_sched_autogroup_enabled = 0; + + return 1; +} + +__setup("noautogroup", setup_autogroup); + +#ifdef CONFIG_PROC_FS + +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) +{ + static unsigned long next = INITIAL_JIFFIES; + struct autogroup *ag; + int err; + + if (nice < MIN_NICE || nice > MAX_NICE) + return -EINVAL; + + err = security_task_setnice(current, nice); + if (err) + return err; + + if (nice < 0 && !can_nice(current, nice)) + return -EPERM; + + /* this is a heavy operation taking global locks.. */ + if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next)) + return -EAGAIN; + + next = HZ / 10 + jiffies; + ag = autogroup_task_get(p); + + down_write(&ag->lock); + err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); + if (!err) + ag->nice = nice; + up_write(&ag->lock); + + autogroup_kref_put(ag); + + return err; +} + +void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) +{ + struct autogroup *ag = autogroup_task_get(p); + + if (!task_group_is_autogroup(ag->tg)) + goto out; + + down_read(&ag->lock); + seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); + up_read(&ag->lock); + +out: + autogroup_kref_put(ag); +} +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SCHED_DEBUG +int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + if (!task_group_is_autogroup(tg)) + return 0; + + return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); +} +#endif /* CONFIG_SCHED_DEBUG */ + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h new file mode 100644 index 000000000..8bd047142 --- /dev/null +++ b/kernel/sched/auto_group.h @@ -0,0 +1,64 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include <linux/kref.h> +#include <linux/rwsem.h> + +struct autogroup { + /* + * reference doesn't mean how many thread attach to this + * autogroup now. It just stands for the number of task + * could use this autogroup. + */ + struct kref kref; + struct task_group *tg; + struct rw_semaphore lock; + unsigned long id; + int nice; +}; + +extern void autogroup_init(struct task_struct *init_task); +extern void autogroup_free(struct task_group *tg); + +static inline bool task_group_is_autogroup(struct task_group *tg) +{ + return !!tg->autogroup; +} + +extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg); + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); + + if (enabled && task_wants_autogroup(p, tg)) + return p->signal->autogroup->tg; + + return tg; +} + +extern int autogroup_path(struct task_group *tg, char *buf, int buflen); + +#else /* !CONFIG_SCHED_AUTOGROUP */ + +static inline void autogroup_init(struct task_struct *init_task) { } +static inline void autogroup_free(struct task_group *tg) { } +static inline bool task_group_is_autogroup(struct task_group *tg) +{ + return 0; +} + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + return tg; +} + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return 0; +} +#endif + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched/bfs.c b/kernel/sched/bfs.c new file mode 100644 index 000000000..a6d06efc1 --- /dev/null +++ b/kernel/sched/bfs.c @@ -0,0 +1,7429 @@ +/* + * kernel/sched/bfs.c, was kernel/sched.c + * + * Kernel scheduler and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and + * make semaphores SMP safe + * 1998-11-19 Implemented schedule_timeout() and related stuff + * by Andrea Arcangeli + * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: + * hybrid priority-list and round-robin design with + * an array-switch method of distributing timeslices + * and per-CPU runqueues. Cleanups and useful suggestions + * by Davide Libenzi, preemptible kernel bits by Robert Love. + * 2003-09-03 Interactivity tuning by Con Kolivas. + * 2004-04-02 Scheduler domains code by Nick Piggin + * 2007-04-15 Work begun on replacing all interactivity tuning with a + * fair scheduling design by Con Kolivas. + * 2007-05-05 Load balancing (smp-nice) and other improvements + * by Peter Williams + * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith + * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri + * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, + * Thomas Gleixner, Mike Kravetz + * now Brainfuck deadline scheduling policy by Con Kolivas deletes + * a whole lot of those previous things. + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/nmi.h> +#include <linux/init.h> +#include <asm/uaccess.h> +#include <linux/highmem.h> +#include <asm/mmu_context.h> +#include <linux/interrupt.h> +#include <linux/capability.h> +#include <linux/completion.h> +#include <linux/kernel_stat.h> +#include <linux/debug_locks.h> +#include <linux/perf_event.h> +#include <linux/security.h> +#include <linux/notifier.h> +#include <linux/profile.h> +#include <linux/freezer.h> +#include <linux/vmalloc.h> +#include <linux/blkdev.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/threads.h> +#include <linux/timer.h> +#include <linux/rcupdate.h> +#include <linux/cpu.h> +#include <linux/cpuset.h> +#include <linux/cpumask.h> +#include <linux/percpu.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/syscalls.h> +#include <linux/sched/sysctl.h> +#include <linux/times.h> +#include <linux/tsacct_kern.h> +#include <linux/kprobes.h> +#include <linux/delayacct.h> +#include <linux/log2.h> +#include <linux/bootmem.h> +#include <linux/ftrace.h> +#include <linux/slab.h> +#include <linux/init_task.h> +#include <linux/binfmts.h> +#include <linux/context_tracking.h> +#include <linux/sched/prio.h> + +#include <asm/irq_regs.h> +#include <asm/switch_to.h> +#include <asm/tlb.h> +#include <asm/unistd.h> +#include <asm/mutex.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#endif + +#include "cpupri.h" +#include "../workqueue_internal.h" +#include "../smpboot.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/sched.h> + +#include "bfs_sched.h" + +#define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO) +#define rt_task(p) rt_prio((p)->prio) +#define rt_queue(rq) rt_prio((rq)->rq_prio) +#define batch_task(p) (unlikely((p)->policy == SCHED_BATCH)) +#define is_rt_policy(policy) ((policy) == SCHED_FIFO || \ + (policy) == SCHED_RR) +#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy)) + +#define is_idle_policy(policy) ((policy) == SCHED_IDLEPRIO) +#define idleprio_task(p) unlikely(is_idle_policy((p)->policy)) +#define task_running_idle(p) unlikely((p)->prio == IDLE_PRIO) +#define idle_queue(rq) (unlikely(is_idle_policy((rq)->rq_policy))) + +#define is_iso_policy(policy) ((policy) == SCHED_ISO) +#define iso_task(p) unlikely(is_iso_policy((p)->policy)) +#define iso_queue(rq) unlikely(is_iso_policy((rq)->rq_policy)) +#define task_running_iso(p) unlikely((p)->prio == ISO_PRIO) +#define rq_running_iso(rq) ((rq)->rq_prio == ISO_PRIO) + +#define rq_idle(rq) ((rq)->rq_prio == PRIO_LIMIT) + +#define ISO_PERIOD ((5 * HZ * grq.noc) + 1) + +#define SCHED_PRIO(p) ((p) + MAX_RT_PRIO) +#define STOP_PRIO (MAX_RT_PRIO - 1) + +/* + * Some helpers for converting to/from various scales. Use shifts to get + * approximate multiples of ten for less overhead. + */ +#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) +#define JIFFY_NS (1000000000 / HZ) +#define HALF_JIFFY_NS (1000000000 / HZ / 2) +#define HALF_JIFFY_US (1000000 / HZ / 2) +#define MS_TO_NS(TIME) ((TIME) << 20) +#define MS_TO_US(TIME) ((TIME) << 10) +#define NS_TO_MS(TIME) ((TIME) >> 20) +#define NS_TO_US(TIME) ((TIME) >> 10) + +#define RESCHED_US (100) /* Reschedule if less than this many μs left */ + +void print_scheduler_version(void) +{ + printk(KERN_INFO "BFS CPU scheduler v0.463 by Con Kolivas.\n"); +} + +/* + * This is the time all tasks within the same priority round robin. + * Value is in ms and set to a minimum of 6ms. Scales with number of cpus. + * Tunable via /proc interface. + */ +#ifdef CONFIG_PCK_INTERACTIVE +int rr_interval __read_mostly = 3; +#else +int rr_interval __read_mostly = 6; +#endif + +/* + * sched_iso_cpu - sysctl which determines the cpu percentage SCHED_ISO tasks + * are allowed to run five seconds as real time tasks. This is the total over + * all online cpus. + */ +#ifdef CONFIG_PCK_INTERACTIVE +int sched_iso_cpu __read_mostly = 25; +#else +int sched_iso_cpu __read_mostly = 70; +#endif + +/* + * The relative length of deadline for each priority(nice) level. + */ +static int prio_ratios[NICE_WIDTH] __read_mostly; + +/* + * The quota handed out to tasks of all priority levels when refilling their + * time_slice. + */ +static inline int timeslice(void) +{ + return MS_TO_US(rr_interval); +} + +/* + * The global runqueue data that all CPUs work off. Data is protected either + * by the global grq lock, or the discrete lock that precedes the data in this + * struct. + */ +struct global_rq { + raw_spinlock_t lock; + unsigned long nr_running; + unsigned long nr_uninterruptible; + unsigned long long nr_switches; + struct list_head queue[PRIO_LIMIT]; + DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1); + unsigned long qnr; /* queued not running */ +#ifdef CONFIG_SMP + cpumask_t cpu_idle_map; + bool idle_cpus; +#endif + int noc; /* num_online_cpus stored and updated when it changes */ + u64 niffies; /* Nanosecond jiffies */ + unsigned long last_jiffy; /* Last jiffy we updated niffies */ + + raw_spinlock_t iso_lock; + int iso_ticks; + bool iso_refractory; +}; + +#ifdef CONFIG_SMP +/* + * We add the notion of a root-domain which will be used to define per-domain + * variables. Each exclusive cpuset essentially defines an island domain by + * fully partitioning the member cpus from any other cpuset. Whenever a new + * exclusive cpuset is created, we also create and attach a new root-domain + * object. + * + */ +struct root_domain { + atomic_t refcount; + atomic_t rto_count; + struct rcu_head rcu; + cpumask_var_t span; + cpumask_var_t online; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_var_t rto_mask; + struct cpupri cpupri; +}; + +/* + * By default the system creates a single root-domain with all cpus as + * members (mimicking the global state we have today). + */ +static struct root_domain def_root_domain; + +#endif /* CONFIG_SMP */ + +/* There can be only one */ +static struct global_rq grq; + +static DEFINE_MUTEX(sched_hotcpu_mutex); + +DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#ifdef CONFIG_SMP +struct rq *cpu_rq(int cpu) +{ + return &per_cpu(runqueues, (cpu)); +} +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) +/* + * sched_domains_mutex serialises calls to init_sched_domains, + * detach_destroy_domains and partition_sched_domains. + */ +static DEFINE_MUTEX(sched_domains_mutex); + +/* + * By default the system creates a single root-domain with all cpus as + * members (mimicking the global state we have today). + */ +static struct root_domain def_root_domain; + +int __weak arch_sd_sibling_asym_packing(void) +{ + return 0*SD_ASYM_PACKING; +} +#else +struct rq *uprq; +#endif /* CONFIG_SMP */ + +static inline void update_rq_clock(struct rq *rq); + +/* + * Sanity check should sched_clock return bogus values. We make sure it does + * not appear to go backwards, and use jiffies to determine the maximum and + * minimum it could possibly have increased, and round down to the nearest + * jiffy when it falls outside this. + */ +static inline void niffy_diff(s64 *niff_diff, int jiff_diff) +{ + unsigned long min_diff, max_diff; + + if (jiff_diff > 1) + min_diff = JIFFIES_TO_NS(jiff_diff - 1); + else + min_diff = 1; + /* Round up to the nearest tick for maximum */ + max_diff = JIFFIES_TO_NS(jiff_diff + 1); + + if (unlikely(*niff_diff < min_diff || *niff_diff > max_diff)) + *niff_diff = min_diff; +} + +#ifdef CONFIG_SMP +static inline int cpu_of(struct rq *rq) +{ + return rq->cpu; +} + +/* + * Niffies are a globally increasing nanosecond counter. Whenever a runqueue + * clock is updated with the grq.lock held, it is an opportunity to update the + * niffies value. Any CPU can update it by adding how much its clock has + * increased since it last updated niffies, minus any added niffies by other + * CPUs. + */ +static inline void update_clocks(struct rq *rq) +{ + s64 ndiff; + long jdiff; + + update_rq_clock(rq); + ndiff = rq->clock - rq->old_clock; + /* old_clock is only updated when we are updating niffies */ + rq->old_clock = rq->clock; + ndiff -= grq.niffies - rq->last_niffy; + jdiff = jiffies - grq.last_jiffy; + niffy_diff(&ndiff, jdiff); + grq.last_jiffy += jdiff; + grq.niffies += ndiff; + rq->last_niffy = grq.niffies; +} +#else /* CONFIG_SMP */ +static inline int cpu_of(struct rq *rq) +{ + return 0; +} + +static inline void update_clocks(struct rq *rq) +{ + s64 ndiff; + long jdiff; + + update_rq_clock(rq); + ndiff = rq->clock - rq->old_clock; + rq->old_clock = rq->clock; + jdiff = jiffies - grq.last_jiffy; + niffy_diff(&ndiff, jdiff); + grq.last_jiffy += jdiff; + grq.niffies += ndiff; +} +#endif + +#include "stats.h" + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_switch +# define finish_arch_switch(prev) do { } while (0) +#endif +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif + +/* + * All common locking functions performed on grq.lock. rq->clock is local to + * the CPU accessing it so it can be modified just with interrupts disabled + * when we're not updating niffies. + * Looking up task_rq must be done under grq.lock to be safe. + */ +static void update_rq_clock_task(struct rq *rq, s64 delta); + +static inline void update_rq_clock(struct rq *rq) +{ + s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + + if (unlikely(delta < 0)) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + +static inline bool task_running(struct task_struct *p) +{ + return p->on_cpu; +} + +static inline void grq_lock(void) + __acquires(grq.lock) +{ + raw_spin_lock(&grq.lock); +} + +static inline void grq_unlock(void) + __releases(grq.lock) +{ + raw_spin_unlock(&grq.lock); +} + +static inline void grq_lock_irq(void) + __acquires(grq.lock) +{ + raw_spin_lock_irq(&grq.lock); +} + +static inline void time_lock_grq(struct rq *rq) + __acquires(grq.lock) +{ + grq_lock(); + update_clocks(rq); +} + +static inline void grq_unlock_irq(void) + __releases(grq.lock) +{ + raw_spin_unlock_irq(&grq.lock); +} + +static inline void grq_lock_irqsave(unsigned long *flags) + __acquires(grq.lock) +{ + raw_spin_lock_irqsave(&grq.lock, *flags); +} + +static inline void grq_unlock_irqrestore(unsigned long *flags) + __releases(grq.lock) +{ + raw_spin_unlock_irqrestore(&grq.lock, *flags); +} + +static inline struct rq +*task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + grq_lock_irqsave(flags); + return task_rq(p); +} + +static inline struct rq +*time_task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + struct rq *rq = task_grq_lock(p, flags); + update_clocks(rq); + return rq; +} + +static inline struct rq *task_grq_lock_irq(struct task_struct *p) + __acquires(grq.lock) +{ + grq_lock_irq(); + return task_rq(p); +} + +static inline void time_task_grq_lock_irq(struct task_struct *p) + __acquires(grq.lock) +{ + struct rq *rq = task_grq_lock_irq(p); + update_clocks(rq); +} + +static inline void task_grq_unlock_irq(void) + __releases(grq.lock) +{ + grq_unlock_irq(); +} + +static inline void task_grq_unlock(unsigned long *flags) + __releases(grq.lock) +{ + grq_unlock_irqrestore(flags); +} + +/** + * grunqueue_is_locked + * + * Returns true if the global runqueue is locked. + * This interface allows printk to be called with the runqueue lock + * held and know whether or not it is OK to wake up the klogd. + */ +bool grunqueue_is_locked(void) +{ + return raw_spin_is_locked(&grq.lock); +} + +void grq_unlock_wait(void) + __releases(grq.lock) +{ + smp_mb(); /* spin-unlock-wait is not a full memory barrier */ + raw_spin_unlock_wait(&grq.lock); +} + +static inline void time_grq_lock(struct rq *rq, unsigned long *flags) + __acquires(grq.lock) +{ + local_irq_save(*flags); + time_lock_grq(rq); +} + +static inline struct rq *__task_grq_lock(struct task_struct *p) + __acquires(grq.lock) +{ + grq_lock(); + return task_rq(p); +} + +static inline void __task_grq_unlock(void) + __releases(grq.lock) +{ + grq_unlock(); +} + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + grq.lock.owner = current; +#endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_); + + grq_unlock_irq(); +} + +static inline bool deadline_before(u64 deadline, u64 time) +{ + return (deadline < time); +} + +static inline bool deadline_after(u64 deadline, u64 time) +{ + return (deadline > time); +} + +/* + * A task that is queued but not running will be on the grq run list. + * A task that is not running or queued will not be on the grq run list. + * A task that is currently running will have ->on_cpu set but not on the + * grq run list. + */ +static inline bool task_queued(struct task_struct *p) +{ + return (!list_empty(&p->run_list)); +} + +/* + * Removing from the global runqueue. Enter with grq locked. + */ +static void dequeue_task(struct task_struct *p) +{ + list_del_init(&p->run_list); + if (list_empty(grq.queue + p->prio)) + __clear_bit(p->prio, grq.prio_bitmap); + sched_info_dequeued(task_rq(p), p); +} + +/* + * To determine if it's safe for a task of SCHED_IDLEPRIO to actually run as + * an idle task, we ensure none of the following conditions are met. + */ +static bool idleprio_suitable(struct task_struct *p) +{ + return (!freezing(p) && !signal_pending(p) && + !(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING))); +} + +/* + * To determine if a task of SCHED_ISO can run in pseudo-realtime, we check + * that the iso_refractory flag is not set. + */ +static bool isoprio_suitable(void) +{ + return !grq.iso_refractory; +} + +/* + * Adding to the global runqueue. Enter with grq locked. + */ +static void enqueue_task(struct task_struct *p, struct rq *rq) +{ + if (!rt_task(p)) { + /* Check it hasn't gotten rt from PI */ + if ((idleprio_task(p) && idleprio_suitable(p)) || + (iso_task(p) && isoprio_suitable())) + p->prio = p->normal_prio; + else + p->prio = NORMAL_PRIO; + } + __set_bit(p->prio, grq.prio_bitmap); + list_add_tail(&p->run_list, grq.queue + p->prio); + sched_info_queued(rq, p); +} + +static inline void requeue_task(struct task_struct *p) +{ + sched_info_queued(task_rq(p), p); +} + +/* + * Returns the relative length of deadline all compared to the shortest + * deadline which is that of nice -20. + */ +static inline int task_prio_ratio(struct task_struct *p) +{ + return prio_ratios[TASK_USER_PRIO(p)]; +} + +/* + * task_timeslice - all tasks of all priorities get the exact same timeslice + * length. CPU distribution is handled by giving different deadlines to + * tasks of different priorities. Use 128 as the base value for fast shifts. + */ +static inline int task_timeslice(struct task_struct *p) +{ + return (rr_interval * task_prio_ratio(p) / 128); +} + +static void resched_task(struct task_struct *p); + +static inline void resched_curr(struct rq *rq) +{ + resched_task(rq->curr); +} + +/* + * qnr is the "queued but not running" count which is the total number of + * tasks on the global runqueue list waiting for cpu time but not actually + * currently running on a cpu. + */ +static inline void inc_qnr(void) +{ + grq.qnr++; +} + +static inline void dec_qnr(void) +{ + grq.qnr--; +} + +static inline int queued_notrunning(void) +{ + return grq.qnr; +} + +#ifdef CONFIG_SMP +/* + * The cpu_idle_map stores a bitmap of all the CPUs currently idle to + * allow easy lookup of whether any suitable idle CPUs are available. + * It's cheaper to maintain a binary yes/no if there are any idle CPUs on the + * idle_cpus variable than to do a full bitmask check when we are busy. + */ +static inline void set_cpuidle_map(int cpu) +{ + if (likely(cpu_online(cpu))) { + cpumask_set_cpu(cpu, &grq.cpu_idle_map); + grq.idle_cpus = true; + } +} + +static inline void clear_cpuidle_map(int cpu) +{ + cpumask_clear_cpu(cpu, &grq.cpu_idle_map); + if (cpumask_empty(&grq.cpu_idle_map)) + grq.idle_cpus = false; +} + +static bool suitable_idle_cpus(struct task_struct *p) +{ + if (!grq.idle_cpus) + return false; + return (cpumask_intersects(&p->cpus_allowed, &grq.cpu_idle_map)); +} + +#define CPUIDLE_DIFF_THREAD (1) +#define CPUIDLE_DIFF_CORE (2) +#define CPUIDLE_CACHE_BUSY (4) +#define CPUIDLE_DIFF_CPU (8) +#define CPUIDLE_THREAD_BUSY (16) +#define CPUIDLE_THROTTLED (32) +#define CPUIDLE_DIFF_NODE (64) + +static inline bool scaling_rq(struct rq *rq); + +/* + * The best idle CPU is chosen according to the CPUIDLE ranking above where the + * lowest value would give the most suitable CPU to schedule p onto next. The + * order works out to be the following: + * + * Same core, idle or busy cache, idle or busy threads + * Other core, same cache, idle or busy cache, idle threads. + * Same node, other CPU, idle cache, idle threads. + * Same node, other CPU, busy cache, idle threads. + * Other core, same cache, busy threads. + * Same node, other CPU, busy threads. + * Other node, other CPU, idle cache, idle threads. + * Other node, other CPU, busy cache, idle threads. + * Other node, other CPU, busy threads. + */ +static int best_mask_cpu(int best_cpu, struct rq *rq, cpumask_t *tmpmask) +{ + int best_ranking = CPUIDLE_DIFF_NODE | CPUIDLE_THROTTLED | + CPUIDLE_THREAD_BUSY | CPUIDLE_DIFF_CPU | CPUIDLE_CACHE_BUSY | + CPUIDLE_DIFF_CORE | CPUIDLE_DIFF_THREAD; + int cpu_tmp; + + if (cpumask_test_cpu(best_cpu, tmpmask)) + goto out; + + for_each_cpu(cpu_tmp, tmpmask) { + int ranking, locality; + struct rq *tmp_rq; + + ranking = 0; + tmp_rq = cpu_rq(cpu_tmp); + + locality = rq->cpu_locality[cpu_tmp]; +#ifdef CONFIG_NUMA + if (locality > 3) + ranking |= CPUIDLE_DIFF_NODE; + else +#endif + if (locality > 2) + ranking |= CPUIDLE_DIFF_CPU; +#ifdef CONFIG_SCHED_MC + else if (locality == 2) + ranking |= CPUIDLE_DIFF_CORE; + if (!(tmp_rq->cache_idle(cpu_tmp))) + ranking |= CPUIDLE_CACHE_BUSY; +#endif +#ifdef CONFIG_SCHED_SMT + if (locality == 1) + ranking |= CPUIDLE_DIFF_THREAD; + if (!(tmp_rq->siblings_idle(cpu_tmp))) + ranking |= CPUIDLE_THREAD_BUSY; +#endif + if (scaling_rq(tmp_rq)) + ranking |= CPUIDLE_THROTTLED; + + if (ranking < best_ranking) { + best_cpu = cpu_tmp; + best_ranking = ranking; + } + } +out: + return best_cpu; +} + +static void resched_best_mask(int best_cpu, struct rq *rq, cpumask_t *tmpmask) +{ + best_cpu = best_mask_cpu(best_cpu, rq, tmpmask); + resched_curr(cpu_rq(best_cpu)); +} + +bool cpus_share_cache(int this_cpu, int that_cpu) +{ + struct rq *this_rq = cpu_rq(this_cpu); + + return (this_rq->cpu_locality[that_cpu] < 3); +} + +#ifdef CONFIG_SCHED_SMT +#ifdef CONFIG_SMT_NICE +static const cpumask_t *thread_cpumask(int cpu); + +/* Find the best real time priority running on any SMT siblings of cpu and if + * none are running, the static priority of the best deadline task running. + * The lookups to the other runqueues is done lockless as the occasional wrong + * value would be harmless. */ +static int best_smt_bias(int cpu) +{ + int other_cpu, best_bias = 0; + + for_each_cpu(other_cpu, thread_cpumask(cpu)) { + struct rq *rq; + + if (other_cpu == cpu) + continue; + rq = cpu_rq(other_cpu); + if (rq_idle(rq)) + continue; + if (!rq->online) + continue; + if (!rq->rq_mm) + continue; + if (likely(rq->rq_smt_bias > best_bias)) + best_bias = rq->rq_smt_bias; + } + return best_bias; +} + +static int task_prio_bias(struct task_struct *p) +{ + if (rt_task(p)) + return 1 << 30; + else if (task_running_iso(p)) + return 1 << 29; + else if (task_running_idle(p)) + return 0; + return MAX_PRIO - p->static_prio; +} + +/* We've already decided p can run on CPU, now test if it shouldn't for SMT + * nice reasons. */ +static bool smt_should_schedule(struct task_struct *p, int cpu) +{ + int best_bias, task_bias; + + /* Kernel threads always run */ + if (unlikely(!p->mm)) + return true; + if (rt_task(p)) + return true; + if (!idleprio_suitable(p)) + return true; + best_bias = best_smt_bias(cpu); + /* The smt siblings are all idle or running IDLEPRIO */ + if (best_bias < 1) + return true; + task_bias = task_prio_bias(p); + if (task_bias < 1) + return false; + if (task_bias >= best_bias) + return true; + /* Dither 25% cpu of normal tasks regardless of nice difference */ + if (best_bias % 4 == 1) + return true; + /* Sorry, you lose */ + return false; +} +#endif +#endif + +static bool resched_best_idle(struct task_struct *p) +{ + cpumask_t tmpmask; + int best_cpu; + + cpumask_and(&tmpmask, &p->cpus_allowed, &grq.cpu_idle_map); + best_cpu = best_mask_cpu(task_cpu(p), task_rq(p), &tmpmask); +#ifdef CONFIG_SMT_NICE + if (!smt_should_schedule(p, best_cpu)) + return false; +#endif + resched_curr(cpu_rq(best_cpu)); + return true; +} + +static inline void resched_suitable_idle(struct task_struct *p) +{ + if (suitable_idle_cpus(p)) + resched_best_idle(p); +} +/* + * Flags to tell us whether this CPU is running a CPU frequency governor that + * has slowed its speed or not. No locking required as the very rare wrongly + * read value would be harmless. + */ +void cpu_scaling(int cpu) +{ + cpu_rq(cpu)->scaling = true; +} + +void cpu_nonscaling(int cpu) +{ + cpu_rq(cpu)->scaling = false; +} + +static inline bool scaling_rq(struct rq *rq) +{ + return rq->scaling; +} + +static inline int locality_diff(struct task_struct *p, struct rq *rq) +{ + return rq->cpu_locality[task_cpu(p)]; +} +#else /* CONFIG_SMP */ +static inline void set_cpuidle_map(int cpu) +{ +} + +static inline void clear_cpuidle_map(int cpu) +{ +} + +static inline bool suitable_idle_cpus(struct task_struct *p) +{ + return uprq->curr == uprq->idle; +} + +static inline void resched_suitable_idle(struct task_struct *p) +{ +} + +void cpu_scaling(int __unused) +{ +} + +void cpu_nonscaling(int __unused) +{ +} + +/* + * Although CPUs can scale in UP, there is nowhere else for tasks to go so this + * always returns 0. + */ +static inline bool scaling_rq(struct rq *rq) +{ + return false; +} + +static inline int locality_diff(struct task_struct *p, struct rq *rq) +{ + return 0; +} +#endif /* CONFIG_SMP */ +EXPORT_SYMBOL_GPL(cpu_scaling); +EXPORT_SYMBOL_GPL(cpu_nonscaling); + +static inline int normal_prio(struct task_struct *p) +{ + if (has_rt_policy(p)) + return MAX_RT_PRIO - 1 - p->rt_priority; + if (idleprio_task(p)) + return IDLE_PRIO; + if (iso_task(p)) + return ISO_PRIO; + return NORMAL_PRIO; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks as it will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/* + * activate_task - move a task to the runqueue. Enter with grq locked. + */ +static void activate_task(struct task_struct *p, struct rq *rq) +{ + update_clocks(rq); + + /* + * Sleep time is in units of nanosecs, so shift by 20 to get a + * milliseconds-range estimation of the amount of time that the task + * spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + if (p->state == TASK_UNINTERRUPTIBLE) + profile_hits(SLEEP_PROFILING, (void *)get_wchan(p), + (rq->clock_task - p->last_ran) >> 20); + } + + p->prio = effective_prio(p); + if (task_contributes_to_load(p)) + grq.nr_uninterruptible--; + enqueue_task(p, rq); + rq->soft_affined++; + p->on_rq = 1; + grq.nr_running++; + inc_qnr(); +} + +static inline void clear_sticky(struct task_struct *p); + +/* + * deactivate_task - If it's running, it's not on the grq and we can just + * decrement the nr_running. Enter with grq locked. + */ +static inline void deactivate_task(struct task_struct *p, struct rq *rq) +{ + if (task_contributes_to_load(p)) + grq.nr_uninterruptible++; + rq->soft_affined--; + p->on_rq = 0; + grq.nr_running--; + clear_sticky(p); +} + +static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); + +void register_task_migration_notifier(struct notifier_block *n) +{ + atomic_notifier_chain_register(&task_migration_notifier, n); +} + +#ifdef CONFIG_SMP +void set_task_cpu(struct task_struct *p, unsigned int cpu) +{ +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold grq lock. + */ + WARN_ON_ONCE(debug_locks && !lockdep_is_held(&grq.lock)); +#endif + if (task_cpu(p) == cpu) + return; + trace_sched_migrate_task(p, cpu); + perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + + /* + * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be + * successfully executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + if (p->on_rq) { + task_rq(p)->soft_affined--; + cpu_rq(cpu)->soft_affined++; + } + task_thread_info(p)->cpu = cpu; +} + +static inline void clear_sticky(struct task_struct *p) +{ + p->sticky = false; +} + +static inline bool task_sticky(struct task_struct *p) +{ + return p->sticky; +} + +/* Reschedule the best idle CPU that is not this one. */ +static void +resched_closest_idle(struct rq *rq, int cpu, struct task_struct *p) +{ + cpumask_t tmpmask; + + cpumask_and(&tmpmask, &p->cpus_allowed, &grq.cpu_idle_map); + cpumask_clear_cpu(cpu, &tmpmask); + if (cpumask_empty(&tmpmask)) + return; + resched_best_mask(cpu, rq, &tmpmask); +} + +/* + * We set the sticky flag on a task that is descheduled involuntarily meaning + * it is awaiting further CPU time. If the last sticky task is still sticky + * but unlucky enough to not be the next task scheduled, we unstick it and try + * to find it an idle CPU. Realtime tasks do not stick to minimise their + * latency at all times. + */ +static inline void +swap_sticky(struct rq *rq, int cpu, struct task_struct *p) +{ + if (rq->sticky_task) { + if (rq->sticky_task == p) { + p->sticky = true; + return; + } + if (task_sticky(rq->sticky_task)) { + clear_sticky(rq->sticky_task); + resched_closest_idle(rq, cpu, rq->sticky_task); + } + } + if (!rt_task(p)) { + p->sticky = true; + rq->sticky_task = p; + } else { + resched_closest_idle(rq, cpu, p); + rq->sticky_task = NULL; + } +} + +static inline void unstick_task(struct rq *rq, struct task_struct *p) +{ + rq->sticky_task = NULL; + clear_sticky(p); +} +#else +static inline void clear_sticky(struct task_struct *p) +{ +} + +static inline bool task_sticky(struct task_struct *p) +{ + return false; +} + +static inline void +swap_sticky(struct rq *rq, int cpu, struct task_struct *p) +{ +} + +static inline void unstick_task(struct rq *rq, struct task_struct *p) +{ +} +#endif + +/* + * Move a task off the global queue and take it to a cpu for it will + * become the running task. + */ +static inline void take_task(int cpu, struct task_struct *p) +{ + set_task_cpu(p, cpu); + dequeue_task(p); + clear_sticky(p); + dec_qnr(); +} + +/* + * Returns a descheduling task to the grq runqueue unless it is being + * deactivated. + */ +static inline void return_task(struct task_struct *p, struct rq *rq, bool deactivate) +{ + if (deactivate) + deactivate_task(p, rq); + else { + inc_qnr(); + enqueue_task(p, rq); + } +} + +/* Enter with grq lock held. We know p is on the local cpu */ +static inline void __set_tsk_resched(struct task_struct *p) +{ + set_tsk_need_resched(p); + set_preempt_need_resched(); +} + +/* + * resched_task - mark a task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +void resched_task(struct task_struct *p) +{ + int cpu; + + lockdep_assert_held(&grq.lock); + + if (test_tsk_need_resched(p)) + return; + + set_tsk_need_resched(p); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_preempt_need_resched(); + return; + } + + smp_send_reschedule(cpu); +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +#ifdef CONFIG_SMP +struct migration_req { + struct task_struct *task; + int dest_cpu; +}; + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + bool running, on_rq; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since this will return false + * if the runqueue has changed and p is actually now + * running somewhere else! + */ + while (task_running(p) && p == rq->curr) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the grq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_grq_lock(p, &flags); + trace_sched_wait_task(p); + running = task_running(p); + on_rq = p->on_rq; + ncsw = 0; + if (!match_state || p->state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_grq_unlock(&flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(on_rq)) { + ktime_t to = ktime_set(0, NSEC_PER_SEC / HZ); + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesn't have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kick_process); +#endif + +/* + * RT tasks preempt purely on priority. SCHED_NORMAL tasks preempt on the + * basis of earlier deadlines. SCHED_IDLEPRIO don't preempt anything else or + * between themselves, they cooperatively multitask. An idle rq scores as + * prio PRIO_LIMIT so it is always preempted. + */ +static inline bool +can_preempt(struct task_struct *p, int prio, u64 deadline) +{ + /* Better static priority RT task or better policy preemption */ + if (p->prio < prio) + return true; + if (p->prio > prio) + return false; + /* SCHED_NORMAL, BATCH and ISO will preempt based on deadline */ + if (!deadline_before(p->deadline, deadline)) + return false; + return true; +} + +#ifdef CONFIG_SMP +#define cpu_online_map (*(cpumask_t *)cpu_online_mask) +#ifdef CONFIG_HOTPLUG_CPU +/* + * Check to see if there is a task that is affined only to offline CPUs but + * still wants runtime. This happens to kernel threads during suspend/halt and + * disabling of CPUs. + */ +static inline bool online_cpus(struct task_struct *p) +{ + return (likely(cpumask_intersects(&cpu_online_map, &p->cpus_allowed))); +} +#else /* CONFIG_HOTPLUG_CPU */ +/* All available CPUs are always online without hotplug. */ +static inline bool online_cpus(struct task_struct *p) +{ + return true; +} +#endif + +/* + * Check to see if p can run on cpu, and if not, whether there are any online + * CPUs it can run on instead. + */ +static inline bool needs_other_cpu(struct task_struct *p, int cpu) +{ + if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed))) + return true; + return false; +} + +/* + * When all else is equal, still prefer this_rq. + */ +static void try_preempt(struct task_struct *p, struct rq *this_rq) +{ + struct rq *highest_prio_rq = NULL; + int cpu, highest_prio; + u64 latest_deadline; + cpumask_t tmp; + + /* + * We clear the sticky flag here because for a task to have called + * try_preempt with the sticky flag enabled means some complicated + * re-scheduling has occurred and we should ignore the sticky flag. + */ + clear_sticky(p); + + if (suitable_idle_cpus(p) && resched_best_idle(p)) + return; + + /* IDLEPRIO tasks never preempt anything but idle */ + if (p->policy == SCHED_IDLEPRIO) + return; + + if (likely(online_cpus(p))) + cpumask_and(&tmp, &cpu_online_map, &p->cpus_allowed); + else + return; + + highest_prio = latest_deadline = 0; + + for_each_cpu(cpu, &tmp) { + struct rq *rq; + int rq_prio; + + rq = cpu_rq(cpu); + rq_prio = rq->rq_prio; + if (rq_prio < highest_prio) + continue; + + if (rq_prio > highest_prio || + deadline_after(rq->rq_deadline, latest_deadline)) { + latest_deadline = rq->rq_deadline; + highest_prio = rq_prio; + highest_prio_rq = rq; + } + } + + if (likely(highest_prio_rq)) { +#ifdef CONFIG_SMT_NICE + cpu = cpu_of(highest_prio_rq); + if (!smt_should_schedule(p, cpu)) + return; +#endif + if (can_preempt(p, highest_prio, highest_prio_rq->rq_deadline)) + resched_curr(highest_prio_rq); + } +} +#else /* CONFIG_SMP */ +static inline bool needs_other_cpu(struct task_struct *p, int cpu) +{ + return false; +} + +static void try_preempt(struct task_struct *p, struct rq *this_rq) +{ + if (p->policy == SCHED_IDLEPRIO) + return; + if (can_preempt(p, uprq->rq_prio, uprq->rq_deadline)) + resched_curr(uprq); +} +#endif /* CONFIG_SMP */ + +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) +{ +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) + schedstat_inc(rq, ttwu_local); + else { + struct sched_domain *sd; + + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + rcu_read_unlock(); + } + +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); +#endif /* CONFIG_SCHEDSTATS */ +} + +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + rcu_read_lock(); + + if (!is_idle_task(rcu_dereference(rq->curr))) + goto out; + + grq_lock_irqsave(&flags); + if (likely(is_idle_task(rq->curr))) + smp_send_reschedule(cpu); + /* Else cpu is not in idle, do nothing here */ + grq_unlock_irqrestore(&flags); + +out: + rcu_read_unlock(); +} + +#ifdef CONFIG_SMP +void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); +} +#endif + +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync) +{ + activate_task(p, rq); + + /* + * Sync wakeups (i.e. those types of wakeups where the waker + * has indicated that it will leave the CPU in short order) + * don't trigger a preemption if there are no idle cpus, + * instead waiting for current to deschedule. + */ + if (!is_sync || suitable_idle_cpus(p)) + try_preempt(p, rq); +} + +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + bool success) +{ + trace_sched_wakeup(p, success); + p->state = TASK_RUNNING; + + /* + * if a worker is waking up, notify workqueue. Note that on BFS, we + * don't really know what cpu it will be, so we fake it for + * wq_worker_waking_up :/ + */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); +} + +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ + +/*** + * try_to_wake_up - wake up a thread + * @p: the thread to be awakened + * @state: the mask of task states that can be woken + * @wake_flags: wake modifier flags (WF_*) + * + * Put it on the run-queue if it's not already there. The "current" + * thread is always on the run-queue (except when the actual + * re-schedule is in progress), and as such you're allowed to do + * the simpler "current->state = TASK_RUNNING" to mark yourself + * runnable without the overhead of this. + * + * Return: %true if @p was woken up, %false if it was already running. + * or @state didn't match @p's state. + */ +static bool try_to_wake_up(struct task_struct *p, unsigned int state, + int wake_flags) +{ + bool success = false; + unsigned long flags; + struct rq *rq; + int cpu; + + get_cpu(); + + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); + + /* + * No need to do time_lock_grq as we only need to update the rq clock + * if we activate the task + */ + rq = task_grq_lock(p, &flags); + cpu = task_cpu(p); + + /* state is a volatile long, どうして、分からない */ + if (!((unsigned int)p->state & state)) + goto out_unlock; + + if (task_queued(p) || task_running(p)) + goto out_running; + + ttwu_activate(p, rq, wake_flags & WF_SYNC); + success = true; + +out_running: + ttwu_post_activation(p, rq, success); +out_unlock: + task_grq_unlock(&flags); + + ttwu_stat(p, cpu, wake_flags); + + put_cpu(); + + return success; +} + +/** + * try_to_wake_up_local - try to wake up a local task with grq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not already there. The caller must + * ensure that grq is locked and, @p is not the current task. + * grq stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + lockdep_assert_held(&grq.lock); + + if (!(p->state & TASK_NORMAL)) + return; + + if (!task_queued(p)) { + if (likely(!task_running(p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false); + ttwu_stat(p, smp_processor_id(), 0); + success = true; + } + ttwu_post_activation(p, rq, success); +} + +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +int wake_up_process(struct task_struct *p) +{ + WARN_ON(task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +static void time_slice_expired(struct task_struct *p); + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + */ +int sched_fork(unsigned long __maybe_unused clone_flags, struct task_struct *p) +{ +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + /* + * The process state is set to the same value of the process executing + * do_fork() code. That is running. This guarantees that nobody will + * actually run it, and a signal or other external event cannot wake + * it up and insert it on the runqueue either. + */ + + /* Should be reset in fork.c but done here for ease of bfs patching */ + p->on_rq = + p->utime = + p->stime = + p->utimescaled = + p->stimescaled = + p->sched_time = + p->stime_pc = + p->utime_pc = 0; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { + p->policy = SCHED_NORMAL; + p->normal_prio = normal_prio(p); + } + + if (PRIO_TO_NICE(p->static_prio) < 0) { + p->static_prio = NICE_TO_PRIO(0); + p->normal_prio = p->static_prio; + } + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + + INIT_LIST_HEAD(&p->run_list); +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + if (unlikely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif + p->on_cpu = false; + clear_sticky(p); + init_task_preempt_count(p); + return 0; +} + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p) +{ + struct task_struct *parent; + unsigned long flags; + struct rq *rq; + + parent = p->parent; + rq = task_grq_lock(p, &flags); + + /* + * Reinit new task deadline as its creator deadline could have changed + * since call to dup_task_struct(). + */ + p->deadline = rq->rq_deadline; + + /* + * If the task is a new process, current and parent are the same. If + * the task is a new thread in the thread group, it will have much more + * in common with current than with the parent. + */ + set_task_cpu(p, task_cpu(rq->curr)); + + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = rq->curr->normal_prio; + + activate_task(p, rq); + trace_sched_wakeup_new(p, 1); + if (unlikely(p->policy == SCHED_FIFO)) + goto after_ts_init; + + /* + * Share the timeslice between parent and child, thus the + * total amount of pending timeslices in the system doesn't change, + * resulting in more scheduling fairness. If it's negative, it won't + * matter since that's the same as being 0. current's time_slice is + * actually in rq_time_slice when it's running, as is its last_ran + * value. rq->rq_deadline is only modified within schedule() so it + * is always equal to current->deadline. + */ + p->last_ran = rq->rq_last_ran; + if (likely(rq->rq_time_slice >= RESCHED_US * 2)) { + rq->rq_time_slice /= 2; + p->time_slice = rq->rq_time_slice; +after_ts_init: + if (rq->curr == parent && !suitable_idle_cpus(p)) { + /* + * The VM isn't cloned, so we're in a good position to + * do child-runs-first in anticipation of an exec. This + * usually avoids a lot of COW overhead. + */ + __set_tsk_resched(parent); + } else + try_preempt(p, rq); + } else { + if (rq->curr == parent) { + /* + * Forking task has run out of timeslice. Reschedule it and + * start its child with a new time slice and deadline. The + * child will end up running first because its deadline will + * be slightly earlier. + */ + rq->rq_time_slice = 0; + __set_tsk_resched(parent); + } + time_slice_expired(p); + } + task_grq_unlock(&flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + sched_info_switch(rq, prev, next); + perf_event_task_sched_out(prev, next); + fire_sched_out_preempt_notifiers(prev, next); + prepare_lock_switch(rq, next); + prepare_arch_switch(next); + trace_sched_switch(prev, next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @rq: runqueue associated with task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + * + * The context switch have flipped the stack from under us and restored the + * local variables which were saved when this task called schedule() in the + * past. prev == current is still correct but we need to recalculate this_rq + * because prev may have moved to another CPU. + */ +static struct rq *finish_task_switch(struct task_struct *prev) + __releases(grq.lock) +{ + struct rq *rq = this_rq(); + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * The test for TASK_DEAD must occur while the runqueue locks are + * still held, otherwise prev could be scheduled on another cpu, die + * there before we look at prev->state, and then the reference would + * be dropped twice. + * Manfred Spraul <manfred@colorfullife.com> + */ + prev_state = prev->state; + vtime_task_switch(prev); + finish_arch_switch(prev); + perf_event_task_sched_in(prev, current); + finish_lock_switch(rq, prev); + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); + if (mm) + mmdrop(mm); + if (unlikely(prev_state == TASK_DEAD)) { + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + put_task_struct(prev); + } + return rq; +} + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage __visible void schedule_tail(struct task_struct *prev) + __releases(grq.lock) +{ + struct rq *rq; + + /* finish_task_switch() drops rq->lock and enables preemption */ + preempt_disable(); + rq = finish_task_switch(prev); + preempt_enable(); + + if (current->set_child_tid) + put_user(task_pid_vnr(current), current->set_child_tid); +} + +/* + * context_switch - switch to the new MM and the new thread's register state. + */ +static inline struct rq * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(rq, prev, next); + + mm = next->mm; + oldmm = prev->active_mm; + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_start_context_switch(prev); + + if (!mm) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm(oldmm, mm, next); + + if (!prev->mm) { + prev->active_mm = NULL; + rq->prev_mm = oldmm; + } + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); + + /* Here we just switch the register state and the stack. */ + context_tracking_task_switch(prev, next); + switch_to(prev, next, prev); + + barrier(); + + return finish_task_switch(prev); +} + +/* + * nr_running, nr_uninterruptible and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, total number of context switches performed since bootup. All are + * measured without grabbing the grq lock but the occasional inaccurate result + * doesn't matter so long as it's positive. + */ +unsigned long nr_running(void) +{ + long nr = grq.nr_running; + + if (unlikely(nr < 0)) + nr = 0; + return (unsigned long)nr; +} + +static unsigned long nr_uninterruptible(void) +{ + long nu = grq.nr_uninterruptible; + + if (unlikely(nu < 0)) + nu = 0; + return nu; +} + +/* + * Check if only the current task is running on the cpu. + */ +bool single_task_running(void) +{ + if (cpu_rq(smp_processor_id())->soft_affined == 1) + return true; + else + return false; +} +EXPORT_SYMBOL(single_task_running); + +unsigned long long nr_context_switches(void) +{ + long long ns = grq.nr_switches; + + /* This is of course impossible */ + if (unlikely(ns < 0)) + ns = 1; + return (unsigned long long)ns; +} + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += atomic_read(&cpu_rq(i)->nr_iowait); + + return sum; +} + +unsigned long nr_iowait_cpu(int cpu) +{ + struct rq *this = cpu_rq(cpu); + return atomic_read(&this->nr_iowait); +} + +unsigned long nr_active(void) +{ + return nr_running() + nr_uninterruptible(); +} + +/* Beyond a task running on this CPU, load is equal everywhere on BFS, so we + * base it on the number of running or queued tasks with their ->rq pointer + * set to this cpu as being the CPU they're more likely to run on. */ +void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) +{ + struct rq *this = this_rq(); + + *nr_waiters = atomic_read(&this->nr_iowait); + *load = this->soft_affined; +} + +/* Variables and functions for calc_load */ +static unsigned long calc_load_update; +unsigned long avenrun[3]; +EXPORT_SYMBOL(avenrun); + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} + +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + return load >> FSHIFT; +} + +/* + * calc_load - update the avenrun load estimates every LOAD_FREQ seconds. + */ +void calc_global_load(unsigned long ticks) +{ + long active; + + if (time_before(jiffies, calc_load_update)) + return; + active = nr_active() * FIXED_1; + + avenrun[0] = calc_load(avenrun[0], EXP_1, active); + avenrun[1] = calc_load(avenrun[1], EXP_5, active); + avenrun[2] = calc_load(avenrun[2], EXP_15, active); + + calc_load_update = jiffies + LOAD_FREQ; +} + +DEFINE_PER_CPU(struct kernel_stat, kstat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); + +EXPORT_PER_CPU_SYMBOL(kstat); +EXPORT_PER_CPU_SYMBOL(kernel_cpustat); + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in account_system_vtime, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/account_system_vtime on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +static DEFINE_PER_CPU(u64, cpu_hardirq_time); +static DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +static DEFINE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void irqtime_account_irq(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(irqtime_account_irq); + +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_PARAVIRT +static inline u64 steal_ticks(u64 steal) +{ + if (unlikely(steal > NSEC_PER_SEC)) + return div_u64(steal, TICK_NSEC); + + return __iter_div_u64_rem(steal, TICK_NSEC, &steal); +} +#endif + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + s64 irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + s64 steal = paravirt_steal_clock(cpu_of(rq)); + + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + + delta -= steal; + } +#endif + + rq->clock_task += delta; +} + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static void irqtime_account_hi_si(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + u64 latest_ns; + + latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time)); + if (latest_ns > cpustat[CPUTIME_IRQ]) + cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy; + + latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time)); + if (latest_ns > cpustat[CPUTIME_SOFTIRQ]) + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy; +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +static inline void irqtime_account_hi_si(void) +{ +} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal; + cputime_t steal_ct; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + + account_steal_time(steal_ct); + return steal_ct; + } +#endif + return false; +} + +/* + * Accumulate raw cputime values of dead tasks (sig->[us]time) and live + * tasks (sum on group iteration) belonging to @tsk's group. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; + struct task_struct *t; + unsigned int seq, nextseq; + unsigned long flags; + + rcu_read_lock(); + /* Attempt a lockless read on the first round. */ + nextseq = 0; + do { + seq = nextseq; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; + + for_each_thread(tsk, t) { + task_cputime(t, &utime, &stime); + times->utime += utime; + times->stime += stime; + times->sum_exec_runtime += task_sched_runtime(t); + } + /* If lockless access failed, take the lock. */ + nextseq = 1; + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + rcu_read_unlock(); +} + +/* + * On each tick, see what percentage of that tick was attributed to each + * component and add the percentage to the _pc values. Once a _pc value has + * accumulated one tick's worth, account for that. This means the total + * percentage of load components will always be 128 (pseudo 100) per tick. + */ +static void pc_idle_time(struct rq *rq, struct task_struct *idle, unsigned long pc) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (atomic_read(&rq->nr_iowait) > 0) { + rq->iowait_pc += pc; + if (rq->iowait_pc >= 128) { + cpustat[CPUTIME_IOWAIT] += (__force u64)cputime_one_jiffy * rq->iowait_pc / 128; + rq->iowait_pc %= 128; + } + } else { + rq->idle_pc += pc; + if (rq->idle_pc >= 128) { + cpustat[CPUTIME_IDLE] += (__force u64)cputime_one_jiffy * rq->idle_pc / 128; + rq->idle_pc %= 128; + } + } + acct_update_integrals(idle); +} + +static void +pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset, + unsigned long pc, unsigned long ns) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + + p->stime_pc += pc; + if (p->stime_pc >= 128) { + int jiffs = p->stime_pc / 128; + + p->stime_pc %= 128; + p->stime += (__force u64)cputime_one_jiffy * jiffs; + p->stimescaled += one_jiffy_scaled * jiffs; + account_group_system_time(p, cputime_one_jiffy * jiffs); + } + p->sched_time += ns; + account_group_exec_runtime(p, ns); + + if (hardirq_count() - hardirq_offset) { + rq->irq_pc += pc; + if (rq->irq_pc >= 128) { + cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy * rq->irq_pc / 128; + rq->irq_pc %= 128; + } + } else if (in_serving_softirq()) { + rq->softirq_pc += pc; + if (rq->softirq_pc >= 128) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128; + rq->softirq_pc %= 128; + } + } else { + rq->system_pc += pc; + if (rq->system_pc >= 128) { + cpustat[CPUTIME_SYSTEM] += (__force u64)cputime_one_jiffy * rq->system_pc / 128; + rq->system_pc %= 128; + } + } + acct_update_integrals(p); +} + +static void pc_user_time(struct rq *rq, struct task_struct *p, + unsigned long pc, unsigned long ns) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + + p->utime_pc += pc; + if (p->utime_pc >= 128) { + int jiffs = p->utime_pc / 128; + + p->utime_pc %= 128; + p->utime += (__force u64)cputime_one_jiffy * jiffs; + p->utimescaled += one_jiffy_scaled * jiffs; + account_group_user_time(p, cputime_one_jiffy * jiffs); + } + p->sched_time += ns; + account_group_exec_runtime(p, ns); + + if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + */ + rq->softirq_pc += pc; + if (rq->softirq_pc >= 128) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128; + rq->softirq_pc %= 128; + } + } + + if (task_nice(p) > 0 || idleprio_task(p)) { + rq->nice_pc += pc; + if (rq->nice_pc >= 128) { + cpustat[CPUTIME_NICE] += (__force u64)cputime_one_jiffy * rq->nice_pc / 128; + rq->nice_pc %= 128; + } + } else { + rq->user_pc += pc; + if (rq->user_pc >= 128) { + cpustat[CPUTIME_USER] += (__force u64)cputime_one_jiffy * rq->user_pc / 128; + rq->user_pc %= 128; + } + } + acct_update_integrals(p); +} + +/* + * Convert nanoseconds to pseudo percentage of one tick. Use 128 for fast + * shifts instead of 100 + */ +#define NS_TO_PC(NS) (NS * 128 / JIFFY_NS) + +/* + * This is called on clock ticks. + * Bank in p->sched_time the ns elapsed since the last tick or switch. + * CPU scheduler quota accounting is also performed here in microseconds. + */ +static void +update_cpu_clock_tick(struct rq *rq, struct task_struct *p) +{ + long account_ns = rq->clock_task - rq->rq_last_ran; + struct task_struct *idle = rq->idle; + unsigned long account_pc; + + if (unlikely(account_ns < 0) || steal_account_process_tick()) + goto ts_account; + + account_pc = NS_TO_PC(account_ns); + + /* Accurate tick timekeeping */ + if (user_mode(get_irq_regs())) + pc_user_time(rq, p, account_pc, account_ns); + else if (p != idle || (irq_count() != HARDIRQ_OFFSET)) + pc_system_time(rq, p, HARDIRQ_OFFSET, + account_pc, account_ns); + else + pc_idle_time(rq, idle, account_pc); + + if (sched_clock_irqtime) + irqtime_account_hi_si(); + +ts_account: + /* time_slice accounting is done in usecs to avoid overflow on 32bit */ + if (rq->rq_policy != SCHED_FIFO && p != idle) { + s64 time_diff = rq->clock - rq->timekeep_clock; + + niffy_diff(&time_diff, 1); + rq->rq_time_slice -= NS_TO_US(time_diff); + } + + rq->rq_last_ran = rq->clock_task; + rq->timekeep_clock = rq->clock; +} + +/* + * This is called on context switches. + * Bank in p->sched_time the ns elapsed since the last tick or switch. + * CPU scheduler quota accounting is also performed here in microseconds. + */ +static void +update_cpu_clock_switch(struct rq *rq, struct task_struct *p) +{ + long account_ns = rq->clock_task - rq->rq_last_ran; + struct task_struct *idle = rq->idle; + unsigned long account_pc; + + if (unlikely(account_ns < 0)) + goto ts_account; + + account_pc = NS_TO_PC(account_ns); + + /* Accurate subtick timekeeping */ + if (p != idle) { + pc_user_time(rq, p, account_pc, account_ns); + } + else + pc_idle_time(rq, idle, account_pc); + +ts_account: + /* time_slice accounting is done in usecs to avoid overflow on 32bit */ + if (rq->rq_policy != SCHED_FIFO && p != idle) { + s64 time_diff = rq->clock - rq->timekeep_clock; + + niffy_diff(&time_diff, 1); + rq->rq_time_slice -= NS_TO_US(time_diff); + } + + rq->rq_last_ran = rq->clock_task; + rq->timekeep_clock = rq->clock; +} + +/* + * Return any ns on the sched_clock that have not yet been accounted in + * @p in case that task is currently running. + * + * Called with task_grq_lock() held. + */ +static inline u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) +{ + u64 ns = 0; + + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (p == rq->curr && p->on_rq) { + update_clocks(rq); + ns = rq->clock_task - rq->rq_last_ran; + if (unlikely((s64)ns < 0)) + ns = 0; + } + + return ns; +} + +/* + * Return accounted runtime for the task. + * Return separately the current's pending runtime that have not been + * accounted yet. + * + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns; + +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. + */ + if (!p->on_cpu || !p->on_rq) + return tsk_seruntime(p); +#endif + + rq = task_grq_lock(p, &flags); + ns = p->sched_time + do_task_delta_exec(p, rq); + task_grq_unlock(&flags); + + return ns; +} + +/* Compatibility crap */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ +} + +void account_idle_time(cputime_t cputime) +{ +} + +void update_cpu_load_nohz(void) +{ +} + +#ifdef CONFIG_NO_HZ_COMMON +void calc_load_enter_idle(void) +{ +} + +void calc_load_exit_idle(void) +{ +} +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += (__force u64)cputime; + p->utimescaled += (__force u64)cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += (__force u64)cputime; + + /* Add guest time to cpustat. */ + if (task_nice(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64)cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64)cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64)cputime; + cpustat[CPUTIME_GUEST] += (__force u64)cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, cputime64_t *target_cputime64) +{ + /* Add system time to process. */ + p->stime += (__force u64)cputime; + p->stimescaled += (__force u64)cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + *target_cputime64 += (__force u64)cputime; + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * This is for guest only now. + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) + account_guest_time(p, cputime, cputime_scaled); +} + +/* + * Account for involuntary wait time. + * @steal: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64)cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +static void account_idle_times(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64)cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64)cputime; +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + +void account_process_tick(struct task_struct *p, int user_tick) +{ +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + account_idle_times(jiffies_to_cputime(ticks)); +} +#endif + +static inline void grq_iso_lock(void) + __acquires(grq.iso_lock) +{ + raw_spin_lock(&grq.iso_lock); +} + +static inline void grq_iso_unlock(void) + __releases(grq.iso_lock) +{ + raw_spin_unlock(&grq.iso_lock); +} + +/* + * Functions to test for when SCHED_ISO tasks have used their allocated + * quota as real time scheduling and convert them back to SCHED_NORMAL. + * Where possible, the data is tested lockless, to avoid grabbing iso_lock + * because the occasional inaccurate result won't matter. However the + * tick data is only ever modified under lock. iso_refractory is only simply + * set to 0 or 1 so it's not worth grabbing the lock yet again for that. + */ +static bool set_iso_refractory(void) +{ + grq.iso_refractory = true; + return grq.iso_refractory; +} + +static bool clear_iso_refractory(void) +{ + grq.iso_refractory = false; + return grq.iso_refractory; +} + +/* + * Test if SCHED_ISO tasks have run longer than their alloted period as RT + * tasks and set the refractory flag if necessary. There is 10% hysteresis + * for unsetting the flag. 115/128 is ~90/100 as a fast shift instead of a + * slow division. + */ +static bool test_ret_isorefractory(struct rq *rq) +{ + if (likely(!grq.iso_refractory)) { + if (grq.iso_ticks > ISO_PERIOD * sched_iso_cpu) + return set_iso_refractory(); + } else { + if (grq.iso_ticks < ISO_PERIOD * (sched_iso_cpu * 115 / 128)) + return clear_iso_refractory(); + } + return grq.iso_refractory; +} + +static void iso_tick(void) +{ + grq_iso_lock(); + grq.iso_ticks += 100; + grq_iso_unlock(); +} + +/* No SCHED_ISO task was running so decrease rq->iso_ticks */ +static inline void no_iso_tick(void) +{ + if (grq.iso_ticks) { + grq_iso_lock(); + grq.iso_ticks -= grq.iso_ticks / ISO_PERIOD + 1; + if (unlikely(grq.iso_refractory && grq.iso_ticks < + ISO_PERIOD * (sched_iso_cpu * 115 / 128))) + clear_iso_refractory(); + grq_iso_unlock(); + } +} + +/* This manages tasks that have run out of timeslice during a scheduler_tick */ +static void task_running_tick(struct rq *rq) +{ + struct task_struct *p; + + /* + * If a SCHED_ISO task is running we increment the iso_ticks. In + * order to prevent SCHED_ISO tasks from causing starvation in the + * presence of true RT tasks we account those as iso_ticks as well. + */ + if ((rt_queue(rq) || (iso_queue(rq) && !grq.iso_refractory))) { + if (grq.iso_ticks <= (ISO_PERIOD * 128) - 128) + iso_tick(); + } else + no_iso_tick(); + + if (iso_queue(rq)) { + if (unlikely(test_ret_isorefractory(rq))) { + if (rq_running_iso(rq)) { + /* + * SCHED_ISO task is running as RT and limit + * has been hit. Force it to reschedule as + * SCHED_NORMAL by zeroing its time_slice + */ + rq->rq_time_slice = 0; + } + } + } + + /* SCHED_FIFO tasks never run out of timeslice. */ + if (rq->rq_policy == SCHED_FIFO) + return; + /* + * Tasks that were scheduled in the first half of a tick are not + * allowed to run into the 2nd half of the next tick if they will + * run out of time slice in the interim. Otherwise, if they have + * less than RESCHED_US μs of time slice left they will be rescheduled. + */ + if (rq->dither) { + if (rq->rq_time_slice > HALF_JIFFY_US) + return; + else + rq->rq_time_slice = 0; + } else if (rq->rq_time_slice >= RESCHED_US) + return; + + /* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */ + p = rq->curr; + + grq_lock(); + requeue_task(p); + __set_tsk_resched(p); + grq_unlock(); +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. The data modified is all + * local to struct rq so we don't need to grab grq lock. + */ +void scheduler_tick(void) +{ + int cpu __maybe_unused = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + + sched_clock_tick(); + /* grq lock not grabbed, so only update rq clock */ + update_rq_clock(rq); + update_cpu_clock_tick(rq, rq->curr); + if (!rq_idle(rq)) + task_running_tick(rq); + else + no_iso_tick(); + rq->last_tick = rq->clock; + perf_event_task_tick(); +} + +notrace unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} + +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) +void preempt_count_add(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + __preempt_count_add(val); +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); + +void preempt_count_sub(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; +#endif + + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + __preempt_count_sub(val); +} +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); +#endif + +/* + * Deadline is "now" in niffies + (offset by priority). Setting the deadline + * is the key to everything. It distributes cpu fairly amongst tasks of the + * same nice value, it proportions cpu according to nice level, it means the + * task that last woke up the longest ago has the earliest deadline, thus + * ensuring that interactive tasks get low latency on wake up. The CPU + * proportion works out to the square of the virtual deadline difference, so + * this equation will give nice 19 3% CPU compared to nice 0. + */ +static inline u64 prio_deadline_diff(int user_prio) +{ + return (prio_ratios[user_prio] * rr_interval * (MS_TO_NS(1) / 128)); +} + +static inline u64 task_deadline_diff(struct task_struct *p) +{ + return prio_deadline_diff(TASK_USER_PRIO(p)); +} + +static inline u64 static_deadline_diff(int static_prio) +{ + return prio_deadline_diff(USER_PRIO(static_prio)); +} + +static inline int longest_deadline_diff(void) +{ + return prio_deadline_diff(39); +} + +static inline int ms_longest_deadline_diff(void) +{ + return NS_TO_MS(longest_deadline_diff()); +} + +/* + * The time_slice is only refilled when it is empty and that is when we set a + * new deadline. + */ +static void time_slice_expired(struct task_struct *p) +{ + p->time_slice = timeslice(); + p->deadline = grq.niffies + task_deadline_diff(p); +#ifdef CONFIG_SMT_NICE + if (!p->mm) + p->smt_bias = 0; + else if (rt_task(p)) + p->smt_bias = 1 << 30; + else if (task_running_iso(p)) + p->smt_bias = 1 << 29; + else if (idleprio_task(p)) { + if (task_running_idle(p)) + p->smt_bias = 0; + else + p->smt_bias = 1; + } else if (--p->smt_bias < 1) + p->smt_bias = MAX_PRIO - p->static_prio; +#endif +} + +/* + * Timeslices below RESCHED_US are considered as good as expired as there's no + * point rescheduling when there's so little time left. SCHED_BATCH tasks + * have been flagged be not latency sensitive and likely to be fully CPU + * bound so every time they're rescheduled they have their time_slice + * refilled, but get a new later deadline to have little effect on + * SCHED_NORMAL tasks. + + */ +static inline void check_deadline(struct task_struct *p) +{ + if (p->time_slice < RESCHED_US || batch_task(p)) + time_slice_expired(p); +} + +#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) + +/* + * Scheduler queue bitmap specific find next bit. + */ +static inline unsigned long +next_sched_bit(const unsigned long *addr, unsigned long offset) +{ + const unsigned long *p; + unsigned long result; + unsigned long size; + unsigned long tmp; + + size = PRIO_LIMIT; + if (offset >= size) + return size; + + p = addr + BITOP_WORD(offset); + result = offset & ~(BITS_PER_LONG-1); + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL << offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __ffs(tmp); +} + +/* + * O(n) lookup of all tasks in the global runqueue. The real brainfuck + * of lock contention and O(n). It's not really O(n) as only the queued, + * but not running tasks are scanned, and is O(n) queued in the worst case + * scenario only because the right task can be found before scanning all of + * them. + * Tasks are selected in this order: + * Real time tasks are selected purely by their static priority and in the + * order they were queued, so the lowest value idx, and the first queued task + * of that priority value is chosen. + * If no real time tasks are found, the SCHED_ISO priority is checked, and + * all SCHED_ISO tasks have the same priority value, so they're selected by + * the earliest deadline value. + * If no SCHED_ISO tasks are found, SCHED_NORMAL tasks are selected by the + * earliest deadline. + * Finally if no SCHED_NORMAL tasks are found, SCHED_IDLEPRIO tasks are + * selected by the earliest deadline. + */ +static inline struct +task_struct *earliest_deadline_task(struct rq *rq, int cpu, struct task_struct *idle) +{ + struct task_struct *edt = NULL; + unsigned long idx = -1; + + do { + struct list_head *queue; + struct task_struct *p; + u64 earliest_deadline; + + idx = next_sched_bit(grq.prio_bitmap, ++idx); + if (idx >= PRIO_LIMIT) + return idle; + queue = grq.queue + idx; + + if (idx < MAX_RT_PRIO) { + /* We found an rt task */ + list_for_each_entry(p, queue, run_list) { + /* Make sure cpu affinity is ok */ + if (needs_other_cpu(p, cpu)) + continue; + edt = p; + goto out_take; + } + /* + * None of the RT tasks at this priority can run on + * this cpu + */ + continue; + } + + /* + * No rt tasks. Find the earliest deadline task. Now we're in + * O(n) territory. + */ + earliest_deadline = ~0ULL; + list_for_each_entry(p, queue, run_list) { + u64 dl; + + /* Make sure cpu affinity is ok */ + if (needs_other_cpu(p, cpu)) + continue; + +#ifdef CONFIG_SMT_NICE + if (!smt_should_schedule(p, cpu)) + continue; +#endif + /* + * Soft affinity happens here by not scheduling a task + * with its sticky flag set that ran on a different CPU + * last when the CPU is scaling, or by greatly biasing + * against its deadline when not, based on cpu cache + * locality. + */ + if (task_sticky(p) && task_rq(p) != rq) { + if (scaling_rq(rq)) + continue; + dl = p->deadline << locality_diff(p, rq); + } else + dl = p->deadline; + + if (deadline_before(dl, earliest_deadline)) { + earliest_deadline = dl; + edt = p; + } + } + } while (!edt); + +out_take: + take_task(cpu, edt); + return edt; +} + + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + if (oops_in_progress) + return; + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + + debug_show_held_locks(prev); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ +#ifdef CONFIG_SCHED_STACK_END_CHECK + BUG_ON(unlikely(task_stack_end_corrupted(prev))); +#endif + /* + * Test if we are atomic. Since do_exit() needs to call into + * schedule() atomically, we ignore that path. Otherwise whine + * if we are scheduling when we should not. + */ + if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD)) + __schedule_bug(prev); + rcu_sleep_check(); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +} + +/* + * The currently running task's information is all stored in rq local data + * which is only modified by the local CPU, thereby allowing the data to be + * changed without grabbing the grq lock. + */ +static inline void set_rq_task(struct rq *rq, struct task_struct *p) +{ + rq->rq_time_slice = p->time_slice; + rq->rq_deadline = p->deadline; + rq->rq_last_ran = p->last_ran = rq->clock_task; + rq->rq_policy = p->policy; + rq->rq_prio = p->prio; +#ifdef CONFIG_SMT_NICE + rq->rq_mm = p->mm; + rq->rq_smt_bias = p->smt_bias; +#endif + if (p != rq->idle) + rq->rq_running = true; + else + rq->rq_running = false; +} + +static void reset_rq_task(struct rq *rq, struct task_struct *p) +{ + rq->rq_policy = p->policy; + rq->rq_prio = p->prio; +#ifdef CONFIG_SMT_NICE + rq->rq_smt_bias = p->smt_bias; +#endif +} + +#ifdef CONFIG_SMT_NICE +/* Iterate over smt siblings when we've scheduled a process on cpu and decide + * whether they should continue running or be descheduled. */ +static void check_smt_siblings(int cpu) +{ + int other_cpu; + + for_each_cpu(other_cpu, thread_cpumask(cpu)) { + struct task_struct *p; + struct rq *rq; + + if (other_cpu == cpu) + continue; + rq = cpu_rq(other_cpu); + if (rq_idle(rq)) + continue; + if (!rq->online) + continue; + p = rq->curr; + if (!smt_should_schedule(p, cpu)) { + set_tsk_need_resched(p); + smp_send_reschedule(other_cpu); + } + } +} + +static void wake_smt_siblings(int cpu) +{ + int other_cpu; + + if (!queued_notrunning()) + return; + + for_each_cpu(other_cpu, thread_cpumask(cpu)) { + struct rq *rq; + + if (other_cpu == cpu) + continue; + rq = cpu_rq(other_cpu); + if (rq_idle(rq)) { + struct task_struct *p = rq->curr; + + set_tsk_need_resched(p); + smp_send_reschedule(other_cpu); + } + } +} +#else +static void check_smt_siblings(int __maybe_unused cpu) {} +static void wake_smt_siblings(int __maybe_unused cpu) {} +#endif + +/* + * schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space + * + * WARNING: all callers must re-check need_resched() afterward and reschedule + * accordingly in case an event triggered the need for rescheduling (such as + * an interrupt waking up a task) while preemption was disabled in __schedule(). + */ +static void __sched __schedule(void) +{ + struct task_struct *prev, *next, *idle; + unsigned long *switch_count; + bool deactivate = false; + struct rq *rq; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + rcu_note_context_switch(); + prev = rq->curr; + + schedule_debug(prev); + + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); + grq_lock_irq(); + + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) { + prev->state = TASK_RUNNING; + } else { + deactivate = true; + prev->on_rq = 0; + + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) { + /* This shouldn't happen, but does */ + if (unlikely(to_wakeup == prev)) + deactivate = false; + else + try_to_wake_up_local(to_wakeup); + } + } + } + switch_count = &prev->nvcsw; + } + + update_clocks(rq); + update_cpu_clock_switch(rq, prev); + if (rq->clock - rq->last_tick > HALF_JIFFY_NS) + rq->dither = false; + else + rq->dither = true; + + clear_tsk_need_resched(prev); + clear_preempt_need_resched(); + + idle = rq->idle; + if (idle != prev) { + /* Update all the information stored on struct rq */ + prev->time_slice = rq->rq_time_slice; + prev->deadline = rq->rq_deadline; + check_deadline(prev); + prev->last_ran = rq->clock_task; + + /* Task changed affinity off this CPU */ + if (likely(!needs_other_cpu(prev, cpu))) { + if (!deactivate) { + if (!queued_notrunning()) { + /* + * We now know prev is the only thing that is + * awaiting CPU so we can bypass rechecking for + * the earliest deadline task and just run it + * again. + */ + set_rq_task(rq, prev); + check_smt_siblings(cpu); + grq_unlock_irq(); + goto rerun_prev_unlocked; + } else + swap_sticky(rq, cpu, prev); + } + } + return_task(prev, rq, deactivate); + } + + if (unlikely(!queued_notrunning())) { + /* + * This CPU is now truly idle as opposed to when idle is + * scheduled as a high priority task in its own right. + */ + next = idle; + schedstat_inc(rq, sched_goidle); + set_cpuidle_map(cpu); + } else { + next = earliest_deadline_task(rq, cpu, idle); + if (likely(next->prio != PRIO_LIMIT)) + clear_cpuidle_map(cpu); + else + set_cpuidle_map(cpu); + } + + if (likely(prev != next)) { + /* + * Don't reschedule an idle task or deactivated tasks + */ + if (prev != idle && !deactivate) + resched_suitable_idle(prev); + /* + * Don't stick tasks when a real time task is going to run as + * they may literally get stuck. + */ + if (rt_task(next)) + unstick_task(rq, prev); + set_rq_task(rq, next); + if (next != idle) + check_smt_siblings(cpu); + else + wake_smt_siblings(cpu); + grq.nr_switches++; + prev->on_cpu = false; + next->on_cpu = true; + rq->curr = next; + ++*switch_count; + + rq = context_switch(rq, prev, next); /* unlocks the grq */ + cpu = cpu_of(rq); + idle = rq->idle; + } else { + check_smt_siblings(cpu); + grq_unlock_irq(); + } + +rerun_prev_unlocked: + sched_preempt_enable_no_resched(); +} + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state || tsk_is_pi_blocked(tsk)) + return; + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + do { + __schedule(); + } while (need_resched()); +} + +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + * + * NB: There are buggy callers of this function. Ideally we + * should warn if prev_state != IN_USER, but that will trigger + * too frequently to make sense yet. + */ + enum ctx_state prev_state = exception_enter(); + schedule(); + exception_exit(prev_state); +} +#endif + +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +static void __sched notrace preempt_schedule_common(void) +{ + do { + __preempt_count_add(PREEMPT_ACTIVE); + __schedule(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} + +#ifdef CONFIG_PREEMPT +/* + * this is the entry point to schedule() from in-kernel preemption + * off of preempt_enable. Kernel preemptions off return from interrupt + * occur there and call schedule directly. + */ +asmlinkage __visible void __sched notrace preempt_schedule(void) +{ + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(!preemptible())) + return; + + preempt_schedule_common(); +} +NOKPROBE_SYMBOL(preempt_schedule); +EXPORT_SYMBOL(preempt_schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +asmlinkage __visible void __sched notrace preempt_schedule_context(void) +{ + enum ctx_state prev_ctx; + + if (likely(!preemptible())) + return; + + do { + __preempt_count_add(PREEMPT_ACTIVE); + /* + * Needs preempt disabled in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + prev_ctx = exception_enter(); + __schedule(); + exception_exit(prev_ctx); + + __preempt_count_sub(PREEMPT_ACTIVE); + barrier(); + } while (need_resched()); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif /* CONFIG_PREEMPT */ + +/* + * this is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage __visible void __sched preempt_schedule_irq(void) +{ + enum ctx_state prev_state; + + /* Catch callers which need to be fixed */ + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); + + do { + __preempt_count_add(PREEMPT_ACTIVE); + local_irq_enable(); + schedule(); + local_irq_disable(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); + + exception_exit(prev_state); +} + +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, + void *key) +{ + return try_to_wake_up(curr->private, mode, wake_flags); +} +EXPORT_SYMBOL(default_wake_function); + +#ifdef CONFIG_RT_MUTEXES + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task + * @prio: prio value (kernel-internal form) + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + unsigned long flags; + int queued, oldprio; + struct rq *rq; + + BUG_ON(prio < 0 || prio > MAX_PRIO); + + rq = task_grq_lock(p, &flags); + + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + + trace_sched_pi_setprio(p, prio); + oldprio = p->prio; + queued = task_queued(p); + if (queued) + dequeue_task(p); + p->prio = prio; + if (task_running(p) && prio > oldprio) + resched_task(p); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + +out_unlock: + task_grq_unlock(&flags); +} + +#endif + +/* + * Adjust the deadline for when the priority is to change, before it's + * changed. + */ +static inline void adjust_deadline(struct task_struct *p, int new_prio) +{ + p->deadline += static_deadline_diff(new_prio) - task_deadline_diff(p); +} + +void set_user_nice(struct task_struct *p, long nice) +{ + int queued, new_static, old_static; + unsigned long flags; + struct rq *rq; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + new_static = NICE_TO_PRIO(nice); + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = time_task_grq_lock(p, &flags); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * not SCHED_NORMAL/SCHED_BATCH: + */ + if (has_rt_policy(p)) { + p->static_prio = new_static; + goto out_unlock; + } + queued = task_queued(p); + if (queued) + dequeue_task(p); + + adjust_deadline(p, new_static); + old_static = p->static_prio; + p->static_prio = new_static; + p->prio = effective_prio(p); + + if (queued) { + enqueue_task(p, rq); + if (new_static < old_static) + try_preempt(p, rq); + } else if (task_running(p)) { + reset_rq_task(rq, p); + if (old_static < new_static) + resched_task(p); + } +out_unlock: + task_grq_unlock(&flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * Return: The priority value as seen by users in /proc. + * RT tasks are offset by -100. Normal tasks are centered around 1, value goes + * from 0 (SCHED_ISO) up to 82 (nice +19 SCHED_IDLEPRIO). + */ +int task_prio(const struct task_struct *p) +{ + int delta, prio = p->prio - MAX_RT_PRIO; + + /* rt tasks and iso tasks */ + if (prio <= 0) + goto out; + + /* Convert to ms to avoid overflows */ + delta = NS_TO_MS(p->deadline - grq.niffies); + delta = delta * 40 / ms_longest_deadline_diff(); + if (delta > 0 && delta <= 80) + prio += delta; + if (idleprio_task(p)) + prio += 40; +out: + return prio; +} + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int idle_cpu(int cpu) +{ + return cpu_curr(cpu) == cpu_rq(cpu)->idle; +} + +/** + * idle_task - return the idle task for a given cpu. + * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. + */ +static inline struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* Actually do priority change: must hold grq lock. */ +static void __setscheduler(struct task_struct *p, struct rq *rq, int policy, + int prio, bool keep_boost) +{ + int oldrtprio, oldprio; + + p->policy = policy; + oldrtprio = p->rt_priority; + p->rt_priority = prio; + p->normal_prio = normal_prio(p); + oldprio = p->prio; + /* + * Keep a potential priority boosting if called from + * sched_setscheduler(). + */ + if (keep_boost) + p->prio = rt_mutex_get_effective_prio(p, p->normal_prio); + else + p->prio = p->normal_prio; + if (task_running(p)) { + reset_rq_task(rq, p); + /* Resched only if we might now be preempted */ + if (p->prio > oldprio || p->rt_priority > oldrtprio) + resched_task(p); + } +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); + rcu_read_unlock(); + return match; +} + +static int __sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool user) +{ + struct sched_param zero_param = { .sched_priority = 0 }; + int queued, retval, oldpolicy = -1; + unsigned long flags, rlim_rtprio = 0; + int reset_on_fork; + struct rq *rq; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); + + if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) { + unsigned long lflags; + + if (!lock_task_sighand(p, &lflags)) + return -ESRCH; + rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); + unlock_task_sighand(p, &lflags); + if (rlim_rtprio) + goto recheck; + /* + * If the caller requested an RT policy without having the + * necessary rights, we downgrade the policy to SCHED_ISO. + * We also set the parameter to zero to pass the checks. + */ + policy = SCHED_ISO; + param = &zero_param; + } +recheck: + /* double check policy once rq lock held */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); + policy &= ~SCHED_RESET_ON_FORK; + + if (!SCHED_RANGE(policy)) + return -EINVAL; + } + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and + * SCHED_BATCH is 0. + */ + if (param->sched_priority < 0 || + (p->mm && param->sched_priority > MAX_USER_RT_PRIO - 1) || + (!p->mm && param->sched_priority > MAX_RT_PRIO - 1)) + return -EINVAL; + if (is_rt_policy(policy) != (param->sched_priority != 0)) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (is_rt_policy(policy)) { + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); + + /* can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* can't increase priority */ + if (param->sched_priority > p->rt_priority && + param->sched_priority > rlim_rtprio) + return -EPERM; + } else { + switch (p->policy) { + /* + * Can only downgrade policies but not back to + * SCHED_NORMAL + */ + case SCHED_ISO: + if (policy == SCHED_ISO) + goto out; + if (policy == SCHED_NORMAL) + return -EPERM; + break; + case SCHED_BATCH: + if (policy == SCHED_BATCH) + goto out; + if (policy != SCHED_IDLEPRIO) + return -EPERM; + break; + case SCHED_IDLEPRIO: + if (policy == SCHED_IDLEPRIO) + goto out; + return -EPERM; + default: + break; + } + } + + /* can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) + return -EPERM; + } + + if (user) { + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + /* + * To be able to change p->policy safely, the grunqueue lock must be + * held. + */ + rq = __task_grq_lock(p); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return -EINVAL; + } + + /* + * If not changing anything there's no need to proceed further: + */ + if (unlikely(policy == p->policy && (!is_rt_policy(policy) || + param->sched_priority == p->rt_priority))) { + + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return 0; + } + + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + goto recheck; + } + update_clocks(rq); + p->sched_reset_on_fork = reset_on_fork; + + queued = task_queued(p); + if (queued) + dequeue_task(p); + __setscheduler(p, rq, policy, param->sched_priority, true); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + rt_mutex_adjust_pi(p); +out: + return 0; +} + +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, true); +} + +EXPORT_SYMBOL_GPL(sched_setscheduler); + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + const struct sched_param param = { .sched_priority = attr->sched_priority }; + int policy = attr->sched_policy; + + return __sched_setscheduler(p, policy, ¶m, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, false); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setscheduler(p, policy, &lparam); + rcu_read_unlock(); + + return retval; +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, + struct sched_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + /* + * XXX: do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, -20, 19); + + /* sched/core.c uses zero here but we already know ret is zero */ + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * + * Return: 0 on success. An error code otherwise. + * @param: structure containing the new RT priority. + */ +asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, + struct sched_param __user *param) +{ + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval = -EINVAL; + + if (pid < 0) + goto out_nounlock; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy; + } + rcu_read_unlock(); + +out_nounlock: + return retval; +} + +/** + * sys_sched_getscheduler - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval = -EINVAL; + + if (!param || pid < 0) + goto out_nounlock; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + if (has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + rcu_read_unlock(); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + +out_nounlock: + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static int sched_read_attr(struct sched_attr __user *uattr, + struct sched_attr *attr, + unsigned int usize) +{ + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, usize)) + return -EFAULT; + + /* + * If we're handed a smaller struct than we know of, + * ensure all the unknown bits are 0 - i.e. old + * user-space does not get uncomplete information. + */ + if (usize < sizeof(*attr)) { + unsigned char *addr; + unsigned char *end; + + addr = (void *)attr + usize; + end = (void *)attr + sizeof(*attr); + + for (; addr < end; addr++) { + if (*addr) + return -EFBIG; + } + + attr->size = usize; + } + + ret = copy_to_user(uattr, attr, attr->size); + if (ret) + return -EFAULT; + + /* sched/core.c uses zero here but we already know ret is zero */ + return ret; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || size > PAGE_SIZE || + size < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + attr.sched_policy = p->policy; + if (rt_task(p)) + attr.sched_priority = p->rt_priority; + else + attr.sched_nice = task_nice(p); + + rcu_read_unlock(); + + retval = sched_read_attr(uattr, &attr, size); + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + get_online_cpus(); + rcu_read_lock(); + + p = find_process_by_pid(pid); + if (!p) { + rcu_read_unlock(); + put_online_cpus(); + return -ESRCH; + } + + /* Prevent p going away */ + get_task_struct(p); + rcu_read_unlock(); + + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_unlock; + } + rcu_read_unlock(); + } + + retval = security_task_setscheduler(p); + if (retval) + goto out_unlock; + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); +again: + retval = set_cpus_allowed_ptr(p, new_mask); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_unlock: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + put_task_struct(p); + put_online_cpus(); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + cpumask_t *new_mask) +{ + if (len < sizeof(cpumask_t)) { + memset(new_mask, 0, sizeof(cpumask_t)); + } else if (len > sizeof(cpumask_t)) { + len = sizeof(cpumask_t); + } + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + + +/** + * sys_sched_setaffinity - set the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, cpumask_t *mask) +{ + struct task_struct *p; + unsigned long flags; + int retval; + + get_online_cpus(); + rcu_read_lock(); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + grq_lock_irqsave(&flags); + cpumask_and(mask, tsk_cpus_allowed(p), cpu_active_mask); + grq_unlock_irqrestore(&flags); + +out_unlock: + rcu_read_unlock(); + put_online_cpus(); + + return retval; +} + +/** + * sys_sched_getaffinity - get the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. It does this by + * scheduling away the current task. If it still has the earliest deadline + * it will be scheduled again as the next task. + * + * Return: 0. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct task_struct *p; + + p = current; + grq_lock_irq(); + schedstat_inc(task_rq(p), yld_count); + requeue_task(p); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(grq.lock); + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); + do_raw_spin_unlock(&grq.lock); + sched_preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +int __sched _cond_resched(void) +{ + if (should_resched()) { + preempt_schedule_common(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(_cond_resched); + +/* + * __cond_resched_lock() - if a reschedule is pending, drop the given lock, + * call schedule, and on return reacquire the lock. + * + * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * operations here to prevent schedule() from being called twice (once via + * spin_unlock(), once by hand). + */ +int __cond_resched_lock(spinlock_t *lock) +{ + int resched = should_resched(); + int ret = 0; + + lockdep_assert_held(lock); + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched) + preempt_schedule_common(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_lock); + +int __sched __cond_resched_softirq(void) +{ + BUG_ON(!in_softirq()); + + if (should_resched()) { + local_bh_enable(); + preempt_schedule_common(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(__cond_resched_softirq); + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + struct rq *rq, *p_rq; + unsigned long flags; + int yielded = 0; + + rq = this_rq(); + grq_lock_irqsave(&flags); + if (task_running(p) || p->state) { + yielded = -ESRCH; + goto out_unlock; + } + + p_rq = task_rq(p); + yielded = 1; + if (p->deadline > rq->rq_deadline) + p->deadline = rq->rq_deadline; + p->time_slice += rq->rq_time_slice; + rq->rq_time_slice = 0; + if (p->time_slice > timeslice()) + p->time_slice = timeslice(); + if (preempt && rq != p_rq) + resched_curr(p_rq); +out_unlock: + grq_unlock_irqrestore(&flags); + + if (yielded > 0) + schedule(); + return yielded; +} +EXPORT_SYMBOL_GPL(yield_to); + +/* + * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * that process accounting knows that this is a task in IO wait state. + * + * But don't do that if it is a deliberate, throttling IO wait (this task + * has set its backing_dev_info: the queue against which it should throttle) + */ + +long __sched io_schedule_timeout(long timeout) +{ + int old_iowait = current->in_iowait; + struct rq *rq; + long ret; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + delayacct_blkio_start(); + rq = raw_rq(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + current->in_iowait = old_iowait; + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + + return ret; +} +EXPORT_SYMBOL(io_schedule_timeout); + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_ISO: + case SCHED_IDLEPRIO: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_ISO: + case SCHED_IDLEPRIO: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + unsigned int time_slice; + unsigned long flags; + int retval; + struct timespec t; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + grq_lock_irqsave(&flags); + time_slice = p->policy == SCHED_FIFO ? 0 : MS_TO_NS(task_timeslice(p)); + grq_unlock_irqrestore(&flags); + + rcu_read_unlock(); + t = ns_to_timespec(time_slice); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + int ppid; + unsigned long state = p->state; + + if (state) + state = __ffs(state) + 1; + printk(KERN_INFO "%-15.15s %c", p->comm, + state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); +#if BITS_PER_LONG == 32 + if (state == TASK_RUNNING) + printk(KERN_CONT " running "); + else + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); +#else + if (state == TASK_RUNNING) + printk(KERN_CONT " running task "); + else + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); +#endif +#ifdef CONFIG_DEBUG_STACK_USAGE + free = stack_not_used(p); +#endif + ppid = 0; + rcu_read_lock(); + if (pid_alive(p)) + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), ppid, + (unsigned long)task_thread_info(p)->flags); + + print_worker_info(KERN_INFO, p); + show_stack(p, NULL); +} + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take a lot of time: + */ + touch_nmi_watchdog(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } + + touch_all_softlockup_watchdogs(); + + rcu_read_unlock(); + /* + * Only show locks if all tasks are dumped: + */ + if (!state_filter) + debug_show_all_locks(); +} + +void dump_cpu_task(int cpu) +{ + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); +} + +#ifdef CONFIG_SMP +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + cpumask_copy(tsk_cpus_allowed(p), new_mask); +} +#endif + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + time_grq_lock(rq, &flags); + idle->last_ran = rq->clock_task; + idle->state = TASK_RUNNING; + /* Setting prio to illegal value shouldn't matter when never queued */ + idle->prio = PRIO_LIMIT; +#ifdef CONFIG_SMT_NICE + idle->smt_bias = 0; +#endif + set_rq_task(rq, idle); + do_set_cpus_allowed(idle, get_cpu_mask(cpu)); + /* Silence PROVE_RCU */ + rcu_read_lock(); + set_task_cpu(idle, cpu); + rcu_read_unlock(); + rq->curr = rq->idle = idle; + idle->on_cpu = 1; + grq_unlock_irqrestore(&flags); + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); + + ftrace_graph_init_idle_task(idle, cpu); +#if defined(CONFIG_SMP) + sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); +#endif +} + +int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur, + const struct cpumask __maybe_unused *trial) +{ + return 1; +} + +int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed) +{ + int ret = 0; + + /* + * Kthreads which disallow setaffinity shouldn't be moved + * to a new cpuset; we don't want to change their cpu + * affinity and isolating such threads by their set of + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks + * before cpus_allowed may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) + ret = -EINVAL; + + return ret; +} + +void resched_cpu(int cpu) +{ + unsigned long flags; + + grq_lock_irqsave(&flags); + resched_task(cpu_curr(cpu)); + grq_unlock_irqrestore(&flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ_COMMON +void nohz_balance_enter_idle(int cpu) +{ +} + +void select_nohz_load_balancer(int stop_tick) +{ +} + +void set_cpu_sd_state_idle(void) {} +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * lowest_flag_domain - Return lowest sched_domain containing flag. + * @cpu: The cpu whose lowest level of sched domain is to + * be returned. + * @flag: The flag to check for the lowest sched_domain + * for the given cpu. + * + * Returns the lowest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) + if (sd && (sd->flags & flag)) + break; + + return sd; +} + +/** + * for_each_flag_domain - Iterates over sched_domains containing the flag. + * @cpu: The cpu whose domains we're iterating over. + * @sd: variable holding the value of the power_savings_sd + * for cpu. + * @flag: The flag to filter the sched_domains to be iterated. + * + * Iterates over all the scheduler domains for a given cpu that has the 'flag' + * set, starting from the lowest sched_domain to the highest. + */ +#define for_each_flag_domain(cpu, sd, flag) \ + for (sd = lowest_flag_domain(cpu, flag); \ + (sd && (sd->flags & flag)); sd = sd->parent) + +#endif /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ + +/* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(int pinned) +{ + int cpu = smp_processor_id(); + int i; + struct sched_domain *sd; + + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + return cpu; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) { + if (!idle_cpu(i)) { + cpu = i; + goto unlock; + } + } + } +unlock: + rcu_read_unlock(); + return cpu; +} + +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +void wake_up_idle_cpu(int cpu) +{ + if (cpu == smp_processor_id()) + return; + + set_tsk_need_resched(cpu_rq(cpu)->idle); + smp_send_reschedule(cpu); +} + +void wake_up_nohz_cpu(int cpu) +{ + wake_up_idle_cpu(cpu); +} +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + bool running_wrong = false; + bool queued = false; + unsigned long flags; + struct rq *rq; + int ret = 0; + + rq = task_grq_lock(p, &flags); + + if (cpumask_equal(tsk_cpus_allowed(p), new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { + ret = -EINVAL; + goto out; + } + + queued = task_queued(p); + + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + if (task_running(p)) { + /* Task is running on the wrong cpu now, reschedule it. */ + if (rq == this_rq()) { + set_tsk_need_resched(p); + running_wrong = true; + } else + resched_task(p); + } else + set_task_cpu(p, cpumask_any_and(cpu_active_mask, new_mask)); + +out: + if (queued) + try_preempt(p, rq); + task_grq_unlock(&flags); + + if (running_wrong) + preempt_schedule_common(); + + return ret; +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +#ifdef CONFIG_HOTPLUG_CPU +extern struct task_struct *cpu_stopper_task; +/* Run through task list and find tasks affined to the dead cpu, then remove + * that cpu from the list, enable cpu0 and set the zerobound flag. */ +static void bind_zero(int src_cpu) +{ + struct task_struct *p, *t, *stopper; + int bound = 0; + + if (src_cpu == 0) + return; + + stopper = per_cpu(cpu_stopper_task, src_cpu); + do_each_thread(t, p) { + if (p != stopper && cpumask_test_cpu(src_cpu, tsk_cpus_allowed(p))) { + cpumask_clear_cpu(src_cpu, tsk_cpus_allowed(p)); + cpumask_set_cpu(0, tsk_cpus_allowed(p)); + p->zerobound = true; + bound++; + } + clear_sticky(p); + } while_each_thread(t, p); + + if (bound) { + printk(KERN_INFO "Removed affinity for %d processes to cpu %d\n", + bound, src_cpu); + } +} + +/* Find processes with the zerobound flag and reenable their affinity for the + * CPU coming alive. */ +static void unbind_zero(int src_cpu) +{ + int unbound = 0, zerobound = 0; + struct task_struct *p, *t; + + if (src_cpu == 0) + return; + + do_each_thread(t, p) { + if (!p->mm) + p->zerobound = false; + if (p->zerobound) { + unbound++; + cpumask_set_cpu(src_cpu, tsk_cpus_allowed(p)); + /* Once every CPU affinity has been re-enabled, remove + * the zerobound flag */ + if (cpumask_subset(cpu_possible_mask, tsk_cpus_allowed(p))) { + p->zerobound = false; + zerobound++; + } + } + } while_each_thread(t, p); + + if (unbound) { + printk(KERN_INFO "Added affinity for %d processes to cpu %d\n", + unbound, src_cpu); + } + if (zerobound) { + printk(KERN_INFO "Released forced binding to cpu0 for %d processes\n", + zerobound); + } +} + +/* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) { + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } + mmdrop(mm); +} +#else /* CONFIG_HOTPLUG_CPU */ +static void unbind_zero(int src_cpu) {} +#endif /* CONFIG_HOTPLUG_CPU */ + +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param stop_param = { .sched_priority = STOP_PRIO }; + struct sched_param start_param = { .sched_priority = 0 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param); + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling policy so that + * it can die in pieces. + */ + sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param); + } +} + + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + mode_t mode, proc_handler *proc_handler) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +static void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +static void unregister_sched_domain_sysctl(void) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#else +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + cpumask_set_cpu(cpu_of(rq), rq->rd->online); + rq->online = true; + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + cpumask_clear_cpu(cpu_of(rq), rq->rd->online); + rq->online = false; + } +} + +/* + * migration_call - callback that gets triggered when a CPU is added. + */ +static int +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + unsigned long flags; + struct rq *rq = cpu_rq(cpu); +#ifdef CONFIG_HOTPLUG_CPU + struct task_struct *idle = rq->idle; +#endif + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + return NOTIFY_OK; + case CPU_UP_PREPARE: + break; + + case CPU_ONLINE: + /* Update our root-domain */ + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + + set_rq_online(rq); + } + unbind_zero(cpu); + grq.noc = num_online_cpus(); + grq_unlock_irqrestore(&flags); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + grq_lock_irq(); + set_rq_task(rq, idle); + update_clocks(rq); + grq_unlock_irq(); + break; + + case CPU_DYING: + /* Update our root-domain */ + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + bind_zero(cpu); + grq.noc = num_online_cpus(); + grq_unlock_irqrestore(&flags); + break; +#endif + } + return NOTIFY_OK; +} + +/* + * Register at high priority so that task migration (migrate_all_tasks) + * happens before everything else. This has to be lower priority than + * the notifier in the perf_counter subsystem, though. + */ +static struct notifier_block migration_notifier = { + .notifier_call = migration_call, + .priority = CPU_PRI_MIGRATION, +}; + +static int sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +int __init migration_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + /* Initialise migration for the boot CPU */ + err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); + BUG_ON(err == NOTIFY_BAD); + migration_call(&migration_notifier, CPU_ONLINE, cpu); + register_cpu_notifier(&migration_notifier); + + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + + return 0; +} +early_initcall(migration_init); +#endif + +#ifdef CONFIG_SMP + +static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + cpumask_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + grq_lock_irqsave(&flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + grq_unlock_irqrestore(&flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_online; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_rto_mask; + return 0; + +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +static void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent, cpu); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp, cpu); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); +} + +/* cpus with isolated domains */ +cpumask_var_t cpu_isolated_map; + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + alloc_bootmem_cpumask_var(&cpu_isolated_map); + cpulist_parse(str, cpu_isolated_map); + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* turn off idle balance on this domain */ + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); /* fall through */ + case sa_sd: + free_percpu(d->sd); /* fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); /* fall through */ + case sa_none: + break; + } +} + +static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, + const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain + * structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +static int *sched_domains_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*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_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; + + return sd; +} + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +static bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int i, j; + int node = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +/* + * Update sched_domains_numa_masks[level][node] array when new cpus + * are onlined. + */ +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + sched_domains_numa_masks_set(cpu); + break; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} +#else +static inline void sched_init_numa(void) +{ +} + +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + return 0; +} +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + } + free_percpu(sdd->sd); + sdd->sd = NULL; + } +} + +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) +{ + struct sched_domain *sd = sd_init(tl, cpu); + if (!sd) + return child; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for cpus specified by the cpu_map. */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Calculate CPU capacity for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d.sd, i); + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +static cpumask_var_t *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +static cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated cpus, but could be used to + * exclude other special cases in the future. + */ +static int init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * Detach sched domains from a group of cpus specified in cpu_map + * These cpus will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* fast path */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur[i]); +match1: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* no match - add a new doms_new */ + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); + kfree(dattr_cur); /* kfree(NULL) is safe */ + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + +/* + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. + */ +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + + case CPU_ONLINE: + cpuset_update_active_cpus(true); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action) { + case CPU_DOWN_PREPARE: + cpuset_update_active_cpus(false); + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) +/* + * Cheaper version of the below functions in case support for SMT and MC is + * compiled in but CPUs have no siblings. + */ +static bool sole_cpu_idle(int cpu) +{ + return rq_idle(cpu_rq(cpu)); +} +#endif +#ifdef CONFIG_SCHED_SMT +static const cpumask_t *thread_cpumask(int cpu) +{ + return topology_thread_cpumask(cpu); +} +/* All this CPU's SMT siblings are idle */ +static bool siblings_cpu_idle(int cpu) +{ + return cpumask_subset(thread_cpumask(cpu), &grq.cpu_idle_map); +} +#endif +#ifdef CONFIG_SCHED_MC +static const cpumask_t *core_cpumask(int cpu) +{ + return topology_core_cpumask(cpu); +} +/* All this CPU's shared cache siblings are idle */ +static bool cache_cpu_idle(int cpu) +{ + return cpumask_subset(core_cpumask(cpu), &grq.cpu_idle_map); +} +#endif + +enum sched_domain_level { + SD_LV_NONE = 0, + SD_LV_SIBLING, + SD_LV_MC, + SD_LV_BOOK, + SD_LV_CPU, + SD_LV_NODE, + SD_LV_ALLNODES, + SD_LV_MAX +}; + +void __init sched_init_smp(void) +{ + struct sched_domain *sd; + int cpu, other_cpu; + + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + + sched_init_numa(); + + /* + * There's no userspace yet to cause hotplug operations; hence all the + * cpu masks are stable and all blatant races in the below code cannot + * happen. + */ + mutex_lock(&sched_domains_mutex); + init_sched_domains(cpu_active_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + + hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + BUG(); + free_cpumask_var(non_isolated_cpus); + + grq_lock_irq(); + /* + * Set up the relative cache distance of each online cpu from each + * other in a simple array for quick lookup. Locality is determined + * by the closest sched_domain that CPUs are separated by. CPUs with + * shared cache in SMT and MC are treated as local. Separate CPUs + * (within the same package or physically) within the same node are + * treated as not local. CPUs not even in the same domain (different + * nodes) are treated as very distant. + */ + for_each_online_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + /* First check if this cpu is in the same node */ + for_each_domain(cpu, sd) { + if (sd->level > SD_LV_NODE) + continue; + /* Set locality to local node if not already found lower */ + for_each_cpu(other_cpu, sched_domain_span(sd)) { + if (rq->cpu_locality[other_cpu] > 3) + rq->cpu_locality[other_cpu] = 3; + } + } + + /* + * Each runqueue has its own function in case it doesn't have + * siblings of its own allowing mixed topologies. + */ +#ifdef CONFIG_SCHED_MC + for_each_cpu(other_cpu, core_cpumask(cpu)) { + if (rq->cpu_locality[other_cpu] > 2) + rq->cpu_locality[other_cpu] = 2; + } + if (cpumask_weight(core_cpumask(cpu)) > 1) + rq->cache_idle = cache_cpu_idle; +#endif +#ifdef CONFIG_SCHED_SMT + for_each_cpu(other_cpu, thread_cpumask(cpu)) + rq->cpu_locality[other_cpu] = 1; + if (cpumask_weight(thread_cpumask(cpu)) > 1) + rq->siblings_idle = siblings_cpu_idle; +#endif + } + grq_unlock_irq(); + + for_each_online_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + for_each_online_cpu(other_cpu) { + if (other_cpu <= cpu) + continue; + printk(KERN_DEBUG "BFS LOCALITY CPU %d to %d: %d\n", cpu, other_cpu, rq->cpu_locality[other_cpu]); + } + } +} +#else +void __init sched_init_smp(void) +{ +} +#endif /* CONFIG_SMP */ + +unsigned int sysctl_timer_migration = 1; + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +void __init sched_init(void) +{ +#ifdef CONFIG_SMP + int cpu_ids; +#endif + int i; + struct rq *rq; + + prio_ratios[0] = 128; + for (i = 1 ; i < NICE_WIDTH ; i++) + prio_ratios[i] = prio_ratios[i - 1] * 11 / 10; + + raw_spin_lock_init(&grq.lock); + grq.nr_running = grq.nr_uninterruptible = grq.nr_switches = 0; + grq.niffies = 0; + grq.last_jiffy = jiffies; + raw_spin_lock_init(&grq.iso_lock); + grq.iso_ticks = 0; + grq.iso_refractory = false; + grq.noc = 1; +#ifdef CONFIG_SMP + init_defrootdomain(); + grq.qnr = grq.idle_cpus = 0; + cpumask_clear(&grq.cpu_idle_map); +#else + uprq = &per_cpu(runqueues, 0); +#endif + for_each_possible_cpu(i) { + rq = cpu_rq(i); + rq->grq_lock = &grq.lock; + rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc = + rq->iowait_pc = rq->idle_pc = 0; + rq->dither = false; +#ifdef CONFIG_SMP + rq->sticky_task = NULL; + rq->last_niffy = 0; + rq->sd = NULL; + rq->rd = NULL; + rq->online = false; + rq->cpu = i; + rq_attach_root(rq, &def_root_domain); +#endif + atomic_set(&rq->nr_iowait, 0); + } + +#ifdef CONFIG_SMP + cpu_ids = i; + /* + * Set the base locality for cpu cache distance calculation to + * "distant" (3). Make sure the distance from a CPU to itself is 0. + */ + for_each_possible_cpu(i) { + int j; + + rq = cpu_rq(i); +#ifdef CONFIG_SCHED_SMT + rq->siblings_idle = sole_cpu_idle; +#endif +#ifdef CONFIG_SCHED_MC + rq->cache_idle = sole_cpu_idle; +#endif + rq->cpu_locality = kmalloc(cpu_ids * sizeof(int *), GFP_ATOMIC); + for_each_possible_cpu(j) { + if (i == j) + rq->cpu_locality[j] = 0; + else + rq->cpu_locality[j] = 4; + } + } +#endif + + for (i = 0; i < PRIO_LIMIT; i++) + INIT_LIST_HEAD(grq.queue + i); + /* delimiter for bitsearch */ + __set_bit(PRIO_LIMIT, grq.prio_bitmap); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + atomic_inc(&init_mm.mm_count); + enter_lazy_tlb(&init_mm, current); + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + +#ifdef CONFIG_SMP + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + idle_thread_set_boot_cpu(); +#endif /* SMP */ +} + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); + + return (nested == preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) +{ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change); + + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; /* ratelimiting */ + + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || + system_state != SYSTEM_RUNNING || oops_in_progress) + return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR + "BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + printk(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); +} +EXPORT_SYMBOL(___might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + int queued; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (!rt_task(p) && !iso_task(p)) + continue; + + rq = task_grq_lock(p, &flags); + queued = task_queued(p); + if (queued) + dequeue_task(p); + __setscheduler(p, rq, SCHED_NORMAL, 0, false); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + + task_grq_unlock(&flags); + } + read_unlock(&tasklist_lock); +} +#endif /* CONFIG_MAGIC_SYSRQ */ + +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +/* + * These functions are only useful for the IA64 MCA handling, or kdb. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given cpu. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 +/** + * set_curr_task - set the current task for a given cpu. + * @cpu: the processor in question. + * @p: the task pointer to set. + * + * Description: This function must only be used when non-maskable interrupts + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a cpu in a non-blocking manner. This function + * must be called with all CPU's synchronised, and interrupts disabled, the + * and caller must save the original value of the current task (see + * curr_task() above) and restore that value before reenabling interrupts and + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} + +void vtime_account_system_irqsafe(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + vtime_account_system(tsk); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe); + +#ifndef __ARCH_HAS_VTIME_TASK_SWITCH +void vtime_task_switch(struct task_struct *prev) +{ + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_system(prev); + + vtime_account_user(prev); + arch_vtime_task_switch(prev); +} +#endif + +#else +/* + * Perform (stime * rtime) / total, but avoid multiplication overflow by + * losing precision when the numbers are big. + */ +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +{ + u64 scaled; + + for (;;) { + /* Make sure "rtime" is the bigger of stime/rtime */ + if (stime > rtime) { + u64 tmp = rtime; rtime = stime; stime = tmp; + } + + /* Make sure 'total' fits in 32 bits */ + if (total >> 32) + goto drop_precision; + + /* Does rtime (and thus stime) fit in 32 bits? */ + if (!(rtime >> 32)) + break; + + /* Can we just balance rtime/stime rather than dropping bits? */ + if (stime >> 31) + goto drop_precision; + + /* We can grow stime and shrink rtime and try to make them both fit */ + stime <<= 1; + rtime >>= 1; + continue; + +drop_precision: + /* We drop from rtime, it has more bits than stime */ + rtime >>= 1; + total >>= 1; + } + + /* + * Make sure gcc understands that this is a 32x32->64 multiply, + * followed by a 64/32->64 divide. + */ + scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); + return (__force cputime_t) scaled; +} + +/* + * Adjust tick based cputime random precision against scheduler + * runtime accounting. + */ +static void cputime_adjust(struct task_cputime *curr, + struct cputime *prev, + cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, stime, utime, total; + + stime = curr->stime; + total = stime + curr->utime; + + /* + * Tick based cputime accounting depend on random scheduling + * timeslices of a task to be interrupted or not by the timer. + * Depending on these circumstances, the number of these interrupts + * may be over or under-optimistic, matching the real user and system + * cputime with a variable precision. + * + * Fix this by scaling these tick based values against the total + * runtime accounted by the CFS scheduler. + */ + rtime = nsecs_to_cputime(curr->sum_exec_runtime); + + /* + * Update userspace visible utime/stime values only if actual execution + * time is bigger than already exported. Note that can happen, that we + * provided bigger values due to scaling inaccuracy on big numbers. + */ + if (prev->stime + prev->utime >= rtime) + goto out; + + if (total) { + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + utime = rtime - stime; + } else { + stime = rtime; + utime = 0; + } + + /* + * If the tick based count grows faster than the scheduler one, + * the result of the scaling may go backward. + * Let's enforce monotonicity. + */ + prev->stime = max(prev->stime, stime); + prev->utime = max(prev->utime, utime); + +out: + *ut = prev->utime; + *st = prev->stime; +} + +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime = { + .sum_exec_runtime = tsk_seruntime(p), + }; + + task_cputime(p, &cputime.utime, &cputime.stime); + cputime_adjust(&cputime, &p->prev_cputime, ut, st); +} + +/* + * Must be called with siglock held. + */ +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); +} +#endif + +void init_idle_bootup_task(struct task_struct *idle) +{} + +#ifdef CONFIG_SCHED_DEBUG +void proc_sched_show_task(struct task_struct *p, struct seq_file *m) +{} + +void proc_sched_set_task(struct task_struct *p) +{} +#endif + +#ifdef CONFIG_SMP +#define SCHED_LOAD_SHIFT (10) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return SCHED_LOAD_SCALE; +} + +unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long smt_gain = sd->smt_gain; + + smt_gain /= weight; + + return smt_gain; +} +#endif diff --git a/kernel/sched/bfs_sched.h b/kernel/sched/bfs_sched.h new file mode 100644 index 000000000..876969fff --- /dev/null +++ b/kernel/sched/bfs_sched.h @@ -0,0 +1,172 @@ +#include <linux/sched.h> +#include <linux/cpuidle.h> + +#ifndef BFS_SCHED_H +#define BFS_SCHED_H + +/* + * This is the main, per-CPU runqueue data structure. + * This data should only be modified by the local cpu. + */ +struct rq { + struct task_struct *curr, *idle, *stop; + struct mm_struct *prev_mm; + + /* Pointer to grq spinlock */ + raw_spinlock_t *grq_lock; + + /* Stored data about rq->curr to work outside grq lock */ + u64 rq_deadline; + unsigned int rq_policy; + int rq_time_slice; + u64 rq_last_ran; + int rq_prio; + bool rq_running; /* There is a task running */ + int soft_affined; /* Running or queued tasks with this set as their rq */ +#ifdef CONFIG_SMT_NICE + struct mm_struct *rq_mm; + int rq_smt_bias; /* Policy/nice level bias across smt siblings */ +#endif + /* Accurate timekeeping data */ + u64 timekeep_clock; + unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc, + iowait_pc, idle_pc; + atomic_t nr_iowait; + +#ifdef CONFIG_SMP + int cpu; /* cpu of this runqueue */ + bool online; + bool scaling; /* This CPU is managed by a scaling CPU freq governor */ + struct task_struct *sticky_task; + + struct root_domain *rd; + struct sched_domain *sd; + int *cpu_locality; /* CPU relative cache distance */ +#ifdef CONFIG_SCHED_SMT + bool (*siblings_idle)(int cpu); + /* See if all smt siblings are idle */ +#endif /* CONFIG_SCHED_SMT */ +#ifdef CONFIG_SCHED_MC + bool (*cache_idle)(int cpu); + /* See if all cache siblings are idle */ +#endif /* CONFIG_SCHED_MC */ + u64 last_niffy; /* Last time this RQ updated grq.niffies */ +#endif /* CONFIG_SMP */ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */ + + u64 clock, old_clock, last_tick; + u64 clock_task; + bool dither; + +#ifdef CONFIG_SCHEDSTATS + + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_switch; + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif +}; + +#ifdef CONFIG_SMP +struct rq *cpu_rq(int cpu); +#endif + +#ifndef CONFIG_SMP +extern struct rq *uprq; +#define cpu_rq(cpu) (uprq) +#define this_rq() (uprq) +#define raw_rq() (uprq) +#define task_rq(p) (uprq) +#define cpu_curr(cpu) ((uprq)->curr) +#else /* CONFIG_SMP */ +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#define this_rq() this_cpu_ptr(&runqueues) +#define raw_rq() raw_cpu_ptr(&runqueues) +#endif /* CONFIG_SMP */ + +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return ACCESS_ONCE(rq->clock); +} + +static inline u64 rq_clock(struct rq *rq) +{ + lockdep_assert_held(rq->grq_lock); + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + lockdep_assert_held(rq->grq_lock); + return rq->clock_task; +} + +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + lockdep_is_held(&sched_domains_mutex)) + +/* + * The domain tree (rq->sd) is protected by RCU's quiescent state transition. + * See detach_destroy_domains: synchronize_sched for details. + * + * The domain tree of any CPU may only be accessed from within + * preempt-disabled sections. + */ +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + +static inline void sched_ttwu_pending(void) { } + +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq; +} + +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif +#endif /* BFS_SCHED_H */ diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c new file mode 100644 index 000000000..c0a205101 --- /dev/null +++ b/kernel/sched/clock.c @@ -0,0 +1,435 @@ +/* + * sched_clock for unstable cpu clocks + * + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * + * Updates and enhancements: + * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com> + * + * Based on code by: + * Ingo Molnar <mingo@redhat.com> + * Guillaume Chazarain <guichaz@gmail.com> + * + * + * What: + * + * cpu_clock(i) provides a fast (execution time) high resolution + * clock with bounded drift between CPUs. The value of cpu_clock(i) + * is monotonic for constant i. The timestamp returned is in nanoseconds. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + * + * There is no strict promise about the base, although it tends to start + * at 0 on boot (but people really shouldn't rely on that). + * + * cpu_clock(i) -- can be used from any context, including NMI. + * local_clock() -- is cpu_clock() on the current cpu. + * + * sched_clock_cpu(i) + * + * How: + * + * The implementation either uses sched_clock() when + * !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the + * sched_clock() is assumed to provide these properties (mostly it means + * the architecture provides a globally synchronized highres time source). + * + * Otherwise it tries to create a semi stable clock from a mixture of other + * clocks, including: + * + * - GTOD (clock monotomic) + * - sched_clock() + * - explicit idle events + * + * We use GTOD as base and use sched_clock() deltas to improve resolution. The + * deltas are filtered to provide monotonicity and keeping it within an + * expected window. + * + * Furthermore, explicit sleep and wakeup hooks allow us to account for time + * that is otherwise invisible (TSC gets stopped). + * + */ +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/export.h> +#include <linux/percpu.h> +#include <linux/ktime.h> +#include <linux/sched.h> +#include <linux/static_key.h> +#include <linux/workqueue.h> +#include <linux/compiler.h> + +/* + * Scheduler clock - returns current time in nanosec units. + * This is default implementation. + * Architectures and sub-architectures can override this. + */ +unsigned long long __weak sched_clock(void) +{ + return (unsigned long long)(jiffies - INITIAL_JIFFIES) + * (NSEC_PER_SEC / HZ); +} +EXPORT_SYMBOL_GPL(sched_clock); + +__read_mostly int sched_clock_running; + +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static struct static_key __sched_clock_stable = STATIC_KEY_INIT; +static int __sched_clock_stable_early; + +int sched_clock_stable(void) +{ + return static_key_false(&__sched_clock_stable); +} + +static void __set_sched_clock_stable(void) +{ + if (!sched_clock_stable()) + static_key_slow_inc(&__sched_clock_stable); +} + +void set_sched_clock_stable(void) +{ + __sched_clock_stable_early = 1; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + __set_sched_clock_stable(); +} + +static void __clear_sched_clock_stable(struct work_struct *work) +{ + /* XXX worry about clock continuity */ + if (sched_clock_stable()) + static_key_slow_dec(&__sched_clock_stable); +} + +static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); + +void clear_sched_clock_stable(void) +{ + __sched_clock_stable_early = 0; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + schedule_work(&sched_clock_work); +} + +struct sched_clock_data { + u64 tick_raw; + u64 tick_gtod; + u64 clock; +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); + +static inline struct sched_clock_data *this_scd(void) +{ + return this_cpu_ptr(&sched_clock_data); +} + +static inline struct sched_clock_data *cpu_sdc(int cpu) +{ + return &per_cpu(sched_clock_data, cpu); +} + +void sched_clock_init(void) +{ + u64 ktime_now = ktime_to_ns(ktime_get()); + int cpu; + + for_each_possible_cpu(cpu) { + struct sched_clock_data *scd = cpu_sdc(cpu); + + scd->tick_raw = 0; + scd->tick_gtod = ktime_now; + scd->clock = ktime_now; + } + + sched_clock_running = 1; + + /* + * Ensure that it is impossible to not do a static_key update. + * + * Either {set,clear}_sched_clock_stable() must see sched_clock_running + * and do the update, or we must see their __sched_clock_stable_early + * and do the update, or both. + */ + smp_mb(); /* matches {set,clear}_sched_clock_stable() */ + + if (__sched_clock_stable_early) + __set_sched_clock_stable(); + else + __clear_sched_clock_stable(NULL); +} + +/* + * min, max except they take wrapping into account + */ + +static inline u64 wrap_min(u64 x, u64 y) +{ + return (s64)(x - y) < 0 ? x : y; +} + +static inline u64 wrap_max(u64 x, u64 y) +{ + return (s64)(x - y) > 0 ? x : y; +} + +/* + * update the percpu scd from the raw @now value + * + * - filter out backward motion + * - use the GTOD tick value to create a window to filter crazy TSC values + */ +static u64 sched_clock_local(struct sched_clock_data *scd) +{ + u64 now, clock, old_clock, min_clock, max_clock; + s64 delta; + +again: + now = sched_clock(); + delta = now - scd->tick_raw; + if (unlikely(delta < 0)) + delta = 0; + + old_clock = scd->clock; + + /* + * scd->clock = clamp(scd->tick_gtod + delta, + * max(scd->tick_gtod, scd->clock), + * scd->tick_gtod + TICK_NSEC); + */ + + clock = scd->tick_gtod + delta; + min_clock = wrap_max(scd->tick_gtod, old_clock); + max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); + + clock = wrap_max(clock, min_clock); + clock = wrap_min(clock, max_clock); + + if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock) + goto again; + + return clock; +} + +static u64 sched_clock_remote(struct sched_clock_data *scd) +{ + struct sched_clock_data *my_scd = this_scd(); + u64 this_clock, remote_clock; + u64 *ptr, old_val, val; + +#if BITS_PER_LONG != 64 +again: + /* + * Careful here: The local and the remote clock values need to + * be read out atomic as we need to compare the values and + * then update either the local or the remote side. So the + * cmpxchg64 below only protects one readout. + * + * We must reread via sched_clock_local() in the retry case on + * 32bit as an NMI could use sched_clock_local() via the + * tracer and hit between the readout of + * the low32bit and the high 32bit portion. + */ + this_clock = sched_clock_local(my_scd); + /* + * We must enforce atomic readout on 32bit, otherwise the + * update on the remote cpu can hit inbetween the readout of + * the low32bit and the high 32bit portion. + */ + remote_clock = cmpxchg64(&scd->clock, 0, 0); +#else + /* + * On 64bit the read of [my]scd->clock is atomic versus the + * update, so we can avoid the above 32bit dance. + */ + sched_clock_local(my_scd); +again: + this_clock = my_scd->clock; + remote_clock = scd->clock; +#endif + + /* + * Use the opportunity that we have both locks + * taken to couple the two clocks: we take the + * larger time as the latest time for both + * runqueues. (this creates monotonic movement) + */ + if (likely((s64)(remote_clock - this_clock) < 0)) { + ptr = &scd->clock; + old_val = remote_clock; + val = this_clock; + } else { + /* + * Should be rare, but possible: + */ + ptr = &my_scd->clock; + old_val = this_clock; + val = remote_clock; + } + + if (cmpxchg64(ptr, old_val, val) != old_val) + goto again; + + return val; +} + +/* + * Similar to cpu_clock(), but requires local IRQs to be disabled. + * + * See cpu_clock(). + */ +u64 sched_clock_cpu(int cpu) +{ + struct sched_clock_data *scd; + u64 clock; + + if (sched_clock_stable()) + return sched_clock(); + + if (unlikely(!sched_clock_running)) + return 0ull; + + preempt_disable_notrace(); + scd = cpu_sdc(cpu); + + if (cpu != smp_processor_id()) + clock = sched_clock_remote(scd); + else + clock = sched_clock_local(scd); + preempt_enable_notrace(); + + return clock; +} + +void sched_clock_tick(void) +{ + struct sched_clock_data *scd; + u64 now, now_gtod; + + if (sched_clock_stable()) + return; + + if (unlikely(!sched_clock_running)) + return; + + WARN_ON_ONCE(!irqs_disabled()); + + scd = this_scd(); + now_gtod = ktime_to_ns(ktime_get()); + now = sched_clock(); + + scd->tick_raw = now; + scd->tick_gtod = now_gtod; + sched_clock_local(scd); +} + +/* + * We are going deep-idle (irqs are disabled): + */ +void sched_clock_idle_sleep_event(void) +{ + sched_clock_cpu(smp_processor_id()); +} +EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); + +/* + * We just idled delta nanoseconds (called with irqs disabled): + */ +void sched_clock_idle_wakeup_event(u64 delta_ns) +{ + if (timekeeping_suspended) + return; + + sched_clock_tick(); + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); + +/* + * As outlined at the top, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +u64 cpu_clock(int cpu) +{ + if (!sched_clock_stable()) + return sched_clock_cpu(cpu); + + return sched_clock(); +} + +/* + * Similar to cpu_clock() for the current cpu. Time will only be observed + * to be monotonic if care is taken to only compare timestampt taken on the + * same CPU. + * + * See cpu_clock(). + */ +u64 local_clock(void) +{ + if (!sched_clock_stable()) + return sched_clock_cpu(raw_smp_processor_id()); + + return sched_clock(); +} + +#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ + +void sched_clock_init(void) +{ + sched_clock_running = 1; +} + +u64 sched_clock_cpu(int cpu) +{ + if (unlikely(!sched_clock_running)) + return 0; + + return sched_clock(); +} + +u64 cpu_clock(int cpu) +{ + return sched_clock(); +} + +u64 local_clock(void) +{ + return sched_clock(); +} + +#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ + +EXPORT_SYMBOL_GPL(cpu_clock); +EXPORT_SYMBOL_GPL(local_clock); + +/* + * Running clock - returns the time that has elapsed while a guest has been + * running. + * On a guest this value should be local_clock minus the time the guest was + * suspended by the hypervisor (for any reason). + * On bare metal this function should return the same as local_clock. + * Architectures and sub-architectures can override this. + */ +u64 __weak running_clock(void) +{ + return local_clock(); +} diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c new file mode 100644 index 000000000..8d0f35deb --- /dev/null +++ b/kernel/sched/completion.c @@ -0,0 +1,317 @@ +/* + * Generic wait-for-completion handler; + * + * It differs from semaphores in that their default case is the opposite, + * wait_for_completion default blocks whereas semaphore default non-block. The + * interface also makes it easy to 'complete' multiple waiting threads, + * something which isn't entirely natural for semaphores. + * + * But more importantly, the primitive documents the usage. Semaphores would + * typically be used for exclusion which gives rise to priority inversion. + * Waiting for completion is a typically sync point, but not an exclusion point. + */ + +#include <linux/sched.h> +#include <linux/completion.h> + +/** + * complete: - signals a single thread waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up a single thread waiting on this completion. Threads will be + * awakened in the same order in which they were queued. + * + * See also complete_all(), wait_for_completion() and related routines. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void complete(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done++; + __wake_up_locked(&x->wait, TASK_NORMAL, 1); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete); + +/** + * complete_all: - signals all threads waiting on this completion + * @x: holds the state of this particular completion + * + * This will wake up all threads waiting on this particular completion event. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void complete_all(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; + __wake_up_locked(&x->wait, TASK_NORMAL, 0); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete_all); + +static inline long __sched +do_wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) +{ + if (!x->done) { + DECLARE_WAITQUEUE(wait, current); + + __add_wait_queue_tail_exclusive(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); + spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); + spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); + __remove_wait_queue(&x->wait, &wait); + if (!x->done) + return timeout; + } + x->done--; + return timeout ?: 1; +} + +static inline long __sched +__wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) +{ + might_sleep(); + + spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); + spin_unlock_irq(&x->wait.lock); + return timeout; +} + +static long __sched +wait_for_common(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, schedule_timeout, timeout, state); +} + +static long __sched +wait_for_common_io(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, io_schedule_timeout, timeout, state); +} + +/** + * wait_for_completion: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. + * + * See also similar routines (i.e. wait_for_completion_timeout()) with timeout + * and interrupt capability. Also see complete(). + */ +void __sched wait_for_completion(struct completion *x) +{ + wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion); + +/** + * wait_for_completion_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. + * + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. + */ +unsigned long __sched +wait_for_completion_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_timeout); + +/** + * wait_for_completion_io: - waits for completion of a task + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It is NOT + * interruptible and there is no timeout. The caller is accounted as waiting + * for IO (which traditionally means blkio only). + */ +void __sched wait_for_completion_io(struct completion *x) +{ + wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io); + +/** + * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. The timeout is in jiffies. It is not + * interruptible. The caller is accounted as waiting for IO (which traditionally + * means blkio only). + * + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. + */ +unsigned long __sched +wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io_timeout); + +/** + * wait_for_completion_interruptible: - waits for completion of a task (w/intr) + * @x: holds the state of this particular completion + * + * This waits for completion of a specific task to be signaled. It is + * interruptible. + * + * Return: -ERESTARTSYS if interrupted, 0 if completed. + */ +int __sched wait_for_completion_interruptible(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_interruptible); + +/** + * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be signaled or for a + * specified timeout to expire. It is interruptible. The timeout is in jiffies. + * + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. + */ +long __sched +wait_for_completion_interruptible_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); + +/** + * wait_for_completion_killable: - waits for completion of a task (killable) + * @x: holds the state of this particular completion + * + * This waits to be signaled for completion of a specific task. It can be + * interrupted by a kill signal. + * + * Return: -ERESTARTSYS if interrupted, 0 if completed. + */ +int __sched wait_for_completion_killable(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_killable); + +/** + * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be + * signaled or for a specified timeout to expire. It can be + * interrupted by a kill signal. The timeout is in jiffies. + * + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. + */ +long __sched +wait_for_completion_killable_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_KILLABLE); +} +EXPORT_SYMBOL(wait_for_completion_killable_timeout); + +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Return: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +bool try_wait_for_completion(struct completion *x) +{ + unsigned long flags; + int ret = 1; + + /* + * Since x->done will need to be locked only + * in the non-blocking case, we check x->done + * first without taking the lock so we can + * return early in the blocking case. + */ + if (!READ_ONCE(x->done)) + return 0; + + spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = 0; + else + x->done--; + spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; +} +EXPORT_SYMBOL(try_wait_for_completion); + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Return: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +bool completion_done(struct completion *x) +{ + if (!READ_ONCE(x->done)) + return false; + + /* + * If ->done, we need to wait for complete() to release ->wait.lock + * otherwise we can end up freeing the completion before complete() + * is done referencing it. + * + * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders + * the loads of ->done and ->wait.lock such that we cannot observe + * the lock before complete() acquires it while observing the ->done + * after it's acquired the lock. + */ + smp_rmb(); + spin_unlock_wait(&x->wait.lock); + return true; +} +EXPORT_SYMBOL(completion_done); diff --git a/kernel/sched/core.c b/kernel/sched/core.c new file mode 100644 index 000000000..123673291 --- /dev/null +++ b/kernel/sched/core.c @@ -0,0 +1,8381 @@ +/* + * kernel/sched/core.c + * + * Kernel scheduler and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and + * make semaphores SMP safe + * 1998-11-19 Implemented schedule_timeout() and related stuff + * by Andrea Arcangeli + * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: + * hybrid priority-list and round-robin design with + * an array-switch method of distributing timeslices + * and per-CPU runqueues. Cleanups and useful suggestions + * by Davide Libenzi, preemptible kernel bits by Robert Love. + * 2003-09-03 Interactivity tuning by Con Kolivas. + * 2004-04-02 Scheduler domains code by Nick Piggin + * 2007-04-15 Work begun on replacing all interactivity tuning with a + * fair scheduling design by Con Kolivas. + * 2007-05-05 Load balancing (smp-nice) and other improvements + * by Peter Williams + * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith + * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri + * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, + * Thomas Gleixner, Mike Kravetz + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/nmi.h> +#include <linux/init.h> +#include <linux/uaccess.h> +#include <linux/highmem.h> +#include <asm/mmu_context.h> +#include <linux/interrupt.h> +#include <linux/capability.h> +#include <linux/completion.h> +#include <linux/kernel_stat.h> +#include <linux/debug_locks.h> +#include <linux/perf_event.h> +#include <linux/security.h> +#include <linux/notifier.h> +#include <linux/profile.h> +#include <linux/freezer.h> +#include <linux/vmalloc.h> +#include <linux/blkdev.h> +#include <linux/delay.h> +#include <linux/pid_namespace.h> +#include <linux/smp.h> +#include <linux/threads.h> +#include <linux/timer.h> +#include <linux/rcupdate.h> +#include <linux/cpu.h> +#include <linux/cpuset.h> +#include <linux/percpu.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/sysctl.h> +#include <linux/syscalls.h> +#include <linux/times.h> +#include <linux/tsacct_kern.h> +#include <linux/kprobes.h> +#include <linux/delayacct.h> +#include <linux/unistd.h> +#include <linux/pagemap.h> +#include <linux/hrtimer.h> +#include <linux/tick.h> +#include <linux/debugfs.h> +#include <linux/ctype.h> +#include <linux/ftrace.h> +#include <linux/slab.h> +#include <linux/init_task.h> +#include <linux/binfmts.h> +#include <linux/context_tracking.h> +#include <linux/compiler.h> + +#include <asm/switch_to.h> +#include <asm/tlb.h> +#include <asm/irq_regs.h> +#include <asm/mutex.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#endif + +#include "sched.h" +#include "../workqueue_internal.h" +#include "../smpboot.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/sched.h> + +void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) +{ + unsigned long delta; + ktime_t soft, hard, now; + + for (;;) { + if (hrtimer_active(period_timer)) + break; + + now = hrtimer_cb_get_time(period_timer); + hrtimer_forward(period_timer, now, period); + + soft = hrtimer_get_softexpires(period_timer); + hard = hrtimer_get_expires(period_timer); + delta = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(period_timer, soft, delta, + HRTIMER_MODE_ABS_PINNED, 0); + } +} + +DEFINE_MUTEX(sched_domains_mutex); +DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +static void update_rq_clock_task(struct rq *rq, s64 delta); + +void update_rq_clock(struct rq *rq) +{ + s64 delta; + + lockdep_assert_held(&rq->lock); + + if (rq->clock_skip_update & RQCF_ACT_SKIP) + return; + + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + +/* + * Debugging: various feature bits + */ + +#define SCHED_FEAT(name, enabled) \ + (1UL << __SCHED_FEAT_##name) * enabled | + +const_debug unsigned int sysctl_sched_features = +#include "features.h" + 0; + +#undef SCHED_FEAT + +#ifdef CONFIG_SCHED_DEBUG +#define SCHED_FEAT(name, enabled) \ + #name , + +static const char * const sched_feat_names[] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static int sched_feat_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); + } + seq_puts(m, "\n"); + + return 0; +} + +#ifdef HAVE_JUMP_LABEL + +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE + +#define SCHED_FEAT(name, enabled) \ + jump_label_key__##enabled , + +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static void sched_feat_disable(int i) +{ + if (static_key_enabled(&sched_feat_keys[i])) + static_key_slow_dec(&sched_feat_keys[i]); +} + +static void sched_feat_enable(int i) +{ + if (!static_key_enabled(&sched_feat_keys[i])) + static_key_slow_inc(&sched_feat_keys[i]); +} +#else +static void sched_feat_disable(int i) { }; +static void sched_feat_enable(int i) { }; +#endif /* HAVE_JUMP_LABEL */ + +static int sched_feat_set(char *cmp) +{ + int i; + int neg = 0; + + if (strncmp(cmp, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); + } + break; + } + } + + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + struct inode *inode; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + mutex_lock(&inode->i_mutex); + i = sched_feat_set(cmp); + mutex_unlock(&inode->i_mutex); + if (i == __SCHED_FEAT_NR) + return -EINVAL; + + *ppos += cnt; + + return cnt; +} + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + +static const struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); +#endif /* CONFIG_SCHED_DEBUG */ + +/* + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ +const_debug unsigned int sysctl_sched_nr_migrate = 32; + +/* + * period over which we average the RT time consumption, measured + * in ms. + * + * default: 1s + */ +const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; + +/* + * period over which we measure -rt task cpu usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +__read_mostly int scheduler_running; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +/* cpus with isolated domains */ +cpumask_var_t cpu_isolated_map; + +/* + * this_rq_lock - lock this runqueue and disable interrupts. + */ +static struct rq *this_rq_lock(void) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + raw_spin_lock(&rq->lock); + + return rq; +} + +#ifdef CONFIG_SCHED_HRTICK +/* + * Use HR-timers to deliver accurate preemption points. + */ + +static void hrtick_clear(struct rq *rq) +{ + if (hrtimer_active(&rq->hrtick_timer)) + hrtimer_cancel(&rq->hrtick_timer); +} + +/* + * High-resolution timer tick. + * Runs from hardirq context with interrupts disabled. + */ +static enum hrtimer_restart hrtick(struct hrtimer *timer) +{ + struct rq *rq = container_of(timer, struct rq, hrtick_timer); + + WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + rq->curr->sched_class->task_tick(rq, rq->curr, 1); + raw_spin_unlock(&rq->lock); + + return HRTIMER_NORESTART; +} + +#ifdef CONFIG_SMP + +static int __hrtick_restart(struct rq *rq) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = hrtimer_get_softexpires(timer); + + return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0); +} + +/* + * called from hardirq (IPI) context + */ +static void __hrtick_start(void *arg) +{ + struct rq *rq = arg; + + raw_spin_lock(&rq->lock); + __hrtick_restart(rq); + rq->hrtick_csd_pending = 0; + raw_spin_unlock(&rq->lock); +} + +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time; + s64 delta; + + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense and can cause timer DoS. + */ + delta = max_t(s64, delay, 10000LL); + time = ktime_add_ns(timer->base->get_time(), delta); + + hrtimer_set_expires(timer, time); + + if (rq == this_rq()) { + __hrtick_restart(rq); + } else if (!rq->hrtick_csd_pending) { + smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); + rq->hrtick_csd_pending = 1; + } +} + +static int +hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (int)(long)hcpu; + + switch (action) { + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + hrtick_clear(cpu_rq(cpu)); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static __init void init_hrtick(void) +{ + hotcpu_notifier(hotplug_hrtick, 0); +} +#else +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +void hrtick_start(struct rq *rq, u64 delay) +{ + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense. Rely on vruntime for fairness. + */ + delay = max_t(u64, delay, 10000LL); + __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static inline void init_hrtick(void) +{ +} +#endif /* CONFIG_SMP */ + +static void init_rq_hrtick(struct rq *rq) +{ +#ifdef CONFIG_SMP + rq->hrtick_csd_pending = 0; + + rq->hrtick_csd.flags = 0; + rq->hrtick_csd.func = __hrtick_start; + rq->hrtick_csd.info = rq; +#endif + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; +} +#else /* CONFIG_SCHED_HRTICK */ +static inline void hrtick_clear(struct rq *rq) +{ +} + +static inline void init_rq_hrtick(struct rq *rq) +{ +} + +static inline void init_hrtick(void) +{ +} +#endif /* CONFIG_SCHED_HRTICK */ + +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif +#endif + +/* + * resched_curr - mark rq's current task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +void resched_curr(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + int cpu; + + lockdep_assert_held(&rq->lock); + + if (test_tsk_need_resched(curr)) + return; + + cpu = cpu_of(rq); + + if (cpu == smp_processor_id()) { + set_tsk_need_resched(curr); + set_preempt_need_resched(); + return; + } + + if (set_nr_and_not_polling(curr)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} + +void resched_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + if (!raw_spin_trylock_irqsave(&rq->lock, flags)) + return; + resched_curr(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ_COMMON +/* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(int pinned) +{ + int cpu = smp_processor_id(); + int i; + struct sched_domain *sd; + + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + return cpu; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) { + if (!idle_cpu(i)) { + cpu = i; + goto unlock; + } + } + } +unlock: + rcu_read_unlock(); + return cpu; +} +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +static void wake_up_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (cpu == smp_processor_id()) + return; + + if (set_nr_and_not_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} + +static bool wake_up_full_nohz_cpu(int cpu) +{ + /* + * We just need the target to call irq_exit() and re-evaluate + * the next tick. The nohz full kick at least implies that. + * If needed we can still optimize that later with an + * empty IRQ. + */ + if (tick_nohz_full_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + tick_nohz_full_kick_cpu(cpu); + return true; + } + + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_full_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); +} + +static inline bool got_nohz_idle_kick(void) +{ + int cpu = smp_processor_id(); + + if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu))) + return false; + + if (idle_cpu(cpu) && !need_resched()) + return true; + + /* + * We can't run Idle Load Balance on this CPU for this time so we + * cancel it and clear NOHZ_BALANCE_KICK + */ + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + return false; +} + +#else /* CONFIG_NO_HZ_COMMON */ + +static inline bool got_nohz_idle_kick(void) +{ + return false; +} + +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + /* + * FIFO realtime policy runs the highest priority task. Other runnable + * tasks are of a lower priority. The scheduler tick does nothing. + */ + if (current->policy == SCHED_FIFO) + return true; + + /* + * Round-robin realtime tasks time slice with other tasks at the same + * realtime priority. Is this task the only one at this priority? + */ + if (current->policy == SCHED_RR) { + struct sched_rt_entity *rt_se = ¤t->rt; + + return rt_se->run_list.prev == rt_se->run_list.next; + } + + /* + * More than one running task need preemption. + * nr_running update is assumed to be visible + * after IPI is sent from wakers. + */ + if (this_rq()->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ + +void sched_avg_update(struct rq *rq) +{ + s64 period = sched_avg_period(); + + while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (rq->age_stamp)); + rq->age_stamp += period; + rq->rt_avg /= 2; + } +} + +#endif /* CONFIG_SMP */ + +#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ + (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH))) +/* + * Iterate task_group tree rooted at *from, calling @down when first entering a + * node and @up when leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. + */ +int walk_tg_tree_from(struct task_group *from, + tg_visitor down, tg_visitor up, void *data) +{ + struct task_group *parent, *child; + int ret; + + parent = from; + +down: + ret = (*down)(parent, data); + if (ret) + goto out; + list_for_each_entry_rcu(child, &parent->children, siblings) { + parent = child; + goto down; + +up: + continue; + } + ret = (*up)(parent, data); + if (ret || parent == from) + goto out; + + child = parent; + parent = parent->parent; + if (parent) + goto up; +out: + return ret; +} + +int tg_nop(struct task_group *tg, void *data) +{ + return 0; +} +#endif + +static void set_load_weight(struct task_struct *p) +{ + int prio = p->static_prio - MAX_RT_PRIO; + struct load_weight *load = &p->se.load; + + /* + * SCHED_IDLE tasks get minimal weight: + */ + if (p->policy == SCHED_IDLE) { + load->weight = scale_load(WEIGHT_IDLEPRIO); + load->inv_weight = WMULT_IDLEPRIO; + return; + } + + load->weight = scale_load(prio_to_weight[prio]); + load->inv_weight = prio_to_wmult[prio]; +} + +static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) +{ + update_rq_clock(rq); + sched_info_queued(rq, p); + p->sched_class->enqueue_task(rq, p, flags); +} + +static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) +{ + update_rq_clock(rq); + sched_info_dequeued(rq, p); + p->sched_class->dequeue_task(rq, p, flags); +} + +void activate_task(struct rq *rq, struct task_struct *p, int flags) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + + enqueue_task(rq, p, flags); +} + +void deactivate_task(struct rq *rq, struct task_struct *p, int flags) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + + dequeue_task(rq, p, flags); +} + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + s64 steal = 0, irq_delta = 0; +#endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + delta -= steal; + } +#endif + + rq->clock_task += delta; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) + sched_rt_avg_update(rq, irq_delta + steal); +#endif +} + +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); + + stop->sched_class = &stop_sched_class; + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling class so that + * it can die in pieces. + */ + old_stop->sched_class = &rt_sched_class; + } +} + +/* + * __normal_prio - return the priority that is based on the static prio + */ +static inline int __normal_prio(struct task_struct *p) +{ + return p->static_prio; +} + +/* + * Calculate the expected normal priority: i.e. priority + * without taking RT-inheritance into account. Might be + * boosted by interactivity modifiers. Changes upon fork, + * setprio syscalls, and whenever the interactivity + * estimator recalculates. + */ +static inline int normal_prio(struct task_struct *p) +{ + int prio; + + if (task_has_dl_policy(p)) + prio = MAX_DL_PRIO-1; + else if (task_has_rt_policy(p)) + prio = MAX_RT_PRIO-1 - p->rt_priority; + else + prio = __normal_prio(p); + return prio; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks, or might be boosted by + * interactivity modifiers. Will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +/* + * Can drop rq->lock because from sched_class::switched_from() methods drop it. + */ +static inline void check_class_changed(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class, + int oldprio) +{ + if (prev_class != p->sched_class) { + if (prev_class->switched_from) + prev_class->switched_from(rq, p); + /* Possble rq->lock 'hole'. */ + p->sched_class->switched_to(rq, p); + } else if (oldprio != p->prio || dl_task(p)) + p->sched_class->prio_changed(rq, p, oldprio); +} + +void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) +{ + const struct sched_class *class; + + if (p->sched_class == rq->curr->sched_class) { + rq->curr->sched_class->check_preempt_curr(rq, p, flags); + } else { + for_each_class(class) { + if (class == rq->curr->sched_class) + break; + if (class == p->sched_class) { + resched_curr(rq); + break; + } + } + } + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr)) + rq_clock_skip_update(rq, true); +} + +#ifdef CONFIG_SMP +void set_task_cpu(struct task_struct *p, unsigned int new_cpu) +{ +#ifdef CONFIG_SCHED_DEBUG + /* + * We should never call set_task_cpu() on a blocked task, + * ttwu() will sort out the placement. + */ + WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && + !p->on_rq); + +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold either p->pi_lock or rq->lock, when changing + * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. + * + * sched_move_task() holds both and thus holding either pins the cgroup, + * see task_group(). + * + * Furthermore, all task_rq users should acquire both locks, see + * task_rq_lock(). + */ + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif +#endif + + trace_sched_migrate_task(p, new_cpu); + + if (task_cpu(p) != new_cpu) { + if (p->sched_class->migrate_task_rq) + p->sched_class->migrate_task_rq(p, new_cpu); + p->se.nr_migrations++; + perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + } + + __set_task_cpu(p, new_cpu); +} + +static void __migrate_swap_task(struct task_struct *p, int cpu) +{ + if (task_on_rq_queued(p)) { + struct rq *src_rq, *dst_rq; + + src_rq = task_rq(p); + dst_rq = cpu_rq(cpu); + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, cpu); + activate_task(dst_rq, p, 0); + check_preempt_curr(dst_rq, p, 0); + } else { + /* + * Task isn't running anymore; make it appear like we migrated + * it before it went to sleep. This means on wakeup we make the + * previous cpu our targer instead of where it really is. + */ + p->wake_cpu = cpu; + } +} + +struct migration_swap_arg { + struct task_struct *src_task, *dst_task; + int src_cpu, dst_cpu; +}; + +static int migrate_swap_stop(void *data) +{ + struct migration_swap_arg *arg = data; + struct rq *src_rq, *dst_rq; + int ret = -EAGAIN; + + src_rq = cpu_rq(arg->src_cpu); + dst_rq = cpu_rq(arg->dst_cpu); + + double_raw_lock(&arg->src_task->pi_lock, + &arg->dst_task->pi_lock); + double_rq_lock(src_rq, dst_rq); + if (task_cpu(arg->dst_task) != arg->dst_cpu) + goto unlock; + + if (task_cpu(arg->src_task) != arg->src_cpu) + goto unlock; + + if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task))) + goto unlock; + + if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task))) + goto unlock; + + __migrate_swap_task(arg->src_task, arg->dst_cpu); + __migrate_swap_task(arg->dst_task, arg->src_cpu); + + ret = 0; + +unlock: + double_rq_unlock(src_rq, dst_rq); + raw_spin_unlock(&arg->dst_task->pi_lock); + raw_spin_unlock(&arg->src_task->pi_lock); + + return ret; +} + +/* + * Cross migrate two tasks + */ +int migrate_swap(struct task_struct *cur, struct task_struct *p) +{ + struct migration_swap_arg arg; + int ret = -EINVAL; + + arg = (struct migration_swap_arg){ + .src_task = cur, + .src_cpu = task_cpu(cur), + .dst_task = p, + .dst_cpu = task_cpu(p), + }; + + if (arg.src_cpu == arg.dst_cpu) + goto out; + + /* + * These three tests are all lockless; this is OK since all of them + * will be re-checked with proper locks held further down the line. + */ + if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) + goto out; + + if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task))) + goto out; + + if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task))) + goto out; + + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); + ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg); + +out: + return ret; +} + +struct migration_arg { + struct task_struct *task; + int dest_cpu; +}; + +static int migration_cpu_stop(void *data); + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + int running, queued; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_running()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &flags); + trace_sched_wait_task(p); + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; + if (!match_state || p->state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(queued)) { + ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesn't have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kick_process); +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_SMP +/* + * ->cpus_allowed is protected by both rq->lock and p->pi_lock + */ +static int select_fallback_rq(int cpu, struct task_struct *p) +{ + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; + enum { cpuset, possible, fail } state = cpuset; + int dest_cpu; + + /* + * If the node that the cpu is on has been offlined, cpu_to_node() + * will return -1. There is no cpu on the node, and we should + * select the cpu on the other node. + */ + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + goto out; + } + + switch (state) { + case cpuset: + /* No more Mr. Nice Guy. */ + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_deferred("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } + } + + return dest_cpu; +} + +/* + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. + */ +static inline +int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) +{ + if (p->nr_cpus_allowed > 1) + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + + /* + * In order not to call set_task_cpu() on a blocking task we need + * to rely on ttwu() to place the task on a valid ->cpus_allowed + * cpu. + * + * Since this is common to all placement strategies, this lives here. + * + * [ this allows ->select_task() to simply return task_cpu(p) and + * not worry about this generic constraint ] + */ + if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) || + !cpu_online(cpu))) + cpu = select_fallback_rq(task_cpu(p), p); + + return cpu; +} + +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} +#endif + +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) +{ +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) { + schedstat_inc(rq, ttwu_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); + } else { + struct sched_domain *sd; + + schedstat_inc(p, se.statistics.nr_wakeups_remote); + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + rcu_read_unlock(); + } + + if (wake_flags & WF_MIGRATED) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); + schedstat_inc(p, se.statistics.nr_wakeups); + + if (wake_flags & WF_SYNC) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + +#endif /* CONFIG_SCHEDSTATS */ +} + +static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) +{ + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; + + /* if a worker is waking up, notify workqueue */ + if (p->flags & PF_WQ_WORKER) + wq_worker_waking_up(p, cpu_of(rq)); +} + +/* + * Mark the task runnable and perform wakeup-preemption. + */ +static void +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + check_preempt_curr(rq, p, wake_flags); + trace_sched_wakeup(p, true); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (rq->idle_stamp) { + u64 delta = rq_clock(rq) - rq->idle_stamp; + u64 max = 2*rq->max_idle_balance_cost; + + update_avg(&rq->avg_idle, delta); + + if (rq->avg_idle > max) + rq->avg_idle = max; + + rq->idle_stamp = 0; + } +#endif +} + +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); + ttwu_do_wakeup(rq, p, wake_flags); +} + +/* + * Called in case the task @p isn't fully descheduled from its runqueue, + * in this case we must do a remote wakeup. Its a 'light' wakeup though, + * since all we need to do is flip p->state to TASK_RUNNING, since + * the task is still ->on_rq. + */ +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (task_on_rq_queued(p)) { + /* check_preempt_curr() may use rq clock */ + update_rq_clock(rq); + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; +} + +#ifdef CONFIG_SMP +void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct llist_node *llist = llist_del_all(&rq->wake_list); + struct task_struct *p; + unsigned long flags; + + if (!llist) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + + while (llist) { + p = llist_entry(llist, struct task_struct, wake_entry); + llist = llist_next(llist); + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); + + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + return; + + /* + * Not all reschedule IPI handlers call irq_enter/irq_exit, since + * traditionally all their work was done from the interrupt return + * path. Now that we actually do some work, we need to make sure + * we do call them. + * + * Some archs already do call them, luckily irq_enter/exit nest + * properly. + * + * Arguably we should visit all archs and update all handlers, + * however a fair share of IPIs are still resched only so this would + * somewhat pessimize the simple resched case. + */ + irq_enter(); + sched_ttwu_pending(); + + /* + * Check if someone kicked us for doing the nohz idle load balance. + */ + if (unlikely(got_nohz_idle_kick())) { + this_rq()->idle_balance = 1; + raise_softirq_irqoff(SCHED_SOFTIRQ); + } + irq_exit(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { + if (!set_nr_if_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); + } +} + +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + rcu_read_lock(); + + if (!is_idle_task(rcu_dereference(rq->curr))) + goto out; + + if (set_nr_if_polling(rq->idle)) { + trace_sched_wake_idle_without_ipi(cpu); + } else { + raw_spin_lock_irqsave(&rq->lock, flags); + if (is_idle_task(rq->curr)) + smp_send_reschedule(cpu); + /* Else cpu is not in idle, do nothing here */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + } + +out: + rcu_read_unlock(); +} + +bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); +} +#endif /* CONFIG_SMP */ + +static void ttwu_queue(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + +#if defined(CONFIG_SMP) + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { + sched_clock_cpu(cpu); /* sync clocks x-cpu */ + ttwu_queue_remote(p, cpu); + return; + } +#endif + + raw_spin_lock(&rq->lock); + ttwu_do_activate(rq, p, 0); + raw_spin_unlock(&rq->lock); +} + +/** + * try_to_wake_up - wake up a thread + * @p: the thread to be awakened + * @state: the mask of task states that can be woken + * @wake_flags: wake modifier flags (WF_*) + * + * Put it on the run-queue if it's not already there. The "current" + * thread is always on the run-queue (except when the actual + * re-schedule is in progress), and as such you're allowed to do + * the simpler "current->state = TASK_RUNNING" to mark yourself + * runnable without the overhead of this. + * + * Return: %true if @p was woken up, %false if it was already running. + * or @state didn't match @p's state. + */ +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) +{ + unsigned long flags; + int cpu, success = 0; + + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); + if (!(p->state & state)) + goto out; + + success = 1; /* we're going to change ->state */ + cpu = task_cpu(p); + + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto stat; + +#ifdef CONFIG_SMP + /* + * If the owning (remote) cpu is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. + */ + while (p->on_cpu) + cpu_relax(); + /* + * Pairs with the smp_wmb() in finish_lock_switch(). + */ + smp_rmb(); + + p->sched_contributes_to_load = !!task_contributes_to_load(p); + p->state = TASK_WAKING; + + if (p->sched_class->task_waking) + p->sched_class->task_waking(p); + + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); + if (task_cpu(p) != cpu) { + wake_flags |= WF_MIGRATED; + set_task_cpu(p, cpu); + } +#endif /* CONFIG_SMP */ + + ttwu_queue(p, cpu); +stat: + ttwu_stat(p, cpu, wake_flags); +out: + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return success; +} + +/** + * try_to_wake_up_local - try to wake up a local task with rq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not already there. The caller must + * ensure that this_rq() is locked, @p is bound to this_rq() and not + * the current task. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + + lockdep_assert_held(&rq->lock); + + if (!raw_spin_trylock(&p->pi_lock)) { + raw_spin_unlock(&rq->lock); + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + } + + if (!(p->state & TASK_NORMAL)) + goto out; + + if (!task_on_rq_queued(p)) + ttwu_activate(rq, p, ENQUEUE_WAKEUP); + + ttwu_do_wakeup(rq, p, 0); + ttwu_stat(p, smp_processor_id(), 0); +out: + raw_spin_unlock(&p->pi_lock); +} + +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +int wake_up_process(struct task_struct *p) +{ + WARN_ON(task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +/* + * This function clears the sched_dl_entity static params. + */ +void __dl_clear_params(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = 0; + dl_se->dl_deadline = 0; + dl_se->dl_period = 0; + dl_se->flags = 0; + dl_se->dl_bw = 0; + + dl_se->dl_throttled = 0; + dl_se->dl_new = 1; + dl_se->dl_yielded = 0; +} + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + * + * __sched_fork() is basic setup used by init_idle() too: + */ +static void __sched_fork(unsigned long clone_flags, struct task_struct *p) +{ + p->on_rq = 0; + + p->se.on_rq = 0; + p->se.exec_start = 0; + p->se.sum_exec_runtime = 0; + p->se.prev_sum_exec_runtime = 0; + p->se.nr_migrations = 0; + p->se.vruntime = 0; +#ifdef CONFIG_SMP + p->se.avg.decay_count = 0; +#endif + INIT_LIST_HEAD(&p->se.group_node); + +#ifdef CONFIG_SCHEDSTATS + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); +#endif + + RB_CLEAR_NODE(&p->dl.rb_node); + init_dl_task_timer(&p->dl); + __dl_clear_params(p); + + INIT_LIST_HEAD(&p->rt.run_list); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + +#ifdef CONFIG_NUMA_BALANCING + if (p->mm && atomic_read(&p->mm->mm_users) == 1) { + p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + p->mm->numa_scan_seq = 0; + } + + if (clone_flags & CLONE_VM) + p->numa_preferred_nid = current->numa_preferred_nid; + else + p->numa_preferred_nid = -1; + + p->node_stamp = 0ULL; + p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + p->numa_group = NULL; +#endif /* CONFIG_NUMA_BALANCING */ +} + +#ifdef CONFIG_NUMA_BALANCING +#ifdef CONFIG_SCHED_DEBUG +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sched_feat_set("NUMA"); + else + sched_feat_set("NO_NUMA"); +} +#else +__read_mostly bool numabalancing_enabled; + +void set_numabalancing_state(bool enabled) +{ + numabalancing_enabled = enabled; +} +#endif /* CONFIG_SCHED_DEBUG */ + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_numa_balancing(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = numabalancing_enabled; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_numabalancing_state(state); + return err; +} +#endif +#endif + +/* + * fork()/clone()-time setup: + */ +int sched_fork(unsigned long clone_flags, struct task_struct *p) +{ + unsigned long flags; + int cpu = get_cpu(); + + __sched_fork(clone_flags, p); + /* + * We mark the process as running here. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; + + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = current->normal_prio; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { + p->policy = SCHED_NORMAL; + p->static_prio = NICE_TO_PRIO(0); + p->rt_priority = 0; + } else if (PRIO_TO_NICE(p->static_prio) < 0) + p->static_prio = NICE_TO_PRIO(0); + + p->prio = p->normal_prio = __normal_prio(p); + set_load_weight(p); + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + + if (dl_prio(p->prio)) { + put_cpu(); + return -EAGAIN; + } else if (rt_prio(p->prio)) { + p->sched_class = &rt_sched_class; + } else { + p->sched_class = &fair_sched_class; + } + + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + + /* + * The child is not yet in the pid-hash so no cgroup attach races, + * and the cgroup is pinned to this child due to cgroup_fork() + * is ran before sched_fork(). + * + * Silence PROVE_RCU. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + set_task_cpu(p, cpu); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + if (likely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif +#if defined(CONFIG_SMP) + p->on_cpu = 0; +#endif + init_task_preempt_count(p); +#ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +#endif + + put_cpu(); + return 0; +} + +unsigned long to_ratio(u64 period, u64 runtime) +{ + if (runtime == RUNTIME_INF) + return 1ULL << 20; + + /* + * Doing this here saves a lot of checks in all + * the calling paths, and returning zero seems + * safe for them anyway. + */ + if (period == 0) + return 0; + + return div64_u64(runtime << 20, period); +} + +#ifdef CONFIG_SMP +inline struct dl_bw *dl_bw_of(int i) +{ + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); + return &cpu_rq(i)->rd->dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + struct root_domain *rd = cpu_rq(i)->rd; + int cpus = 0; + + rcu_lockdep_assert(rcu_read_lock_sched_held(), + "sched RCU must be held"); + for_each_cpu_and(i, rd->span, cpu_active_mask) + cpus++; + + return cpus; +} +#else +inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->dl.dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + return 1; +} +#endif + +/* + * We must be sure that accepting a new task (or allowing changing the + * parameters of an existing one) is consistent with the bandwidth + * constraints. If yes, this function also accordingly updates the currently + * allocated bandwidth to reflect the new situation. + * + * This function is called while holding p's rq->lock. + * + * XXX we should delay bw change until the task's 0-lag point, see + * __setparam_dl(). + */ +static int dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr) +{ + + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + u64 period = attr->sched_period ?: attr->sched_deadline; + u64 runtime = attr->sched_runtime; + u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; + int cpus, err = -1; + + if (new_bw == p->dl.dl_bw) + return 0; + + /* + * Either if a task, enters, leave, or stays -deadline but changes + * its parameters, we may need to update accordingly the total + * allocated bandwidth of the container. + */ + raw_spin_lock(&dl_b->lock); + cpus = dl_bw_cpus(task_cpu(p)); + if (dl_policy(policy) && !task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, 0, new_bw)) { + __dl_add(dl_b, new_bw); + err = 0; + } else if (dl_policy(policy) && task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { + __dl_clear(dl_b, p->dl.dl_bw); + __dl_add(dl_b, new_bw); + err = 0; + } else if (!dl_policy(policy) && task_has_dl_policy(p)) { + __dl_clear(dl_b, p->dl.dl_bw); + err = 0; + } + raw_spin_unlock(&dl_b->lock); + + return err; +} + +extern void init_dl_bw(struct dl_bw *dl_b); + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + + raw_spin_lock_irqsave(&p->pi_lock, flags); +#ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: + * - cpus_allowed can change in the fork path + * - any previously selected cpu might disappear through hotplug + */ + set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); +#endif + + /* Initialize new task's runnable average */ + init_task_runnable_average(p); + rq = __task_rq_lock(p); + activate_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; + trace_sched_wakeup_new(p, true); + check_preempt_curr(rq, p, WF_FORK); +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); +#endif + task_rq_unlock(rq, p, &flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @prev: the current task that is being switched out + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + trace_sched_switch(prev, next); + sched_info_switch(rq, prev, next); + perf_event_task_sched_out(prev, next); + fire_sched_out_preempt_notifiers(prev, next); + prepare_lock_switch(rq, next); + prepare_arch_switch(next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + * + * The context switch have flipped the stack from under us and restored the + * local variables which were saved when this task called schedule() in the + * past. prev == current is still correct but we need to recalculate this_rq + * because prev may have moved to another CPU. + */ +static struct rq *finish_task_switch(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq = this_rq(); + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * The test for TASK_DEAD must occur while the runqueue locks are + * still held, otherwise prev could be scheduled on another cpu, die + * there before we look at prev->state, and then the reference would + * be dropped twice. + * Manfred Spraul <manfred@colorfullife.com> + */ + prev_state = prev->state; + vtime_task_switch(prev); + finish_arch_switch(prev); + perf_event_task_sched_in(prev, current); + finish_lock_switch(rq, prev); + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); + if (mm) + mmdrop(mm); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); + + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + put_task_struct(prev); + } + + tick_nohz_task_switch(current); + return rq; +} + +#ifdef CONFIG_SMP + +/* rq->lock is NOT held, but preemption is disabled */ +static inline void post_schedule(struct rq *rq) +{ + if (rq->post_schedule) { + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->curr->sched_class->post_schedule) + rq->curr->sched_class->post_schedule(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); + + rq->post_schedule = 0; + } +} + +#else + +static inline void post_schedule(struct rq *rq) +{ +} + +#endif + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage __visible void schedule_tail(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq; + + /* finish_task_switch() drops rq->lock and enables preemtion */ + preempt_disable(); + rq = finish_task_switch(prev); + post_schedule(rq); + preempt_enable(); + + if (current->set_child_tid) + put_user(task_pid_vnr(current), current->set_child_tid); +} + +/* + * context_switch - switch to the new MM and the new thread's register state. + */ +static inline struct rq * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(rq, prev, next); + + mm = next->mm; + oldmm = prev->active_mm; + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_start_context_switch(prev); + + if (!mm) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm(oldmm, mm, next); + + if (!prev->mm) { + prev->active_mm = NULL; + rq->prev_mm = oldmm; + } + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + + context_tracking_task_switch(prev, next); + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + barrier(); + + return finish_task_switch(prev); +} + +/* + * nr_running and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, total number of context switches performed since bootup. + */ +unsigned long nr_running(void) +{ + unsigned long i, sum = 0; + + for_each_online_cpu(i) + sum += cpu_rq(i)->nr_running; + + return sum; +} + +/* + * Check if only the current task is running on the cpu. + */ +bool single_task_running(void) +{ + if (cpu_rq(smp_processor_id())->nr_running == 1) + return true; + else + return false; +} +EXPORT_SYMBOL(single_task_running); + +unsigned long long nr_context_switches(void) +{ + int i; + unsigned long long sum = 0; + + for_each_possible_cpu(i) + sum += cpu_rq(i)->nr_switches; + + return sum; +} + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += atomic_read(&cpu_rq(i)->nr_iowait); + + return sum; +} + +unsigned long nr_iowait_cpu(int cpu) +{ + struct rq *this = cpu_rq(cpu); + return atomic_read(&this->nr_iowait); +} + +void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) +{ + struct rq *this = this_rq(); + *nr_waiters = atomic_read(&this->nr_iowait); + *load = this->cpu_load[0]; +} + +#ifdef CONFIG_SMP + +/* + * sched_exec - execve() is a valuable balancing opportunity, because at + * this point the task has the smallest effective memory and cache footprint. + */ +void sched_exec(void) +{ + struct task_struct *p = current; + unsigned long flags; + int dest_cpu; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0); + if (dest_cpu == smp_processor_id()) + goto unlock; + + if (likely(cpu_active(dest_cpu))) { + struct migration_arg arg = { p, dest_cpu }; + + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + return; + } +unlock: + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} + +#endif + +DEFINE_PER_CPU(struct kernel_stat, kstat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); + +EXPORT_PER_CPU_SYMBOL(kstat); +EXPORT_PER_CPU_SYMBOL(kernel_cpustat); + +/* + * Return accounted runtime for the task. + * In case the task is currently running, return the runtime plus current's + * pending runtime that have not been accounted yet. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns; + +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. + */ + if (!p->on_cpu || !task_on_rq_queued(p)) + return p->se.sum_exec_runtime; +#endif + + rq = task_rq_lock(p, &flags); + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (task_current(rq, p) && task_on_rq_queued(p)) { + update_rq_clock(rq); + p->sched_class->update_curr(rq); + } + ns = p->se.sum_exec_runtime; + task_rq_unlock(rq, p, &flags); + + return ns; +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. + */ +void scheduler_tick(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + struct task_struct *curr = rq->curr; + + sched_clock_tick(); + + raw_spin_lock(&rq->lock); + update_rq_clock(rq); + curr->sched_class->task_tick(rq, curr, 0); + update_cpu_load_active(rq); + raw_spin_unlock(&rq->lock); + + perf_event_task_tick(); + +#ifdef CONFIG_SMP + rq->idle_balance = idle_cpu(cpu); + trigger_load_balance(rq); +#endif + rq_last_tick_reset(rq); +} + +#ifdef CONFIG_NO_HZ_FULL +/** + * scheduler_tick_max_deferment + * + * Keep at least one tick per second when a single + * active task is running because the scheduler doesn't + * yet completely support full dynticks environment. + * + * This makes sure that uptime, CFS vruntime, load + * balancing, etc... continue to move forward, even + * with a very low granularity. + * + * Return: Maximum deferment in nanoseconds. + */ +u64 scheduler_tick_max_deferment(void) +{ + struct rq *rq = this_rq(); + unsigned long next, now = ACCESS_ONCE(jiffies); + + next = rq->last_sched_tick + HZ; + + if (time_before_eq(next, now)) + return 0; + + return jiffies_to_nsecs(next - now); +} +#endif + +notrace unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} + +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +void preempt_count_add(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + __preempt_count_add(val); +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); + +void preempt_count_sub(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; +#endif + + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + __preempt_count_sub(val); +} +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); + +#endif + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + if (oops_in_progress) + return; + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + + debug_show_held_locks(prev); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ +#ifdef CONFIG_SCHED_STACK_END_CHECK + BUG_ON(unlikely(task_stack_end_corrupted(prev))); +#endif + /* + * Test if we are atomic. Since do_exit() needs to call into + * schedule() atomically, we ignore that path. Otherwise whine + * if we are scheduling when we should not. + */ + if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD)) + __schedule_bug(prev); + rcu_sleep_check(); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +} + +/* + * Pick up the highest-prio task: + */ +static inline struct task_struct * +pick_next_task(struct rq *rq, struct task_struct *prev) +{ + const struct sched_class *class = &fair_sched_class; + struct task_struct *p; + + /* + * Optimization: we know that if all tasks are in + * the fair class we can call that function directly: + */ + if (likely(prev->sched_class == class && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev); + if (unlikely(p == RETRY_TASK)) + goto again; + + /* assumes fair_sched_class->next == idle_sched_class */ + if (unlikely(!p)) + p = idle_sched_class.pick_next_task(rq, prev); + + return p; + } + +again: + for_each_class(class) { + p = class->pick_next_task(rq, prev); + if (p) { + if (unlikely(p == RETRY_TASK)) + goto again; + return p; + } + } + + BUG(); /* the idle class will always have a runnable task */ +} + +/* + * __schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space + * + * WARNING: all callers must re-check need_resched() afterward and reschedule + * accordingly in case an event triggered the need for rescheduling (such as + * an interrupt waking up a task) while preemption was disabled in __schedule(). + */ +static void __sched __schedule(void) +{ + struct task_struct *prev, *next; + unsigned long *switch_count; + struct rq *rq; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + rcu_note_context_switch(); + prev = rq->curr; + + schedule_debug(prev); + + if (sched_feat(HRTICK)) + hrtick_clear(rq); + + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); + raw_spin_lock_irq(&rq->lock); + + rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) { + prev->state = TASK_RUNNING; + } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; + + /* + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) + try_to_wake_up_local(to_wakeup); + } + } + switch_count = &prev->nvcsw; + } + + if (task_on_rq_queued(prev)) + update_rq_clock(rq); + + next = pick_next_task(rq, prev); + clear_tsk_need_resched(prev); + clear_preempt_need_resched(); + rq->clock_skip_update = 0; + + if (likely(prev != next)) { + rq->nr_switches++; + rq->curr = next; + ++*switch_count; + + rq = context_switch(rq, prev, next); /* unlocks the rq */ + cpu = cpu_of(rq); + } else + raw_spin_unlock_irq(&rq->lock); + + post_schedule(rq); + + sched_preempt_enable_no_resched(); +} + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state || tsk_is_pi_blocked(tsk)) + return; + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + do { + __schedule(); + } while (need_resched()); +} +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + * + * NB: There are buggy callers of this function. Ideally we + * should warn if prev_state != CONTEXT_USER, but that will trigger + * too frequently to make sense yet. + */ + enum ctx_state prev_state = exception_enter(); + schedule(); + exception_exit(prev_state); +} +#endif + +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +static void __sched notrace preempt_schedule_common(void) +{ + do { + __preempt_count_add(PREEMPT_ACTIVE); + __schedule(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} + +#ifdef CONFIG_PREEMPT +/* + * this is the entry point to schedule() from in-kernel preemption + * off of preempt_enable. Kernel preemptions off return from interrupt + * occur there and call schedule directly. + */ +asmlinkage __visible void __sched notrace preempt_schedule(void) +{ + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(!preemptible())) + return; + + preempt_schedule_common(); +} +NOKPROBE_SYMBOL(preempt_schedule); +EXPORT_SYMBOL(preempt_schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +asmlinkage __visible void __sched notrace preempt_schedule_context(void) +{ + enum ctx_state prev_ctx; + + if (likely(!preemptible())) + return; + + do { + __preempt_count_add(PREEMPT_ACTIVE); + /* + * Needs preempt disabled in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + prev_ctx = exception_enter(); + __schedule(); + exception_exit(prev_ctx); + + __preempt_count_sub(PREEMPT_ACTIVE); + barrier(); + } while (need_resched()); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif /* CONFIG_PREEMPT */ + +/* + * this is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage __visible void __sched preempt_schedule_irq(void) +{ + enum ctx_state prev_state; + + /* Catch callers which need to be fixed */ + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); + + do { + __preempt_count_add(PREEMPT_ACTIVE); + local_irq_enable(); + __schedule(); + local_irq_disable(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); + + exception_exit(prev_state); +} + +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, + void *key) +{ + return try_to_wake_up(curr->private, mode, wake_flags); +} +EXPORT_SYMBOL(default_wake_function); + +#ifdef CONFIG_RT_MUTEXES + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task + * @prio: prio value (kernel-internal form) + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + int oldprio, queued, running, enqueue_flag = 0; + struct rq *rq; + const struct sched_class *prev_class; + + BUG_ON(prio > MAX_PRIO); + + rq = __task_rq_lock(p); + + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + + trace_sched_pi_setprio(p, prio); + oldprio = p->prio; + prev_class = p->sched_class; + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + /* + * Boosting condition are: + * 1. -rt task is running and holds mutex A + * --> -dl task blocks on mutex A + * + * 2. -dl task is running and holds mutex A + * --> -dl task blocks on mutex A and could preempt the + * running task + */ + if (dl_prio(prio)) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + if (!dl_prio(p->normal_prio) || + (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { + p->dl.dl_boosted = 1; + p->dl.dl_throttled = 0; + enqueue_flag = ENQUEUE_REPLENISH; + } else + p->dl.dl_boosted = 0; + p->sched_class = &dl_sched_class; + } else if (rt_prio(prio)) { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; + if (oldprio < prio) + enqueue_flag = ENQUEUE_HEAD; + p->sched_class = &rt_sched_class; + } else { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; + p->sched_class = &fair_sched_class; + } + + p->prio = prio; + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, p, enqueue_flag); + + check_class_changed(rq, p, prev_class, oldprio); +out_unlock: + __task_rq_unlock(rq); +} +#endif + +void set_user_nice(struct task_struct *p, long nice) +{ + int old_prio, delta, queued; + unsigned long flags; + struct rq *rq; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = task_rq_lock(p, &flags); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: + */ + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { + p->static_prio = NICE_TO_PRIO(nice); + goto out_unlock; + } + queued = task_on_rq_queued(p); + if (queued) + dequeue_task(rq, p, 0); + + p->static_prio = NICE_TO_PRIO(nice); + set_load_weight(p); + old_prio = p->prio; + p->prio = effective_prio(p); + delta = p->prio - old_prio; + + if (queued) { + enqueue_task(rq, p, 0); + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + if (delta < 0 || (delta > 0 && task_running(rq, p))) + resched_curr(rq); + } +out_unlock: + task_rq_unlock(rq, p, &flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * Return: The priority value as seen by users in /proc. + * RT tasks are offset by -200. Normal tasks are centered + * around 0, value goes from -16 to +15. + */ +int task_prio(const struct task_struct *p) +{ + return p->prio - MAX_RT_PRIO; +} + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->curr != rq->idle) + return 0; + + if (rq->nr_running) + return 0; + +#ifdef CONFIG_SMP + if (!llist_empty(&rq->wake_list)) + return 0; +#endif + + return 1; +} + +/** + * idle_task - return the idle task for a given cpu. + * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. + */ +static struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* + * This function initializes the sched_dl_entity of a newly becoming + * SCHED_DEADLINE task. + * + * Only the static values are considered here, the actual runtime and the + * absolute deadline will be properly calculated when the task is enqueued + * for the first time with its new policy. + */ +static void +__setparam_dl(struct task_struct *p, const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + dl_se->dl_runtime = attr->sched_runtime; + dl_se->dl_deadline = attr->sched_deadline; + dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; + dl_se->flags = attr->sched_flags; + dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); + + /* + * Changing the parameters of a task is 'tricky' and we're not doing + * the correct thing -- also see task_dead_dl() and switched_from_dl(). + * + * What we SHOULD do is delay the bandwidth release until the 0-lag + * point. This would include retaining the task_struct until that time + * and change dl_overflow() to not immediately decrement the current + * amount. + * + * Instead we retain the current runtime/deadline and let the new + * parameters take effect after the current reservation period lapses. + * This is safe (albeit pessimistic) because the 0-lag point is always + * before the current scheduling deadline. + * + * We can still have temporary overloads because we do not delay the + * change in bandwidth until that time; so admission control is + * not on the safe side. It does however guarantee tasks will never + * consume more than promised. + */ +} + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +static void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) +{ + int policy = attr->sched_policy; + + if (policy == SETPARAM_POLICY) + policy = p->policy; + + p->policy = policy; + + if (dl_policy(policy)) + __setparam_dl(p, attr); + else if (fair_policy(policy)) + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + + /* + * __sched_setscheduler() ensures attr->sched_priority == 0 when + * !rt_policy. Always setting this ensures that things like + * getparam()/getattr() don't report silly values for !rt tasks. + */ + p->rt_priority = attr->sched_priority; + p->normal_prio = normal_prio(p); + set_load_weight(p); +} + +/* Actually do priority change: must hold pi & rq lock. */ +static void __setscheduler(struct rq *rq, struct task_struct *p, + const struct sched_attr *attr, bool keep_boost) +{ + __setscheduler_params(p, attr); + + /* + * Keep a potential priority boosting if called from + * sched_setscheduler(). + */ + if (keep_boost) + p->prio = rt_mutex_get_effective_prio(p, normal_prio(p)); + else + p->prio = normal_prio(p); + + if (dl_prio(p->prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; +} + +static void +__getparam_dl(struct task_struct *p, struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + attr->sched_priority = p->rt_priority; + attr->sched_runtime = dl_se->dl_runtime; + attr->sched_deadline = dl_se->dl_deadline; + attr->sched_period = dl_se->dl_period; + attr->sched_flags = dl_se->flags; +} + +/* + * This function validates the new parameters of a -deadline task. + * We ask for the deadline not being zero, and greater or equal + * than the runtime, as well as the period of being zero or + * greater than deadline. Furthermore, we have to be sure that + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). + */ +static bool +__checkparam_dl(const struct sched_attr *attr) +{ + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); + rcu_read_unlock(); + return match; +} + +static bool dl_param_changed(struct task_struct *p, + const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + if (dl_se->dl_runtime != attr->sched_runtime || + dl_se->dl_deadline != attr->sched_deadline || + dl_se->dl_period != attr->sched_period || + dl_se->flags != attr->sched_flags) + return true; + + return false; +} + +static int __sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + bool user) +{ + int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : + MAX_RT_PRIO - 1 - attr->sched_priority; + int retval, oldprio, oldpolicy = -1, queued, running; + int new_effective_prio, policy = attr->sched_policy; + unsigned long flags; + const struct sched_class *prev_class; + struct rq *rq; + int reset_on_fork; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); +recheck: + /* double check policy once rq lock held */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); + + if (policy != SCHED_DEADLINE && + policy != SCHED_FIFO && policy != SCHED_RR && + policy != SCHED_NORMAL && policy != SCHED_BATCH && + policy != SCHED_IDLE) + return -EINVAL; + } + + if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK)) + return -EINVAL; + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, + * SCHED_BATCH and SCHED_IDLE is 0. + */ + if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && attr->sched_priority > MAX_RT_PRIO-1)) + return -EINVAL; + if ((dl_policy(policy) && !__checkparam_dl(attr)) || + (rt_policy(policy) != (attr->sched_priority != 0))) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !can_nice(p, attr->sched_nice)) + return -EPERM; + } + + if (rt_policy(policy)) { + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); + + /* can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* can't increase priority */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + return -EPERM; + } + + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + return -EPERM; + + /* + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. + */ + if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { + if (!can_nice(p, task_nice(p))) + return -EPERM; + } + + /* can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) + return -EPERM; + } + + if (user) { + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + * + * To be able to change p->policy safely, the appropriate + * runqueue lock must be held. + */ + rq = task_rq_lock(p, &flags); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + task_rq_unlock(rq, p, &flags); + return -EINVAL; + } + + /* + * If not changing anything there's no need to proceed further, + * but store a possible modification of reset_on_fork. + */ + if (unlikely(policy == p->policy)) { + if (fair_policy(policy) && attr->sched_nice != task_nice(p)) + goto change; + if (rt_policy(policy) && attr->sched_priority != p->rt_priority) + goto change; + if (dl_policy(policy) && dl_param_changed(p, attr)) + goto change; + + p->sched_reset_on_fork = reset_on_fork; + task_rq_unlock(rq, p, &flags); + return 0; + } +change: + + if (user) { +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0 && + !task_group_is_autogroup(task_group(p))) { + task_rq_unlock(rq, p, &flags); + return -EPERM; + } +#endif +#ifdef CONFIG_SMP + if (dl_bandwidth_enabled() && dl_policy(policy)) { + cpumask_t *span = rq->rd->span; + + /* + * Don't allow tasks with an affinity mask smaller than + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ + if (!cpumask_subset(span, &p->cpus_allowed) || + rq->rd->dl_bw.bw == 0) { + task_rq_unlock(rq, p, &flags); + return -EPERM; + } + } +#endif + } + + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + task_rq_unlock(rq, p, &flags); + goto recheck; + } + + /* + * If setscheduling to SCHED_DEADLINE (or changing the parameters + * of a SCHED_DEADLINE task) we need to check if enough bandwidth + * is available. + */ + if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { + task_rq_unlock(rq, p, &flags); + return -EBUSY; + } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + new_effective_prio = rt_mutex_get_effective_prio(p, newprio); + if (new_effective_prio == oldprio) { + __setscheduler_params(p, attr); + task_rq_unlock(rq, p, &flags); + return 0; + } + + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + prev_class = p->sched_class; + __setscheduler(rq, p, attr, true); + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } + + check_class_changed(rq, p, prev_class, oldprio); + task_rq_unlock(rq, p, &flags); + + rt_mutex_adjust_pi(p); + + return 0; +} + +static int _sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool check) +{ + struct sched_attr attr = { + .sched_policy = policy, + .sched_priority = param->sched_priority, + .sched_nice = PRIO_TO_NICE(p->static_prio), + }; + + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + policy &= ~SCHED_RESET_ON_FORK; + attr.sched_policy = policy; + } + + return __sched_setscheduler(p, &attr, check); +} +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, true); +} +EXPORT_SYMBOL_GPL(sched_setscheduler); + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, false); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setscheduler(p, policy, &lparam); + rcu_read_unlock(); + + return retval; +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, + struct sched_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + /* + * XXX: do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); + + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, + struct sched_param __user *, param) +{ + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @flags: for future extension. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy + | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); + } + rcu_read_unlock(); + return retval; +} + +/** + * sys_sched_getparam - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + rcu_read_unlock(); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static int sched_read_attr(struct sched_attr __user *uattr, + struct sched_attr *attr, + unsigned int usize) +{ + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, usize)) + return -EFAULT; + + /* + * If we're handed a smaller struct than we know of, + * ensure all the unknown bits are 0 - i.e. old + * user-space does not get uncomplete information. + */ + if (usize < sizeof(*attr)) { + unsigned char *addr; + unsigned char *end; + + addr = (void *)attr + usize; + end = (void *)attr + sizeof(*attr); + + for (; addr < end; addr++) { + if (*addr) + return -EFBIG; + } + + attr->size = usize; + } + + ret = copy_to_user(uattr, attr, attr->size); + if (ret) + return -EFAULT; + + return 0; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || size > PAGE_SIZE || + size < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + attr.sched_policy = p->policy; + if (p->sched_reset_on_fork) + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + if (task_has_dl_policy(p)) + __getparam_dl(p, &attr); + else if (task_has_rt_policy(p)) + attr.sched_priority = p->rt_priority; + else + attr.sched_nice = task_nice(p); + + rcu_read_unlock(); + + retval = sched_read_attr(uattr, &attr, size); + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + rcu_read_lock(); + + p = find_process_by_pid(pid); + if (!p) { + rcu_read_unlock(); + return -ESRCH; + } + + /* Prevent p going away */ + get_task_struct(p); + rcu_read_unlock(); + + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_free_new_mask; + } + rcu_read_unlock(); + } + + retval = security_task_setscheduler(p); + if (retval) + goto out_free_new_mask; + + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); + + /* + * Since bandwidth control happens on root_domain basis, + * if admission test is enabled, we only admit -deadline + * tasks allowed to run on all the CPUs in the task's + * root_domain. + */ +#ifdef CONFIG_SMP + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + rcu_read_lock(); + if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { + retval = -EBUSY; + rcu_read_unlock(); + goto out_free_new_mask; + } + rcu_read_unlock(); + } +#endif +again: + retval = set_cpus_allowed_ptr(p, new_mask); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_free_new_mask: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + put_task_struct(p); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + struct cpumask *new_mask) +{ + if (len < cpumask_size()) + cpumask_clear(new_mask); + else if (len > cpumask_size()) + len = cpumask_size(); + + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + +/** + * sys_sched_setaffinity - set the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, struct cpumask *mask) +{ + struct task_struct *p; + unsigned long flags; + int retval; + + rcu_read_lock(); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + +out_unlock: + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getaffinity - get the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. If there are no + * other threads running on this CPU then this function will return. + * + * Return: 0. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct rq *rq = this_rq_lock(); + + schedstat_inc(rq, yld_count); + current->sched_class->yield_task(rq); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(rq->lock); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + do_raw_spin_unlock(&rq->lock); + sched_preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +int __sched _cond_resched(void) +{ + if (should_resched()) { + preempt_schedule_common(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(_cond_resched); + +/* + * __cond_resched_lock() - if a reschedule is pending, drop the given lock, + * call schedule, and on return reacquire the lock. + * + * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * operations here to prevent schedule() from being called twice (once via + * spin_unlock(), once by hand). + */ +int __cond_resched_lock(spinlock_t *lock) +{ + int resched = should_resched(); + int ret = 0; + + lockdep_assert_held(lock); + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched) + preempt_schedule_common(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_lock); + +int __sched __cond_resched_softirq(void) +{ + BUG_ON(!in_softirq()); + + if (should_resched()) { + local_bh_enable(); + preempt_schedule_common(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(__cond_resched_softirq); + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + struct task_struct *curr = current; + struct rq *rq, *p_rq; + unsigned long flags; + int yielded = 0; + + local_irq_save(flags); + rq = this_rq(); + +again: + p_rq = task_rq(p); + /* + * If we're the only runnable task on the rq and target rq also + * has only one task, there's absolutely no point in yielding. + */ + if (rq->nr_running == 1 && p_rq->nr_running == 1) { + yielded = -ESRCH; + goto out_irq; + } + + double_rq_lock(rq, p_rq); + if (task_rq(p) != p_rq) { + double_rq_unlock(rq, p_rq); + goto again; + } + + if (!curr->sched_class->yield_to_task) + goto out_unlock; + + if (curr->sched_class != p->sched_class) + goto out_unlock; + + if (task_running(p_rq, p) || p->state) + goto out_unlock; + + yielded = curr->sched_class->yield_to_task(rq, p, preempt); + if (yielded) { + schedstat_inc(rq, yld_count); + /* + * Make p's CPU reschedule; pick_next_entity takes care of + * fairness. + */ + if (preempt && rq != p_rq) + resched_curr(p_rq); + } + +out_unlock: + double_rq_unlock(rq, p_rq); +out_irq: + local_irq_restore(flags); + + if (yielded > 0) + schedule(); + + return yielded; +} +EXPORT_SYMBOL_GPL(yield_to); + +/* + * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * that process accounting knows that this is a task in IO wait state. + */ +long __sched io_schedule_timeout(long timeout) +{ + int old_iowait = current->in_iowait; + struct rq *rq; + long ret; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + delayacct_blkio_start(); + rq = raw_rq(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + current->in_iowait = old_iowait; + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + + return ret; +} +EXPORT_SYMBOL(io_schedule_timeout); + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + } + return ret; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + unsigned int time_slice; + unsigned long flags; + struct rq *rq; + int retval; + struct timespec t; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + rq = task_rq_lock(p, &flags); + time_slice = 0; + if (p->sched_class->get_rr_interval) + time_slice = p->sched_class->get_rr_interval(rq, p); + task_rq_unlock(rq, p, &flags); + + rcu_read_unlock(); + jiffies_to_timespec(time_slice, &t); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + int ppid; + unsigned long state = p->state; + + if (state) + state = __ffs(state) + 1; + printk(KERN_INFO "%-15.15s %c", p->comm, + state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); +#if BITS_PER_LONG == 32 + if (state == TASK_RUNNING) + printk(KERN_CONT " running "); + else + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); +#else + if (state == TASK_RUNNING) + printk(KERN_CONT " running task "); + else + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); +#endif +#ifdef CONFIG_DEBUG_STACK_USAGE + free = stack_not_used(p); +#endif + ppid = 0; + rcu_read_lock(); + if (pid_alive(p)) + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), ppid, + (unsigned long)task_thread_info(p)->flags); + + print_worker_info(KERN_INFO, p); + show_stack(p, NULL); +} + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take a lot of time: + */ + touch_nmi_watchdog(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } + + touch_all_softlockup_watchdogs(); + +#ifdef CONFIG_SCHED_DEBUG + sysrq_sched_debug_show(); +#endif + rcu_read_unlock(); + /* + * Only show locks if all tasks are dumped: + */ + if (!state_filter) + debug_show_all_locks(); +} + +void init_idle_bootup_task(struct task_struct *idle) +{ + idle->sched_class = &idle_sched_class; +} + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + __sched_fork(0, idle); + idle->state = TASK_RUNNING; + idle->se.exec_start = sched_clock(); + + do_set_cpus_allowed(idle, cpumask_of(cpu)); + /* + * We're having a chicken and egg problem, even though we are + * holding rq->lock, the cpu isn't yet set to this cpu so the + * lockdep check in task_group() will fail. + * + * Similar case to sched_fork(). / Alternatively we could + * use task_rq_lock() here and obtain the other rq->lock. + * + * Silence PROVE_RCU + */ + rcu_read_lock(); + __set_task_cpu(idle, cpu); + rcu_read_unlock(); + + rq->curr = rq->idle = idle; + idle->on_rq = TASK_ON_RQ_QUEUED; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; +#endif + raw_spin_unlock_irqrestore(&rq->lock, flags); + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); + + /* + * The idle tasks have their own, simple scheduling class: + */ + idle->sched_class = &idle_sched_class; + ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle, cpu); +#if defined(CONFIG_SMP) + sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); +#endif +} + +int cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial) +{ + int ret = 1, trial_cpus; + struct dl_bw *cur_dl_b; + unsigned long flags; + + if (!cpumask_weight(cur)) + return ret; + + rcu_read_lock_sched(); + cur_dl_b = dl_bw_of(cpumask_any(cur)); + trial_cpus = cpumask_weight(trial); + + raw_spin_lock_irqsave(&cur_dl_b->lock, flags); + if (cur_dl_b->bw != -1 && + cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) + ret = 0; + raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); + rcu_read_unlock_sched(); + + return ret; +} + +int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed) +{ + int ret = 0; + + /* + * Kthreads which disallow setaffinity shouldn't be moved + * to a new cpuset; we don't want to change their cpu + * affinity and isolating such threads by their set of + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks + * before cpus_allowed may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) { + ret = -EINVAL; + goto out; + } + +#ifdef CONFIG_SMP + if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, + cs_cpus_allowed)) { + unsigned int dest_cpu = cpumask_any_and(cpu_active_mask, + cs_cpus_allowed); + struct dl_bw *dl_b; + bool overflow; + int cpus; + unsigned long flags; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(dest_cpu); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(dest_cpu); + overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw); + if (overflow) + ret = -EBUSY; + else { + /* + * We reserve space for this task in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, p->dl.dl_bw); + } + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + rcu_read_unlock_sched(); + + } +#endif +out: + return ret; +} + +#ifdef CONFIG_SMP +/* + * move_queued_task - move a queued task to new rq. + * + * Returns (locked) new rq. Old rq's lock is released. + */ +static struct rq *move_queued_task(struct task_struct *p, int new_cpu) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_held(&rq->lock); + + dequeue_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, new_cpu); + raw_spin_unlock(&rq->lock); + + rq = cpu_rq(new_cpu); + + raw_spin_lock(&rq->lock); + BUG_ON(task_cpu(p) != new_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; + enqueue_task(rq, p, 0); + check_preempt_curr(rq, p, 0); + + return rq; +} + +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + + cpumask_copy(&p->cpus_allowed, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +/* + * This is how migration works: + * + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes + * it and puts it into the right queue. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. + */ + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + unsigned long flags; + struct rq *rq; + unsigned int dest_cpu; + int ret = 0; + + rq = task_rq_lock(p, &flags); + + if (cpumask_equal(&p->cpus_allowed, new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { + ret = -EINVAL; + goto out; + } + + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; + /* Need help from migration thread: drop lock and wait. */ + task_rq_unlock(rq, p, &flags); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + return 0; + } else if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); +out: + task_rq_unlock(rq, p, &flags); + + return ret; +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +/* + * Move (not current) task off this cpu, onto dest cpu. We're doing + * this because either it can't run here any more (set_cpus_allowed() + * away from this CPU, or CPU going down), or because we're + * attempting to rebalance this task on exec (sched_exec). + * + * So we race with normal scheduler movements, but that's OK, as long + * as the task is no longer on this CPU. + * + * Returns non-zero if task was successfully migrated. + */ +static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) +{ + struct rq *rq; + int ret = 0; + + if (unlikely(!cpu_active(dest_cpu))) + return ret; + + rq = cpu_rq(src_cpu); + + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + /* Already moved. */ + if (task_cpu(p) != src_cpu) + goto done; + + /* Affinity changed (again). */ + if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + goto fail; + + /* + * If we're not on a rq, the next wake-up will ensure we're + * placed properly. + */ + if (task_on_rq_queued(p)) + rq = move_queued_task(p, dest_cpu); +done: + ret = 1; +fail: + raw_spin_unlock(&rq->lock); + raw_spin_unlock(&p->pi_lock); + return ret; +} + +#ifdef CONFIG_NUMA_BALANCING +/* Migrate current task p to target_cpu */ +int migrate_task_to(struct task_struct *p, int target_cpu) +{ + struct migration_arg arg = { p, target_cpu }; + int curr_cpu = task_cpu(p); + + if (curr_cpu == target_cpu) + return 0; + + if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p))) + return -EINVAL; + + /* TODO: This is not properly updating schedstats */ + + trace_sched_move_numa(p, curr_cpu, target_cpu); + return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); +} + +/* + * Requeue a task on a given node and accurately track the number of NUMA + * tasks on the runqueues + */ +void sched_setnuma(struct task_struct *p, int nid) +{ + struct rq *rq; + unsigned long flags; + bool queued, running; + + rq = task_rq_lock(p, &flags); + queued = task_on_rq_queued(p); + running = task_current(rq, p); + + if (queued) + dequeue_task(rq, p, 0); + if (running) + put_prev_task(rq, p); + + p->numa_preferred_nid = nid; + + if (running) + p->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, p, 0); + task_rq_unlock(rq, p, &flags); +} +#endif + +/* + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. + */ +static int migration_cpu_stop(void *data) +{ + struct migration_arg *arg = data; + + /* + * The original target cpu might have gone down and we might + * be on another cpu but it doesn't matter. + */ + local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running + * __migrate_task() such that we will not miss enforcing cpus_allowed + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); + __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); + local_irq_enable(); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) { + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } + mmdrop(mm); +} + +/* + * Since this CPU is going 'away' for a while, fold any nr_active delta + * we might have. Assumes we're called after migrate_tasks() so that the + * nr_active count is stable. + * + * Also see the comment "Global load-average calculations". + */ +static void calc_load_migrate(struct rq *rq) +{ + long delta = calc_load_fold_active(rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); +} + +static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +{ +} + +static const struct sched_class fake_sched_class = { + .put_prev_task = put_prev_task_fake, +}; + +static struct task_struct fake_task = { + /* + * Avoid pull_{rt,dl}_task() + */ + .prio = MAX_PRIO + 1, + .sched_class = &fake_sched_class, +}; + +/* + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. + */ +static void migrate_tasks(unsigned int dead_cpu) +{ + struct rq *rq = cpu_rq(dead_cpu); + struct task_struct *next, *stop = rq->stop; + int dest_cpu; + + /* + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. + */ + rq->stop = NULL; + + /* + * put_prev_task() and pick_next_task() sched + * class method both need to have an up-to-date + * value of rq->clock[_task] + */ + update_rq_clock(rq); + + for ( ; ; ) { + /* + * There's this thread running, bail when that's the only + * remaining thread. + */ + if (rq->nr_running == 1) + break; + + next = pick_next_task(rq, &fake_task); + BUG_ON(!next); + next->sched_class->put_prev_task(rq, next); + + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_cpu, next); + raw_spin_unlock(&rq->lock); + + __migrate_task(next, dead_cpu, dest_cpu); + + raw_spin_lock(&rq->lock); + } + + rq->stop = stop; +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +static void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +static void unregister_sched_domain_sysctl(void) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#else +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + const struct sched_class *class; + + cpumask_set_cpu(rq->cpu, rq->rd->online); + rq->online = 1; + + for_each_class(class) { + if (class->rq_online) + class->rq_online(rq); + } + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + const struct sched_class *class; + + for_each_class(class) { + if (class->rq_offline) + class->rq_offline(rq); + } + + cpumask_clear_cpu(rq->cpu, rq->rd->online); + rq->online = 0; + } +} + +/* + * migration_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + unsigned long flags; + struct rq *rq = cpu_rq(cpu); + + switch (action & ~CPU_TASKS_FROZEN) { + + case CPU_UP_PREPARE: + rq->calc_load_update = calc_load_update; + break; + + case CPU_ONLINE: + /* Update our root-domain */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + + set_rq_online(rq); + } + raw_spin_unlock_irqrestore(&rq->lock, flags); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DYING: + sched_ttwu_pending(); + /* Update our root-domain */ + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + migrate_tasks(cpu); + BUG_ON(rq->nr_running != 1); /* the migration thread */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + break; + + case CPU_DEAD: + calc_load_migrate(rq); + break; +#endif + } + + update_max_interval(); + + return NOTIFY_OK; +} + +/* + * Register at high priority so that task migration (migrate_all_tasks) + * happens before everything else. This has to be lower priority than + * the notifier in the perf_event subsystem, though. + */ +static struct notifier_block migration_notifier = { + .notifier_call = migration_call, + .priority = CPU_PRI_MIGRATION, +}; + +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + +static int sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __init migration_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + /* Initialize migration for the boot CPU */ + err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); + BUG_ON(err == NOTIFY_BAD); + migration_call(&migration_notifier, CPU_ONLINE, cpu); + register_cpu_notifier(&migration_notifier); + + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + + return 0; +} +early_initcall(migration_init); +#endif + +#ifdef CONFIG_SMP + +static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + struct sched_group *group = sd->groups; + + cpumask_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!cpumask_weight(sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %d)", + group->sgc->capacity); + } + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + cpudl_cleanup(&rd->cpudl); + free_cpumask_var(rd->dlo_mask); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + goto free_online; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_dlo_mask; + + init_dl_bw(&rd->dl_bw); + if (cpudl_init(&rd->cpudl) != 0) + goto free_dlo_mask; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_rto_mask; + return 0; + +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_dlo_mask: + free_cpumask_var(rd->dlo_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +/* + * By default the system creates a single root-domain with all cpus as + * members (mimicking the global state we have today). + */ +struct root_domain def_root_domain; + +static void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_groups(struct sched_group *sg, int free_sgc) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgc); + kfree(sd->groups); + } + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + +/* + * Keep a special pointer to the highest sched_domain that has + * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this + * allows us to avoid some pointer chasing select_idle_sibling(). + * + * Also keep a unique ID per domain (we use the first cpu number in + * the cpumask of the domain), this allows us to quickly tell if + * two cpus are in the same cache domain, see cpus_share_cache(). + */ +DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); +DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(struct sched_domain *, sd_numa); +DEFINE_PER_CPU(struct sched_domain *, sd_busy); +DEFINE_PER_CPU(struct sched_domain *, sd_asym); + +static void update_top_cache_domain(int cpu) +{ + struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; + int id = cpu; + int size = 1; + + sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + if (sd) { + id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + busy_sd = sd->parent; /* sd_busy */ + } + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); + + rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; + per_cpu(sd_llc_id, cpu) = id; + + sd = lowest_flag_domain(cpu, SD_NUMA); + rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); + + sd = highest_flag_domain(cpu, SD_ASYM_PACKING); + rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent, cpu); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp, cpu); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); + + update_top_cache_domain(cpu); +} + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + alloc_bootmem_cpumask_var(&cpu_isolated_map); + cpulist_parse(str, cpu_isolated_map); + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Build an iteration mask that can exclude certain CPUs from the upwards + * domain traversal. + * + * Asymmetric node setups can result in situations where the domain tree is of + * unequal depth, make sure to skip domains that already cover the entire + * range. + * + * In that case build_sched_domains() will have terminated the iteration early + * and our sibling sd spans will be empty. Domains should always include the + * cpu they're built on, so check that. + * + */ +static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +{ + const struct cpumask *span = sched_domain_span(sd); + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + for_each_cpu(i, span) { + sibling = *per_cpu_ptr(sdd->sd, i); + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + cpumask_set_cpu(i, sched_group_mask(sg)); + } +} + +/* + * Return the canonical balance cpu for this group, this is the first cpu + * of this group that's also in the iteration mask. + */ +int group_balance_cpu(struct sched_group *sg) +{ + return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); +} + +static int +build_overlap_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct cpumask *sg_span; + + if (cpumask_test_cpu(i, covered)) + continue; + + sibling = *per_cpu_ptr(sdd->sd, i); + + /* See the comment near build_group_mask(). */ + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + goto fail; + + sg_span = sched_group_cpus(sg); + if (sibling->child) + cpumask_copy(sg_span, sched_domain_span(sibling->child)); + else + cpumask_set_cpu(i, sg_span); + + cpumask_or(covered, covered, sg_span); + + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) + build_group_mask(sd, sg); + + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + + /* + * Make sure the first group of this domain contains the + * canonical balance cpu. Otherwise the sched_domain iteration + * breaks. See update_sg_lb_stats(). + */ + if ((!groups && cpumask_test_cpu(cpu, sg_span)) || + group_balance_cpu(sg) == cpu) + groups = sg; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; + + return 0; + +fail: + free_sched_groups(first, 0); + + return -ENOMEM; +} + +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) +{ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; + + if (child) + cpu = cpumask_first(sched_domain_span(child)); + + if (sg) { + *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ + } + + return cpu; +} + +/* + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_capacity to 0. + * + * Assumes the sched_domain tree is fully constructed + */ +static int +build_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered; + int i; + + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); + + if (cpu != cpumask_first(span)) + return 0; + + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct sched_group *sg; + int group, j; + + if (cpumask_test_cpu(i, covered)) + continue; + + group = get_group(i, sdd, &sg); + cpumask_setall(sched_group_mask(sg)); + + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; + + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; + + return 0; +} + +/* + * Initialize sched groups cpu_capacity. + * + * cpu_capacity indicates the capacity of sched group, which is used while + * distributing the load between different sched groups in a sched domain. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. + */ +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) +{ + struct sched_group *sg = sd->groups; + + WARN_ON(!sg); + + do { + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg = sg->next; + } while (sg != sd->groups); + + if (cpu != group_balance_cpu(sg)) + return; + + update_group_capacity(sd, cpu); + atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* turn off idle balance on this domain */ + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); /* fall through */ + case sa_sd: + free_percpu(d->sd); /* fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); /* fall through */ + case sa_none: + break; + } +} + +static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, + const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) + *per_cpu_ptr(sdd->sg, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +enum numa_topology_type sched_numa_topology_type; +static int *sched_domains_numa_distance; +int sched_max_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*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_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; + + return sd; +} + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +/* + * A system can have three types of NUMA topology: + * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system + * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes + * NUMA_BACKPLANE: nodes can reach other nodes through a backplane + * + * The difference between a glueless mesh topology and a backplane + * topology lies in whether communication between not directly + * connected nodes goes through intermediary nodes (where programs + * could run), or through backplane controllers. This affects + * placement of programs. + * + * The type of topology can be discerned with the following tests: + * - If the maximum distance between any nodes is 1 hop, the system + * is directly connected. + * - If for two nodes A and B, located N > 1 hops away from each other, + * there is an intermediary node C, which is < N hops away from both + * nodes A and B, the system is a glueless mesh. + */ +static void init_numa_topology_type(void) +{ + int a, b, c, n; + + n = sched_max_numa_distance; + + if (n <= 1) + sched_numa_topology_type = NUMA_DIRECT; + + for_each_online_node(a) { + for_each_online_node(b) { + /* Find two nodes furthest removed from each other. */ + if (node_distance(a, b) < n) + continue; + + /* Is there an intermediary node between a and b? */ + for_each_online_node(c) { + if (node_distance(a, c) < n && + node_distance(b, c) < n) { + sched_numa_topology_type = + NUMA_GLUELESS_MESH; + return; + } + } + + sched_numa_topology_type = NUMA_BACKPLANE; + return; + } + } +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + + if (!level) + return; + + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; + sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + + init_numa_topology_type(); +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int i, j; + int node = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +/* + * Update sched_domains_numa_masks[level][node] array when new cpus + * are onlined. + */ +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + sched_domains_numa_masks_set(cpu); + break; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} +#else +static inline void sched_init_numa(void) +{ +} + +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + return 0; +} +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + sdd->sg = alloc_percpu(struct sched_group *); + if (!sdd->sg) + return -ENOMEM; + + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_group *sg; + struct sched_group_capacity *sgc; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return -ENOMEM; + + sg->next = sg; + + *per_cpu_ptr(sdd->sg, j) = sg; + + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sgc) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgc, j) = sgc; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); + } + free_percpu(sdd->sd); + sdd->sd = NULL; + free_percpu(sdd->sg); + sdd->sg = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; + } +} + +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) +{ + struct sched_domain *sd = sd_init(tl, cpu); + if (!sd) + return child; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for cpus specified by the cpu_map. */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } + } + } + + /* Calculate CPU capacity for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + init_sched_groups_capacity(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d.sd, i); + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +static cpumask_var_t *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +static cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated cpus, but could be used to + * exclude other special cases in the future. + */ +static int init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * Detach sched domains from a group of cpus specified in cpu_map + * These cpus will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* fast path */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur[i]); +match1: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* no match - add a new doms_new */ + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); + kfree(dattr_cur); /* kfree(NULL) is safe */ + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + +/* + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. + */ +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + + case CPU_ONLINE: + cpuset_update_active_cpus(true); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + bool overflow; + int cpus; + + switch (action) { + case CPU_DOWN_PREPARE: + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) + return notifier_from_errno(-EBUSY); + cpuset_update_active_cpus(false); + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; + default: + return NOTIFY_DONE; + } + return NOTIFY_OK; +} + +void __init sched_init_smp(void) +{ + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + + sched_init_numa(); + + /* + * There's no userspace yet to cause hotplug operations; hence all the + * cpu masks are stable and all blatant races in the below code cannot + * happen. + */ + mutex_lock(&sched_domains_mutex); + init_sched_domains(cpu_active_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + + hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); + + init_hrtick(); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + BUG(); + sched_init_granularity(); + free_cpumask_var(non_isolated_cpus); + + init_sched_rt_class(); + init_sched_dl_class(); +} +#else +void __init sched_init_smp(void) +{ + sched_init_granularity(); +} +#endif /* CONFIG_SMP */ + +const_debug unsigned int sysctl_timer_migration = 1; + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +#ifdef CONFIG_CGROUP_SCHED +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ +struct task_group root_task_group; +LIST_HEAD(task_groups); +#endif + +DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); + +void __init sched_init(void) +{ + int i, j; + unsigned long alloc_size = 0, ptr; + +#ifdef CONFIG_FAIR_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif +#ifdef CONFIG_RT_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif + if (alloc_size) { + ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); + +#ifdef CONFIG_FAIR_GROUP_SCHED + root_task_group.se = (struct sched_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.cfs_rq = (struct cfs_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_RT_GROUP_SCHED + root_task_group.rt_se = (struct sched_rt_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.rt_rq = (struct rt_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#endif /* CONFIG_RT_GROUP_SCHED */ + } +#ifdef CONFIG_CPUMASK_OFFSTACK + for_each_possible_cpu(i) { + per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node( + cpumask_size(), GFP_KERNEL, cpu_to_node(i)); + } +#endif /* CONFIG_CPUMASK_OFFSTACK */ + + init_rt_bandwidth(&def_rt_bandwidth, + global_rt_period(), global_rt_runtime()); + init_dl_bandwidth(&def_dl_bandwidth, + global_rt_period(), global_rt_runtime()); + +#ifdef CONFIG_SMP + init_defrootdomain(); +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + init_rt_bandwidth(&root_task_group.rt_bandwidth, + global_rt_period(), global_rt_runtime()); +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_CGROUP_SCHED + list_add(&root_task_group.list, &task_groups); + INIT_LIST_HEAD(&root_task_group.children); + INIT_LIST_HEAD(&root_task_group.siblings); + autogroup_init(&init_task); + +#endif /* CONFIG_CGROUP_SCHED */ + + for_each_possible_cpu(i) { + struct rq *rq; + + rq = cpu_rq(i); + raw_spin_lock_init(&rq->lock); + rq->nr_running = 0; + rq->calc_load_active = 0; + rq->calc_load_update = jiffies + LOAD_FREQ; + init_cfs_rq(&rq->cfs); + init_rt_rq(&rq->rt); + init_dl_rq(&rq->dl); +#ifdef CONFIG_FAIR_GROUP_SCHED + root_task_group.shares = ROOT_TASK_GROUP_LOAD; + INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); + /* + * How much cpu bandwidth does root_task_group get? + * + * In case of task-groups formed thr' the cgroup filesystem, it + * gets 100% of the cpu resources in the system. This overall + * system cpu resource is divided among the tasks of + * root_task_group and its child task-groups in a fair manner, + * based on each entity's (task or task-group's) weight + * (se->load.weight). + * + * In other words, if root_task_group has 10 tasks of weight + * 1024) and two child groups A0 and A1 (of weight 1024 each), + * then A0's share of the cpu resource is: + * + * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% + * + * We achieve this by letting root_task_group's tasks sit + * directly in rq->cfs (i.e root_task_group->se[] = NULL). + */ + init_cfs_bandwidth(&root_task_group.cfs_bandwidth); + init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; +#ifdef CONFIG_RT_GROUP_SCHED + init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); +#endif + + for (j = 0; j < CPU_LOAD_IDX_MAX; j++) + rq->cpu_load[j] = 0; + + rq->last_load_update_tick = jiffies; + +#ifdef CONFIG_SMP + rq->sd = NULL; + rq->rd = NULL; + rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; + rq->post_schedule = 0; + rq->active_balance = 0; + rq->next_balance = jiffies; + rq->push_cpu = 0; + rq->cpu = i; + rq->online = 0; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; + rq->max_idle_balance_cost = sysctl_sched_migration_cost; + + INIT_LIST_HEAD(&rq->cfs_tasks); + + rq_attach_root(rq, &def_root_domain); +#ifdef CONFIG_NO_HZ_COMMON + rq->nohz_flags = 0; +#endif +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = 0; +#endif +#endif + init_rq_hrtick(rq); + atomic_set(&rq->nr_iowait, 0); + } + + set_load_weight(&init_task); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + atomic_inc(&init_mm.mm_count); + enter_lazy_tlb(&init_mm, current); + + /* + * During early bootup we pretend to be a normal task: + */ + current->sched_class = &fair_sched_class; + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + + calc_load_update = jiffies + LOAD_FREQ; + +#ifdef CONFIG_SMP + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); +#endif + init_sched_fair_class(); + + scheduler_running = 1; +} + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); + + return (nested == preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) +{ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change); + + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; /* ratelimiting */ + + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || + system_state != SYSTEM_RUNNING || oops_in_progress) + return; + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR + "BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + printk(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); +} +EXPORT_SYMBOL(___might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +static void normalize_task(struct rq *rq, struct task_struct *p) +{ + const struct sched_class *prev_class = p->sched_class; + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + }; + int old_prio = p->prio; + int queued; + + queued = task_on_rq_queued(p); + if (queued) + dequeue_task(rq, p, 0); + __setscheduler(rq, p, &attr, false); + if (queued) { + enqueue_task(rq, p, 0); + resched_curr(rq); + } + + check_class_changed(rq, p, prev_class, old_prio); +} + +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + /* + * Only normalize user tasks: + */ + if (p->flags & PF_KTHREAD) + continue; + + p->se.exec_start = 0; +#ifdef CONFIG_SCHEDSTATS + p->se.statistics.wait_start = 0; + p->se.statistics.sleep_start = 0; + p->se.statistics.block_start = 0; +#endif + + if (!dl_task(p) && !rt_task(p)) { + /* + * Renice negative nice level userspace + * tasks back to 0: + */ + if (task_nice(p) < 0) + set_user_nice(p, 0); + continue; + } + + rq = task_rq_lock(p, &flags); + normalize_task(rq, p); + task_rq_unlock(rq, p, &flags); + } + read_unlock(&tasklist_lock); +} + +#endif /* CONFIG_MAGIC_SYSRQ */ + +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +/* + * These functions are only useful for the IA64 MCA handling, or kdb. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given cpu. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 +/** + * set_curr_task - set the current task for a given cpu. + * @cpu: the processor in question. + * @p: the task pointer to set. + * + * Description: This function must only be used when non-maskable interrupts + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a cpu in a non-blocking manner. This function + * must be called with all CPU's synchronized, and interrupts disabled, the + * and caller must save the original value of the current task (see + * curr_task() above) and restore that value before reenabling interrupts and + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +#ifdef CONFIG_CGROUP_SCHED +/* task_group_lock serializes the addition/removal of task groups */ +static DEFINE_SPINLOCK(task_group_lock); + +static void free_sched_group(struct task_group *tg) +{ + free_fair_sched_group(tg); + free_rt_sched_group(tg); + autogroup_free(tg); + kfree(tg); +} + +/* allocate runqueue etc for a new task group */ +struct task_group *sched_create_group(struct task_group *parent) +{ + struct task_group *tg; + + tg = kzalloc(sizeof(*tg), GFP_KERNEL); + if (!tg) + return ERR_PTR(-ENOMEM); + + if (!alloc_fair_sched_group(tg, parent)) + goto err; + + if (!alloc_rt_sched_group(tg, parent)) + goto err; + + return tg; + +err: + free_sched_group(tg); + return ERR_PTR(-ENOMEM); +} + +void sched_online_group(struct task_group *tg, struct task_group *parent) +{ + unsigned long flags; + + spin_lock_irqsave(&task_group_lock, flags); + list_add_rcu(&tg->list, &task_groups); + + WARN_ON(!parent); /* root should already exist */ + + tg->parent = parent; + INIT_LIST_HEAD(&tg->children); + list_add_rcu(&tg->siblings, &parent->children); + spin_unlock_irqrestore(&task_group_lock, flags); +} + +/* rcu callback to free various structures associated with a task group */ +static void free_sched_group_rcu(struct rcu_head *rhp) +{ + /* now it should be safe to free those cfs_rqs */ + free_sched_group(container_of(rhp, struct task_group, rcu)); +} + +/* Destroy runqueue etc associated with a task group */ +void sched_destroy_group(struct task_group *tg) +{ + /* wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, free_sched_group_rcu); +} + +void sched_offline_group(struct task_group *tg) +{ + unsigned long flags; + int i; + + /* end participation in shares distribution */ + for_each_possible_cpu(i) + unregister_fair_sched_group(tg, i); + + spin_lock_irqsave(&task_group_lock, flags); + list_del_rcu(&tg->list); + list_del_rcu(&tg->siblings); + spin_unlock_irqrestore(&task_group_lock, flags); +} + +/* change task's runqueue when it moves between groups. + * The caller of this function should have put the task in its new group + * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to + * reflect its new group. + */ +void sched_move_task(struct task_struct *tsk) +{ + struct task_group *tg; + int queued, running; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(tsk, &flags); + + running = task_current(rq, tsk); + queued = task_on_rq_queued(tsk); + + if (queued) + dequeue_task(rq, tsk, 0); + if (unlikely(running)) + put_prev_task(rq, tsk); + + /* + * All callers are synchronized by task_rq_lock(); we do not use RCU + * which is pointless here. Thus, we pass "true" to task_css_check() + * to prevent lockdep warnings. + */ + tg = container_of(task_css_check(tsk, cpu_cgrp_id, true), + struct task_group, css); + tg = autogroup_task_group(tsk, tg); + tsk->sched_task_group = tg; + +#ifdef CONFIG_FAIR_GROUP_SCHED + if (tsk->sched_class->task_move_group) + tsk->sched_class->task_move_group(tsk, queued); + else +#endif + set_task_rq(tsk, task_cpu(tsk)); + + if (unlikely(running)) + tsk->sched_class->set_curr_task(rq); + if (queued) + enqueue_task(rq, tsk, 0); + + task_rq_unlock(rq, tsk, &flags); +} +#endif /* CONFIG_CGROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); + +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) +{ + struct task_struct *g, *p; + + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + + for_each_process_thread(g, p) { + if (rt_task(p) && task_group(p) == tg) + return 1; + } + + return 0; +} + +struct rt_schedulable_data { + struct task_group *tg; + u64 rt_period; + u64 rt_runtime; +}; + +static int tg_rt_schedulable(struct task_group *tg, void *data) +{ + struct rt_schedulable_data *d = data; + struct task_group *child; + unsigned long total, sum = 0; + u64 period, runtime; + + period = ktime_to_ns(tg->rt_bandwidth.rt_period); + runtime = tg->rt_bandwidth.rt_runtime; + + if (tg == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + /* + * Cannot have more runtime than the period. + */ + if (runtime > period && runtime != RUNTIME_INF) + return -EINVAL; + + /* + * Ensure we don't starve existing RT tasks. + */ + if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg)) + return -EBUSY; + + total = to_ratio(period, runtime); + + /* + * Nobody can have more than the global setting allows. + */ + if (total > to_ratio(global_rt_period(), global_rt_runtime())) + return -EINVAL; + + /* + * The sum of our children's runtime should not exceed our own. + */ + list_for_each_entry_rcu(child, &tg->children, siblings) { + period = ktime_to_ns(child->rt_bandwidth.rt_period); + runtime = child->rt_bandwidth.rt_runtime; + + if (child == d->tg) { + period = d->rt_period; + runtime = d->rt_runtime; + } + + sum += to_ratio(period, runtime); + } + + if (sum > total) + return -EINVAL; + + return 0; +} + +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + int ret; + + struct rt_schedulable_data data = { + .tg = tg, + .rt_period = period, + .rt_runtime = runtime, + }; + + rcu_read_lock(); + ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int tg_set_rt_bandwidth(struct task_group *tg, + u64 rt_period, u64 rt_runtime) +{ + int i, err = 0; + + /* + * Disallowing the root group RT runtime is BAD, it would disallow the + * kernel creating (and or operating) RT threads. + */ + if (tg == &root_task_group && rt_runtime == 0) + return -EINVAL; + + /* No period doesn't make any sense. */ + if (rt_period == 0) + return -EINVAL; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + err = __rt_schedulable(tg, rt_period, rt_runtime); + if (err) + goto unlock; + + raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); + tg->rt_bandwidth.rt_runtime = rt_runtime; + + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = tg->rt_rq[i]; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_runtime; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); +unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return err; +} + +static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +{ + u64 rt_runtime, rt_period; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; + if (rt_runtime_us < 0) + rt_runtime = RUNTIME_INF; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +static long sched_group_rt_runtime(struct task_group *tg) +{ + u64 rt_runtime_us; + + if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) + return -1; + + rt_runtime_us = tg->rt_bandwidth.rt_runtime; + do_div(rt_runtime_us, NSEC_PER_USEC); + return rt_runtime_us; +} + +static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +{ + u64 rt_runtime, rt_period; + + rt_period = (u64)rt_period_us * NSEC_PER_USEC; + rt_runtime = tg->rt_bandwidth.rt_runtime; + + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); +} + +static long sched_group_rt_period(struct task_group *tg) +{ + u64 rt_period_us; + + rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); + do_div(rt_period_us, NSEC_PER_USEC); + return rt_period_us; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static int sched_rt_global_constraints(void) +{ + int ret = 0; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + ret = __rt_schedulable(NULL, 0, 0); + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return ret; +} + +static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +{ + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) + return 0; + + return 1; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ +static int sched_rt_global_constraints(void) +{ + unsigned long flags; + int i, ret = 0; + + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = &cpu_rq(i)->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = global_rt_runtime(); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + + return ret; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static int sched_dl_global_validate(void) +{ + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + struct dl_bw *dl_b; + int cpu, ret = 0; + unsigned long flags; + + /* + * Here we want to check the bandwidth not being set to some + * value smaller than the currently allocated bandwidth in + * any of the root_domains. + * + * FIXME: Cycling on all the CPUs is overdoing, but simpler than + * cycling on root_domains... Discussion on different/better + * solutions is welcome! + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + if (new_bw < dl_b->total_bw) + ret = -EBUSY; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (ret) + break; + } + + return ret; +} + +static void sched_dl_do_global(void) +{ + u64 new_bw = -1; + struct dl_bw *dl_b; + int cpu; + unsigned long flags; + + def_dl_bandwidth.dl_period = global_rt_period(); + def_dl_bandwidth.dl_runtime = global_rt_runtime(); + + if (global_rt_runtime() != RUNTIME_INF) + new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + + /* + * FIXME: As above... + */ + for_each_possible_cpu(cpu) { + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + dl_b->bw = new_bw; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + } +} + +static int sched_rt_global_validate(void) +{ + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + return -EINVAL; + + return 0; +} + +static void sched_rt_do_global(void) +{ + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); +} + +int sched_rt_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old_period, old_runtime; + static DEFINE_MUTEX(mutex); + int ret; + + mutex_lock(&mutex); + old_period = sysctl_sched_rt_period; + old_runtime = sysctl_sched_rt_runtime; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (!ret && write) { + ret = sched_rt_global_validate(); + if (ret) + goto undo; + + ret = sched_dl_global_validate(); + if (ret) + goto undo; + + ret = sched_rt_global_constraints(); + if (ret) + goto undo; + + sched_rt_do_global(); + sched_dl_do_global(); + } + if (0) { +undo: + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; + } + mutex_unlock(&mutex); + + return ret; +} + +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* make sure that internally we keep jiffies */ + /* also, writing zero resets timeslice to default */ + if (!ret && write) { + sched_rr_timeslice = sched_rr_timeslice <= 0 ? + RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + +#ifdef CONFIG_CGROUP_SCHED + +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct task_group, css) : NULL; +} + +static struct cgroup_subsys_state * +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; + + if (!parent) { + /* This is early initialization for the top cgroup */ + return &root_task_group.css; + } + + tg = sched_create_group(parent); + if (IS_ERR(tg)) + return ERR_PTR(-ENOMEM); + + return &tg->css; +} + +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_destroy_group(tg); +} + +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_offline_group(tg); +} + +static void cpu_cgroup_fork(struct task_struct *task) +{ + sched_move_task(task); +} + +static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *task; + + cgroup_taskset_for_each(task, tset) { +#ifdef CONFIG_RT_GROUP_SCHED + if (!sched_rt_can_attach(css_tg(css), task)) + return -EINVAL; +#else + /* We don't support RT-tasks being in separate groups */ + if (task->sched_class != &fair_sched_class) + return -EINVAL; +#endif + } + return 0; +} + +static void cpu_cgroup_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *task; + + cgroup_taskset_for_each(task, tset) + sched_move_task(task); +} + +static void cpu_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task) +{ + /* + * cgroup_exit() is called in the copy_process() failure path. + * Ignore this case since the task hasn't ran yet, this avoids + * trying to poke a half freed task state from generic code. + */ + if (!(task->flags & PF_EXITING)) + return; + + sched_move_task(task); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static int cpu_shares_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 shareval) +{ + return sched_group_set_shares(css_tg(css), scale_load(shareval)); +} + +static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct task_group *tg = css_tg(css); + + return (u64) scale_load_down(tg->shares); +} + +#ifdef CONFIG_CFS_BANDWIDTH +static DEFINE_MUTEX(cfs_constraints_mutex); + +const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ +const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); + +static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) +{ + int i, ret = 0, runtime_enabled, runtime_was_enabled; + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + + if (tg == &root_task_group) + return -EINVAL; + + /* + * Ensure we have at some amount of bandwidth every period. This is + * to prevent reaching a state of large arrears when throttled via + * entity_tick() resulting in prolonged exit starvation. + */ + if (quota < min_cfs_quota_period || period < min_cfs_quota_period) + return -EINVAL; + + /* + * Likewise, bound things on the otherside by preventing insane quota + * periods. This also allows us to normalize in computing quota + * feasibility. + */ + if (period > max_cfs_quota_period) + return -EINVAL; + + /* + * Prevent race between setting of cfs_rq->runtime_enabled and + * unthrottle_offline_cfs_rqs(). + */ + get_online_cpus(); + mutex_lock(&cfs_constraints_mutex); + ret = __cfs_schedulable(tg, period, quota); + if (ret) + goto out_unlock; + + runtime_enabled = quota != RUNTIME_INF; + runtime_was_enabled = cfs_b->quota != RUNTIME_INF; + /* + * If we need to toggle cfs_bandwidth_used, off->on must occur + * before making related changes, and on->off must occur afterwards + */ + if (runtime_enabled && !runtime_was_enabled) + cfs_bandwidth_usage_inc(); + raw_spin_lock_irq(&cfs_b->lock); + cfs_b->period = ns_to_ktime(period); + cfs_b->quota = quota; + + __refill_cfs_bandwidth_runtime(cfs_b); + /* restart the period timer (if active) to handle new period expiry */ + if (runtime_enabled && cfs_b->timer_active) { + /* force a reprogram */ + __start_cfs_bandwidth(cfs_b, true); + } + raw_spin_unlock_irq(&cfs_b->lock); + + for_each_online_cpu(i) { + struct cfs_rq *cfs_rq = tg->cfs_rq[i]; + struct rq *rq = cfs_rq->rq; + + raw_spin_lock_irq(&rq->lock); + cfs_rq->runtime_enabled = runtime_enabled; + cfs_rq->runtime_remaining = 0; + + if (cfs_rq->throttled) + unthrottle_cfs_rq(cfs_rq); + raw_spin_unlock_irq(&rq->lock); + } + if (runtime_was_enabled && !runtime_enabled) + cfs_bandwidth_usage_dec(); +out_unlock: + mutex_unlock(&cfs_constraints_mutex); + put_online_cpus(); + + return ret; +} + +int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) +{ + u64 quota, period; + + period = ktime_to_ns(tg->cfs_bandwidth.period); + if (cfs_quota_us < 0) + quota = RUNTIME_INF; + else + quota = (u64)cfs_quota_us * NSEC_PER_USEC; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_quota(struct task_group *tg) +{ + u64 quota_us; + + if (tg->cfs_bandwidth.quota == RUNTIME_INF) + return -1; + + quota_us = tg->cfs_bandwidth.quota; + do_div(quota_us, NSEC_PER_USEC); + + return quota_us; +} + +int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) +{ + u64 quota, period; + + period = (u64)cfs_period_us * NSEC_PER_USEC; + quota = tg->cfs_bandwidth.quota; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_period(struct task_group *tg) +{ + u64 cfs_period_us; + + cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period); + do_div(cfs_period_us, NSEC_PER_USEC); + + return cfs_period_us; +} + +static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return tg_get_cfs_quota(css_tg(css)); +} + +static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 cfs_quota_us) +{ + return tg_set_cfs_quota(css_tg(css), cfs_quota_us); +} + +static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return tg_get_cfs_period(css_tg(css)); +} + +static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 cfs_period_us) +{ + return tg_set_cfs_period(css_tg(css), cfs_period_us); +} + +struct cfs_schedulable_data { + struct task_group *tg; + u64 period, quota; +}; + +/* + * normalize group quota/period to be quota/max_period + * note: units are usecs + */ +static u64 normalize_cfs_quota(struct task_group *tg, + struct cfs_schedulable_data *d) +{ + u64 quota, period; + + if (tg == d->tg) { + period = d->period; + quota = d->quota; + } else { + period = tg_get_cfs_period(tg); + quota = tg_get_cfs_quota(tg); + } + + /* note: these should typically be equivalent */ + if (quota == RUNTIME_INF || quota == -1) + return RUNTIME_INF; + + return to_ratio(period, quota); +} + +static int tg_cfs_schedulable_down(struct task_group *tg, void *data) +{ + struct cfs_schedulable_data *d = data; + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + s64 quota = 0, parent_quota = -1; + + if (!tg->parent) { + quota = RUNTIME_INF; + } else { + struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth; + + quota = normalize_cfs_quota(tg, d); + parent_quota = parent_b->hierarchical_quota; + + /* + * ensure max(child_quota) <= parent_quota, inherit when no + * limit is set + */ + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF && quota > parent_quota) + return -EINVAL; + } + cfs_b->hierarchical_quota = quota; + + return 0; +} + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) +{ + int ret; + struct cfs_schedulable_data data = { + .tg = tg, + .period = period, + .quota = quota, + }; + + if (quota != RUNTIME_INF) { + do_div(data.period, NSEC_PER_USEC); + do_div(data.quota, NSEC_PER_USEC); + } + + rcu_read_lock(); + ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int cpu_stats_show(struct seq_file *sf, void *v) +{ + struct task_group *tg = css_tg(seq_css(sf)); + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + + seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods); + seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); + seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); + + return 0; +} +#endif /* CONFIG_CFS_BANDWIDTH */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) +{ + return sched_group_set_rt_runtime(css_tg(css), val); +} + +static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return sched_group_rt_runtime(css_tg(css)); +} + +static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 rt_period_us) +{ + return sched_group_set_rt_period(css_tg(css), rt_period_us); +} + +static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return sched_group_rt_period(css_tg(css)); +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static struct cftype cpu_files[] = { +#ifdef CONFIG_FAIR_GROUP_SCHED + { + .name = "shares", + .read_u64 = cpu_shares_read_u64, + .write_u64 = cpu_shares_write_u64, + }, +#endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .name = "cfs_quota_us", + .read_s64 = cpu_cfs_quota_read_s64, + .write_s64 = cpu_cfs_quota_write_s64, + }, + { + .name = "cfs_period_us", + .read_u64 = cpu_cfs_period_read_u64, + .write_u64 = cpu_cfs_period_write_u64, + }, + { + .name = "stat", + .seq_show = cpu_stats_show, + }, +#endif +#ifdef CONFIG_RT_GROUP_SCHED + { + .name = "rt_runtime_us", + .read_s64 = cpu_rt_runtime_read, + .write_s64 = cpu_rt_runtime_write, + }, + { + .name = "rt_period_us", + .read_u64 = cpu_rt_period_read_uint, + .write_u64 = cpu_rt_period_write_uint, + }, +#endif + { } /* terminate */ +}; + +struct cgroup_subsys cpu_cgrp_subsys = { + .css_alloc = cpu_cgroup_css_alloc, + .css_free = cpu_cgroup_css_free, + .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, + .fork = cpu_cgroup_fork, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, + .exit = cpu_cgroup_exit, + .legacy_cftypes = cpu_files, + .early_init = 1, +}; + +#endif /* CONFIG_CGROUP_SCHED */ + +void dump_cpu_task(int cpu) +{ + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); +} diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c new file mode 100644 index 000000000..dd7cbb55b --- /dev/null +++ b/kernel/sched/cpuacct.c @@ -0,0 +1,283 @@ +#include <linux/cgroup.h> +#include <linux/slab.h> +#include <linux/percpu.h> +#include <linux/spinlock.h> +#include <linux/cpumask.h> +#include <linux/seq_file.h> +#include <linux/rcupdate.h> +#include <linux/kernel_stat.h> +#include <linux/err.h> + +#include "sched.h" + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { + CPUACCT_STAT_USER, /* ... user mode */ + CPUACCT_STAT_SYSTEM, /* ... kernel mode */ + + CPUACCT_STAT_NSTATS, +}; + +/* track cpu usage of a group of tasks and its child groups */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 __percpu *cpuusage; + struct kernel_cpustat __percpu *cpustat; +}; + +static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cpuacct, css) : NULL; +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return css_ca(task_css(tsk, cpuacct_cgrp_id)); +} + +static inline struct cpuacct *parent_ca(struct cpuacct *ca) +{ + return css_ca(ca->css.parent); +} + +static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); +static struct cpuacct root_cpuacct = { + .cpustat = &kernel_cpustat, + .cpuusage = &root_cpuacct_cpuusage, +}; + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state * +cpuacct_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cpuacct *ca; + + if (!parent_css) + return &root_cpuacct.css; + + ca = kzalloc(sizeof(*ca), GFP_KERNEL); + if (!ca) + goto out; + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) + goto out_free_ca; + + ca->cpustat = alloc_percpu(struct kernel_cpustat); + if (!ca->cpustat) + goto out_free_cpuusage; + + return &ca->css; + +out_free_cpuusage: + free_percpu(ca->cpuusage); +out_free_ca: + kfree(ca); +out: + return ERR_PTR(-ENOMEM); +} + +/* destroy an existing cpu accounting group */ +static void cpuacct_css_free(struct cgroup_subsys_state *css) +{ + struct cpuacct *ca = css_ca(css); + + free_percpu(ca->cpustat); + free_percpu(ca->cpuusage); + kfree(ca); +} + +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + u64 data; + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit read safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + data = *cpuusage; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + data = *cpuusage; +#endif + + return data; +} + +static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit write safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + *cpuusage = val; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + *cpuusage = val; +#endif +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct cpuacct *ca = css_ca(css); + u64 totalcpuusage = 0; + int i; + + for_each_present_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i); + + return totalcpuusage; +} + +static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, + u64 reset) +{ + struct cpuacct *ca = css_ca(css); + int err = 0; + int i; + + if (reset) { + err = -EINVAL; + goto out; + } + + for_each_present_cpu(i) + cpuacct_cpuusage_write(ca, i, 0); + +out: + return err; +} + +static int cpuacct_percpu_seq_show(struct seq_file *m, void *V) +{ + struct cpuacct *ca = css_ca(seq_css(m)); + u64 percpu; + int i; + + for_each_present_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i); + seq_printf(m, "%llu ", (unsigned long long) percpu); + } + seq_printf(m, "\n"); + return 0; +} + +static const char * const cpuacct_stat_desc[] = { + [CPUACCT_STAT_USER] = "user", + [CPUACCT_STAT_SYSTEM] = "system", +}; + +static int cpuacct_stats_show(struct seq_file *sf, void *v) +{ + struct cpuacct *ca = css_ca(seq_css(sf)); + int cpu; + s64 val = 0; + + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_USER]; + val += kcpustat->cpustat[CPUTIME_NICE]; + } + val = cputime64_to_clock_t(val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val); + + val = 0; + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_SYSTEM]; + val += kcpustat->cpustat[CPUTIME_IRQ]; + val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; + } + + val = cputime64_to_clock_t(val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); + + return 0; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_u64 = cpuusage_read, + .write_u64 = cpuusage_write, + }, + { + .name = "usage_percpu", + .seq_show = cpuacct_percpu_seq_show, + }, + { + .name = "stat", + .seq_show = cpuacct_stats_show, + }, + { } /* terminate */ +}; + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + int cpu; + + cpu = task_cpu(tsk); + + rcu_read_lock(); + + ca = task_ca(tsk); + + while (true) { + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + *cpuusage += cputime; + + ca = parent_ca(ca); + if (!ca) + break; + } + + rcu_read_unlock(); +} + +/* + * Add user/system time to cpuacct. + * + * Note: it's the caller that updates the account of the root cgroup. + */ +void cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; + + rcu_read_lock(); + ca = task_ca(p); + while (ca != &root_cpuacct) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += val; + ca = parent_ca(ca); + } + rcu_read_unlock(); +} + +struct cgroup_subsys cpuacct_cgrp_subsys = { + .css_alloc = cpuacct_css_alloc, + .css_free = cpuacct_css_free, + .legacy_cftypes = files, + .early_init = 1, +}; diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h new file mode 100644 index 000000000..ed605624a --- /dev/null +++ b/kernel/sched/cpuacct.h @@ -0,0 +1,17 @@ +#ifdef CONFIG_CGROUP_CPUACCT + +extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); +extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); + +#else + +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ +} + +static inline void +cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ +} + +#endif diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c new file mode 100644 index 000000000..c6acb0746 --- /dev/null +++ b/kernel/sched/cpudeadline.c @@ -0,0 +1,246 @@ +/* + * kernel/sched/cpudl.c + * + * Global CPU deadline management + * + * Author: Juri Lelli <j.lelli@sssup.it> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include "cpudeadline.h" + +static inline int parent(int i) +{ + return (i - 1) >> 1; +} + +static inline int left_child(int i) +{ + return (i << 1) + 1; +} + +static inline int right_child(int i) +{ + return (i << 1) + 2; +} + +static inline int dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +static void cpudl_exchange(struct cpudl *cp, int a, int b) +{ + int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu; + + swap(cp->elements[a].cpu, cp->elements[b].cpu); + swap(cp->elements[a].dl , cp->elements[b].dl ); + + swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx); +} + +static void cpudl_heapify(struct cpudl *cp, int idx) +{ + int l, r, largest; + + /* adapted from lib/prio_heap.c */ + while(1) { + l = left_child(idx); + r = right_child(idx); + largest = idx; + + if ((l < cp->size) && dl_time_before(cp->elements[idx].dl, + cp->elements[l].dl)) + largest = l; + if ((r < cp->size) && dl_time_before(cp->elements[largest].dl, + cp->elements[r].dl)) + largest = r; + if (largest == idx) + break; + + /* Push idx down the heap one level and bump one up */ + cpudl_exchange(cp, largest, idx); + idx = largest; + } +} + +static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) +{ + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); + + if (dl_time_before(new_dl, cp->elements[idx].dl)) { + cp->elements[idx].dl = new_dl; + cpudl_heapify(cp, idx); + } else { + cp->elements[idx].dl = new_dl; + while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl, + cp->elements[idx].dl)) { + cpudl_exchange(cp, idx, parent(idx)); + idx = parent(idx); + } + } +} + +static inline int cpudl_maximum(struct cpudl *cp) +{ + return cp->elements[0].cpu; +} + +/* + * cpudl_find - find the best (later-dl) CPU in the system + * @cp: the cpudl max-heap context + * @p: the task + * @later_mask: a mask to fill in with the selected CPUs (or NULL) + * + * Returns: int - best CPU (heap maximum if suitable) + */ +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask) +{ + int best_cpu = -1; + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && + cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + best_cpu = cpumask_any(later_mask); + goto out; + } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + best_cpu = cpudl_maximum(cp); + if (later_mask) + cpumask_set_cpu(best_cpu, later_mask); + } + +out: + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); + + return best_cpu; +} + +/* + * cpudl_set - update the cpudl max-heap + * @cp: the cpudl max-heap context + * @cpu: the target cpu + * @dl: the new earliest deadline for this cpu + * + * Notes: assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) +{ + int old_idx, new_cpu; + unsigned long flags; + + WARN_ON(!cpu_present(cpu)); + + raw_spin_lock_irqsave(&cp->lock, flags); + old_idx = cp->elements[cpu].idx; + if (!is_valid) { + /* remove item */ + if (old_idx == IDX_INVALID) { + /* + * Nothing to remove if old_idx was invalid. + * This could happen if a rq_offline_dl is + * called for a CPU without -dl tasks running. + */ + goto out; + } + new_cpu = cp->elements[cp->size - 1].cpu; + cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl; + cp->elements[old_idx].cpu = new_cpu; + cp->size--; + cp->elements[new_cpu].idx = old_idx; + cp->elements[cpu].idx = IDX_INVALID; + while (old_idx > 0 && dl_time_before( + cp->elements[parent(old_idx)].dl, + cp->elements[old_idx].dl)) { + cpudl_exchange(cp, old_idx, parent(old_idx)); + old_idx = parent(old_idx); + } + cpumask_set_cpu(cpu, cp->free_cpus); + cpudl_heapify(cp, old_idx); + + goto out; + } + + if (old_idx == IDX_INVALID) { + cp->size++; + cp->elements[cp->size - 1].dl = 0; + cp->elements[cp->size - 1].cpu = cpu; + cp->elements[cpu].idx = cp->size - 1; + cpudl_change_key(cp, cp->size - 1, dl); + cpumask_clear_cpu(cpu, cp->free_cpus); + } else { + cpudl_change_key(cp, old_idx, dl); + } + +out: + raw_spin_unlock_irqrestore(&cp->lock, flags); +} + +/* + * cpudl_set_freecpu - Set the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_set_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_set_cpu(cpu, cp->free_cpus); +} + +/* + * cpudl_clear_freecpu - Clear the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_clear_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_clear_cpu(cpu, cp->free_cpus); +} + +/* + * cpudl_init - initialize the cpudl structure + * @cp: the cpudl max-heap context + */ +int cpudl_init(struct cpudl *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + raw_spin_lock_init(&cp->lock); + cp->size = 0; + + cp->elements = kcalloc(nr_cpu_ids, + sizeof(struct cpudl_item), + GFP_KERNEL); + if (!cp->elements) + return -ENOMEM; + + if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { + kfree(cp->elements); + return -ENOMEM; + } + + for_each_possible_cpu(i) + cp->elements[i].idx = IDX_INVALID; + + return 0; +} + +/* + * cpudl_cleanup - clean up the cpudl structure + * @cp: the cpudl max-heap context + */ +void cpudl_cleanup(struct cpudl *cp) +{ + free_cpumask_var(cp->free_cpus); + kfree(cp->elements); +} diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h new file mode 100644 index 000000000..1a0a6ef2f --- /dev/null +++ b/kernel/sched/cpudeadline.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_CPUDL_H +#define _LINUX_CPUDL_H + +#include <linux/sched.h> + +#define IDX_INVALID -1 + +struct cpudl_item { + u64 dl; + int cpu; + int idx; +}; + +struct cpudl { + raw_spinlock_t lock; + int size; + cpumask_var_t free_cpus; + struct cpudl_item *elements; +}; + + +#ifdef CONFIG_SMP +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask); +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid); +int cpudl_init(struct cpudl *cp); +void cpudl_set_freecpu(struct cpudl *cp, int cpu); +void cpudl_clear_freecpu(struct cpudl *cp, int cpu); +void cpudl_cleanup(struct cpudl *cp); +#endif /* CONFIG_SMP */ + +#endif /* _LINUX_CPUDL_H */ diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c new file mode 100644 index 000000000..981fcd7dc --- /dev/null +++ b/kernel/sched/cpupri.c @@ -0,0 +1,248 @@ +/* + * kernel/sched/cpupri.c + * + * CPU priority management + * + * Copyright (C) 2007-2008 Novell + * + * Author: Gregory Haskins <ghaskins@novell.com> + * + * This code tracks the priority of each CPU so that global migration + * decisions are easy to calculate. Each CPU can be in a state as follows: + * + * (INVALID), IDLE, NORMAL, RT1, ... RT99 + * + * going from the lowest priority to the highest. CPUs in the INVALID state + * are not eligible for routing. The system maintains this state with + * a 2 dimensional bitmap (the first for priority class, the second for cpus + * in that class). Therefore a typical application without affinity + * restrictions can find a suitable CPU with O(1) complexity (e.g. two bit + * searches). For tasks with affinity restrictions, the algorithm has a + * worst case complexity of O(min(102, nr_domcpus)), though the scenario that + * yields the worst case search is fairly contrived. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/gfp.h> +#include <linux/sched.h> +#include <linux/sched/rt.h> +#include <linux/slab.h> +#include "cpupri.h" + +/* Convert between a 140 based task->prio, and our 102 based cpupri */ +static int convert_prio(int prio) +{ + int cpupri; + + if (prio == CPUPRI_INVALID) + cpupri = CPUPRI_INVALID; + else if (prio == MAX_PRIO) + cpupri = CPUPRI_IDLE; + else if (prio >= MAX_RT_PRIO) + cpupri = CPUPRI_NORMAL; + else + cpupri = MAX_RT_PRIO - prio + 1; + + return cpupri; +} + +/** + * cpupri_find - find the best (lowest-pri) CPU in the system + * @cp: The cpupri context + * @p: The task + * @lowest_mask: A mask to fill in with selected CPUs (or NULL) + * + * Note: This function returns the recommended CPUs as calculated during the + * current invocation. By the time the call returns, the CPUs may have in + * fact changed priorities any number of times. While not ideal, it is not + * an issue of correctness since the normal rebalancer logic will correct + * any discrepancies created by racing against the uncertainty of the current + * priority configuration. + * + * Return: (int)bool - CPUs were found + */ +int cpupri_find(struct cpupri *cp, struct task_struct *p, + struct cpumask *lowest_mask) +{ + int idx = 0; + int task_pri = convert_prio(p->prio); + + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); + + for (idx = 0; idx < task_pri; idx++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; + int skip = 0; + + if (!atomic_read(&(vec)->count)) + skip = 1; + /* + * When looking at the vector, we need to read the counter, + * do a memory barrier, then read the mask. + * + * Note: This is still all racey, but we can deal with it. + * Ideally, we only want to look at masks that are set. + * + * If a mask is not set, then the only thing wrong is that we + * did a little more work than necessary. + * + * If we read a zero count but the mask is set, because of the + * memory barriers, that can only happen when the highest prio + * task for a run queue has left the run queue, in which case, + * it will be followed by a pull. If the task we are processing + * fails to find a proper place to go, that pull request will + * pull this task if the run queue is running at a lower + * priority. + */ + smp_rmb(); + + /* Need to do the rmb for every iteration */ + if (skip) + continue; + + if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + continue; + + if (lowest_mask) { + cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + + /* + * We have to ensure that we have at least one bit + * still set in the array, since the map could have + * been concurrently emptied between the first and + * second reads of vec->mask. If we hit this + * condition, simply act as though we never hit this + * priority level and continue on. + */ + if (cpumask_any(lowest_mask) >= nr_cpu_ids) + continue; + } + + return 1; + } + + return 0; +} + +/** + * cpupri_set - update the cpu priority setting + * @cp: The cpupri context + * @cpu: The target cpu + * @newpri: The priority (INVALID-RT99) to assign to this CPU + * + * Note: Assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpupri_set(struct cpupri *cp, int cpu, int newpri) +{ + int *currpri = &cp->cpu_to_pri[cpu]; + int oldpri = *currpri; + int do_mb = 0; + + newpri = convert_prio(newpri); + + BUG_ON(newpri >= CPUPRI_NR_PRIORITIES); + + if (newpri == oldpri) + return; + + /* + * If the cpu was currently mapped to a different value, we + * need to map it to the new value then remove the old value. + * Note, we must add the new value first, otherwise we risk the + * cpu being missed by the priority loop in cpupri_find. + */ + if (likely(newpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[newpri]; + + cpumask_set_cpu(cpu, vec->mask); + /* + * When adding a new vector, we update the mask first, + * do a write memory barrier, and then update the count, to + * make sure the vector is visible when count is set. + */ + smp_mb__before_atomic(); + atomic_inc(&(vec)->count); + do_mb = 1; + } + if (likely(oldpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri]; + + /* + * Because the order of modification of the vec->count + * is important, we must make sure that the update + * of the new prio is seen before we decrement the + * old prio. This makes sure that the loop sees + * one or the other when we raise the priority of + * the run queue. We don't care about when we lower the + * priority, as that will trigger an rt pull anyway. + * + * We only need to do a memory barrier if we updated + * the new priority vec. + */ + if (do_mb) + smp_mb__after_atomic(); + + /* + * When removing from the vector, we decrement the counter first + * do a memory barrier and then clear the mask. + */ + atomic_dec(&(vec)->count); + smp_mb__after_atomic(); + cpumask_clear_cpu(cpu, vec->mask); + } + + *currpri = newpri; +} + +/** + * cpupri_init - initialize the cpupri structure + * @cp: The cpupri context + * + * Return: -ENOMEM on memory allocation failure. + */ +int cpupri_init(struct cpupri *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[i]; + + atomic_set(&vec->count, 0); + if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL)) + goto cleanup; + } + + cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL); + if (!cp->cpu_to_pri) + goto cleanup; + + for_each_possible_cpu(i) + cp->cpu_to_pri[i] = CPUPRI_INVALID; + + return 0; + +cleanup: + for (i--; i >= 0; i--) + free_cpumask_var(cp->pri_to_cpu[i].mask); + return -ENOMEM; +} + +/** + * cpupri_cleanup - clean up the cpupri structure + * @cp: The cpupri context + */ +void cpupri_cleanup(struct cpupri *cp) +{ + int i; + + kfree(cp->cpu_to_pri); + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) + free_cpumask_var(cp->pri_to_cpu[i].mask); +} diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h new file mode 100644 index 000000000..63cbb9ca0 --- /dev/null +++ b/kernel/sched/cpupri.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_CPUPRI_H +#define _LINUX_CPUPRI_H + +#include <linux/sched.h> + +#define CPUPRI_NR_PRIORITIES (MAX_RT_PRIO + 2) + +#define CPUPRI_INVALID -1 +#define CPUPRI_IDLE 0 +#define CPUPRI_NORMAL 1 +/* values 2-101 are RT priorities 0-99 */ + +struct cpupri_vec { + atomic_t count; + cpumask_var_t mask; +}; + +struct cpupri { + struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; + int *cpu_to_pri; +}; + +#ifdef CONFIG_SMP +int cpupri_find(struct cpupri *cp, + struct task_struct *p, struct cpumask *lowest_mask); +void cpupri_set(struct cpupri *cp, int cpu, int pri); +int cpupri_init(struct cpupri *cp); +void cpupri_cleanup(struct cpupri *cp); +#endif + +#endif /* _LINUX_CPUPRI_H */ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c new file mode 100644 index 000000000..8394b1ee6 --- /dev/null +++ b/kernel/sched/cputime.c @@ -0,0 +1,852 @@ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/tsacct_kern.h> +#include <linux/kernel_stat.h> +#include <linux/static_key.h> +#include <linux/context_tracking.h> +#include "sched.h" + + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in vtime_account, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/vtime_account on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +DEFINE_PER_CPU(u64, cpu_hardirq_time); +DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +DEFINE_PER_CPU(seqcount_t, irq_time_seq); +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void irqtime_account_irq(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(irqtime_account_irq); + +static int irqtime_account_hi_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_hardirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_softirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void task_group_account_field(struct task_struct *p, int index, + u64 tmp) +{ + /* + * Since all updates are sure to touch the root cgroup, we + * get ourselves ahead and touch it first. If the root cgroup + * is the only cgroup, then nothing else should be necessary. + * + */ + __this_cpu_add(kernel_cpustat.cpustat[index], tmp); + + cpuacct_account_field(p, index, tmp); +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + int index; + + /* Add user time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + + index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + + /* Add user time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for user time used */ + acct_account_cputime(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += cputime; + + /* Add guest time to cpustat. */ + if (task_nice(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64) cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64) cputime; + cpustat[CPUTIME_GUEST] += (__force u64) cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, int index) +{ + /* Add system time to process. */ + p->stime += cputime; + p->stimescaled += cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for system time used */ + acct_account_cputime(p); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + int index; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime, cputime_scaled); + return; + } + + if (hardirq_count() - hardirq_offset) + index = CPUTIME_IRQ; + else if (in_serving_softirq()) + index = CPUTIME_SOFTIRQ; + else + index = CPUTIME_SYSTEM; + + __account_system_time(p, cputime, cputime_scaled, index); +} + +/* + * Account for involuntary wait time. + * @cputime: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64) cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +void account_idle_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64) cputime; +} + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal; + cputime_t steal_ct; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + + account_steal_time(steal_ct); + return steal_ct; + } +#endif + return false; +} + +/* + * Accumulate raw cputime values of dead tasks (sig->[us]time) and live + * tasks (sum on group iteration) belonging to @tsk's group. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; + struct task_struct *t; + unsigned int seq, nextseq; + unsigned long flags; + + rcu_read_lock(); + /* Attempt a lockless read on the first round. */ + nextseq = 0; + do { + seq = nextseq; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; + + for_each_thread(tsk, t) { + task_cputime(t, &utime, &stime); + times->utime += utime; + times->stime += stime; + times->sum_exec_runtime += task_sched_runtime(t); + } + /* If lockless access failed, take the lock. */ + nextseq = 1; + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + rcu_read_unlock(); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - pending softirq update + * - user_time + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * opportunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq, int ticks) +{ + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (steal_account_process_tick()) + return; + + cputime *= ticks; + scaled *= ticks; + + if (irqtime_account_hi_update()) { + cpustat[CPUTIME_IRQ] += cputime; + } else if (irqtime_account_si_update()) { + cpustat[CPUTIME_SOFTIRQ] += cputime; + } else if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + * Also, p->stime needs to be updated for ksoftirqd. + */ + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); + } else if (user_tick) { + account_user_time(p, cputime, scaled); + } else if (p == rq->idle) { + account_idle_time(cputime); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime, scaled); + } else { + __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + struct rq *rq = this_rq(); + + irqtime_account_process_tick(current, 0, rq, ticks); +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ +static inline void irqtime_account_idle_ticks(int ticks) {} +static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq, int nr_ticks) {} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifndef __ARCH_HAS_VTIME_TASK_SWITCH +void vtime_common_task_switch(struct task_struct *prev) +{ + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_system(prev); + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + vtime_account_user(prev); +#endif + arch_vtime_task_switch(prev); +} +#endif + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_common_account_irq_enter(struct task_struct *tsk) +{ + if (!in_interrupt()) { + /* + * If we interrupted user, context_tracking_in_user() + * is 1 because the context tracking don't hook + * on irq entry/exit. This way we know if + * we need to flush user time on kernel entry. + */ + if (context_tracking_in_user()) { + vtime_account_user(tsk); + return; + } + + if (is_idle_task(tsk)) { + vtime_account_idle(tsk); + return; + } + } + vtime_account_system(tsk); +} +EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ + + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + struct rq *rq = this_rq(); + + if (vtime_accounting_enabled()) + return; + + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq, 1); + return; + } + + if (steal_account_process_tick()) + return; + + if (user_tick) + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, + one_jiffy_scaled); + else + account_idle_time(cputime_one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + + account_idle_time(jiffies_to_cputime(ticks)); +} + +/* + * Perform (stime * rtime) / total, but avoid multiplication overflow by + * loosing precision when the numbers are big. + */ +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +{ + u64 scaled; + + for (;;) { + /* Make sure "rtime" is the bigger of stime/rtime */ + if (stime > rtime) + swap(rtime, stime); + + /* Make sure 'total' fits in 32 bits */ + if (total >> 32) + goto drop_precision; + + /* Does rtime (and thus stime) fit in 32 bits? */ + if (!(rtime >> 32)) + break; + + /* Can we just balance rtime/stime rather than dropping bits? */ + if (stime >> 31) + goto drop_precision; + + /* We can grow stime and shrink rtime and try to make them both fit */ + stime <<= 1; + rtime >>= 1; + continue; + +drop_precision: + /* We drop from rtime, it has more bits than stime */ + rtime >>= 1; + total >>= 1; + } + + /* + * Make sure gcc understands that this is a 32x32->64 multiply, + * followed by a 64/32->64 divide. + */ + scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); + return (__force cputime_t) scaled; +} + +/* + * Atomically advance counter to the new value. Interrupts, vcpu + * scheduling, and scaling inaccuracies can cause cputime_advance + * to be occasionally called with a new value smaller than counter. + * Let's enforce atomicity. + * + * Normally a caller will only go through this loop once, or not + * at all in case a previous caller updated counter the same jiffy. + */ +static void cputime_advance(cputime_t *counter, cputime_t new) +{ + cputime_t old; + + while (new > (old = ACCESS_ONCE(*counter))) + cmpxchg_cputime(counter, old, new); +} + +/* + * Adjust tick based cputime random precision against scheduler + * runtime accounting. + */ +static void cputime_adjust(struct task_cputime *curr, + struct cputime *prev, + cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, stime, utime; + + /* + * Tick based cputime accounting depend on random scheduling + * timeslices of a task to be interrupted or not by the timer. + * Depending on these circumstances, the number of these interrupts + * may be over or under-optimistic, matching the real user and system + * cputime with a variable precision. + * + * Fix this by scaling these tick based values against the total + * runtime accounted by the CFS scheduler. + */ + rtime = nsecs_to_cputime(curr->sum_exec_runtime); + + /* + * Update userspace visible utime/stime values only if actual execution + * time is bigger than already exported. Note that can happen, that we + * provided bigger values due to scaling inaccuracy on big numbers. + */ + if (prev->stime + prev->utime >= rtime) + goto out; + + stime = curr->stime; + utime = curr->utime; + + if (utime == 0) { + stime = rtime; + } else if (stime == 0) { + utime = rtime; + } else { + cputime_t total = stime + utime; + + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + utime = rtime - stime; + } + + cputime_advance(&prev->stime, stime); + cputime_advance(&prev->utime, utime); + +out: + *ut = prev->utime; + *st = prev->stime; +} + +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime = { + .sum_exec_runtime = p->se.sum_exec_runtime, + }; + + task_cputime(p, &cputime.utime, &cputime.stime); + cputime_adjust(&cputime, &p->prev_cputime, ut, st); +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); +} +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static unsigned long long vtime_delta(struct task_struct *tsk) +{ + unsigned long long clock; + + clock = local_clock(); + if (clock < tsk->vtime_snap) + return 0; + + return clock - tsk->vtime_snap; +} + +static cputime_t get_vtime_delta(struct task_struct *tsk) +{ + unsigned long long delta = vtime_delta(tsk); + + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + tsk->vtime_snap += delta; + + /* CHECKME: always safe to convert nsecs to cputime? */ + return nsecs_to_cputime(delta); +} + +static void __vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); +} + +void vtime_account_system(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_gen_account_irq_exit(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_cpu; + + write_seqlock(&tsk->vtime_seqlock); + delta_cpu = get_vtime_delta(tsk); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_user_enter(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + tsk->vtime_snap_whence = VTIME_USER; + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_guest_enter(struct task_struct *tsk) +{ + /* + * The flags must be updated under the lock with + * the vtime_snap flush and update. + * That enforces a right ordering and update sequence + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); +} +EXPORT_SYMBOL_GPL(vtime_guest_enter); + +void vtime_guest_exit(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); +} +EXPORT_SYMBOL_GPL(vtime_guest_exit); + +void vtime_account_idle(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_idle_time(delta_cpu); +} + +void arch_vtime_task_switch(struct task_struct *prev) +{ + write_seqlock(&prev->vtime_seqlock); + prev->vtime_snap_whence = VTIME_SLEEPING; + write_sequnlock(&prev->vtime_seqlock); + + write_seqlock(¤t->vtime_seqlock); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock_cpu(smp_processor_id()); + write_sequnlock(¤t->vtime_seqlock); +} + +void vtime_init_idle(struct task_struct *t, int cpu) +{ + unsigned long flags; + + write_seqlock_irqsave(&t->vtime_seqlock, flags); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock_cpu(cpu); + write_sequnlock_irqrestore(&t->vtime_seqlock, flags); +} + +cputime_t task_gtime(struct task_struct *t) +{ + unsigned int seq; + cputime_t gtime; + + do { + seq = read_seqbegin(&t->vtime_seqlock); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + + } while (read_seqretry(&t->vtime_seqlock, seq)); + + return gtime; +} + +/* + * Fetch cputime raw values from fields of task_struct and + * add up the pending nohz execution time since the last + * cputime snapshot. + */ +static void +fetch_task_cputime(struct task_struct *t, + cputime_t *u_dst, cputime_t *s_dst, + cputime_t *u_src, cputime_t *s_src, + cputime_t *udelta, cputime_t *sdelta) +{ + unsigned int seq; + unsigned long long delta; + + do { + *udelta = 0; + *sdelta = 0; + + seq = read_seqbegin(&t->vtime_seqlock); + + if (u_dst) + *u_dst = *u_src; + if (s_dst) + *s_dst = *s_src; + + /* Task is sleeping, nothing to add */ + if (t->vtime_snap_whence == VTIME_SLEEPING || + is_idle_task(t)) + continue; + + delta = vtime_delta(t); + + /* + * Task runs either in user or kernel space, add pending nohz time to + * the right place. + */ + if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) { + *udelta = delta; + } else { + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } + } while (read_seqretry(&t->vtime_seqlock, seq)); +} + + +void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utime, stime, &t->utime, + &t->stime, &udelta, &sdelta); + if (utime) + *utime += udelta; + if (stime) + *stime += sdelta; +} + +void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, cputime_t *stimescaled) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utimescaled, stimescaled, + &t->utimescaled, &t->stimescaled, &udelta, &sdelta); + if (utimescaled) + *utimescaled += cputime_to_scaled(udelta); + if (stimescaled) + *stimescaled += cputime_to_scaled(sdelta); +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c new file mode 100644 index 000000000..5e9514508 --- /dev/null +++ b/kernel/sched/deadline.c @@ -0,0 +1,1818 @@ +/* + * Deadline Scheduling Class (SCHED_DEADLINE) + * + * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS). + * + * Tasks that periodically executes their instances for less than their + * runtime won't miss any of their deadlines. + * Tasks that are not periodic or sporadic or that tries to execute more + * than their reserved bandwidth will be slowed down (and may potentially + * miss some of their deadlines), and won't affect any other task. + * + * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>, + * Juri Lelli <juri.lelli@gmail.com>, + * Michael Trimarchi <michael@amarulasolutions.com>, + * Fabio Checconi <fchecconi@gmail.com> + */ +#include "sched.h" + +#include <linux/slab.h> + +struct dl_bandwidth def_dl_bandwidth; + +static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) +{ + return container_of(dl_se, struct task_struct, dl); +} + +static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq) +{ + return container_of(dl_rq, struct rq, dl); +} + +static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = task_rq(p); + + return &rq->dl; +} + +static inline int on_dl_rq(struct sched_dl_entity *dl_se) +{ + return !RB_EMPTY_NODE(&dl_se->rb_node); +} + +static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) +{ + struct sched_dl_entity *dl_se = &p->dl; + + return dl_rq->rb_leftmost == &dl_se->rb_node; +} + +void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) +{ + raw_spin_lock_init(&dl_b->dl_runtime_lock); + dl_b->dl_period = period; + dl_b->dl_runtime = runtime; +} + +void init_dl_bw(struct dl_bw *dl_b) +{ + raw_spin_lock_init(&dl_b->lock); + raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock); + if (global_rt_runtime() == RUNTIME_INF) + dl_b->bw = -1; + else + dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime()); + raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock); + dl_b->total_bw = 0; +} + +void init_dl_rq(struct dl_rq *dl_rq) +{ + dl_rq->rb_root = RB_ROOT; + +#ifdef CONFIG_SMP + /* zero means no -deadline tasks */ + dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0; + + dl_rq->dl_nr_migratory = 0; + dl_rq->overloaded = 0; + dl_rq->pushable_dl_tasks_root = RB_ROOT; +#else + init_dl_bw(&dl_rq->dl_bw); +#endif +} + +#ifdef CONFIG_SMP + +static inline int dl_overloaded(struct rq *rq) +{ + return atomic_read(&rq->rd->dlo_count); +} + +static inline void dl_set_overload(struct rq *rq) +{ + if (!rq->online) + return; + + cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask); + /* + * Must be visible before the overload count is + * set (as in sched_rt.c). + * + * Matched by the barrier in pull_dl_task(). + */ + smp_wmb(); + atomic_inc(&rq->rd->dlo_count); +} + +static inline void dl_clear_overload(struct rq *rq) +{ + if (!rq->online) + return; + + atomic_dec(&rq->rd->dlo_count); + cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask); +} + +static void update_dl_migration(struct dl_rq *dl_rq) +{ + if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) { + if (!dl_rq->overloaded) { + dl_set_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 1; + } + } else if (dl_rq->overloaded) { + dl_clear_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 0; + } +} + +static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory++; + + update_dl_migration(dl_rq); +} + +static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory--; + + update_dl_migration(dl_rq); +} + +/* + * The list of pushable -deadline task is not a plist, like in + * sched_rt.c, it is an rb-tree with tasks ordered by deadline. + */ +static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node; + struct rb_node *parent = NULL; + struct task_struct *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct task_struct, + pushable_dl_tasks); + if (dl_entity_preempt(&p->dl, &entry->dl)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks; + + rb_link_node(&p->pushable_dl_tasks, parent, link); + rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); +} + +static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + + if (RB_EMPTY_NODE(&p->pushable_dl_tasks)) + return; + + if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) { + struct rb_node *next_node; + + next_node = rb_next(&p->pushable_dl_tasks); + dl_rq->pushable_dl_tasks_leftmost = next_node; + } + + rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +} + +static inline int has_pushable_dl_tasks(struct rq *rq) +{ + return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root); +} + +static int push_dl_task(struct rq *rq); + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return dl_task(prev); +} + +static inline void set_post_schedule(struct rq *rq) +{ + rq->post_schedule = has_pushable_dl_tasks(rq); +} + +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); + +static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) +{ + struct rq *later_rq = NULL; + bool fallback = false; + + later_rq = find_lock_later_rq(p, rq); + + if (!later_rq) { + int cpu; + + /* + * If we cannot preempt any rq, fall back to pick any + * online cpu. + */ + fallback = true; + cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p)); + if (cpu >= nr_cpu_ids) { + /* + * Fail to find any suitable cpu. + * The task will never come back! + */ + BUG_ON(dl_bandwidth_enabled()); + + /* + * If admission control is disabled we + * try a little harder to let the task + * run. + */ + cpu = cpumask_any(cpu_active_mask); + } + later_rq = cpu_rq(cpu); + double_lock_balance(rq, later_rq); + } + + deactivate_task(rq, p, 0); + set_task_cpu(p, later_rq->cpu); + activate_task(later_rq, p, ENQUEUE_REPLENISH); + + if (!fallback) + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); +} + +#else + +static inline +void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline +void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_dl_task(struct rq *rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} +#endif /* CONFIG_SMP */ + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags); + +/* + * We are being explicitly informed that a new instance is starting, + * and this means that: + * - the absolute deadline of the entity has to be placed at + * current time + relative deadline; + * - the runtime of the entity has to be set to the maximum value. + * + * The capability of specifying such event is useful whenever a -deadline + * entity wants to (try to!) synchronize its behaviour with the scheduler's + * one, and to (try to!) reconcile itself with its own scheduling + * parameters. + */ +static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + + /* + * We use the regular wall clock time to set deadlines in the + * future; in fact, we must consider execution overheads (time + * spent on hardirq context, etc.). + */ + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + dl_se->dl_new = 0; +} + +/* + * Pure Earliest Deadline First (EDF) scheduling does not deal with the + * possibility of a entity lasting more than what it declared, and thus + * exhausting its runtime. + * + * Here we are interested in making runtime overrun possible, but we do + * not want a entity which is misbehaving to affect the scheduling of all + * other entities. + * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS) + * is used, in order to confine each entity within its own bandwidth. + * + * This function deals exactly with that, and ensures that when the runtime + * of a entity is replenished, its deadline is also postponed. That ensures + * the overrunning entity can't interfere with other entity in the system and + * can't make them miss their deadlines. Reasons why this kind of overruns + * could happen are, typically, a entity voluntarily trying to overcome its + * runtime, or it just underestimated it during sched_setattr(). + */ +static void replenish_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + BUG_ON(pi_se->dl_runtime <= 0); + + /* + * This could be the case for a !-dl task that is boosted. + * Just go with full inherited parameters. + */ + if (dl_se->dl_deadline == 0) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } + + /* + * We keep moving the deadline away until we get some + * available runtime for the entity. This ensures correct + * handling of situations where the runtime overrun is + * arbitrary large. + */ + while (dl_se->runtime <= 0) { + dl_se->deadline += pi_se->dl_period; + dl_se->runtime += pi_se->dl_runtime; + } + + /* + * At this point, the deadline really should be "in + * the future" with respect to rq->clock. If it's + * not, we are, for some reason, lagging too much! + * Anyway, after having warn userspace abut that, + * we still try to keep the things running by + * resetting the deadline and the budget of the + * entity. + */ + if (dl_time_before(dl_se->deadline, rq_clock(rq))) { + printk_deferred_once("sched: DL replenish lagged to much\n"); + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } + + if (dl_se->dl_yielded) + dl_se->dl_yielded = 0; + if (dl_se->dl_throttled) + dl_se->dl_throttled = 0; +} + +/* + * Here we check if --at time t-- an entity (which is probably being + * [re]activated or, in general, enqueued) can use its remaining runtime + * and its current deadline _without_ exceeding the bandwidth it is + * assigned (function returns true if it can't). We are in fact applying + * one of the CBS rules: when a task wakes up, if the residual runtime + * over residual deadline fits within the allocated bandwidth, then we + * can keep the current (absolute) deadline and residual budget without + * disrupting the schedulability of the system. Otherwise, we should + * refill the runtime and set the deadline a period in the future, + * because keeping the current (absolute) deadline of the task would + * result in breaking guarantees promised to other tasks (refer to + * Documentation/scheduler/sched-deadline.txt for more informations). + * + * This function returns true if: + * + * runtime / (deadline - t) > dl_runtime / dl_period , + * + * IOW we can't recycle current parameters. + * + * Notice that the bandwidth check is done against the period. For + * task with deadline equal to period this is the same of using + * dl_deadline instead of dl_period in the equation above. + */ +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, u64 t) +{ + u64 left, right; + + /* + * left and right are the two sides of the equation above, + * after a bit of shuffling to use multiplications instead + * of divisions. + * + * Note that none of the time values involved in the two + * multiplications are absolute: dl_deadline and dl_runtime + * are the relative deadline and the maximum runtime of each + * instance, runtime is the runtime left for the last instance + * and (deadline - t), since t is rq->clock, is the time left + * to the (absolute) deadline. Even if overflowing the u64 type + * is very unlikely to occur in both cases, here we scale down + * as we want to avoid that risk at all. Scaling down by 10 + * means that we reduce granularity to 1us. We are fine with it, + * since this is only a true/false check and, anyway, thinking + * of anything below microseconds resolution is actually fiction + * (but still we want to give the user that illusion >;). + */ + left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + right = ((dl_se->deadline - t) >> DL_SCALE) * + (pi_se->dl_runtime >> DL_SCALE); + + return dl_time_before(right, left); +} + +/* + * When a -deadline entity is queued back on the runqueue, its runtime and + * deadline might need updating. + * + * The policy here is that we update the deadline of the entity only if: + * - the current deadline is in the past, + * - using the remaining runtime with the current deadline would make + * the entity exceed its bandwidth. + */ +static void update_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * The arrival of a new instance needs special treatment, i.e., + * the actual scheduling parameters have to be "renewed". + */ + if (dl_se->dl_new) { + setup_new_dl_entity(dl_se, pi_se); + return; + } + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) || + dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } +} + +/* + * If the entity depleted all its runtime, and if we want it to sleep + * while waiting for some new execution time to become available, we + * set the bandwidth enforcement timer to the replenishment instant + * and try to activate it. + * + * Notice that it is important for the caller to know if the timer + * actually started or not (i.e., the replenishment instant is in + * the future or in the past). + */ +static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + ktime_t now, act; + ktime_t soft, hard; + unsigned long range; + s64 delta; + + if (boosted) + return 0; + /* + * We want the timer to fire at the deadline, but considering + * that it is actually coming from rq->clock and not from + * hrtimer's time base reading. + */ + act = ns_to_ktime(dl_se->deadline); + now = hrtimer_cb_get_time(&dl_se->dl_timer); + delta = ktime_to_ns(now) - rq_clock(rq); + act = ktime_add_ns(act, delta); + + /* + * If the expiry time already passed, e.g., because the value + * chosen as the deadline is too small, don't even try to + * start the timer in the past! + */ + if (ktime_us_delta(act, now) < 0) + return 0; + + hrtimer_set_expires(&dl_se->dl_timer, act); + + soft = hrtimer_get_softexpires(&dl_se->dl_timer); + hard = hrtimer_get_expires(&dl_se->dl_timer); + range = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(&dl_se->dl_timer, soft, + range, HRTIMER_MODE_ABS, 0); + + return hrtimer_active(&dl_se->dl_timer); +} + +/* + * This is the bandwidth enforcement timer callback. If here, we know + * a task is not on its dl_rq, since the fact that the timer was running + * means the task is throttled and needs a runtime replenishment. + * + * However, what we actually do depends on the fact the task is active, + * (it is on its rq) or has been removed from there by a call to + * dequeue_task_dl(). In the former case we must issue the runtime + * replenishment and add the task back to the dl_rq; in the latter, we just + * do nothing but clearing dl_throttled, so that runtime and deadline + * updating (and the queueing back to dl_rq) will be done by the + * next call to enqueue_task_dl(). + */ +static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + dl_timer); + struct task_struct *p = dl_task_of(dl_se); + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + + /* + * We need to take care of several possible races here: + * + * - the task might have changed its scheduling policy + * to something different than SCHED_DEADLINE + * - the task might have changed its reservation parameters + * (through sched_setattr()) + * - the task might have been boosted by someone else and + * might be in the boosting/deboosting path + * + * In all this cases we bail out, as the task is already + * in the runqueue or is going to be enqueued back anyway. + */ + if (!dl_task(p) || dl_se->dl_new || + dl_se->dl_boosted || !dl_se->dl_throttled) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + +#ifdef CONFIG_SMP + /* + * If we find that the rq the task was on is no longer + * available, we need to select a new rq. + */ + if (unlikely(!rq->online)) { + dl_task_offline_migration(rq, p); + goto unlock; + } +#endif + + /* + * If the throttle happened during sched-out; like: + * + * schedule() + * deactivate_task() + * dequeue_task_dl() + * update_curr_dl() + * start_dl_timer() + * __dequeue_task_dl() + * prev->on_rq = 0; + * + * We can be both throttled and !queued. Replenish the counter + * but do not enqueue -- wait for our wakeup to do that. + */ + if (!task_on_rq_queued(p)) { + replenish_dl_entity(dl_se, dl_se); + goto unlock; + } + + enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); +#ifdef CONFIG_SMP + /* + * Queueing this task back might have overloaded rq, + * check if we need to kick someone away. + */ + if (has_pushable_dl_tasks(rq)) + push_dl_task(rq); +#endif +unlock: + task_rq_unlock(rq, p, &flags); + + return HRTIMER_NORESTART; +} + +void init_dl_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->dl_timer; + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; +} + +static +int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) +{ + return (dl_se->runtime <= 0); +} + +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + +/* + * Update the current task's runtime statistics (provided it is still + * a -deadline task and has not been removed from the dl_rq). + */ +static void update_curr_dl(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_dl_entity *dl_se = &curr->dl; + u64 delta_exec; + + if (!dl_task(curr) || !on_dl_rq(dl_se)) + return; + + /* + * Consumed budget is computed considering the time as + * observed by schedulable tasks (excluding time spent + * in hardirq context, etc.). Deadlines are instead + * computed using hard walltime. This seems to be the more + * natural solution, but the full ramifications of this + * approach need further study. + */ + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); + + sched_rt_avg_update(rq, delta_exec); + + dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec; + if (dl_runtime_exceeded(rq, dl_se)) { + dl_se->dl_throttled = 1; + __dequeue_task_dl(rq, curr, 0); + if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted))) + enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); + + if (!is_leftmost(curr, &rq->dl)) + resched_curr(rq); + } + + /* + * Because -- for now -- we share the rt bandwidth, we need to + * account our runtime there too, otherwise actual rt tasks + * would be able to exceed the shared quota. + * + * Account to the root rt group for now. + * + * The solution we're working towards is having the RT groups scheduled + * using deadline servers -- however there's a few nasties to figure + * out before that can happen. + */ + if (rt_bandwidth_enabled()) { + struct rt_rq *rt_rq = &rq->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * We'll let actual RT tasks worry about the overflow here, we + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. + */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } +} + +#ifdef CONFIG_SMP + +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu); + +static inline u64 next_deadline(struct rq *rq) +{ + struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu); + + if (next && dl_prio(next->prio)) + return next->dl.deadline; + else + return 0; +} + +static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + if (dl_rq->earliest_dl.curr == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.curr)) { + /* + * If the dl_rq had no -deadline tasks, or if the new task + * has shorter deadline than the current one on dl_rq, we + * know that the previous earliest becomes our next earliest, + * as the new task becomes the earliest itself. + */ + dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr; + dl_rq->earliest_dl.curr = deadline; + cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1); + } else if (dl_rq->earliest_dl.next == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.next)) { + /* + * On the other hand, if the new -deadline task has a + * a later deadline than the earliest one on dl_rq, but + * it is earlier than the next (if any), we must + * recompute the next-earliest. + */ + dl_rq->earliest_dl.next = next_deadline(rq); + } +} + +static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * Since we may have removed our earliest (and/or next earliest) + * task we must recompute them. + */ + if (!dl_rq->dl_nr_running) { + dl_rq->earliest_dl.curr = 0; + dl_rq->earliest_dl.next = 0; + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + } else { + struct rb_node *leftmost = dl_rq->rb_leftmost; + struct sched_dl_entity *entry; + + entry = rb_entry(leftmost, struct sched_dl_entity, rb_node); + dl_rq->earliest_dl.curr = entry->deadline; + dl_rq->earliest_dl.next = next_deadline(rq); + cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1); + } +} + +#else + +static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} +static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} + +#endif /* CONFIG_SMP */ + +static inline +void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + u64 deadline = dl_se->deadline; + + WARN_ON(!dl_prio(prio)); + dl_rq->dl_nr_running++; + add_nr_running(rq_of_dl_rq(dl_rq), 1); + + inc_dl_deadline(dl_rq, deadline); + inc_dl_migration(dl_se, dl_rq); +} + +static inline +void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + + WARN_ON(!dl_prio(prio)); + WARN_ON(!dl_rq->dl_nr_running); + dl_rq->dl_nr_running--; + sub_nr_running(rq_of_dl_rq(dl_rq), 1); + + dec_dl_deadline(dl_rq, dl_se->deadline); + dec_dl_migration(dl_se, dl_rq); +} + +static void __enqueue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rb_node **link = &dl_rq->rb_root.rb_node; + struct rb_node *parent = NULL; + struct sched_dl_entity *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct sched_dl_entity, rb_node); + if (dl_time_before(dl_se->deadline, entry->deadline)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->rb_leftmost = &dl_se->rb_node; + + rb_link_node(&dl_se->rb_node, parent, link); + rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root); + + inc_dl_tasks(dl_se, dl_rq); +} + +static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + if (RB_EMPTY_NODE(&dl_se->rb_node)) + return; + + if (dl_rq->rb_leftmost == &dl_se->rb_node) { + struct rb_node *next_node; + + next_node = rb_next(&dl_se->rb_node); + dl_rq->rb_leftmost = next_node; + } + + rb_erase(&dl_se->rb_node, &dl_rq->rb_root); + RB_CLEAR_NODE(&dl_se->rb_node); + + dec_dl_tasks(dl_se, dl_rq); +} + +static void +enqueue_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, int flags) +{ + BUG_ON(on_dl_rq(dl_se)); + + /* + * If this is a wakeup or a new instance, the scheduling + * parameters of the task might need updating. Otherwise, + * we want a replenishment of its runtime. + */ + if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) + update_dl_entity(dl_se, pi_se); + else if (flags & ENQUEUE_REPLENISH) + replenish_dl_entity(dl_se, pi_se); + + __enqueue_dl_entity(dl_se); +} + +static void dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + __dequeue_dl_entity(dl_se); +} + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + struct task_struct *pi_task = rt_mutex_get_top_task(p); + struct sched_dl_entity *pi_se = &p->dl; + + /* + * Use the scheduling parameters of the top pi-waiter + * task if we have one and its (relative) deadline is + * smaller than our one... OTW we keep our runtime and + * deadline. + */ + if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) { + pi_se = &pi_task->dl; + } else if (!dl_prio(p->normal_prio)) { + /* + * Special case in which we have a !SCHED_DEADLINE task + * that is going to be deboosted, but exceedes its + * runtime while doing so. No point in replenishing + * it, as it's going to return back to its original + * scheduling class after this. + */ + BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + return; + } + + /* + * If p is throttled, we do nothing. In fact, if it exhausted + * its budget it needs a replenishment and, since it now is on + * its rq, the bandwidth timer callback (which clearly has not + * run yet) will take care of this. + */ + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) + return; + + enqueue_dl_entity(&p->dl, pi_se, flags); + + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + dequeue_dl_entity(&p->dl); + dequeue_pushable_dl_task(rq, p); +} + +static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + update_curr_dl(rq); + __dequeue_task_dl(rq, p, flags); +} + +/* + * Yield task semantic for -deadline tasks is: + * + * get off from the CPU until our next instance, with + * a new runtime. This is of little use now, since we + * don't have a bandwidth reclaiming mechanism. Anyway, + * bandwidth reclaiming is planned for the future, and + * yield_task_dl will indicate that some spare budget + * is available for other task instances to use it. + */ +static void yield_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + /* + * We make the task go to sleep until its current deadline by + * forcing its runtime to zero. This way, update_curr_dl() stops + * it and the bandwidth timer will wake it up and will give it + * new scheduling parameters (thanks to dl_yielded=1). + */ + if (p->dl.runtime > 0) { + rq->curr->dl.dl_yielded = 1; + p->dl.runtime = 0; + } + update_rq_clock(rq); + update_curr_dl(rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); +} + +#ifdef CONFIG_SMP + +static int find_later_rq(struct task_struct *task); + +static int +select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + struct task_struct *curr; + struct rq *rq; + + if (sd_flag != SD_BALANCE_WAKE) + goto out; + + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + + /* + * If we are dealing with a -deadline task, we must + * decide where to wake it up. + * If it has a later deadline and the current task + * on this rq can't move (provided the waking task + * can!) we prefer to send it somewhere else. On the + * other hand, if it has a shorter deadline, we + * try to make it stay here, it might be important. + */ + if (unlikely(dl_task(curr)) && + (curr->nr_cpus_allowed < 2 || + !dl_entity_preempt(&p->dl, &curr->dl)) && + (p->nr_cpus_allowed > 1)) { + int target = find_later_rq(p); + + if (target != -1) + cpu = target; + } + rcu_read_unlock(); + +out: + return cpu; +} + +static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) +{ + /* + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ + if (rq->curr->nr_cpus_allowed == 1 || + cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) + return; + + /* + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ + if (p->nr_cpus_allowed != 1 && + cpudl_find(&rq->rd->cpudl, p, NULL) != -1) + return; + + resched_curr(rq); +} + +static int pull_dl_task(struct rq *this_rq); + +#endif /* CONFIG_SMP */ + +/* + * Only called when both the current and waking task are -deadline + * tasks. + */ +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags) +{ + if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { + resched_curr(rq); + return; + } + +#ifdef CONFIG_SMP + /* + * In the unlikely case current and p have the same deadline + * let us try to decide what's the best thing to do... + */ + if ((p->dl.deadline == rq->curr->dl.deadline) && + !test_tsk_need_resched(rq->curr)) + check_preempt_equal_dl(rq, p); +#endif /* CONFIG_SMP */ +} + +#ifdef CONFIG_SCHED_HRTICK +static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +{ + hrtick_start(rq, p->dl.runtime); +} +#else /* !CONFIG_SCHED_HRTICK */ +static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +{ +} +#endif + +static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, + struct dl_rq *dl_rq) +{ + struct rb_node *left = dl_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_dl_entity, rb_node); +} + +struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) +{ + struct sched_dl_entity *dl_se; + struct task_struct *p; + struct dl_rq *dl_rq; + + dl_rq = &rq->dl; + + if (need_pull_dl_task(rq, prev)) { + pull_dl_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a stop task can slip in, in which case we need to + * re-start task selection. + */ + if (rq->stop && task_on_rq_queued(rq->stop)) + return RETRY_TASK; + } + + /* + * When prev is DL, we may throttle it in put_prev_task(). + * So, we update time before we check for dl_nr_running. + */ + if (prev->sched_class == &dl_sched_class) + update_curr_dl(rq); + + if (unlikely(!dl_rq->dl_nr_running)) + return NULL; + + put_prev_task(rq, prev); + + dl_se = pick_next_dl_entity(rq, dl_rq); + BUG_ON(!dl_se); + + p = dl_task_of(dl_se); + p->se.exec_start = rq_clock_task(rq); + + /* Running task will never be pushed. */ + dequeue_pushable_dl_task(rq, p); + + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, p); + + set_post_schedule(rq); + + return p; +} + +static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +{ + update_curr_dl(rq); + + if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) +{ + update_curr_dl(rq); + + /* + * Even when we have runtime, update_curr_dl() might have resulted in us + * not being the leftmost task anymore. In that case NEED_RESCHED will + * be set and schedule() will start a new hrtick for the next task. + */ + if (hrtick_enabled(rq) && queued && p->dl.runtime > 0 && + is_leftmost(p, &rq->dl)) + start_hrtick_dl(rq, p); +} + +static void task_fork_dl(struct task_struct *p) +{ + /* + * SCHED_DEADLINE tasks cannot fork and this is achieved through + * sched_fork() + */ +} + +static void task_dead_dl(struct task_struct *p) +{ + struct hrtimer *timer = &p->dl.dl_timer; + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + /* + * Since we are TASK_DEAD we won't slip out of the domain! + */ + raw_spin_lock_irq(&dl_b->lock); + /* XXX we should retain the bw until 0-lag */ + dl_b->total_bw -= p->dl.dl_bw; + raw_spin_unlock_irq(&dl_b->lock); + + hrtimer_cancel(timer); +} + +static void set_curr_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + p->se.exec_start = rq_clock_task(rq); + + /* You can't push away the running task */ + dequeue_pushable_dl_task(rq, p); +} + +#ifdef CONFIG_SMP + +/* Only try algorithms three times */ +#define DL_MAX_TRIES 3 + +static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) +{ + if (!task_running(rq, p) && + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + return 1; + return 0; +} + +/* Returns the second earliest -deadline task, NULL otherwise */ +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu) +{ + struct rb_node *next_node = rq->dl.rb_leftmost; + struct sched_dl_entity *dl_se; + struct task_struct *p = NULL; + +next_node: + next_node = rb_next(next_node); + if (next_node) { + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); + p = dl_task_of(dl_se); + + if (pick_dl_task(rq, p, cpu)) + return p; + + goto next_node; + } + + return NULL; +} + +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl); + +static int find_later_rq(struct task_struct *task) +{ + struct sched_domain *sd; + struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); + int this_cpu = smp_processor_id(); + int best_cpu, cpu = task_cpu(task); + + /* Make sure the mask is initialized first */ + if (unlikely(!later_mask)) + return -1; + + if (task->nr_cpus_allowed == 1) + return -1; + + /* + * We have to consider system topology and task affinity + * first, then we can look for a suitable cpu. + */ + best_cpu = cpudl_find(&task_rq(task)->rd->cpudl, + task, later_mask); + if (best_cpu == -1) + return -1; + + /* + * If we are here, some target has been found, + * the most suitable of which is cached in best_cpu. + * This is, among the runqueues where the current tasks + * have later deadlines than the task's one, the rq + * with the latest possible one. + * + * Now we check how well this matches with task's + * affinity and system topology. + * + * The last cpu where the task run is our first + * guess, since it is most likely cache-hot there. + */ + if (cpumask_test_cpu(cpu, later_mask)) + return cpu; + /* + * Check if this_cpu is to be skipped (i.e., it is + * not in the mask) or not. + */ + if (!cpumask_test_cpu(this_cpu, later_mask)) + this_cpu = -1; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + + /* + * If possible, preempting this_cpu is + * cheaper than migrating. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return this_cpu; + } + + /* + * Last chance: if best_cpu is valid and is + * in the mask, that becomes our choice. + */ + if (best_cpu < nr_cpu_ids && + cpumask_test_cpu(best_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return best_cpu; + } + } + } + rcu_read_unlock(); + + /* + * At this point, all our guesses failed, we just return + * 'something', and let the caller sort the things out. + */ + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(later_mask); + if (cpu < nr_cpu_ids) + return cpu; + + return -1; +} + +/* Locks the rq it finds */ +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) +{ + struct rq *later_rq = NULL; + int tries; + int cpu; + + for (tries = 0; tries < DL_MAX_TRIES; tries++) { + cpu = find_later_rq(task); + + if ((cpu == -1) || (cpu == rq->cpu)) + break; + + later_rq = cpu_rq(cpu); + + /* Retry if something changed. */ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(later_rq->cpu, + &task->cpus_allowed) || + task_running(rq, task) || + !task_on_rq_queued(task))) { + double_unlock_balance(rq, later_rq); + later_rq = NULL; + break; + } + } + + /* + * If the rq we found has no -deadline task, or + * its earliest one has a later deadline than our + * task, the rq is a good one. + */ + if (!later_rq->dl.dl_nr_running || + dl_time_before(task->dl.deadline, + later_rq->dl.earliest_dl.curr)) + break; + + /* Otherwise we try again. */ + double_unlock_balance(rq, later_rq); + later_rq = NULL; + } + + return later_rq; +} + +static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_dl_tasks(rq)) + return NULL; + + p = rb_entry(rq->dl.pushable_dl_tasks_leftmost, + struct task_struct, pushable_dl_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!dl_task(p)); + + return p; +} + +/* + * See if the non running -deadline tasks on this rq + * can be sent to some other CPU where they can preempt + * and start executing. + */ +static int push_dl_task(struct rq *rq) +{ + struct task_struct *next_task; + struct rq *later_rq; + int ret = 0; + + if (!rq->dl.overloaded) + return 0; + + next_task = pick_next_pushable_dl_task(rq); + if (!next_task) + return 0; + +retry: + if (unlikely(next_task == rq->curr)) { + WARN_ON(1); + return 0; + } + + /* + * If next_task preempts rq->curr, and rq->curr + * can move away, it makes sense to just reschedule + * without going further in pushing next_task. + */ + if (dl_task(rq->curr) && + dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && + rq->curr->nr_cpus_allowed > 1) { + resched_curr(rq); + return 0; + } + + /* We might release rq lock */ + get_task_struct(next_task); + + /* Will lock the rq it'll find */ + later_rq = find_lock_later_rq(next_task, rq); + if (!later_rq) { + struct task_struct *task; + + /* + * We must check all this again, since + * find_lock_later_rq releases rq->lock and it is + * then possible that next_task has migrated. + */ + task = pick_next_pushable_dl_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * The task is still there. We don't try + * again, some other cpu will pull it when ready. + */ + goto out; + } + + if (!task) + /* No more tasks */ + goto out; + + put_task_struct(next_task); + next_task = task; + goto retry; + } + + deactivate_task(rq, next_task, 0); + set_task_cpu(next_task, later_rq->cpu); + activate_task(later_rq, next_task, 0); + ret = 1; + + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); + +out: + put_task_struct(next_task); + + return ret; +} + +static void push_dl_tasks(struct rq *rq) +{ + /* Terminates as it moves a -deadline task */ + while (push_dl_task(rq)) + ; +} + +static int pull_dl_task(struct rq *this_rq) +{ + int this_cpu = this_rq->cpu, ret = 0, cpu; + struct task_struct *p; + struct rq *src_rq; + u64 dmin = LONG_MAX; + + if (likely(!dl_overloaded(this_rq))) + return 0; + + /* + * Match the barrier from dl_set_overloaded; this guarantees that if we + * see overloaded we must also see the dlo_mask bit. + */ + smp_rmb(); + + for_each_cpu(cpu, this_rq->rd->dlo_mask) { + if (this_cpu == cpu) + continue; + + src_rq = cpu_rq(cpu); + + /* + * It looks racy, abd it is! However, as in sched_rt.c, + * we are fine with this. + */ + if (this_rq->dl.dl_nr_running && + dl_time_before(this_rq->dl.earliest_dl.curr, + src_rq->dl.earliest_dl.next)) + continue; + + /* Might drop this_rq->lock */ + double_lock_balance(this_rq, src_rq); + + /* + * If there are no more pullable tasks on the + * rq, we're done with it. + */ + if (src_rq->dl.dl_nr_running <= 1) + goto skip; + + p = pick_next_earliest_dl_task(src_rq, this_cpu); + + /* + * We found a task to be pulled if: + * - it preempts our current (if there's one), + * - it will preempt the last one we pulled (if any). + */ + if (p && dl_time_before(p->dl.deadline, dmin) && + (!this_rq->dl.dl_nr_running || + dl_time_before(p->dl.deadline, + this_rq->dl.earliest_dl.curr))) { + WARN_ON(p == src_rq->curr); + WARN_ON(!task_on_rq_queued(p)); + + /* + * Then we pull iff p has actually an earlier + * deadline than the current task of its runqueue. + */ + if (dl_time_before(p->dl.deadline, + src_rq->curr->dl.deadline)) + goto skip; + + ret = 1; + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + dmin = p->dl.deadline; + + /* Is there any other task even earlier? */ + } +skip: + double_unlock_balance(this_rq, src_rq); + } + + return ret; +} + +static void post_schedule_dl(struct rq *rq) +{ + push_dl_tasks(rq); +} + +/* + * Since the task is not running and a reschedule is not going to happen + * anytime soon on its runqueue, we try pushing it away now. + */ +static void task_woken_dl(struct rq *rq, struct task_struct *p) +{ + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + has_pushable_dl_tasks(rq) && + p->nr_cpus_allowed > 1 && + dl_task(rq->curr) && + (rq->curr->nr_cpus_allowed < 2 || + !dl_entity_preempt(&p->dl, &rq->curr->dl))) { + push_dl_tasks(rq); + } +} + +static void set_cpus_allowed_dl(struct task_struct *p, + const struct cpumask *new_mask) +{ + struct rq *rq; + struct root_domain *src_rd; + int weight; + + BUG_ON(!dl_task(p)); + + rq = task_rq(p); + src_rd = rq->rd; + /* + * Migrating a SCHED_DEADLINE task between exclusive + * cpusets (different root_domains) entails a bandwidth + * update. We already made space for us in the destination + * domain (see cpuset_can_attach()). + */ + if (!cpumask_intersects(src_rd->span, new_mask)) { + struct dl_bw *src_dl_b; + + src_dl_b = dl_bw_of(cpu_of(rq)); + /* + * We now free resources of the root_domain we are migrating + * off. In the worst case, sched_setattr() may temporary fail + * until we complete the update. + */ + raw_spin_lock(&src_dl_b->lock); + __dl_clear(src_dl_b, p->dl.dl_bw); + raw_spin_unlock(&src_dl_b->lock); + } + + /* + * Update only if the task is actually running (i.e., + * it is on the rq AND it is not throttled). + */ + if (!on_dl_rq(&p->dl)) + return; + + weight = cpumask_weight(new_mask); + + /* + * Only update if the process changes its state from whether it + * can migrate or not. + */ + if ((p->nr_cpus_allowed > 1) == (weight > 1)) + return; + + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_dl_task(rq, p); + BUG_ON(!rq->dl.dl_nr_migratory); + rq->dl.dl_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_dl_task(rq, p); + rq->dl.dl_nr_migratory++; + } + + update_dl_migration(&rq->dl); +} + +/* Assumes rq->lock is held */ +static void rq_online_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_set_overload(rq); + + cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu); + if (rq->dl.dl_nr_running > 0) + cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1); +} + +/* Assumes rq->lock is held */ +static void rq_offline_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_clear_overload(rq); + + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu); +} + +void init_sched_dl_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i), + GFP_KERNEL, cpu_to_node(i)); +} + +#endif /* CONFIG_SMP */ + +/* + * Ensure p's dl_timer is cancelled. May drop rq->lock for a while. + */ +static void cancel_dl_timer(struct rq *rq, struct task_struct *p) +{ + struct hrtimer *dl_timer = &p->dl.dl_timer; + + /* Nobody will change task's class if pi_lock is held */ + lockdep_assert_held(&p->pi_lock); + + if (hrtimer_active(dl_timer)) { + int ret = hrtimer_try_to_cancel(dl_timer); + + if (unlikely(ret == -1)) { + /* + * Note, p may migrate OR new deadline tasks + * may appear in rq when we are unlocking it. + * A caller of us must be fine with that. + */ + raw_spin_unlock(&rq->lock); + hrtimer_cancel(dl_timer); + raw_spin_lock(&rq->lock); + } + } +} + +static void switched_from_dl(struct rq *rq, struct task_struct *p) +{ + /* XXX we should retain the bw until 0-lag */ + cancel_dl_timer(rq, p); + __dl_clear_params(p); + + /* + * Since this might be the only -deadline task on the rq, + * this is the right place to try to pull some other one + * from an overloaded cpu, if any. + */ + if (!task_on_rq_queued(p) || rq->dl.dl_nr_running) + return; + + if (pull_dl_task(rq)) + resched_curr(rq); +} + +/* + * When switching to -deadline, we may overload the rq, then + * we try to push someone off, if possible. + */ +static void switched_to_dl(struct rq *rq, struct task_struct *p) +{ + int check_resched = 1; + + if (task_on_rq_queued(p) && rq->curr != p) { +#ifdef CONFIG_SMP + if (p->nr_cpus_allowed > 1 && rq->dl.overloaded && + push_dl_task(rq) && rq != task_rq(p)) + /* Only reschedule if pushing failed */ + check_resched = 0; +#endif /* CONFIG_SMP */ + if (check_resched) { + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); + } + } +} + +/* + * If the scheduling parameters of a -deadline task changed, + * a push or pull operation might be needed. + */ +static void prio_changed_dl(struct rq *rq, struct task_struct *p, + int oldprio) +{ + if (task_on_rq_queued(p) || rq->curr == p) { +#ifdef CONFIG_SMP + /* + * This might be too much, but unfortunately + * we don't have the old deadline value, and + * we can't argue if the task is increasing + * or lowering its prio, so... + */ + if (!rq->dl.overloaded) + pull_dl_task(rq); + + /* + * If we now have a earlier deadline task than p, + * then reschedule, provided p is still on this + * runqueue. + */ + if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && + rq->curr == p) + resched_curr(rq); +#else + /* + * Again, we don't know if p has a earlier + * or later deadline, so let's blindly set a + * (maybe not needed) rescheduling point. + */ + resched_curr(rq); +#endif /* CONFIG_SMP */ + } else + switched_to_dl(rq, p); +} + +const struct sched_class dl_sched_class = { + .next = &rt_sched_class, + .enqueue_task = enqueue_task_dl, + .dequeue_task = dequeue_task_dl, + .yield_task = yield_task_dl, + + .check_preempt_curr = check_preempt_curr_dl, + + .pick_next_task = pick_next_task_dl, + .put_prev_task = put_prev_task_dl, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_dl, + .set_cpus_allowed = set_cpus_allowed_dl, + .rq_online = rq_online_dl, + .rq_offline = rq_offline_dl, + .post_schedule = post_schedule_dl, + .task_woken = task_woken_dl, +#endif + + .set_curr_task = set_curr_task_dl, + .task_tick = task_tick_dl, + .task_fork = task_fork_dl, + .task_dead = task_dead_dl, + + .prio_changed = prio_changed_dl, + .switched_from = switched_from_dl, + .switched_to = switched_to_dl, + + .update_curr = update_curr_dl, +}; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); + +void print_dl_stats(struct seq_file *m, int cpu) +{ + print_dl_rq(m, cpu, &cpu_rq(cpu)->dl); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c new file mode 100644 index 000000000..a245c1fc6 --- /dev/null +++ b/kernel/sched/debug.c @@ -0,0 +1,674 @@ +/* + * kernel/sched/debug.c + * + * Print the CFS rbtree + * + * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/kallsyms.h> +#include <linux/utsname.h> +#include <linux/mempolicy.h> + +#include "sched.h" + +static DEFINE_SPINLOCK(sched_debug_lock); + +/* + * This allows printing both to /proc/sched_debug and + * to the console + */ +#define SEQ_printf(m, x...) \ + do { \ + if (m) \ + seq_printf(m, x); \ + else \ + printk(x); \ + } while (0) + +/* + * Ease the printing of nsec fields: + */ +static long long nsec_high(unsigned long long nsec) +{ + if ((long long)nsec < 0) { + nsec = -nsec; + do_div(nsec, 1000000); + return -nsec; + } + do_div(nsec, 1000000); + + return nsec; +} + +static unsigned long nsec_low(unsigned long long nsec) +{ + if ((long long)nsec < 0) + nsec = -nsec; + + return do_div(nsec, 1000000); +} + +#define SPLIT_NS(x) nsec_high(x), nsec_low(x) + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) +{ + struct sched_entity *se = tg->se[cpu]; + +#define P(F) \ + SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) +#define PN(F) \ + SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) + + if (!se) { + struct sched_avg *avg = &cpu_rq(cpu)->avg; + P(avg->runnable_avg_sum); + P(avg->avg_period); + return; + } + + + PN(se->exec_start); + PN(se->vruntime); + PN(se->sum_exec_runtime); +#ifdef CONFIG_SCHEDSTATS + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); +#endif + P(se->load.weight); +#ifdef CONFIG_SMP + P(se->avg.runnable_avg_sum); + P(se->avg.running_avg_sum); + P(se->avg.avg_period); + P(se->avg.load_avg_contrib); + P(se->avg.utilization_avg_contrib); + P(se->avg.decay_count); +#endif +#undef PN +#undef P +} +#endif + +#ifdef CONFIG_CGROUP_SCHED +static char group_path[PATH_MAX]; + +static char *task_group_path(struct task_group *tg) +{ + if (autogroup_path(tg, group_path, PATH_MAX)) + return group_path; + + return cgroup_path(tg->css.cgroup, group_path, PATH_MAX); +} +#endif + +static void +print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) +{ + if (rq->curr == p) + SEQ_printf(m, "R"); + else + SEQ_printf(m, " "); + + SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ", + p->comm, task_pid_nr(p), + SPLIT_NS(p->se.vruntime), + (long long)(p->nvcsw + p->nivcsw), + p->prio); +#ifdef CONFIG_SCHEDSTATS + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SPLIT_NS(p->se.vruntime), + SPLIT_NS(p->se.sum_exec_runtime), + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); +#else + SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", + 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); +#endif +#ifdef CONFIG_NUMA_BALANCING + SEQ_printf(m, " %d", task_node(p)); +#endif +#ifdef CONFIG_CGROUP_SCHED + SEQ_printf(m, " %s", task_group_path(task_group(p))); +#endif + + SEQ_printf(m, "\n"); +} + +static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) +{ + struct task_struct *g, *p; + + SEQ_printf(m, + "\nrunnable tasks:\n" + " task PID tree-key switches prio" + " exec-runtime sum-exec sum-sleep\n" + "------------------------------------------------------" + "----------------------------------------------------\n"); + + rcu_read_lock(); + for_each_process_thread(g, p) { + if (task_cpu(p) != rq_cpu) + continue; + + print_task(m, rq, p); + } + rcu_read_unlock(); +} + +void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) +{ + s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1, + spread, rq0_min_vruntime, spread0; + struct rq *rq = cpu_rq(cpu); + struct sched_entity *last; + unsigned long flags; + +#ifdef CONFIG_FAIR_GROUP_SCHED + SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg)); +#else + SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); +#endif + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", + SPLIT_NS(cfs_rq->exec_clock)); + + raw_spin_lock_irqsave(&rq->lock, flags); + if (cfs_rq->rb_leftmost) + MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime; + last = __pick_last_entity(cfs_rq); + if (last) + max_vruntime = last->vruntime; + min_vruntime = cfs_rq->min_vruntime; + rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime; + raw_spin_unlock_irqrestore(&rq->lock, flags); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime", + SPLIT_NS(MIN_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", + SPLIT_NS(min_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime", + SPLIT_NS(max_vruntime)); + spread = max_vruntime - MIN_vruntime; + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", + SPLIT_NS(spread)); + spread0 = min_vruntime - rq0_min_vruntime; + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0", + SPLIT_NS(spread0)); + SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", + cfs_rq->nr_spread_over); + SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); + SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); +#ifdef CONFIG_SMP + SEQ_printf(m, " .%-30s: %ld\n", "runnable_load_avg", + cfs_rq->runnable_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", + cfs_rq->blocked_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "utilization_load_avg", + cfs_rq->utilization_load_avg); +#ifdef CONFIG_FAIR_GROUP_SCHED + SEQ_printf(m, " .%-30s: %ld\n", "tg_load_contrib", + cfs_rq->tg_load_contrib); + SEQ_printf(m, " .%-30s: %d\n", "tg_runnable_contrib", + cfs_rq->tg_runnable_contrib); + SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg", + atomic_long_read(&cfs_rq->tg->load_avg)); + SEQ_printf(m, " .%-30s: %d\n", "tg->runnable_avg", + atomic_read(&cfs_rq->tg->runnable_avg)); +#endif +#endif +#ifdef CONFIG_CFS_BANDWIDTH + SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active", + cfs_rq->tg->cfs_bandwidth.timer_active); + SEQ_printf(m, " .%-30s: %d\n", "throttled", + cfs_rq->throttled); + SEQ_printf(m, " .%-30s: %d\n", "throttle_count", + cfs_rq->throttle_count); +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED + print_cfs_group_stats(m, cpu, cfs_rq->tg); +#endif +} + +void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) +{ +#ifdef CONFIG_RT_GROUP_SCHED + SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg)); +#else + SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); +#endif + +#define P(x) \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) +#define PN(x) \ + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) + + P(rt_nr_running); + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); + +#undef PN +#undef P +} + +void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) +{ + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); + SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +} + +extern __read_mostly int sched_clock_running; + +static void print_cpu(struct seq_file *m, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + +#ifdef CONFIG_X86 + { + unsigned int freq = cpu_khz ? : 1; + + SEQ_printf(m, "cpu#%d, %u.%03u MHz\n", + cpu, freq / 1000, (freq % 1000)); + } +#else + SEQ_printf(m, "cpu#%d\n", cpu); +#endif + +#define P(x) \ +do { \ + if (sizeof(rq->x) == 4) \ + SEQ_printf(m, " .%-30s: %ld\n", #x, (long)(rq->x)); \ + else \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x));\ +} while (0) + +#define PN(x) \ + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) + + P(nr_running); + SEQ_printf(m, " .%-30s: %lu\n", "load", + rq->load.weight); + P(nr_switches); + P(nr_load_updates); + P(nr_uninterruptible); + PN(next_balance); + SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); + PN(clock); + PN(clock_task); + P(cpu_load[0]); + P(cpu_load[1]); + P(cpu_load[2]); + P(cpu_load[3]); + P(cpu_load[4]); +#undef P +#undef PN + +#ifdef CONFIG_SCHEDSTATS +#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); +#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); + + P(yld_count); + + P(sched_count); + P(sched_goidle); +#ifdef CONFIG_SMP + P64(avg_idle); + P64(max_idle_balance_cost); +#endif + + P(ttwu_count); + P(ttwu_local); + +#undef P +#undef P64 +#endif + spin_lock_irqsave(&sched_debug_lock, flags); + print_cfs_stats(m, cpu); + print_rt_stats(m, cpu); + print_dl_stats(m, cpu); + + print_rq(m, rq, cpu); + spin_unlock_irqrestore(&sched_debug_lock, flags); + SEQ_printf(m, "\n"); +} + +static const char *sched_tunable_scaling_names[] = { + "none", + "logaritmic", + "linear" +}; + +static void sched_debug_header(struct seq_file *m) +{ + u64 ktime, sched_clk, cpu_clk; + unsigned long flags; + + local_irq_save(flags); + ktime = ktime_to_ns(ktime_get()); + sched_clk = sched_clock(); + cpu_clk = local_clock(); + local_irq_restore(flags); + + SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n", + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + +#define P(x) \ + SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x)) +#define PN(x) \ + SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) + PN(ktime); + PN(sched_clk); + PN(cpu_clk); + P(jiffies); +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + P(sched_clock_stable()); +#endif +#undef PN +#undef P + + SEQ_printf(m, "\n"); + SEQ_printf(m, "sysctl_sched\n"); + +#define P(x) \ + SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x)) +#define PN(x) \ + SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x)) + PN(sysctl_sched_latency); + PN(sysctl_sched_min_granularity); + PN(sysctl_sched_wakeup_granularity); + P(sysctl_sched_child_runs_first); + P(sysctl_sched_features); +#undef PN +#undef P + + SEQ_printf(m, " .%-40s: %d (%s)\n", + "sysctl_sched_tunable_scaling", + sysctl_sched_tunable_scaling, + sched_tunable_scaling_names[sysctl_sched_tunable_scaling]); + SEQ_printf(m, "\n"); +} + +static int sched_debug_show(struct seq_file *m, void *v) +{ + int cpu = (unsigned long)(v - 2); + + if (cpu != -1) + print_cpu(m, cpu); + else + sched_debug_header(m); + + return 0; +} + +void sysrq_sched_debug_show(void) +{ + int cpu; + + sched_debug_header(NULL); + for_each_online_cpu(cpu) + print_cpu(NULL, cpu); + +} + +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *sched_debug_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return sched_debug_start(file, offset); +} + +static void sched_debug_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations sched_debug_sops = { + .start = sched_debug_start, + .next = sched_debug_next, + .stop = sched_debug_stop, + .show = sched_debug_show, +}; + +static int sched_debug_release(struct inode *inode, struct file *file) +{ + seq_release(inode, file); + + return 0; +} + +static int sched_debug_open(struct inode *inode, struct file *filp) +{ + int ret = 0; + + ret = seq_open(filp, &sched_debug_sops); + + return ret; +} + +static const struct file_operations sched_debug_fops = { + .open = sched_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = sched_debug_release, +}; + +static int __init init_sched_debug_procfs(void) +{ + struct proc_dir_entry *pe; + + pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); + if (!pe) + return -ENOMEM; + return 0; +} + +__initcall(init_sched_debug_procfs); + +#define __P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) +#define P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) +#define __PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) +#define PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + + +static void sched_show_numa(struct task_struct *p, struct seq_file *m) +{ +#ifdef CONFIG_NUMA_BALANCING + struct mempolicy *pol; + int node, i; + + if (p->mm) + P(mm->numa_scan_seq); + + task_lock(p); + pol = p->mempolicy; + if (pol && !(pol->flags & MPOL_F_MORON)) + pol = NULL; + mpol_get(pol); + task_unlock(p); + + SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0)); + + for_each_online_node(node) { + for (i = 0; i < 2; i++) { + unsigned long nr_faults = -1; + int cpu_current, home_node; + + if (p->numa_faults) + nr_faults = p->numa_faults[2*node + i]; + + cpu_current = !i ? (task_node(p) == node) : + (pol && node_isset(node, pol->v.nodes)); + + home_node = (p->numa_preferred_nid == node); + + SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", + i, node, cpu_current, home_node, nr_faults); + } + } + + mpol_put(pol); +#endif +} + +void proc_sched_show_task(struct task_struct *p, struct seq_file *m) +{ + unsigned long nr_switches; + + SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p), + get_nr_threads(p)); + SEQ_printf(m, + "---------------------------------------------------------" + "----------\n"); +#define __P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) +#define P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) +#define __PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) +#define PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + + PN(se.exec_start); + PN(se.vruntime); + PN(se.sum_exec_runtime); + + nr_switches = p->nvcsw + p->nivcsw; + +#ifdef CONFIG_SCHEDSTATS + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); + P(se.nr_migrations); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); + + { + u64 avg_atom, avg_per_cpu; + + avg_atom = p->se.sum_exec_runtime; + if (nr_switches) + avg_atom = div64_ul(avg_atom, nr_switches); + else + avg_atom = -1LL; + + avg_per_cpu = p->se.sum_exec_runtime; + if (p->se.nr_migrations) { + avg_per_cpu = div64_u64(avg_per_cpu, + p->se.nr_migrations); + } else { + avg_per_cpu = -1LL; + } + + __PN(avg_atom); + __PN(avg_per_cpu); + } +#endif + __P(nr_switches); + SEQ_printf(m, "%-45s:%21Ld\n", + "nr_voluntary_switches", (long long)p->nvcsw); + SEQ_printf(m, "%-45s:%21Ld\n", + "nr_involuntary_switches", (long long)p->nivcsw); + + P(se.load.weight); +#ifdef CONFIG_SMP + P(se.avg.runnable_avg_sum); + P(se.avg.running_avg_sum); + P(se.avg.avg_period); + P(se.avg.load_avg_contrib); + P(se.avg.utilization_avg_contrib); + P(se.avg.decay_count); +#endif + P(policy); + P(prio); +#undef PN +#undef __PN +#undef P +#undef __P + + { + unsigned int this_cpu = raw_smp_processor_id(); + u64 t0, t1; + + t0 = cpu_clock(this_cpu); + t1 = cpu_clock(this_cpu); + SEQ_printf(m, "%-45s:%21Ld\n", + "clock-delta", (long long)(t1-t0)); + } + + sched_show_numa(p, m); +} + +void proc_sched_set_task(struct task_struct *p) +{ +#ifdef CONFIG_SCHEDSTATS + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); +#endif +} diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c new file mode 100644 index 000000000..936664319 --- /dev/null +++ b/kernel/sched/fair.c @@ -0,0 +1,8310 @@ +/* + * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH) + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith <efault@gmx.de> + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com> + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + */ + +#include <linux/latencytop.h> +#include <linux/sched.h> +#include <linux/cpumask.h> +#include <linux/cpuidle.h> +#include <linux/slab.h> +#include <linux/profile.h> +#include <linux/interrupt.h> +#include <linux/mempolicy.h> +#include <linux/migrate.h> +#include <linux/task_work.h> + +#include <trace/events/sched.h> + +#include "sched.h" + +/* + * Targeted preemption latency for CPU-bound tasks: + * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) + * + * NOTE: this latency value is not the same as the concept of + * 'timeslice length' - timeslices in CFS are of variable length + * and have no persistent notion like in traditional, time-slice + * based scheduling concepts. + * + * (to see the precise effective timeslice length of your workload, + * run vmstat and monitor the context-switches (cs) field) + */ +#ifdef CONFIG_PCK_INTERACTIVE +unsigned int sysctl_sched_latency = 3000000ULL; +unsigned int normalized_sysctl_sched_latency = 3000000ULL; +#else +unsigned int sysctl_sched_latency = 6000000ULL; +unsigned int normalized_sysctl_sched_latency = 6000000ULL; +#endif + +/* + * The initial- and re-scaling of tunables is configurable + * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) + * + * Options are: + * SCHED_TUNABLESCALING_NONE - unscaled, always *1 + * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) + * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + */ +enum sched_tunable_scaling sysctl_sched_tunable_scaling + = SCHED_TUNABLESCALING_LOG; + +/* + * Minimal preemption granularity for CPU-bound tasks: + * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) + */ +#ifdef CONFIG_PCK_INTERACTIVE +unsigned int sysctl_sched_min_granularity = 300000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 300000ULL; +#else +unsigned int sysctl_sched_min_granularity = 750000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; +#endif + +/* + * is kept at sysctl_sched_latency / sysctl_sched_min_granularity + */ +#ifdef CONFIG_PCK_INTERACTIVE +static unsigned int sched_nr_latency = 10; +#else +static unsigned int sched_nr_latency = 8; +#endif + +/* + * After fork, child runs first. If set to 0 (default) then + * parent will (try to) run first. + */ +unsigned int sysctl_sched_child_runs_first __read_mostly; + +/* + * SCHED_OTHER wake-up granularity. + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) + * + * This option delays the preemption effects of decoupled workloads + * and reduces their over-scheduling. Synchronous workloads will still + * have immediate wakeup/sleep latencies. + */ +#ifdef CONFIG_PCK_INTERACTIVE +unsigned int sysctl_sched_wakeup_granularity = 500000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 500000UL; + +const_debug unsigned int sysctl_sched_migration_cost = 250000UL; +#else +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; + +const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +#endif + +/* + * The exponential sliding window over which load is averaged for shares + * distribution. + * (default: 10msec) + */ +unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; + +#ifdef CONFIG_CFS_BANDWIDTH +/* + * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool + * each time a cfs_rq requests quota. + * + * Note: in the case that the slice exceeds the runtime remaining (either due + * to consumption or the quota being specified to be smaller than the slice) + * we will always only issue the remaining available time. + * + * default: 5 msec, units: microseconds + */ +#ifdef CONFIG_PCK_INTERACTIVE +unsigned int sysctl_sched_cfs_bandwidth_slice = 3000UL; +#else +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif +#endif + +static inline void update_load_add(struct load_weight *lw, unsigned long inc) +{ + lw->weight += inc; + lw->inv_weight = 0; +} + +static inline void update_load_sub(struct load_weight *lw, unsigned long dec) +{ + lw->weight -= dec; + lw->inv_weight = 0; +} + +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + +/* + * Increase the granularity value when there are more CPUs, + * because with more CPUs the 'effective latency' as visible + * to users decreases. But the relationship is not linear, + * so pick a second-best guess by going with the log2 of the + * number of CPUs. + * + * This idea comes from the SD scheduler of Con Kolivas: + */ +static int get_update_sysctl_factor(void) +{ + unsigned int cpus = min_t(int, num_online_cpus(), 8); + unsigned int factor; + + switch (sysctl_sched_tunable_scaling) { + case SCHED_TUNABLESCALING_NONE: + factor = 1; + break; + case SCHED_TUNABLESCALING_LINEAR: + factor = cpus; + break; + case SCHED_TUNABLESCALING_LOG: + default: + factor = 1 + ilog2(cpus); + break; + } + + return factor; +} + +static void update_sysctl(void) +{ + unsigned int factor = get_update_sysctl_factor(); + +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); +#undef SET_SYSCTL +} + +void sched_init_granularity(void) +{ + update_sysctl(); +} + +#define WMULT_CONST (~0U) +#define WMULT_SHIFT 32 + +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} + +/* + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. + */ +static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) +{ + u64 fact = scale_load_down(weight); + int shift = WMULT_SHIFT; + + __update_inv_weight(lw); + + if (unlikely(fact >> 32)) { + while (fact >> 32) { + fact >>= 1; + shift--; + } + } + + /* hint to use a 32x32->64 mul */ + fact = (u64)(u32)fact * lw->inv_weight; + + while (fact >> 32) { + fact >>= 1; + shift--; + } + + return mul_u64_u32_shr(delta_exec, fact, shift); +} + + +const struct sched_class fair_sched_class; + +/************************************************************** + * CFS operations on generic schedulable entities: + */ + +#ifdef CONFIG_FAIR_GROUP_SCHED + +/* cpu runqueue to which this cfs_rq is attached */ +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return cfs_rq->rq; +} + +/* An entity is a task if it doesn't "own" a runqueue */ +#define entity_is_task(se) (!se->my_q) + +static inline struct task_struct *task_of(struct sched_entity *se) +{ +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(!entity_is_task(se)); +#endif + return container_of(se, struct task_struct, se); +} + +/* Walk up scheduling entities hierarchy */ +#define for_each_sched_entity(se) \ + for (; se; se = se->parent) + +static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +{ + return p->se.cfs_rq; +} + +/* runqueue on which this entity is (to be) queued */ +static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +{ + return se->cfs_rq; +} + +/* runqueue "owned" by this group */ +static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) +{ + return grp->my_q; +} + +static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, + int force_update); + +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (!cfs_rq->on_list) { + /* + * Ensure we either appear before our parent (if already + * enqueued) or force our parent to appear after us when it is + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases. + */ + if (cfs_rq->tg->parent && + cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) { + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq_of(cfs_rq)->leaf_cfs_rq_list); + } else { + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq_of(cfs_rq)->leaf_cfs_rq_list); + } + + cfs_rq->on_list = 1; + /* We should have no load, but we need to update last_decay. */ + update_cfs_rq_blocked_load(cfs_rq, 0); + } +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->on_list) { + list_del_rcu(&cfs_rq->leaf_cfs_rq_list); + cfs_rq->on_list = 0; + } +} + +/* Iterate thr' all leaf cfs_rq's on a runqueue */ +#define for_each_leaf_cfs_rq(rq, cfs_rq) \ + list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) + +/* Do the two (enqueued) entities belong to the same group ? */ +static inline struct cfs_rq * +is_same_group(struct sched_entity *se, struct sched_entity *pse) +{ + if (se->cfs_rq == pse->cfs_rq) + return se->cfs_rq; + + return NULL; +} + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return se->parent; +} + +static void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ + int se_depth, pse_depth; + + /* + * preemption test can be made between sibling entities who are in the + * same cfs_rq i.e who have a common parent. Walk up the hierarchy of + * both tasks until we find their ancestors who are siblings of common + * parent. + */ + + /* First walk up until both entities are at same depth */ + se_depth = (*se)->depth; + pse_depth = (*pse)->depth; + + while (se_depth > pse_depth) { + se_depth--; + *se = parent_entity(*se); + } + + while (pse_depth > se_depth) { + pse_depth--; + *pse = parent_entity(*pse); + } + + while (!is_same_group(*se, *pse)) { + *se = parent_entity(*se); + *pse = parent_entity(*pse); + } +} + +#else /* !CONFIG_FAIR_GROUP_SCHED */ + +static inline struct task_struct *task_of(struct sched_entity *se) +{ + return container_of(se, struct task_struct, se); +} + +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return container_of(cfs_rq, struct rq, cfs); +} + +#define entity_is_task(se) 1 + +#define for_each_sched_entity(se) \ + for (; se; se = NULL) + +static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +{ + return &task_rq(p)->cfs; +} + +static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +{ + struct task_struct *p = task_of(se); + struct rq *rq = task_rq(p); + + return &rq->cfs; +} + +/* runqueue "owned" by this group */ +static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) +{ + return NULL; +} + +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +#define for_each_leaf_cfs_rq(rq, cfs_rq) \ + for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return NULL; +} + +static inline void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ +} + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); + +/************************************************************** + * Scheduling class tree data structure manipulation methods: + */ + +static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - max_vruntime); + if (delta > 0) + max_vruntime = vruntime; + + return max_vruntime; +} + +static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - min_vruntime); + if (delta < 0) + min_vruntime = vruntime; + + return min_vruntime; +} + +static inline int entity_before(struct sched_entity *a, + struct sched_entity *b) +{ + return (s64)(a->vruntime - b->vruntime) < 0; +} + +static void update_min_vruntime(struct cfs_rq *cfs_rq) +{ + u64 vruntime = cfs_rq->min_vruntime; + + if (cfs_rq->curr) + vruntime = cfs_rq->curr->vruntime; + + if (cfs_rq->rb_leftmost) { + struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost, + struct sched_entity, + run_node); + + if (!cfs_rq->curr) + vruntime = se->vruntime; + else + vruntime = min_vruntime(vruntime, se->vruntime); + } + + /* ensure we never gain time by being placed backwards. */ + cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif +} + +/* + * Enqueue an entity into the rb-tree: + */ +static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct rb_node **link = &cfs_rq->tasks_timeline.rb_node; + struct rb_node *parent = NULL; + struct sched_entity *entry; + int leftmost = 1; + + /* + * Find the right place in the rbtree: + */ + while (*link) { + parent = *link; + entry = rb_entry(parent, struct sched_entity, run_node); + /* + * We dont care about collisions. Nodes with + * the same key stay together. + */ + if (entity_before(se, entry)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = 0; + } + } + + /* + * Maintain a cache of leftmost tree entries (it is frequently + * used): + */ + if (leftmost) + cfs_rq->rb_leftmost = &se->run_node; + + rb_link_node(&se->run_node, parent, link); + rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline); +} + +static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->rb_leftmost == &se->run_node) { + struct rb_node *next_node; + + next_node = rb_next(&se->run_node); + cfs_rq->rb_leftmost = next_node; + } + + rb_erase(&se->run_node, &cfs_rq->tasks_timeline); +} + +struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *left = cfs_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_entity, run_node); +} + +static struct sched_entity *__pick_next_entity(struct sched_entity *se) +{ + struct rb_node *next = rb_next(&se->run_node); + + if (!next) + return NULL; + + return rb_entry(next, struct sched_entity, run_node); +} + +#ifdef CONFIG_SCHED_DEBUG +struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); + + if (!last) + return NULL; + + return rb_entry(last, struct sched_entity, run_node); +} + +/************************************************************** + * Scheduling class statistics methods: + */ + +int sched_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + int factor = get_update_sysctl_factor(); + + if (ret || !write) + return ret; + + sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, + sysctl_sched_min_granularity); + +#define WRT_SYSCTL(name) \ + (normalized_sysctl_##name = sysctl_##name / (factor)) + WRT_SYSCTL(sched_min_granularity); + WRT_SYSCTL(sched_latency); + WRT_SYSCTL(sched_wakeup_granularity); +#undef WRT_SYSCTL + + return 0; +} +#endif + +/* + * delta /= w + */ +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) +{ + if (unlikely(se->load.weight != NICE_0_LOAD)) + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); + + return delta; +} + +/* + * The idea is to set a period in which each task runs once. + * + * When there are too many tasks (sched_nr_latency) we have to stretch + * this period because otherwise the slices get too small. + * + * p = (nr <= nl) ? l : l*nr/nl + */ +static u64 __sched_period(unsigned long nr_running) +{ + u64 period = sysctl_sched_latency; + unsigned long nr_latency = sched_nr_latency; + + if (unlikely(nr_running > nr_latency)) { + period = sysctl_sched_min_granularity; + period *= nr_running; + } + + return period; +} + +/* + * We calculate the wall-time slice from the period by taking a part + * proportional to the weight. + * + * s = p*P[w/rw] + */ +static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); + + for_each_sched_entity(se) { + struct load_weight *load; + struct load_weight lw; + + cfs_rq = cfs_rq_of(se); + load = &cfs_rq->load; + + if (unlikely(!se->on_rq)) { + lw = cfs_rq->load; + + update_load_add(&lw, se->load.weight); + load = &lw; + } + slice = __calc_delta(slice, se->load.weight, load); + } + return slice; +} + +/* + * We calculate the vruntime slice of a to-be-inserted task. + * + * vs = s/w + */ +static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + return calc_delta_fair(sched_slice(cfs_rq, se), se); +} + +#ifdef CONFIG_SMP +static int select_idle_sibling(struct task_struct *p, int cpu); +static unsigned long task_h_load(struct task_struct *p); + +static inline void __update_task_entity_contrib(struct sched_entity *se); +static inline void __update_task_entity_utilization(struct sched_entity *se); + +/* Give new task start runnable values to heavy its load in infant time */ +void init_task_runnable_average(struct task_struct *p) +{ + u32 slice; + + slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; + p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice; + p->se.avg.avg_period = slice; + __update_task_entity_contrib(&p->se); + __update_task_entity_utilization(&p->se); +} +#else +void init_task_runnable_average(struct task_struct *p) +{ +} +#endif + +/* + * Update the current task's runtime statistics. + */ +static void update_curr(struct cfs_rq *cfs_rq) +{ + struct sched_entity *curr = cfs_rq->curr; + u64 now = rq_clock_task(rq_of(cfs_rq)); + u64 delta_exec; + + if (unlikely(!curr)) + return; + + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + curr->exec_start = now; + + schedstat_set(curr->statistics.exec_max, + max(delta_exec, curr->statistics.exec_max)); + + curr->sum_exec_runtime += delta_exec; + schedstat_add(cfs_rq, exec_clock, delta_exec); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + + if (entity_is_task(curr)) { + struct task_struct *curtask = task_of(curr); + + trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime); + cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); + } + + account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static void update_curr_fair(struct rq *rq) +{ + update_curr(cfs_rq_of(&rq->curr->se)); +} + +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq))); +} + +/* + * Task is being enqueued - update stats: + */ +static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * Are we enqueueing a waiting task? (for current tasks + * a dequeue/enqueue event is a NOP) + */ + if (se != cfs_rq->curr) + update_stats_wait_start(cfs_rq, se); +} + +static void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max, + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start)); + schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1); + schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum + + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); +#ifdef CONFIG_SCHEDSTATS + if (entity_is_task(se)) { + trace_sched_stat_wait(task_of(se), + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); + } +#endif + schedstat_set(se->statistics.wait_start, 0); +} + +static inline void +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * Mark the end of the wait period if dequeueing a + * waiting task: + */ + if (se != cfs_rq->curr) + update_stats_wait_end(cfs_rq, se); +} + +/* + * We are picking a new current task - update its stats: + */ +static inline void +update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * We are starting a new run period: + */ + se->exec_start = rq_clock_task(rq_of(cfs_rq)); +} + +/************************************************** + * Scheduling class queueing methods: + */ + +#ifdef CONFIG_NUMA_BALANCING +/* + * Approximate time to scan a full NUMA task in ms. The task scan period is + * calculated based on the tasks virtual memory size and + * numa_balancing_scan_size. + */ +unsigned int sysctl_numa_balancing_scan_period_min = 1000; +unsigned int sysctl_numa_balancing_scan_period_max = 60000; + +/* Portion of address space to scan in MB */ +unsigned int sysctl_numa_balancing_scan_size = 256; + +/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ +unsigned int sysctl_numa_balancing_scan_delay = 1000; + +static unsigned int task_nr_scan_windows(struct task_struct *p) +{ + unsigned long rss = 0; + unsigned long nr_scan_pages; + + /* + * Calculations based on RSS as non-present and empty pages are skipped + * by the PTE scanner and NUMA hinting faults should be trapped based + * on resident pages + */ + nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT); + rss = get_mm_rss(p->mm); + if (!rss) + rss = nr_scan_pages; + + rss = round_up(rss, nr_scan_pages); + return rss / nr_scan_pages; +} + +/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */ +#define MAX_SCAN_WINDOW 2560 + +static unsigned int task_scan_min(struct task_struct *p) +{ + unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size); + unsigned int scan, floor; + unsigned int windows = 1; + + if (scan_size < MAX_SCAN_WINDOW) + windows = MAX_SCAN_WINDOW / scan_size; + floor = 1000 / windows; + + scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p); + return max_t(unsigned int, floor, scan); +} + +static unsigned int task_scan_max(struct task_struct *p) +{ + unsigned int smin = task_scan_min(p); + unsigned int smax; + + /* Watch for min being lower than max due to floor calculations */ + smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); + return max(smin, smax); +} + +static void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); +} + +static void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); +} + +struct numa_group { + atomic_t refcount; + + spinlock_t lock; /* nr_tasks, tasks */ + int nr_tasks; + pid_t gid; + + struct rcu_head rcu; + nodemask_t active_nodes; + unsigned long total_faults; + /* + * Faults_cpu is used to decide whether memory should move + * towards the CPU. As a consequence, these stats are weighted + * more by CPU use than by memory faults. + */ + unsigned long *faults_cpu; + unsigned long faults[0]; +}; + +/* Shared or private faults. */ +#define NR_NUMA_HINT_FAULT_TYPES 2 + +/* Memory and CPU locality */ +#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2) + +/* Averaged statistics, and temporary buffers. */ +#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2) + +pid_t task_numa_group_id(struct task_struct *p) +{ + return p->numa_group ? p->numa_group->gid : 0; +} + +/* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ +static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv) +{ + return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv; +} + +static inline unsigned long task_faults(struct task_struct *p, int nid) +{ + if (!p->numa_faults) + return 0; + + return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults(struct task_struct *p, int nid) +{ + if (!p->numa_group) + return 0; + + return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) +{ + return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] + + group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +/* Handle placement on systems where not all nodes are directly connected. */ +static unsigned long score_nearby_nodes(struct task_struct *p, int nid, + int maxdist, bool task) +{ + unsigned long score = 0; + int node; + + /* + * All nodes are directly connected, and the same distance + * from each other. No need for fancy placement algorithms. + */ + if (sched_numa_topology_type == NUMA_DIRECT) + return 0; + + /* + * This code is called for each node, introducing N^2 complexity, + * which should be ok given the number of nodes rarely exceeds 8. + */ + for_each_online_node(node) { + unsigned long faults; + int dist = node_distance(nid, node); + + /* + * The furthest away nodes in the system are not interesting + * for placement; nid was already counted. + */ + if (dist == sched_max_numa_distance || node == nid) + continue; + + /* + * On systems with a backplane NUMA topology, compare groups + * of nodes, and move tasks towards the group with the most + * memory accesses. When comparing two nodes at distance + * "hoplimit", only nodes closer by than "hoplimit" are part + * of each group. Skip other nodes. + */ + if (sched_numa_topology_type == NUMA_BACKPLANE && + dist > maxdist) + continue; + + /* Add up the faults from nearby nodes. */ + if (task) + faults = task_faults(p, node); + else + faults = group_faults(p, node); + + /* + * On systems with a glueless mesh NUMA topology, there are + * no fixed "groups of nodes". Instead, nodes that are not + * directly connected bounce traffic through intermediate + * nodes; a numa_group can occupy any set of nodes. + * The further away a node is, the less the faults count. + * This seems to result in good task placement. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + faults *= (sched_max_numa_distance - dist); + faults /= (sched_max_numa_distance - LOCAL_DISTANCE); + } + + score += faults; + } + + return score; +} + +/* + * These return the fraction of accesses done by a particular task, or + * task group, on a particular numa node. The group weight is given a + * larger multiplier, in order to group tasks together that are almost + * evenly spread out between numa nodes. + */ +static inline unsigned long task_weight(struct task_struct *p, int nid, + int dist) +{ + unsigned long faults, total_faults; + + if (!p->numa_faults) + return 0; + + total_faults = p->total_numa_faults; + + if (!total_faults) + return 0; + + faults = task_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, true); + + return 1000 * faults / total_faults; +} + +static inline unsigned long group_weight(struct task_struct *p, int nid, + int dist) +{ + unsigned long faults, total_faults; + + if (!p->numa_group) + return 0; + + total_faults = p->numa_group->total_faults; + + if (!total_faults) + return 0; + + faults = group_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, false); + + return 1000 * faults / total_faults; +} + +bool should_numa_migrate_memory(struct task_struct *p, struct page * page, + int src_nid, int dst_cpu) +{ + struct numa_group *ng = p->numa_group; + int dst_nid = cpu_to_node(dst_cpu); + int last_cpupid, this_cpupid; + + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + + /* + * Multi-stage node selection is used in conjunction with a periodic + * migration fault to build a temporal task<->page relation. By using + * a two-stage filter we remove short/unlikely relations. + * + * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate + * a task's usage of a particular page (n_p) per total usage of this + * page (n_t) (in a given time-span) to a probability. + * + * Our periodic faults will sample this probability and getting the + * same result twice in a row, given these samples are fully + * independent, is then given by P(n)^2, provided our sample period + * is sufficiently short compared to the usage pattern. + * + * This quadric squishes small probabilities, making it less likely we + * act on an unlikely task<->page relation. + */ + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!cpupid_pid_unset(last_cpupid) && + cpupid_to_nid(last_cpupid) != dst_nid) + return false; + + /* Always allow migrate on private faults */ + if (cpupid_match_pid(p, last_cpupid)) + return true; + + /* A shared fault, but p->numa_group has not been set up yet. */ + if (!ng) + return true; + + /* + * Do not migrate if the destination is not a node that + * is actively used by this numa group. + */ + if (!node_isset(dst_nid, ng->active_nodes)) + return false; + + /* + * Source is a node that is not actively used by this + * numa group, while the destination is. Migrate. + */ + if (!node_isset(src_nid, ng->active_nodes)) + return true; + + /* + * Both source and destination are nodes in active + * use by this numa group. Maximize memory bandwidth + * by migrating from more heavily used groups, to less + * heavily used ones, spreading the load around. + * Use a 1/4 hysteresis to avoid spurious page movement. + */ + return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); +} + +static unsigned long weighted_cpuload(const int cpu); +static unsigned long source_load(int cpu, int type); +static unsigned long target_load(int cpu, int type); +static unsigned long capacity_of(int cpu); +static long effective_load(struct task_group *tg, int cpu, long wl, long wg); + +/* Cached statistics for all CPUs within a node */ +struct numa_stats { + unsigned long nr_running; + unsigned long load; + + /* Total compute capacity of CPUs on a node */ + unsigned long compute_capacity; + + /* Approximate capacity in terms of runnable tasks on a node */ + unsigned long task_capacity; + int has_free_capacity; +}; + +/* + * XXX borrowed from update_sg_lb_stats + */ +static void update_numa_stats(struct numa_stats *ns, int nid) +{ + int smt, cpu, cpus = 0; + unsigned long capacity; + + memset(ns, 0, sizeof(*ns)); + for_each_cpu(cpu, cpumask_of_node(nid)) { + struct rq *rq = cpu_rq(cpu); + + ns->nr_running += rq->nr_running; + ns->load += weighted_cpuload(cpu); + ns->compute_capacity += capacity_of(cpu); + + cpus++; + } + + /* + * If we raced with hotplug and there are no CPUs left in our mask + * the @ns structure is NULL'ed and task_numa_compare() will + * not find this node attractive. + * + * We'll either bail at !has_free_capacity, or we'll detect a huge + * imbalance and bail there. + */ + if (!cpus) + return; + + /* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); + capacity = cpus / smt; /* cores */ + + ns->task_capacity = min_t(unsigned, capacity, + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); + ns->has_free_capacity = (ns->nr_running < ns->task_capacity); +} + +struct task_numa_env { + struct task_struct *p; + + int src_cpu, src_nid; + int dst_cpu, dst_nid; + + struct numa_stats src_stats, dst_stats; + + int imbalance_pct; + int dist; + + struct task_struct *best_task; + long best_imp; + int best_cpu; +}; + +static void task_numa_assign(struct task_numa_env *env, + struct task_struct *p, long imp) +{ + if (env->best_task) + put_task_struct(env->best_task); + if (p) + get_task_struct(p); + + env->best_task = p; + env->best_imp = imp; + env->best_cpu = env->dst_cpu; +} + +static bool load_too_imbalanced(long src_load, long dst_load, + struct task_numa_env *env) +{ + long src_capacity, dst_capacity; + long orig_src_load; + long load_a, load_b; + long moved_load; + long imb; + + /* + * The load is corrected for the CPU capacity available on each node. + * + * src_load dst_load + * ------------ vs --------- + * src_capacity dst_capacity + */ + src_capacity = env->src_stats.compute_capacity; + dst_capacity = env->dst_stats.compute_capacity; + + /* We care about the slope of the imbalance, not the direction. */ + load_a = dst_load; + load_b = src_load; + if (load_a < load_b) + swap(load_a, load_b); + + /* Is the difference below the threshold? */ + imb = load_a * src_capacity * 100 - + load_b * dst_capacity * env->imbalance_pct; + if (imb <= 0) + return false; + + /* + * The imbalance is above the allowed threshold. + * Allow a move that brings us closer to a balanced situation, + * without moving things past the point of balance. + */ + orig_src_load = env->src_stats.load; + + /* + * In a task swap, there will be one load moving from src to dst, + * and another moving back. This is the net sum of both moves. + * A simple task move will always have a positive value. + * Allow the move if it brings the system closer to a balanced + * situation, without crossing over the balance point. + */ + moved_load = orig_src_load - src_load; + + if (moved_load > 0) + /* Moving src -> dst. Did we overshoot balance? */ + return src_load * dst_capacity < dst_load * src_capacity; + else + /* Moving dst -> src. Did we overshoot balance? */ + return dst_load * src_capacity < src_load * dst_capacity; +} + +/* + * This checks if the overall compute and NUMA accesses of the system would + * be improved if the source tasks was migrated to the target dst_cpu taking + * into account that it might be best if task running on the dst_cpu should + * be exchanged with the source task + */ +static void task_numa_compare(struct task_numa_env *env, + long taskimp, long groupimp) +{ + struct rq *src_rq = cpu_rq(env->src_cpu); + struct rq *dst_rq = cpu_rq(env->dst_cpu); + struct task_struct *cur; + long src_load, dst_load; + long load; + long imp = env->p->numa_group ? groupimp : taskimp; + long moveimp = imp; + int dist = env->dist; + + rcu_read_lock(); + + raw_spin_lock_irq(&dst_rq->lock); + cur = dst_rq->curr; + /* + * No need to move the exiting task, and this ensures that ->curr + * wasn't reaped and thus get_task_struct() in task_numa_assign() + * is safe under RCU read lock. + * Note that rcu_read_lock() itself can't protect from the final + * put_task_struct() after the last schedule(). + */ + if ((cur->flags & PF_EXITING) || is_idle_task(cur)) + cur = NULL; + raw_spin_unlock_irq(&dst_rq->lock); + + /* + * Because we have preemption enabled we can get migrated around and + * end try selecting ourselves (current == env->p) as a swap candidate. + */ + if (cur == env->p) + goto unlock; + + /* + * "imp" is the fault differential for the source task between the + * source and destination node. Calculate the total differential for + * the source task and potential destination task. The more negative + * the value is, the more rmeote accesses that would be expected to + * be incurred if the tasks were swapped. + */ + if (cur) { + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur))) + goto unlock; + + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); + /* + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. + */ + if (cur->numa_group) + imp -= imp/16; + } else { + /* + * Compare the group weights. If a task is all by + * itself (not part of a group), use the task weight + * instead. + */ + if (cur->numa_group) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); + } + } + + if (imp <= env->best_imp && moveimp <= env->best_imp) + goto unlock; + + if (!cur) { + /* Is there capacity at our destination? */ + if (env->src_stats.nr_running <= env->src_stats.task_capacity && + !env->dst_stats.has_free_capacity) + goto unlock; + + goto balance; + } + + /* Balance doesn't matter much if we're running a task per cpu */ + if (imp > env->best_imp && src_rq->nr_running == 1 && + dst_rq->nr_running == 1) + goto assign; + + /* + * In the overloaded case, try and keep the load balanced. + */ +balance: + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + if (moveimp > imp && moveimp > env->best_imp) { + /* + * If the improvement from just moving env->p direction is + * better than swapping tasks around, check if a move is + * possible. Store a slightly smaller score than moveimp, + * so an actually idle CPU will win. + */ + if (!load_too_imbalanced(src_load, dst_load, env)) { + imp = moveimp - 1; + cur = NULL; + goto assign; + } + } + + if (imp <= env->best_imp) + goto unlock; + + if (cur) { + load = task_h_load(cur); + dst_load -= load; + src_load += load; + } + + if (load_too_imbalanced(src_load, dst_load, env)) + goto unlock; + + /* + * One idle CPU per node is evaluated for a task numa move. + * Call select_idle_sibling to maybe find a better one. + */ + if (!cur) + env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); + +assign: + task_numa_assign(env, cur, imp); +unlock: + rcu_read_unlock(); +} + +static void task_numa_find_cpu(struct task_numa_env *env, + long taskimp, long groupimp) +{ + int cpu; + + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { + /* Skip this CPU if the source task cannot migrate */ + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p))) + continue; + + env->dst_cpu = cpu; + task_numa_compare(env, taskimp, groupimp); + } +} + +static int task_numa_migrate(struct task_struct *p) +{ + struct task_numa_env env = { + .p = p, + + .src_cpu = task_cpu(p), + .src_nid = task_node(p), + + .imbalance_pct = 112, + + .best_task = NULL, + .best_imp = 0, + .best_cpu = -1 + }; + struct sched_domain *sd; + unsigned long taskweight, groupweight; + int nid, ret, dist; + long taskimp, groupimp; + + /* + * Pick the lowest SD_NUMA domain, as that would have the smallest + * imbalance and would be the first to start moving tasks about. + * + * And we want to avoid any moving of tasks about, as that would create + * random movement of tasks -- counter the numa conditions we're trying + * to satisfy here. + */ + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); + if (sd) + env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + rcu_read_unlock(); + + /* + * Cpusets can break the scheduler domain tree into smaller + * balance domains, some of which do not cross NUMA boundaries. + * Tasks that are "trapped" in such domains cannot be migrated + * elsewhere, so there is no point in (re)trying. + */ + if (unlikely(!sd)) { + p->numa_preferred_nid = task_node(p); + return -EINVAL; + } + + env.dst_nid = p->numa_preferred_nid; + dist = env.dist = node_distance(env.src_nid, env.dst_nid); + taskweight = task_weight(p, env.src_nid, dist); + groupweight = group_weight(p, env.src_nid, dist); + update_numa_stats(&env.src_stats, env.src_nid); + taskimp = task_weight(p, env.dst_nid, dist) - taskweight; + groupimp = group_weight(p, env.dst_nid, dist) - groupweight; + update_numa_stats(&env.dst_stats, env.dst_nid); + + /* Try to find a spot on the preferred nid. */ + task_numa_find_cpu(&env, taskimp, groupimp); + + /* + * Look at other nodes in these cases: + * - there is no space available on the preferred_nid + * - the task is part of a numa_group that is interleaved across + * multiple NUMA nodes; in order to better consolidate the group, + * we need to check other locations. + */ + if (env.best_cpu == -1 || (p->numa_group && + nodes_weight(p->numa_group->active_nodes) > 1)) { + for_each_online_node(nid) { + if (nid == env.src_nid || nid == p->numa_preferred_nid) + continue; + + dist = node_distance(env.src_nid, env.dst_nid); + if (sched_numa_topology_type == NUMA_BACKPLANE && + dist != env.dist) { + taskweight = task_weight(p, env.src_nid, dist); + groupweight = group_weight(p, env.src_nid, dist); + } + + /* Only consider nodes where both task and groups benefit */ + taskimp = task_weight(p, nid, dist) - taskweight; + groupimp = group_weight(p, nid, dist) - groupweight; + if (taskimp < 0 && groupimp < 0) + continue; + + env.dist = dist; + env.dst_nid = nid; + update_numa_stats(&env.dst_stats, env.dst_nid); + task_numa_find_cpu(&env, taskimp, groupimp); + } + } + + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (p->numa_group) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = env.dst_nid; + + if (node_isset(nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; + + /* + * Reset the scan period if the task is being rescheduled on an + * alternative node to recheck if the tasks is now properly placed. + */ + p->numa_scan_period = task_scan_min(p); + + if (env.best_task == NULL) { + ret = migrate_task_to(p, env.best_cpu); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); + return ret; + } + + ret = migrate_swap(p, env.best_task); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); + put_task_struct(env.best_task); + return ret; +} + +/* Attempt to migrate a task to a CPU on the preferred node. */ +static void numa_migrate_preferred(struct task_struct *p) +{ + unsigned long interval = HZ; + + /* This task has no NUMA fault statistics yet */ + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + return; + + /* Periodically retry migrating the task to the preferred node */ + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; + + /* Success if task is already running on preferred CPU */ + if (task_node(p) == p->numa_preferred_nid) + return; + + /* Otherwise, try migrate to a CPU on the preferred node */ + task_numa_migrate(p); +} + +/* + * Find the nodes on which the workload is actively running. We do this by + * tracking the nodes from which NUMA hinting faults are triggered. This can + * be different from the set of nodes where the workload's memory is currently + * located. + * + * The bitmask is used to make smarter decisions on when to do NUMA page + * migrations, To prevent flip-flopping, and excessive page migrations, nodes + * are added when they cause over 6/16 of the maximum number of faults, but + * only removed when they drop below 3/16. + */ +static void update_numa_active_node_mask(struct numa_group *numa_group) +{ + unsigned long faults, max_faults = 0; + int nid; + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (faults > max_faults) + max_faults = faults; + } + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (!node_isset(nid, numa_group->active_nodes)) { + if (faults > max_faults * 6 / 16) + node_set(nid, numa_group->active_nodes); + } else if (faults < max_faults * 3 / 16) + node_clear(nid, numa_group->active_nodes); + } +} + +/* + * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS + * increments. The more local the fault statistics are, the higher the scan + * period will be for the next scan window. If local/(local+remote) ratio is + * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) + * the scan period will decrease. Aim for 70% local accesses. + */ +#define NUMA_PERIOD_SLOTS 10 +#define NUMA_PERIOD_THRESHOLD 7 + +/* + * Increase the scan period (slow down scanning) if the majority of + * our memory is already on our local node, or if the majority of + * the page accesses are shared with other processes. + * Otherwise, decrease the scan period. + */ +static void update_task_scan_period(struct task_struct *p, + unsigned long shared, unsigned long private) +{ + unsigned int period_slot; + int ratio; + int diff; + + unsigned long remote = p->numa_faults_locality[0]; + unsigned long local = p->numa_faults_locality[1]; + + /* + * If there were no record hinting faults then either the task is + * completely idle or all activity is areas that are not of interest + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower + */ + if (local + shared == 0 || p->numa_faults_locality[2]) { + p->numa_scan_period = min(p->numa_scan_period_max, + p->numa_scan_period << 1); + + p->mm->numa_next_scan = jiffies + + msecs_to_jiffies(p->numa_scan_period); + + return; + } + + /* + * Prepare to scale scan period relative to the current period. + * == NUMA_PERIOD_THRESHOLD scan period stays the same + * < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster) + * >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower) + */ + period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS); + ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote); + if (ratio >= NUMA_PERIOD_THRESHOLD) { + int slot = ratio - NUMA_PERIOD_THRESHOLD; + if (!slot) + slot = 1; + diff = slot * period_slot; + } else { + diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot; + + /* + * Scale scan rate increases based on sharing. There is an + * inverse relationship between the degree of sharing and + * the adjustment made to the scanning period. Broadly + * speaking the intent is that there is little point + * scanning faster if shared accesses dominate as it may + * simply bounce migrations uselessly + */ + ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1)); + diff = (diff * ratio) / NUMA_PERIOD_SLOTS; + } + + p->numa_scan_period = clamp(p->numa_scan_period + diff, + task_scan_min(p), task_scan_max(p)); + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); +} + +/* + * Get the fraction of time the task has been running since the last + * NUMA placement cycle. The scheduler keeps similar statistics, but + * decays those on a 32ms period, which is orders of magnitude off + * from the dozens-of-seconds NUMA balancing period. Use the scheduler + * stats only if the task is so new there are no NUMA statistics yet. + */ +static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) +{ + u64 runtime, delta, now; + /* Use the start of this time slice to avoid calculations. */ + now = p->se.exec_start; + runtime = p->se.sum_exec_runtime; + + if (p->last_task_numa_placement) { + delta = runtime - p->last_sum_exec_runtime; + *period = now - p->last_task_numa_placement; + } else { + delta = p->se.avg.runnable_avg_sum; + *period = p->se.avg.avg_period; + } + + p->last_sum_exec_runtime = runtime; + p->last_task_numa_placement = now; + + return delta; +} + +/* + * Determine the preferred nid for a task in a numa_group. This needs to + * be done in a way that produces consistent results with group_weight, + * otherwise workloads might not converge. + */ +static int preferred_group_nid(struct task_struct *p, int nid) +{ + nodemask_t nodes; + int dist; + + /* Direct connections between all NUMA nodes. */ + if (sched_numa_topology_type == NUMA_DIRECT) + return nid; + + /* + * On a system with glueless mesh NUMA topology, group_weight + * scores nodes according to the number of NUMA hinting faults on + * both the node itself, and on nearby nodes. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + unsigned long score, max_score = 0; + int node, max_node = nid; + + dist = sched_max_numa_distance; + + for_each_online_node(node) { + score = group_weight(p, node, dist); + if (score > max_score) { + max_score = score; + max_node = node; + } + } + return max_node; + } + + /* + * Finding the preferred nid in a system with NUMA backplane + * interconnect topology is more involved. The goal is to locate + * tasks from numa_groups near each other in the system, and + * untangle workloads from different sides of the system. This requires + * searching down the hierarchy of node groups, recursively searching + * inside the highest scoring group of nodes. The nodemask tricks + * keep the complexity of the search down. + */ + nodes = node_online_map; + for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) { + unsigned long max_faults = 0; + nodemask_t max_group = NODE_MASK_NONE; + int a, b; + + /* Are there nodes at this distance from each other? */ + if (!find_numa_distance(dist)) + continue; + + for_each_node_mask(a, nodes) { + unsigned long faults = 0; + nodemask_t this_group; + nodes_clear(this_group); + + /* Sum group's NUMA faults; includes a==b case. */ + for_each_node_mask(b, nodes) { + if (node_distance(a, b) < dist) { + faults += group_faults(p, b); + node_set(b, this_group); + node_clear(b, nodes); + } + } + + /* Remember the top group. */ + if (faults > max_faults) { + max_faults = faults; + max_group = this_group; + /* + * subtle: at the smallest distance there is + * just one node left in each "group", the + * winner is the preferred nid. + */ + nid = a; + } + } + /* Next round, evaluate the nodes within max_group. */ + if (!max_faults) + break; + nodes = max_group; + } + return nid; +} + +static void task_numa_placement(struct task_struct *p) +{ + int seq, nid, max_nid = -1, max_group_nid = -1; + unsigned long max_faults = 0, max_group_faults = 0; + unsigned long fault_types[2] = { 0, 0 }; + unsigned long total_faults; + u64 runtime, period; + spinlock_t *group_lock = NULL; + + seq = ACCESS_ONCE(p->mm->numa_scan_seq); + if (p->numa_scan_seq == seq) + return; + p->numa_scan_seq = seq; + p->numa_scan_period_max = task_scan_max(p); + + total_faults = p->numa_faults_locality[0] + + p->numa_faults_locality[1]; + runtime = numa_get_avg_runtime(p, &period); + + /* If the task is part of a group prevent parallel updates to group stats */ + if (p->numa_group) { + group_lock = &p->numa_group->lock; + spin_lock_irq(group_lock); + } + + /* Find the node with the highest number of faults */ + for_each_online_node(nid) { + /* Keep track of the offsets in numa_faults array */ + int mem_idx, membuf_idx, cpu_idx, cpubuf_idx; + unsigned long faults = 0, group_faults = 0; + int priv; + + for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { + long diff, f_diff, f_weight; + + mem_idx = task_faults_idx(NUMA_MEM, nid, priv); + membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv); + cpu_idx = task_faults_idx(NUMA_CPU, nid, priv); + cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv); + + /* Decay existing window, copy faults since last scan */ + diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2; + fault_types[priv] += p->numa_faults[membuf_idx]; + p->numa_faults[membuf_idx] = 0; + + /* + * Normalize the faults_from, so all tasks in a group + * count according to CPU use, instead of by the raw + * number of faults. Tasks with little runtime have + * little over-all impact on throughput, and thus their + * faults are less important. + */ + f_weight = div64_u64(runtime << 16, period + 1); + f_weight = (f_weight * p->numa_faults[cpubuf_idx]) / + (total_faults + 1); + f_diff = f_weight - p->numa_faults[cpu_idx] / 2; + p->numa_faults[cpubuf_idx] = 0; + + p->numa_faults[mem_idx] += diff; + p->numa_faults[cpu_idx] += f_diff; + faults += p->numa_faults[mem_idx]; + p->total_numa_faults += diff; + if (p->numa_group) { + /* + * safe because we can only change our own group + * + * mem_idx represents the offset for a given + * nid and priv in a specific region because it + * is at the beginning of the numa_faults array. + */ + p->numa_group->faults[mem_idx] += diff; + p->numa_group->faults_cpu[mem_idx] += f_diff; + p->numa_group->total_faults += diff; + group_faults += p->numa_group->faults[mem_idx]; + } + } + + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + + if (group_faults > max_group_faults) { + max_group_faults = group_faults; + max_group_nid = nid; + } + } + + update_task_scan_period(p, fault_types[0], fault_types[1]); + + if (p->numa_group) { + update_numa_active_node_mask(p->numa_group); + spin_unlock_irq(group_lock); + max_nid = preferred_group_nid(p, max_group_nid); + } + + if (max_faults) { + /* Set the new preferred node */ + if (max_nid != p->numa_preferred_nid) + sched_setnuma(p, max_nid); + + if (task_node(p) != p->numa_preferred_nid) + numa_migrate_preferred(p); + } +} + +static inline int get_numa_group(struct numa_group *grp) +{ + return atomic_inc_not_zero(&grp->refcount); +} + +static inline void put_numa_group(struct numa_group *grp) +{ + if (atomic_dec_and_test(&grp->refcount)) + kfree_rcu(grp, rcu); +} + +static void task_numa_group(struct task_struct *p, int cpupid, int flags, + int *priv) +{ + struct numa_group *grp, *my_grp; + struct task_struct *tsk; + bool join = false; + int cpu = cpupid_to_cpu(cpupid); + int i; + + if (unlikely(!p->numa_group)) { + unsigned int size = sizeof(struct numa_group) + + 4*nr_node_ids*sizeof(unsigned long); + + grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!grp) + return; + + atomic_set(&grp->refcount, 1); + spin_lock_init(&grp->lock); + grp->gid = p->pid; + /* Second half of the array tracks nids where faults happen */ + grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * + nr_node_ids; + + node_set(task_node(current), grp->active_nodes); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] = p->numa_faults[i]; + + grp->total_faults = p->total_numa_faults; + + grp->nr_tasks++; + rcu_assign_pointer(p->numa_group, grp); + } + + rcu_read_lock(); + tsk = ACCESS_ONCE(cpu_rq(cpu)->curr); + + if (!cpupid_match_pid(tsk, cpupid)) + goto no_join; + + grp = rcu_dereference(tsk->numa_group); + if (!grp) + goto no_join; + + my_grp = p->numa_group; + if (grp == my_grp) + goto no_join; + + /* + * Only join the other group if its bigger; if we're the bigger group, + * the other task will join us. + */ + if (my_grp->nr_tasks > grp->nr_tasks) + goto no_join; + + /* + * Tie-break on the grp address. + */ + if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp) + goto no_join; + + /* Always join threads in the same process. */ + if (tsk->mm == current->mm) + join = true; + + /* Simple filter to avoid false positives due to PID collisions */ + if (flags & TNF_SHARED) + join = true; + + /* Update priv based on whether false sharing was detected */ + *priv = !join; + + if (join && !get_numa_group(grp)) + goto no_join; + + rcu_read_unlock(); + + if (!join) + return; + + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; + } + my_grp->total_faults -= p->total_numa_faults; + grp->total_faults += p->total_numa_faults; + + my_grp->nr_tasks--; + grp->nr_tasks++; + + spin_unlock(&my_grp->lock); + spin_unlock_irq(&grp->lock); + + rcu_assign_pointer(p->numa_group, grp); + + put_numa_group(my_grp); + return; + +no_join: + rcu_read_unlock(); + return; +} + +void task_numa_free(struct task_struct *p) +{ + struct numa_group *grp = p->numa_group; + void *numa_faults = p->numa_faults; + unsigned long flags; + int i; + + if (grp) { + spin_lock_irqsave(&grp->lock, flags); + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] -= p->numa_faults[i]; + grp->total_faults -= p->total_numa_faults; + + grp->nr_tasks--; + spin_unlock_irqrestore(&grp->lock, flags); + RCU_INIT_POINTER(p->numa_group, NULL); + put_numa_group(grp); + } + + p->numa_faults = NULL; + kfree(numa_faults); +} + +/* + * Got a PROT_NONE fault for a page on @node. + */ +void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) +{ + struct task_struct *p = current; + bool migrated = flags & TNF_MIGRATED; + int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); + int priv; + + if (!numabalancing_enabled) + return; + + /* for example, ksmd faulting in a user's mm */ + if (!p->mm) + return; + + /* Allocate buffer to track faults on a per-node basis */ + if (unlikely(!p->numa_faults)) { + int size = sizeof(*p->numa_faults) * + NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; + + p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults) + return; + + p->total_numa_faults = 0; + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); + } + + /* + * First accesses are treated as private, otherwise consider accesses + * to be private if the accessing pid has not changed + */ + if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) { + priv = 1; + } else { + priv = cpupid_match_pid(p, last_cpupid); + if (!priv && !(flags & TNF_NO_GROUP)) + task_numa_group(p, last_cpupid, flags, &priv); + } + + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; + + task_numa_placement(p); + + /* + * Retry task to preferred node migration periodically, in case it + * case it previously failed, or the scheduler moved us. + */ + if (time_after(jiffies, p->numa_migrate_retry)) + numa_migrate_preferred(p); + + if (migrated) + p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; + + p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; + p->numa_faults_locality[local] += pages; +} + +static void reset_ptenuma_scan(struct task_struct *p) +{ + ACCESS_ONCE(p->mm->numa_scan_seq)++; + p->mm->numa_scan_offset = 0; +} + +/* + * The expensive part of numa migration is done from task_work context. + * Triggered from task_tick_numa(). + */ +void task_numa_work(struct callback_head *work) +{ + unsigned long migrate, next_scan, now = jiffies; + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + struct vm_area_struct *vma; + unsigned long start, end; + unsigned long nr_pte_updates = 0; + long pages; + + WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); + + work->next = work; /* protect against double add */ + /* + * Who cares about NUMA placement when they're dying. + * + * NOTE: make sure not to dereference p->mm before this check, + * exit_task_work() happens _after_ exit_mm() so we could be called + * without p->mm even though we still had it when we enqueued this + * work. + */ + if (p->flags & PF_EXITING) + return; + + if (!mm->numa_next_scan) { + mm->numa_next_scan = now + + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + } + + /* + * Enforce maximal scan/migration frequency.. + */ + migrate = mm->numa_next_scan; + if (time_before(now, migrate)) + return; + + if (p->numa_scan_period == 0) { + p->numa_scan_period_max = task_scan_max(p); + p->numa_scan_period = task_scan_min(p); + } + + next_scan = now + msecs_to_jiffies(p->numa_scan_period); + if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) + return; + + /* + * Delay this task enough that another task of this mm will likely win + * the next time around. + */ + p->node_stamp += 2 * TICK_NSEC; + + start = mm->numa_scan_offset; + pages = sysctl_numa_balancing_scan_size; + pages <<= 20 - PAGE_SHIFT; /* MB in pages */ + if (!pages) + return; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, start); + if (!vma) { + reset_ptenuma_scan(p); + start = 0; + vma = mm->mmap; + } + for (; vma; vma = vma->vm_next) { + if (!vma_migratable(vma) || !vma_policy_mof(vma) || + is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { + continue; + } + + /* + * Shared library pages mapped by multiple processes are not + * migrated as it is expected they are cache replicated. Avoid + * hinting faults in read-only file-backed mappings or the vdso + * as migrating the pages will be of marginal benefit. + */ + if (!vma->vm_mm || + (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) + continue; + + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) + continue; + + do { + start = max(start, vma->vm_start); + end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); + end = min(end, vma->vm_end); + nr_pte_updates += change_prot_numa(vma, start, end); + + /* + * Scan sysctl_numa_balancing_scan_size but ensure that + * at least one PTE is updated so that unused virtual + * address space is quickly skipped. + */ + if (nr_pte_updates) + pages -= (end - start) >> PAGE_SHIFT; + + start = end; + if (pages <= 0) + goto out; + + cond_resched(); + } while (end != vma->vm_end); + } + +out: + /* + * It is possible to reach the end of the VMA list but the last few + * VMAs are not guaranteed to the vma_migratable. If they are not, we + * would find the !migratable VMA on the next scan but not reset the + * scanner to the start so check it now. + */ + if (vma) + mm->numa_scan_offset = start; + else + reset_ptenuma_scan(p); + up_read(&mm->mmap_sem); +} + +/* + * Drive the periodic memory faults.. + */ +void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->numa_work; + u64 period, now; + + /* + * We don't care about NUMA placement if we don't have memory. + */ + if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + return; + + /* + * Using runtime rather than walltime has the dual advantage that + * we (mostly) drive the selection from busy threads and that the + * task needs to have done some actual work before we bother with + * NUMA placement. + */ + now = curr->se.sum_exec_runtime; + period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; + + if (now - curr->node_stamp > period) { + if (!curr->node_stamp) + curr->numa_scan_period = task_scan_min(curr); + curr->node_stamp += period; + + if (!time_before(jiffies, curr->mm->numa_next_scan)) { + init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + task_work_add(curr, work, true); + } + } +} +#else +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ +} + +static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ +} + +static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + +static void +account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_add(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + update_load_add(&rq_of(cfs_rq)->load, se->load.weight); +#ifdef CONFIG_SMP + if (entity_is_task(se)) { + struct rq *rq = rq_of(cfs_rq); + + account_numa_enqueue(rq, task_of(se)); + list_add(&se->group_node, &rq->cfs_tasks); + } +#endif + cfs_rq->nr_running++; +} + +static void +account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_sub(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); + if (entity_is_task(se)) { + account_numa_dequeue(rq_of(cfs_rq), task_of(se)); + list_del_init(&se->group_node); + } + cfs_rq->nr_running--; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +# ifdef CONFIG_SMP +static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) +{ + long tg_weight; + + /* + * Use this CPU's actual weight instead of the last load_contribution + * to gain a more accurate current total weight. See + * update_cfs_rq_load_contribution(). + */ + tg_weight = atomic_long_read(&tg->load_avg); + tg_weight -= cfs_rq->tg_load_contrib; + tg_weight += cfs_rq->load.weight; + + return tg_weight; +} + +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) +{ + long tg_weight, load, shares; + + tg_weight = calc_tg_weight(tg, cfs_rq); + load = cfs_rq->load.weight; + + shares = (tg->shares * load); + if (tg_weight) + shares /= tg_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + if (shares > tg->shares) + shares = tg->shares; + + return shares; +} +# else /* CONFIG_SMP */ +static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) +{ + return tg->shares; +} +# endif /* CONFIG_SMP */ +static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + if (se->on_rq) { + /* commit outstanding execution time */ + if (cfs_rq->curr == se) + update_curr(cfs_rq); + account_entity_dequeue(cfs_rq, se); + } + + update_load_set(&se->load, weight); + + if (se->on_rq) + account_entity_enqueue(cfs_rq, se); +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); + +static void update_cfs_shares(struct cfs_rq *cfs_rq) +{ + struct task_group *tg; + struct sched_entity *se; + long shares; + + tg = cfs_rq->tg; + se = tg->se[cpu_of(rq_of(cfs_rq))]; + if (!se || throttled_hierarchy(cfs_rq)) + return; +#ifndef CONFIG_SMP + if (likely(se->load.weight == tg->shares)) + return; +#endif + shares = calc_cfs_shares(cfs_rq, tg); + + reweight_entity(cfs_rq_of(se), se, shares); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_SMP +/* + * We choose a half-life close to 1 scheduling period. + * Note: The tables below are dependent on this value. + */ +#define LOAD_AVG_PERIOD 32 +#define LOAD_AVG_MAX 47742 /* maximum possible load avg */ +#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */ + +/* Precomputed fixed inverse multiplies for multiplication by y^n */ +static const u32 runnable_avg_yN_inv[] = { + 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, + 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85, + 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581, + 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9, + 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80, + 0x85aac367, 0x82cd8698, +}; + +/* + * Precomputed \Sum y^k { 1<=k<=n }. These are floor(true_value) to prevent + * over-estimates when re-combining. + */ +static const u32 runnable_avg_yN_sum[] = { + 0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103, + 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082, + 17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371, +}; + +/* + * Approximate: + * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) + */ +static __always_inline u64 decay_load(u64 val, u64 n) +{ + unsigned int local_n; + + if (!n) + return val; + else if (unlikely(n > LOAD_AVG_PERIOD * 63)) + return 0; + + /* after bounds checking we can collapse to 32-bit */ + local_n = n; + + /* + * As y^PERIOD = 1/2, we can combine + * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) + * With a look-up table which covers y^n (n<PERIOD) + * + * To achieve constant time decay_load. + */ + if (unlikely(local_n >= LOAD_AVG_PERIOD)) { + val >>= local_n / LOAD_AVG_PERIOD; + local_n %= LOAD_AVG_PERIOD; + } + + val *= runnable_avg_yN_inv[local_n]; + /* We don't use SRR here since we always want to round down. */ + return val >> 32; +} + +/* + * For updates fully spanning n periods, the contribution to runnable + * average will be: \Sum 1024*y^n + * + * We can compute this reasonably efficiently by combining: + * y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for n <PERIOD} + */ +static u32 __compute_runnable_contrib(u64 n) +{ + u32 contrib = 0; + + if (likely(n <= LOAD_AVG_PERIOD)) + return runnable_avg_yN_sum[n]; + else if (unlikely(n >= LOAD_AVG_MAX_N)) + return LOAD_AVG_MAX; + + /* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */ + do { + contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */ + contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD]; + + n -= LOAD_AVG_PERIOD; + } while (n > LOAD_AVG_PERIOD); + + contrib = decay_load(contrib, n); + return contrib + runnable_avg_yN_sum[n]; +} + +/* + * 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. + * + * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... + * p0 p1 p2 + * (now) (~1ms ago) (~2ms ago) + * + * Let u_i denote the fraction of p_i that the entity was runnable. + * + * We then designate the fractions u_i as our co-efficients, yielding the + * following representation of historical load: + * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... + * + * We choose y based on the with of a reasonably scheduling period, fixing: + * y^32 = 0.5 + * + * This means that the contribution to load ~32ms ago (u_32) will be weighted + * approximately half as much as the contribution to load within the last ms + * (u_0). + * + * When a period "rolls over" and we have new u_0`, multiplying the previous + * sum again by y is sufficient to update: + * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) + * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] + */ +static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, + struct sched_avg *sa, + int runnable, + int running) +{ + u64 delta, periods; + u32 runnable_contrib; + int delta_w, decayed = 0; + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); + + delta = now - sa->last_runnable_update; + /* + * This should only happen when time goes backwards, which it + * unfortunately does during sched clock init when we swap over to TSC. + */ + if ((s64)delta < 0) { + sa->last_runnable_update = now; + return 0; + } + + /* + * Use 1024ns as the unit of measurement since it's a reasonable + * approximation of 1us and fast to compute. + */ + delta >>= 10; + if (!delta) + return 0; + sa->last_runnable_update = now; + + /* delta_w is the amount already accumulated against our next period */ + delta_w = sa->avg_period % 1024; + if (delta + delta_w >= 1024) { + /* period roll-over */ + decayed = 1; + + /* + * Now that we know we're crossing a period boundary, figure + * out how much from delta we need to complete the current + * period and accrue it. + */ + delta_w = 1024 - delta_w; + if (runnable) + sa->runnable_avg_sum += delta_w; + if (running) + sa->running_avg_sum += delta_w * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta_w; + + delta -= delta_w; + + /* Figure out how many additional periods this update spans */ + periods = delta / 1024; + delta %= 1024; + + sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, + periods + 1); + sa->running_avg_sum = decay_load(sa->running_avg_sum, + periods + 1); + sa->avg_period = decay_load(sa->avg_period, + periods + 1); + + /* Efficiently calculate \sum (1..n_period) 1024*y^i */ + runnable_contrib = __compute_runnable_contrib(periods); + if (runnable) + sa->runnable_avg_sum += runnable_contrib; + if (running) + sa->running_avg_sum += runnable_contrib * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += runnable_contrib; + } + + /* Remainder of delta accrued against u_0` */ + if (runnable) + sa->runnable_avg_sum += delta; + if (running) + sa->running_avg_sum += delta * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta; + + return decayed; +} + +/* Synchronize an entity's decay with its parenting cfs_rq.*/ +static inline u64 __synchronize_entity_decay(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 decays = atomic64_read(&cfs_rq->decay_counter); + + decays -= se->avg.decay_count; + se->avg.decay_count = 0; + if (!decays) + return 0; + + se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); + se->avg.utilization_avg_contrib = + decay_load(se->avg.utilization_avg_contrib, decays); + + return decays; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, + int force_update) +{ + struct task_group *tg = cfs_rq->tg; + long tg_contrib; + + tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; + tg_contrib -= cfs_rq->tg_load_contrib; + + if (!tg_contrib) + return; + + if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) { + atomic_long_add(tg_contrib, &tg->load_avg); + cfs_rq->tg_load_contrib += tg_contrib; + } +} + +/* + * Aggregate cfs_rq runnable averages into an equivalent task_group + * representation for computing load contributions. + */ +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; + + /* The fraction of a cpu used by this cfs_rq */ + contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, + sa->avg_period + 1); + contrib -= cfs_rq->tg_runnable_contrib; + + if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { + atomic_add(contrib, &tg->runnable_avg); + cfs_rq->tg_runnable_contrib += contrib; + } +} + +static inline void __update_group_entity_contrib(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = group_cfs_rq(se); + struct task_group *tg = cfs_rq->tg; + int runnable_avg; + + u64 contrib; + + contrib = cfs_rq->tg_load_contrib * tg->shares; + se->avg.load_avg_contrib = div_u64(contrib, + atomic_long_read(&tg->load_avg) + 1); + + /* + * For group entities we need to compute a correction term in the case + * that they are consuming <1 cpu so that we would contribute the same + * load as a task of equal weight. + * + * Explicitly co-ordinating this measurement would be expensive, but + * fortunately the sum of each cpus contribution forms a usable + * lower-bound on the true value. + * + * Consider the aggregate of 2 contributions. Either they are disjoint + * (and the sum represents true value) or they are disjoint and we are + * understating by the aggregate of their overlap. + * + * Extending this to N cpus, for a given overlap, the maximum amount we + * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of + * cpus that overlap for this interval and w_i is the interval width. + * + * On a small machine; the first term is well-bounded which bounds the + * total error since w_i is a subset of the period. Whereas on a + * larger machine, while this first term can be larger, if w_i is the + * of consequential size guaranteed to see n_i*w_i quickly converge to + * our upper bound of 1-cpu. + */ + runnable_avg = atomic_read(&tg->runnable_avg); + if (runnable_avg < NICE_0_LOAD) { + se->avg.load_avg_contrib *= runnable_avg; + se->avg.load_avg_contrib >>= NICE_0_SHIFT; + } +} + +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) +{ + __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg, + runnable, runnable); + __update_tg_runnable_avg(&rq->avg, &rq->cfs); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, + int force_update) {} +static inline void __update_tg_runnable_avg(struct sched_avg *sa, + struct cfs_rq *cfs_rq) {} +static inline void __update_group_entity_contrib(struct sched_entity *se) {} +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +static inline void __update_task_entity_contrib(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); + contrib /= (se->avg.avg_period + 1); + se->avg.load_avg_contrib = scale_load(contrib); +} + +/* Compute the current contribution to load_avg by se, return any delta */ +static long __update_entity_load_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.load_avg_contrib; + + if (entity_is_task(se)) { + __update_task_entity_contrib(se); + } else { + __update_tg_runnable_avg(&se->avg, group_cfs_rq(se)); + __update_group_entity_contrib(se); + } + + return se->avg.load_avg_contrib - old_contrib; +} + + +static inline void __update_task_entity_utilization(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE); + contrib /= (se->avg.avg_period + 1); + se->avg.utilization_avg_contrib = scale_load(contrib); +} + +static long __update_entity_utilization_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.utilization_avg_contrib; + + if (entity_is_task(se)) + __update_task_entity_utilization(se); + else + se->avg.utilization_avg_contrib = + group_cfs_rq(se)->utilization_load_avg; + + return se->avg.utilization_avg_contrib - old_contrib; +} + +static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq, + long load_contrib) +{ + if (likely(load_contrib < cfs_rq->blocked_load_avg)) + cfs_rq->blocked_load_avg -= load_contrib; + else + cfs_rq->blocked_load_avg = 0; +} + +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); + +/* Update a sched_entity's runnable average */ +static inline void update_entity_load_avg(struct sched_entity *se, + int update_cfs_rq) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + long contrib_delta, utilization_delta; + int cpu = cpu_of(rq_of(cfs_rq)); + u64 now; + + /* + * For a group entity we need to use their owned cfs_rq_clock_task() in + * case they are the parent of a throttled hierarchy. + */ + if (entity_is_task(se)) + now = cfs_rq_clock_task(cfs_rq); + else + now = cfs_rq_clock_task(group_cfs_rq(se)); + + if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq, + cfs_rq->curr == se)) + return; + + contrib_delta = __update_entity_load_avg_contrib(se); + utilization_delta = __update_entity_utilization_avg_contrib(se); + + if (!update_cfs_rq) + return; + + if (se->on_rq) { + cfs_rq->runnable_load_avg += contrib_delta; + cfs_rq->utilization_load_avg += utilization_delta; + } else { + subtract_blocked_load_contrib(cfs_rq, -contrib_delta); + } +} + +/* + * Decay the load contributed by all blocked children and account this so that + * their contribution may appropriately discounted when they wake up. + */ +static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) +{ + u64 now = cfs_rq_clock_task(cfs_rq) >> 20; + u64 decays; + + decays = now - cfs_rq->last_decay; + if (!decays && !force_update) + return; + + if (atomic_long_read(&cfs_rq->removed_load)) { + unsigned long removed_load; + removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0); + subtract_blocked_load_contrib(cfs_rq, removed_load); + } + + if (decays) { + cfs_rq->blocked_load_avg = decay_load(cfs_rq->blocked_load_avg, + decays); + atomic64_add(decays, &cfs_rq->decay_counter); + cfs_rq->last_decay = now; + } + + __update_cfs_rq_tg_load_contrib(cfs_rq, force_update); +} + +/* Add the load generated by se into cfs_rq's child load-average */ +static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int wakeup) +{ + /* + * We track migrations using entity decay_count <= 0, on a wake-up + * migration we use a negative decay count to track the remote decays + * accumulated while sleeping. + * + * Newly forked tasks are enqueued with se->avg.decay_count == 0, they + * are seen by enqueue_entity_load_avg() as a migration with an already + * constructed load_avg_contrib. + */ + if (unlikely(se->avg.decay_count <= 0)) { + se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq)); + if (se->avg.decay_count) { + /* + * In a wake-up migration we have to approximate the + * time sleeping. This is because we can't synchronize + * clock_task between the two cpus, and it is not + * guaranteed to be read-safe. Instead, we can + * approximate this using our carried decays, which are + * explicitly atomically readable. + */ + se->avg.last_runnable_update -= (-se->avg.decay_count) + << 20; + update_entity_load_avg(se, 0); + /* Indicate that we're now synchronized and on-rq */ + se->avg.decay_count = 0; + } + wakeup = 0; + } else { + __synchronize_entity_decay(se); + } + + /* migrated tasks did not contribute to our blocked load */ + if (wakeup) { + subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); + update_entity_load_avg(se, 0); + } + + cfs_rq->runnable_load_avg += se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib; + /* we force update consideration on load-balancer moves */ + update_cfs_rq_blocked_load(cfs_rq, !wakeup); +} + +/* + * Remove se's load from this cfs_rq child load-average, if the entity is + * transitioning to a blocked state we track its projected decay using + * blocked_load_avg. + */ +static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int sleep) +{ + update_entity_load_avg(se, 1); + /* we force update consideration on load-balancer moves */ + update_cfs_rq_blocked_load(cfs_rq, !sleep); + + cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib; + if (sleep) { + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + } /* migrations, e.g. sleep=0 leave decay_count == 0 */ +} + +/* + * Update the rq's load with the elapsed running time before entering + * idle. if the last scheduled task is not a CFS task, idle_enter will + * be the only way to update the runnable statistic. + */ +void idle_enter_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 1); +} + +/* + * Update the rq's load with the elapsed idle time before a task is + * scheduled. if the newly scheduled task is not a CFS task, idle_exit will + * be the only way to update the runnable statistic. + */ +void idle_exit_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 0); +} + +static int idle_balance(struct rq *this_rq); + +#else /* CONFIG_SMP */ + +static inline void update_entity_load_avg(struct sched_entity *se, + int update_cfs_rq) {} +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int wakeup) {} +static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, + struct sched_entity *se, + int sleep) {} +static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, + int force_update) {} + +static inline int idle_balance(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SMP */ + +static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_SCHEDSTATS + struct task_struct *tsk = NULL; + + if (entity_is_task(se)) + tsk = task_of(se); + + if (se->statistics.sleep_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > se->statistics.sleep_max)) + se->statistics.sleep_max = delta; + + se->statistics.sleep_start = 0; + se->statistics.sum_sleep_runtime += delta; + + if (tsk) { + account_scheduler_latency(tsk, delta >> 10, 1); + trace_sched_stat_sleep(tsk, delta); + } + } + if (se->statistics.block_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > se->statistics.block_max)) + se->statistics.block_max = delta; + + se->statistics.block_start = 0; + se->statistics.sum_sleep_runtime += delta; + + if (tsk) { + if (tsk->in_iowait) { + se->statistics.iowait_sum += delta; + se->statistics.iowait_count++; + trace_sched_stat_iowait(tsk, delta); + } + + trace_sched_stat_blocked(tsk, delta); + + /* + * Blocking time is in units of nanosecs, so shift by + * 20 to get a milliseconds-range estimation of the + * amount of time that the task spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + profile_hits(SLEEP_PROFILING, + (void *)get_wchan(tsk), + delta >> 20); + } + account_scheduler_latency(tsk, delta >> 10, 0); + } + } +#endif +} + +static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_SCHED_DEBUG + s64 d = se->vruntime - cfs_rq->min_vruntime; + + if (d < 0) + d = -d; + + if (d > 3*sysctl_sched_latency) + schedstat_inc(cfs_rq, nr_spread_over); +#endif +} + +static void +place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) +{ + u64 vruntime = cfs_rq->min_vruntime; + + /* + * The 'current' period is already promised to the current tasks, + * however the extra weight of the new task will slow them down a + * little, place the new task so that it fits in the slot that + * stays open at the end. + */ + if (initial && sched_feat(START_DEBIT)) + vruntime += sched_vslice(cfs_rq, se); + + /* sleeps up to a single latency don't count. */ + if (!initial) { + unsigned long thresh = sysctl_sched_latency; + + /* + * Halve their sleep time's effect, to allow + * for a gentler effect of sleepers: + */ + if (sched_feat(GENTLE_FAIR_SLEEPERS)) + thresh >>= 1; + + vruntime -= thresh; + } + + /* ensure we never gain time by being placed backwards. */ + se->vruntime = max_vruntime(se->vruntime, vruntime); +} + +static void check_enqueue_throttle(struct cfs_rq *cfs_rq); + +static void +enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + /* + * Update the normalized vruntime before updating min_vruntime + * through calling update_curr(). + */ + if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) + se->vruntime += cfs_rq->min_vruntime; + + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP); + account_entity_enqueue(cfs_rq, se); + update_cfs_shares(cfs_rq); + + if (flags & ENQUEUE_WAKEUP) { + place_entity(cfs_rq, se, 0); + enqueue_sleeper(cfs_rq, se); + } + + update_stats_enqueue(cfs_rq, se); + check_spread(cfs_rq, se); + if (se != cfs_rq->curr) + __enqueue_entity(cfs_rq, se); + se->on_rq = 1; + + if (cfs_rq->nr_running == 1) { + list_add_leaf_cfs_rq(cfs_rq); + check_enqueue_throttle(cfs_rq); + } +} + +static void __clear_buddies_last(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->last != se) + break; + + cfs_rq->last = NULL; + } +} + +static void __clear_buddies_next(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->next != se) + break; + + cfs_rq->next = NULL; + } +} + +static void __clear_buddies_skip(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->skip != se) + break; + + cfs_rq->skip = NULL; + } +} + +static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->last == se) + __clear_buddies_last(se); + + if (cfs_rq->next == se) + __clear_buddies_next(se); + + if (cfs_rq->skip == se) + __clear_buddies_skip(se); +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); + +static void +dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP); + + update_stats_dequeue(cfs_rq, se); + if (flags & DEQUEUE_SLEEP) { +#ifdef CONFIG_SCHEDSTATS + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + if (tsk->state & TASK_INTERRUPTIBLE) + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); + if (tsk->state & TASK_UNINTERRUPTIBLE) + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); + } +#endif + } + + clear_buddies(cfs_rq, se); + + if (se != cfs_rq->curr) + __dequeue_entity(cfs_rq, se); + se->on_rq = 0; + account_entity_dequeue(cfs_rq, se); + + /* + * Normalize the entity after updating the min_vruntime because the + * update can refer to the ->curr item and we need to reflect this + * movement in our normalized position. + */ + if (!(flags & DEQUEUE_SLEEP)) + se->vruntime -= cfs_rq->min_vruntime; + + /* return excess runtime on last dequeue */ + return_cfs_rq_runtime(cfs_rq); + + update_min_vruntime(cfs_rq); + update_cfs_shares(cfs_rq); +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void +check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + unsigned long ideal_runtime, delta_exec; + struct sched_entity *se; + s64 delta; + + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { + resched_curr(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. + */ + clear_buddies(cfs_rq, curr); + return; + } + + /* + * Ensure that a task that missed wakeup preemption by a + * narrow margin doesn't have to wait for a full slice. + * This also mitigates buddy induced latencies under load. + */ + if (delta_exec < sysctl_sched_min_granularity) + return; + + se = __pick_first_entity(cfs_rq); + delta = curr->vruntime - se->vruntime; + + if (delta < 0) + return; + + if (delta > ideal_runtime) + resched_curr(rq_of(cfs_rq)); +} + +static void +set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* 'current' is not kept within the tree. */ + if (se->on_rq) { + /* + * Any task has to be enqueued before it get to execute on + * a CPU. So account for the time it spent waiting on the + * runqueue. + */ + 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); + cfs_rq->curr = se; +#ifdef CONFIG_SCHEDSTATS + /* + * Track our maximum slice length, if the CPU's load is at + * least twice that of our own weight (i.e. dont track it + * when there are only lesser-weight tasks around): + */ + if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + se->statistics.slice_max = max(se->statistics.slice_max, + se->sum_exec_runtime - se->prev_sum_exec_runtime); + } +#endif + se->prev_sum_exec_runtime = se->sum_exec_runtime; +} + +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); + +/* + * Pick the next process, keeping these things in mind, in this order: + * 1) keep things fair between processes/task groups + * 2) pick the "next" process, since someone really wants that to run + * 3) pick the "last" process, for cache locality + * 4) do not run the "skip" process, if something else is available + */ +static struct sched_entity * +pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + struct sched_entity *left = __pick_first_entity(cfs_rq); + struct sched_entity *se; + + /* + * If curr is set we have to see if its left of the leftmost entity + * still in the tree, provided there was anything in the tree at all. + */ + if (!left || (curr && entity_before(curr, left))) + left = curr; + + se = left; /* ideally we run the leftmost entity */ + + /* + * Avoid running the skip buddy, if running something else can + * be done without getting too unfair. + */ + if (cfs_rq->skip == se) { + struct sched_entity *second; + + if (se == curr) { + second = __pick_first_entity(cfs_rq); + } else { + second = __pick_next_entity(se); + if (!second || (curr && entity_before(curr, second))) + second = curr; + } + + if (second && wakeup_preempt_entity(second, left) < 1) + se = second; + } + + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) + se = cfs_rq->last; + + /* + * Someone really wants this to run. If it's not unfair, run it. + */ + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + se = cfs_rq->next; + + clear_buddies(cfs_rq, se); + + return se; +} + +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); + +static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) +{ + /* + * If still on the runqueue then deactivate_task() + * was not called and update_curr() has to be done: + */ + if (prev->on_rq) + update_curr(cfs_rq); + + /* throttle cfs_rqs exceeding runtime */ + check_cfs_rq_runtime(cfs_rq); + + check_spread(cfs_rq, prev); + if (prev->on_rq) { + update_stats_wait_start(cfs_rq, prev); + /* Put 'current' back into the tree. */ + __enqueue_entity(cfs_rq, prev); + /* in !on_rq case, update occurred at dequeue */ + update_entity_load_avg(prev, 1); + } + cfs_rq->curr = NULL; +} + +static void +entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) +{ + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + + /* + * Ensure that runnable average is periodically updated. + */ + update_entity_load_avg(curr, 1); + update_cfs_rq_blocked_load(cfs_rq, 1); + update_cfs_shares(cfs_rq); + +#ifdef CONFIG_SCHED_HRTICK + /* + * queued ticks are scheduled to match the slice, so don't bother + * validating it and just reschedule. + */ + if (queued) { + resched_curr(rq_of(cfs_rq)); + return; + } + /* + * don't let the period tick interfere with the hrtick preemption + */ + if (!sched_feat(DOUBLE_TICK) && + hrtimer_active(&rq_of(cfs_rq)->hrtick_timer)) + return; +#endif + + if (cfs_rq->nr_running > 1) + check_preempt_tick(cfs_rq, curr); +} + + +/************************************************** + * CFS bandwidth control machinery + */ + +#ifdef CONFIG_CFS_BANDWIDTH + +#ifdef HAVE_JUMP_LABEL +static struct static_key __cfs_bandwidth_used; + +static inline bool cfs_bandwidth_used(void) +{ + return static_key_false(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_inc(void) +{ + static_key_slow_inc(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_dec(void) +{ + static_key_slow_dec(&__cfs_bandwidth_used); +} +#else /* HAVE_JUMP_LABEL */ +static bool cfs_bandwidth_used(void) +{ + return true; +} + +void cfs_bandwidth_usage_inc(void) {} +void cfs_bandwidth_usage_dec(void) {} +#endif /* HAVE_JUMP_LABEL */ + +/* + * default period for cfs group bandwidth. + * default: 0.1s, units: nanoseconds + */ +static inline u64 default_cfs_period(void) +{ + return 100000000ULL; +} + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +/* + * Replenish runtime according to assigned quota and update expiration time. + * We use sched_clock_cpu directly instead of rq->clock to avoid adding + * additional synchronization around rq->lock. + * + * requires cfs_b->lock + */ +void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) +{ + u64 now; + + if (cfs_b->quota == RUNTIME_INF) + return; + + now = sched_clock_cpu(smp_processor_id()); + cfs_b->runtime = cfs_b->quota; + cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); +} + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return &tg->cfs_bandwidth; +} + +/* rq->task_clock normalized against any time this cfs_rq has spent throttled */ +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) +{ + if (unlikely(cfs_rq->throttle_count)) + return cfs_rq->throttled_clock_task; + + return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; +} + +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct task_group *tg = cfs_rq->tg; + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + u64 amount = 0, min_amount, expires; + + /* note: this is a positive sum as runtime_remaining <= 0 */ + min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota == RUNTIME_INF) + amount = min_amount; + else { + /* + * If the bandwidth pool has become inactive, then at least one + * period must have elapsed since the last consumption. + * Refresh the global state and ensure bandwidth timer becomes + * active. + */ + if (!cfs_b->timer_active) { + __refill_cfs_bandwidth_runtime(cfs_b); + __start_cfs_bandwidth(cfs_b, false); + } + + if (cfs_b->runtime > 0) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + cfs_b->idle = 0; + } + } + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + cfs_rq->runtime_remaining += amount; + /* + * we may have advanced our local expiration to account for allowed + * spread between our sched_clock and the one on which runtime was + * issued. + */ + if ((s64)(expires - cfs_rq->runtime_expires) > 0) + cfs_rq->runtime_expires = expires; + + return cfs_rq->runtime_remaining > 0; +} + +/* + * Note: This depends on the synchronization provided by sched_clock and the + * fact that rq->clock snapshots this value. + */ +static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + + /* if the deadline is ahead of our clock, nothing to do */ + if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) + return; + + if (cfs_rq->runtime_remaining < 0) + return; + + /* + * If the local deadline has passed we have to consider the + * possibility that our sched_clock is 'fast' and the global deadline + * has not truly expired. + * + * Fortunately we can check determine whether this the case by checking + * whether the global deadline has advanced. It is valid to compare + * cfs_b->runtime_expires without any locks since we only care about + * exact equality, so a partial write will still work. + */ + + if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { + /* extend local deadline, drift is bounded above by 2 ticks */ + cfs_rq->runtime_expires += TICK_NSEC; + } else { + /* global deadline is ahead, expiration has passed */ + cfs_rq->runtime_remaining = 0; + } +} + +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +{ + /* dock delta_exec before expiring quota (as it could span periods) */ + cfs_rq->runtime_remaining -= delta_exec; + expire_cfs_rq_runtime(cfs_rq); + + if (likely(cfs_rq->runtime_remaining > 0)) + return; + + /* + * if we're unable to extend our runtime we resched so that the active + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) + resched_curr(rq_of(cfs_rq)); +} + +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +{ + if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) + return; + + __account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttled; +} + +/* check whether cfs_rq, or any parent, is throttled */ +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttle_count; +} + +/* + * Ensure that neither of the group entities corresponding to src_cpu or + * dest_cpu are members of a throttled hierarchy when performing group + * load-balance operations. + */ +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + struct cfs_rq *src_cfs_rq, *dest_cfs_rq; + + src_cfs_rq = tg->cfs_rq[src_cpu]; + dest_cfs_rq = tg->cfs_rq[dest_cpu]; + + return throttled_hierarchy(src_cfs_rq) || + throttled_hierarchy(dest_cfs_rq); +} + +/* updated child weight may affect parent so we have to do this bottom up */ +static int tg_unthrottle_up(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + cfs_rq->throttle_count--; +#ifdef CONFIG_SMP + if (!cfs_rq->throttle_count) { + /* adjust cfs_rq_clock_task() */ + cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - + cfs_rq->throttled_clock_task; + } +#endif + + return 0; +} + +static int tg_throttle_down(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + /* group is entering throttled state, stop time */ + if (!cfs_rq->throttle_count) + cfs_rq->throttled_clock_task = rq_clock_task(rq); + cfs_rq->throttle_count++; + + return 0; +} + +static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + long task_delta, dequeue = 1; + + se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; + + /* freeze hierarchy runnable averages while throttled */ + rcu_read_lock(); + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); + rcu_read_unlock(); + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + /* throttled entity or throttle-on-deactivate */ + if (!se->on_rq) + break; + + if (dequeue) + dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); + qcfs_rq->h_nr_running -= task_delta; + + if (qcfs_rq->load.weight) + dequeue = 0; + } + + if (!se) + sub_nr_running(rq, task_delta); + + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + raw_spin_lock(&cfs_b->lock); + /* + * Add to the _head_ of the list, so that an already-started + * distribute_cfs_runtime will not see us + */ + list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + if (!cfs_b->timer_active) + __start_cfs_bandwidth(cfs_b, false); + raw_spin_unlock(&cfs_b->lock); +} + +void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + int enqueue = 1; + long task_delta; + + se = cfs_rq->tg->se[cpu_of(rq)]; + + cfs_rq->throttled = 0; + + update_rq_clock(rq); + + raw_spin_lock(&cfs_b->lock); + cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock; + list_del_rcu(&cfs_rq->throttled_list); + raw_spin_unlock(&cfs_b->lock); + + /* update hierarchical throttle state */ + walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); + + if (!cfs_rq->load.weight) + return; + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + if (se->on_rq) + enqueue = 0; + + cfs_rq = cfs_rq_of(se); + if (enqueue) + enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); + cfs_rq->h_nr_running += task_delta; + + if (cfs_rq_throttled(cfs_rq)) + break; + } + + if (!se) + add_nr_running(rq, task_delta); + + /* determine whether we need to wake up potentially idle cpu */ + if (rq->curr == rq->idle && rq->cfs.nr_running) + resched_curr(rq); +} + +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, + u64 remaining, u64 expires) +{ + struct cfs_rq *cfs_rq; + u64 runtime; + u64 starting_runtime = remaining; + + rcu_read_lock(); + list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, + throttled_list) { + struct rq *rq = rq_of(cfs_rq); + + raw_spin_lock(&rq->lock); + if (!cfs_rq_throttled(cfs_rq)) + goto next; + + runtime = -cfs_rq->runtime_remaining + 1; + if (runtime > remaining) + runtime = remaining; + remaining -= runtime; + + cfs_rq->runtime_remaining += runtime; + cfs_rq->runtime_expires = expires; + + /* we check whether we're throttled above */ + if (cfs_rq->runtime_remaining > 0) + unthrottle_cfs_rq(cfs_rq); + +next: + raw_spin_unlock(&rq->lock); + + if (!remaining) + break; + } + rcu_read_unlock(); + + return starting_runtime - remaining; +} + +/* + * Responsible for refilling a task_group's bandwidth and unthrottling its + * cfs_rqs as appropriate. If there has been no activity within the last + * period the timer is deactivated until scheduling resumes; cfs_b->idle is + * used to track this state. + */ +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +{ + u64 runtime, runtime_expires; + int throttled; + + /* no need to continue the timer with no bandwidth constraint */ + if (cfs_b->quota == RUNTIME_INF) + goto out_deactivate; + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + cfs_b->nr_periods += overrun; + + /* + * idle depends on !throttled (for the case of a large deficit), and if + * we're going inactive then everything else can be deferred + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; + + /* + * if we have relooped after returning idle once, we need to update our + * status as actually running, so that other cpus doing + * __start_cfs_bandwidth will stop trying to cancel us. + */ + cfs_b->timer_active = 1; + + __refill_cfs_bandwidth_runtime(cfs_b); + + if (!throttled) { + /* mark as potentially idle for the upcoming period */ + cfs_b->idle = 1; + return 0; + } + + /* account preceding periods in which throttling occurred */ + cfs_b->nr_throttled += overrun; + + runtime_expires = cfs_b->runtime_expires; + + /* + * This check is repeated as we are holding onto the new bandwidth while + * we unthrottle. This can potentially race with an unthrottled group + * trying to acquire new bandwidth from the global pool. This can result + * in us over-using our runtime if it is all used during this loop, but + * only by limited amounts in that extreme case. + */ + while (throttled && cfs_b->runtime > 0) { + runtime = cfs_b->runtime; + raw_spin_unlock(&cfs_b->lock); + /* we can't nest cfs_b->lock while distributing bandwidth */ + runtime = distribute_cfs_runtime(cfs_b, runtime, + runtime_expires); + raw_spin_lock(&cfs_b->lock); + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + + cfs_b->runtime -= min(runtime, cfs_b->runtime); + } + + /* + * While we are ensured activity in the period following an + * unthrottle, this also covers the case in which the new bandwidth is + * insufficient to cover the existing bandwidth deficit. (Forcing the + * timer to remain active while there are any throttled entities.) + */ + cfs_b->idle = 0; + + return 0; + +out_deactivate: + cfs_b->timer_active = 0; + return 1; +} + +/* a cfs_rq won't donate quota below this amount */ +static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC; +/* minimum remaining period time to redistribute slack quota */ +static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC; +/* how long we wait to gather additional slack before distributing */ +static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; + +/* + * Are we near the end of the current quota period? + * + * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the + * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of + * migrate_hrtimers, base is never cleared, so we are fine. + */ +static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) +{ + struct hrtimer *refresh_timer = &cfs_b->period_timer; + u64 remaining; + + /* if the call-back is running a quota refresh is already occurring */ + if (hrtimer_callback_running(refresh_timer)) + return 1; + + /* is a quota refresh about to occur? */ + remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); + if (remaining < min_expire) + return 1; + + return 0; +} + +static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) +{ + u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration; + + /* if there's a quota refresh soon don't bother with slack */ + if (runtime_refresh_within(cfs_b, min_left)) + return; + + start_bandwidth_timer(&cfs_b->slack_timer, + ns_to_ktime(cfs_bandwidth_slack_period)); +} + +/* we know any runtime found here is valid as update_curr() precedes return */ +static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime; + + if (slack_runtime <= 0) + return; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF && + cfs_rq->runtime_expires == cfs_b->runtime_expires) { + cfs_b->runtime += slack_runtime; + + /* we are under rq->lock, defer unthrottling using a timer */ + if (cfs_b->runtime > sched_cfs_bandwidth_slice() && + !list_empty(&cfs_b->throttled_cfs_rq)) + start_cfs_slack_bandwidth(cfs_b); + } + raw_spin_unlock(&cfs_b->lock); + + /* even if it's not valid for return we don't want to try again */ + cfs_rq->runtime_remaining -= slack_runtime; +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + if (!cfs_rq->runtime_enabled || cfs_rq->nr_running) + return; + + __return_cfs_rq_runtime(cfs_rq); +} + +/* + * This is done with a timer (instead of inline with bandwidth return) since + * it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs. + */ +static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) +{ + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + u64 expires; + + /* confirm we're still not at a refresh boundary */ + raw_spin_lock(&cfs_b->lock); + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { + raw_spin_unlock(&cfs_b->lock); + return; + } + + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) + runtime = cfs_b->runtime; + + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + if (!runtime) + return; + + runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + + raw_spin_lock(&cfs_b->lock); + if (expires == cfs_b->runtime_expires) + cfs_b->runtime -= min(runtime, cfs_b->runtime); + raw_spin_unlock(&cfs_b->lock); +} + +/* + * When a group wakes up we want to make sure that its quota is not already + * expired/exceeded, otherwise it may be allowed to steal additional ticks of + * runtime as update_curr() throttling can not not trigger until it's on-rq. + */ +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + /* an active group must be handled by the update_curr()->put() path */ + if (!cfs_rq->runtime_enabled || cfs_rq->curr) + return; + + /* ensure the group is not already throttled */ + if (cfs_rq_throttled(cfs_rq)) + return; + + /* update runtime allocation */ + account_cfs_rq_runtime(cfs_rq, 0); + if (cfs_rq->runtime_remaining <= 0) + throttle_cfs_rq(cfs_rq); +} + +/* conditionally throttle active cfs_rq's from put_prev_entity() */ +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return false; + + if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) + return false; + + /* + * it's possible for a throttled entity to be forced into a running + * state (e.g. set_curr_task), in this case we're finished. + */ + if (cfs_rq_throttled(cfs_rq)) + return true; + + throttle_cfs_rq(cfs_rq); + return true; +} + +static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, slack_timer); + do_sched_cfs_slack_timer(cfs_b); + + return HRTIMER_NORESTART; +} + +static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, period_timer); + ktime_t now; + int overrun; + int idle = 0; + + raw_spin_lock(&cfs_b->lock); + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, cfs_b->period); + + if (!overrun) + break; + + idle = do_sched_cfs_period_timer(cfs_b, overrun); + } + raw_spin_unlock(&cfs_b->lock); + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + raw_spin_lock_init(&cfs_b->lock); + cfs_b->runtime = 0; + cfs_b->quota = RUNTIME_INF; + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); + hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->period_timer.function = sched_cfs_period_timer; + hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->slack_timer.function = sched_cfs_slack_timer; +} + +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + cfs_rq->runtime_enabled = 0; + INIT_LIST_HEAD(&cfs_rq->throttled_list); +} + +/* requires cfs_b->lock, may release to reprogram timer */ +void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force) +{ + /* + * The timer may be active because we're trying to set a new bandwidth + * period or because we're racing with the tear-down path + * (timer_active==0 becomes visible before the hrtimer call-back + * terminates). In either case we ensure that it's re-programmed + */ + while (unlikely(hrtimer_active(&cfs_b->period_timer)) && + hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) { + /* bounce the lock to allow do_sched_cfs_period_timer to run */ + raw_spin_unlock(&cfs_b->lock); + cpu_relax(); + raw_spin_lock(&cfs_b->lock); + /* if someone else restarted the timer then we're done */ + if (!force && cfs_b->timer_active) + return; + } + + cfs_b->timer_active = 1; + start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period); +} + +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + /* init_cfs_bandwidth() was not called */ + if (!cfs_b->throttled_cfs_rq.next) + return; + + hrtimer_cancel(&cfs_b->period_timer); + hrtimer_cancel(&cfs_b->slack_timer); +} + +static void __maybe_unused update_runtime_enabled(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + + raw_spin_lock(&cfs_b->lock); + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; + raw_spin_unlock(&cfs_b->lock); + } +} + +static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + if (!cfs_rq->runtime_enabled) + continue; + + /* + * clock_task is not advancing so we just need to make sure + * there's some valid quota amount + */ + cfs_rq->runtime_remaining = 1; + /* + * Offline rq is schedulable till cpu is completely disabled + * in take_cpu_down(), so we prevent new cfs throttling here. + */ + cfs_rq->runtime_enabled = 0; + + if (cfs_rq_throttled(cfs_rq)) + unthrottle_cfs_rq(cfs_rq); + } +} + +#else /* CONFIG_CFS_BANDWIDTH */ +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) +{ + return rq_clock_task(rq_of(cfs_rq)); +} + +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + return 0; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +#endif + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return NULL; +} +static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static inline void update_runtime_enabled(struct rq *rq) {} +static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} + +#endif /* CONFIG_CFS_BANDWIDTH */ + +/************************************************** + * CFS operations on tasks: + */ + +#ifdef CONFIG_SCHED_HRTICK +static void hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + WARN_ON(task_rq(p) != rq); + + if (cfs_rq->nr_running > 1) { + u64 slice = sched_slice(cfs_rq, se); + u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; + s64 delta = slice - ran; + + if (delta < 0) { + if (rq->curr == p) + resched_curr(rq); + return; + } + hrtick_start(rq, delta); + } +} + +/* + * called from enqueue/dequeue and updates the hrtick when the + * current task is from our class and nr_running is low enough + * to matter. + */ +static void hrtick_update(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + + if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class) + return; + + if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) + hrtick_start_fair(rq, curr); +} +#else /* !CONFIG_SCHED_HRTICK */ +static inline void +hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ +} + +static inline void hrtick_update(struct rq *rq) +{ +} +#endif + +/* + * The enqueue_task method is called before nr_running is + * increased. Here we update the fair scheduling stats and + * then put the task into the rbtree: + */ +static void +enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se; + + for_each_sched_entity(se) { + if (se->on_rq) + break; + cfs_rq = cfs_rq_of(se); + enqueue_entity(cfs_rq, se, flags); + + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running increment below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running++; + + flags = ENQUEUE_WAKEUP; + } + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running++; + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_cfs_shares(cfs_rq); + update_entity_load_avg(se, 1); + } + + if (!se) { + update_rq_runnable_avg(rq, rq->nr_running); + add_nr_running(rq, 1); + } + hrtick_update(rq); +} + +static void set_next_buddy(struct sched_entity *se); + +/* + * The dequeue_task method is called before nr_running is + * decreased. We remove the task from the rbtree and + * update the fair scheduling stats: + */ +static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se; + int task_sleep = flags & DEQUEUE_SLEEP; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + dequeue_entity(cfs_rq, se, flags); + + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running decrement below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running--; + + /* Don't dequeue parent if it has other entities besides us */ + if (cfs_rq->load.weight) { + /* + * Bias pick_next to pick a task from this cfs_rq, as + * p is sleeping when it is within its sched_slice. + */ + if (task_sleep && parent_entity(se)) + set_next_buddy(parent_entity(se)); + + /* avoid re-evaluating load for this entity */ + se = parent_entity(se); + break; + } + flags |= DEQUEUE_SLEEP; + } + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running--; + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_cfs_shares(cfs_rq); + update_entity_load_avg(se, 1); + } + + if (!se) { + sub_nr_running(rq, 1); + update_rq_runnable_avg(rq, 1); + } + hrtick_update(rq); +} + +#ifdef CONFIG_SMP +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->cfs.runnable_load_avg; +} + +/* + * Return a low guess at the load of a migration-source cpu weighted + * according to the scheduling class and "nice" value. + * + * We want to under-estimate the load of migration sources, to + * balance conservatively. + */ +static unsigned long source_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return min(rq->cpu_load[type-1], total); +} + +/* + * Return a high guess at the load of a migration-target cpu weighted + * according to the scheduling class and "nice" value. + */ +static unsigned long target_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return max(rq->cpu_load[type-1], total); +} + +static unsigned long capacity_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity; +} + +static unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running); + unsigned long load_avg = rq->cfs.runnable_load_avg; + + if (nr_running) + return load_avg / nr_running; + + return 0; +} + +static void record_wakee(struct task_struct *p) +{ + /* + * Rough decay (wiping) for cost saving, don't worry + * about the boundary, really active task won't care + * about the loss. + */ + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; + current->wakee_flip_decay_ts = jiffies; + } + + if (current->last_wakee != p) { + current->last_wakee = p; + current->wakee_flips++; + } +} + +static void task_waking_fair(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; + +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; + + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; + record_wakee(p); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * effective_load() calculates the load change as seen from the root_task_group + * + * Adding load to a group doesn't make a group heavier, but can cause movement + * of group shares between cpus. Assuming the shares were perfectly aligned one + * can calculate the shift in shares. + * + * Calculate the effective load difference if @wl is added (subtracted) to @tg + * on this @cpu and results in a total addition (subtraction) of @wg to the + * total group weight. + * + * Given a runqueue weight distribution (rw_i) we can compute a shares + * distribution (s_i) using: + * + * s_i = rw_i / \Sum rw_j (1) + * + * Suppose we have 4 CPUs and our @tg is a direct child of the root group and + * has 7 equal weight tasks, distributed as below (rw_i), with the resulting + * shares distribution (s_i): + * + * rw_i = { 2, 4, 1, 0 } + * s_i = { 2/7, 4/7, 1/7, 0 } + * + * As per wake_affine() we're interested in the load of two CPUs (the CPU the + * task used to run on and the CPU the waker is running on), we need to + * compute the effect of waking a task on either CPU and, in case of a sync + * wakeup, compute the effect of the current task going to sleep. + * + * So for a change of @wl to the local @cpu with an overall group weight change + * of @wl we can compute the new shares distribution (s'_i) using: + * + * s'_i = (rw_i + @wl) / (@wg + \Sum rw_j) (2) + * + * Suppose we're interested in CPUs 0 and 1, and want to compute the load + * differences in waking a task to CPU 0. The additional task changes the + * weight and shares distributions like: + * + * rw'_i = { 3, 4, 1, 0 } + * s'_i = { 3/8, 4/8, 1/8, 0 } + * + * We can then compute the difference in effective weight by using: + * + * dw_i = S * (s'_i - s_i) (3) + * + * Where 'S' is the group weight as seen by its parent. + * + * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7) + * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 - + * 4/7) times the weight of the group. + */ +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) +{ + struct sched_entity *se = tg->se[cpu]; + + if (!tg->parent) /* the trivial, non-cgroup case */ + return wl; + + for_each_sched_entity(se) { + long w, W; + + tg = se->my_q->tg; + + /* + * W = @wg + \Sum rw_j + */ + W = wg + calc_tg_weight(tg, se->my_q); + + /* + * w = rw_i + @wl + */ + w = se->my_q->load.weight + wl; + + /* + * wl = S * s'_i; see (2) + */ + if (W > 0 && w < W) + wl = (w * (long)tg->shares) / W; + else + wl = tg->shares; + + /* + * Per the above, wl is the new se->load.weight value; since + * those are clipped to [MIN_SHARES, ...) do so now. See + * calc_cfs_shares(). + */ + if (wl < MIN_SHARES) + wl = MIN_SHARES; + + /* + * wl = dw_i = S * (s'_i - s_i); see (3) + */ + wl -= se->load.weight; + + /* + * Recursively apply this logic to all parent groups to compute + * the final effective load change on the root group. Since + * only the @tg group gets extra weight, all parent groups can + * only redistribute existing shares. @wl is the shift in shares + * resulting from this level per the above. + */ + wg = 0; + } + + return wl; +} +#else + +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) +{ + return wl; +} + +#endif + +static int wake_wide(struct task_struct *p) +{ + int factor = this_cpu_read(sd_llc_size); + + /* + * Yeah, it's the switching-frequency, could means many wakee or + * rapidly switch, use factor here will just help to automatically + * adjust the loose-degree, so bigger node will lead to more pull. + */ + if (p->wakee_flips > factor) { + /* + * wakee is somewhat hot, it needs certain amount of cpu + * resource, so if waker is far more hot, prefer to leave + * it alone. + */ + if (current->wakee_flips > (factor * p->wakee_flips)) + return 1; + } + + return 0; +} + +static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) +{ + s64 this_load, load; + s64 this_eff_load, prev_eff_load; + int idx, this_cpu, prev_cpu; + struct task_group *tg; + unsigned long weight; + int balanced; + + /* + * If we wake multiple tasks be careful to not bounce + * ourselves around too much. + */ + if (wake_wide(p)) + return 0; + + idx = sd->wake_idx; + this_cpu = smp_processor_id(); + prev_cpu = task_cpu(p); + load = source_load(prev_cpu, idx); + this_load = target_load(this_cpu, idx); + + /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) { + tg = task_group(current); + weight = current->se.load.weight; + + this_load += effective_load(tg, this_cpu, -weight, -weight); + load += effective_load(tg, prev_cpu, 0, -weight); + } + + tg = task_group(p); + weight = p->se.load.weight; + + /* + * In low-load situations, where prev_cpu is idle and this_cpu is idle + * due to the sync cause above having dropped this_load to 0, we'll + * always have an imbalance, but there's really nothing you can do + * about that, so that's good too. + * + * Otherwise check if either cpus are near enough in load to allow this + * task to be woken on this_cpu. + */ + this_eff_load = 100; + this_eff_load *= capacity_of(prev_cpu); + + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); + + if (this_load > 0) { + this_eff_load *= this_load + + effective_load(tg, this_cpu, weight, weight); + + prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); + } + + balanced = this_eff_load <= prev_eff_load; + + schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts); + + if (!balanced) + return 0; + + schedstat_inc(sd, ttwu_move_affine); + schedstat_inc(p, se.statistics.nr_wakeups_affine); + + return 1; +} + +/* + * find_idlest_group finds and returns the least busy CPU group within the + * domain. + */ +static struct sched_group * +find_idlest_group(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int sd_flag) +{ + struct sched_group *idlest = NULL, *group = sd->groups; + unsigned long min_load = ULONG_MAX, this_load = 0; + int load_idx = sd->forkexec_idx; + int imbalance = 100 + (sd->imbalance_pct-100)/2; + + if (sd_flag & SD_BALANCE_WAKE) + load_idx = sd->wake_idx; + + do { + unsigned long load, avg_load; + int local_group; + int i; + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_cpus(group), + tsk_cpus_allowed(p))) + continue; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + + /* Tally up the load of all CPUs in the group */ + avg_load = 0; + + for_each_cpu(i, sched_group_cpus(group)) { + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = source_load(i, load_idx); + else + load = target_load(i, load_idx); + + avg_load += load; + } + + /* Adjust by relative CPU capacity of the group */ + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; + + if (local_group) { + this_load = avg_load; + } else if (avg_load < min_load) { + min_load = avg_load; + idlest = group; + } + } while (group = group->next, group != sd->groups); + + if (!idlest || 100*this_load < imbalance*min_load) + return NULL; + return idlest; +} + +/* + * find_idlest_cpu - find the idlest cpu among the cpus in group. + */ +static int +find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +{ + unsigned long load, min_load = ULONG_MAX; + unsigned int min_exit_latency = UINT_MAX; + u64 latest_idle_timestamp = 0; + int least_loaded_cpu = this_cpu; + int shallowest_idle_cpu = -1; + int i; + + /* Traverse only the allowed CPUs */ + for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { + if (idle_cpu(i)) { + struct rq *rq = cpu_rq(i); + struct cpuidle_state *idle = idle_get_state(rq); + if (idle && idle->exit_latency < min_exit_latency) { + /* + * We give priority to a CPU whose idle state + * has the smallest exit latency irrespective + * of any idle timestamp. + */ + min_exit_latency = idle->exit_latency; + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } else if ((!idle || idle->exit_latency == min_exit_latency) && + rq->idle_stamp > latest_idle_timestamp) { + /* + * If equal or no active idle state, then + * the most recently idled CPU might have + * a warmer cache. + */ + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } + } else if (shallowest_idle_cpu == -1) { + load = weighted_cpuload(i); + if (load < min_load || (load == min_load && i == this_cpu)) { + min_load = load; + least_loaded_cpu = i; + } + } + } + + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; +} + +/* + * Try and locate an idle CPU in the sched_domain. + */ +static int select_idle_sibling(struct task_struct *p, int target) +{ + struct sched_domain *sd; + struct sched_group *sg; + int i = task_cpu(p); + + if (idle_cpu(target)) + return target; + + /* + * If the prevous cpu is cache affine and idle, don't be stupid. + */ + if (i != target && cpus_share_cache(i, target) && idle_cpu(i)) + return i; + + /* + * Otherwise, iterate the domains and find an elegible idle cpu. + */ + sd = rcu_dereference(per_cpu(sd_llc, target)); + for_each_lower_domain(sd) { + sg = sd->groups; + do { + if (!cpumask_intersects(sched_group_cpus(sg), + tsk_cpus_allowed(p))) + goto next; + + for_each_cpu(i, sched_group_cpus(sg)) { + if (i == target || !idle_cpu(i)) + goto next; + } + + target = cpumask_first_and(sched_group_cpus(sg), + tsk_cpus_allowed(p)); + goto done; +next: + sg = sg->next; + } while (sg != sd->groups); + } +done: + return target; +} +/* + * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the usage with the capacity of the CPU that is available for CFS + * task (ie cpu_capacity). + * cfs.utilization_load_avg is the sum of running time of runnable tasks on a + * CPU. It represents the amount of utilization of a CPU in the range + * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full + * capacity of the CPU because it's about the running time on this CPU. + * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE + * because of unfortunate rounding in avg_period and running_load_avg or just + * after migrating tasks until the average stabilizes with the new running + * time. So we need to check that the usage stays into the range + * [0..cpu_capacity_orig] and cap if necessary. + * Without capping the usage, a group could be seen as overloaded (CPU0 usage + * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity + */ +static int get_cpu_usage(int cpu) +{ + unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg; + unsigned long capacity = capacity_orig_of(cpu); + + if (usage >= SCHED_LOAD_SCALE) + return capacity; + + return (usage * capacity) >> SCHED_LOAD_SHIFT; +} + +/* + * select_task_rq_fair: Select target runqueue for the waking task in domains + * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, + * SD_BALANCE_FORK, or SD_BALANCE_EXEC. + * + * Balances load by selecting the idlest cpu in the idlest group, or under + * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set. + * + * Returns the target cpu number. + * + * preempt must be disabled. + */ +static int +select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) +{ + struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; + int cpu = smp_processor_id(); + int new_cpu = cpu; + int want_affine = 0; + int sync = wake_flags & WF_SYNC; + + if (sd_flag & SD_BALANCE_WAKE) + want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + + rcu_read_lock(); + for_each_domain(cpu, tmp) { + if (!(tmp->flags & SD_LOAD_BALANCE)) + continue; + + /* + * If both cpu and prev_cpu are part of this domain, + * cpu is a valid SD_WAKE_AFFINE target. + */ + if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && + cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { + affine_sd = tmp; + break; + } + + if (tmp->flags & sd_flag) + sd = tmp; + } + + if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + prev_cpu = cpu; + + if (sd_flag & SD_BALANCE_WAKE) { + new_cpu = select_idle_sibling(p, prev_cpu); + goto unlock; + } + + while (sd) { + struct sched_group *group; + int weight; + + if (!(sd->flags & sd_flag)) { + sd = sd->child; + continue; + } + + group = find_idlest_group(sd, p, cpu, sd_flag); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_cpu(group, p, cpu); + if (new_cpu == -1 || new_cpu == cpu) { + /* Now try balancing at a lower domain level of cpu */ + sd = sd->child; + continue; + } + + /* Now try balancing at a lower domain level of new_cpu */ + cpu = new_cpu; + weight = sd->span_weight; + sd = NULL; + for_each_domain(cpu, tmp) { + if (weight <= tmp->span_weight) + break; + if (tmp->flags & sd_flag) + sd = tmp; + } + /* while loop will break here if sd == NULL */ + } +unlock: + rcu_read_unlock(); + + return new_cpu; +} + +/* + * Called immediately before a task is migrated to a new cpu; task_cpu(p) and + * cfs_rq_of(p) references at time of call are still valid and identify the + * previous cpu. However, the caller only guarantees p->pi_lock is held; no + * other assumptions, including the state of rq->lock, should be made. + */ +static void +migrate_task_rq_fair(struct task_struct *p, int next_cpu) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* + * Load tracking: accumulate removed load so that it can be processed + * when we next update owning cfs_rq under rq->lock. Tasks contribute + * to blocked load iff they have a positive decay-count. It can never + * be negative here since on-rq tasks have decay-count == 0. + */ + if (se->avg.decay_count) { + se->avg.decay_count = -__synchronize_entity_decay(se); + atomic_long_add(se->avg.load_avg_contrib, + &cfs_rq->removed_load); + } + + /* We have migrated, no longer consider this task hot */ + se->exec_start = 0; +} +#endif /* CONFIG_SMP */ + +static unsigned long +wakeup_gran(struct sched_entity *curr, struct sched_entity *se) +{ + unsigned long gran = sysctl_sched_wakeup_granularity; + + /* + * Since its curr running now, convert the gran from real-time + * to virtual-time in his units. + * + * By using 'se' instead of 'curr' we penalize light tasks, so + * they get preempted easier. That is, if 'se' < 'curr' then + * the resulting gran will be larger, therefore penalizing the + * lighter, if otoh 'se' > 'curr' then the resulting gran will + * be smaller, again penalizing the lighter task. + * + * This is especially important for buddies when the leftmost + * task is higher priority than the buddy. + */ + return calc_delta_fair(gran, se); +} + +/* + * Should 'se' preempt 'curr'. + * + * |s1 + * |s2 + * |s3 + * g + * |<--->|c + * + * w(c, s1) = -1 + * w(c, s2) = 0 + * w(c, s3) = 1 + * + */ +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) +{ + s64 gran, vdiff = curr->vruntime - se->vruntime; + + if (vdiff <= 0) + return -1; + + gran = wakeup_gran(curr, se); + if (vdiff > gran) + return 1; + + return 0; +} + +static void set_last_buddy(struct sched_entity *se) +{ + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->last = se; +} + +static void set_next_buddy(struct sched_entity *se) +{ + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->next = se; +} + +static void set_skip_buddy(struct sched_entity *se) +{ + for_each_sched_entity(se) + cfs_rq_of(se)->skip = se; +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + struct task_struct *curr = rq->curr; + struct sched_entity *se = &curr->se, *pse = &p->se; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + int scale = cfs_rq->nr_running >= sched_nr_latency; + int next_buddy_marked = 0; + + if (unlikely(se == pse)) + return; + + /* + * This is possible from callers such as attach_tasks(), in which we + * unconditionally check_prempt_curr() after an enqueue (which may have + * lead to a throttle). This both saves work and prevents false + * next-buddy nomination below. + */ + if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) + return; + + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { + set_next_buddy(pse); + next_buddy_marked = 1; + } + + /* + * We can come here with TIF_NEED_RESCHED already set from new task + * wake up path. + * + * Note: this also catches the edge-case of curr being in a throttled + * group (e.g. via set_curr_task), since update_curr() (in the + * enqueue of curr) will have resulted in resched being set. This + * prevents us from potentially nominating it as a false LAST_BUDDY + * below. + */ + if (test_tsk_need_resched(curr)) + return; + + /* Idle tasks are by definition preempted by non-idle tasks. */ + if (unlikely(curr->policy == SCHED_IDLE) && + likely(p->policy != SCHED_IDLE)) + goto preempt; + + /* + * Batch and idle tasks do not preempt non-idle tasks (their preemption + * is driven by the tick): + */ + if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION)) + return; + + find_matching_se(&se, &pse); + update_curr(cfs_rq_of(se)); + BUG_ON(!pse); + if (wakeup_preempt_entity(se, pse) == 1) { + /* + * Bias pick_next to pick the sched entity that is + * triggering this preemption. + */ + if (!next_buddy_marked) + set_next_buddy(pse); + goto preempt; + } + + return; + +preempt: + resched_curr(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved + * with schedule on the ->pre_schedule() or idle_balance() + * point, either of which can * drop the rq lock. + * + * Also, during early boot the idle thread is in the fair class, + * for obvious reasons its a bad idea to schedule back to it. + */ + if (unlikely(!se->on_rq || curr == rq->idle)) + return; + + if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se)) + set_last_buddy(se); +} + +static struct task_struct * +pick_next_task_fair(struct rq *rq, struct task_struct *prev) +{ + struct cfs_rq *cfs_rq = &rq->cfs; + struct sched_entity *se; + struct task_struct *p; + int new_tasks; + +again: +#ifdef CONFIG_FAIR_GROUP_SCHED + if (!cfs_rq->nr_running) + goto idle; + + if (prev->sched_class != &fair_sched_class) + goto simple; + + /* + * Because of the set_next_buddy() in dequeue_task_fair() it is rather + * likely that a next task is from the same cgroup as the current. + * + * Therefore attempt to avoid putting and setting the entire cgroup + * hierarchy, only change the part that actually changes. + */ + + do { + struct sched_entity *curr = cfs_rq->curr; + + /* + * Since we got here without doing put_prev_entity() we also + * have to consider cfs_rq->curr. If it is still a runnable + * entity, update_curr() will update its vruntime, otherwise + * forget we've ever seen it. + */ + if (curr && curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + /* + * This call to check_cfs_rq_runtime() will do the throttle and + * dequeue its entity in the parent(s). Therefore the 'simple' + * nr_running test will indeed be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + /* + * Since we haven't yet done put_prev_entity and if the selected task + * is a different task than we started out with, try and touch the + * least amount of cfs_rqs. + */ + if (prev != p) { + struct sched_entity *pse = &prev->se; + + while (!(cfs_rq = is_same_group(se, pse))) { + int se_depth = se->depth; + int pse_depth = pse->depth; + + if (se_depth <= pse_depth) { + put_prev_entity(cfs_rq_of(pse), pse); + pse = parent_entity(pse); + } + if (se_depth >= pse_depth) { + set_next_entity(cfs_rq_of(se), se); + se = parent_entity(se); + } + } + + put_prev_entity(cfs_rq, pse); + set_next_entity(cfs_rq, se); + } + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; +simple: + cfs_rq = &rq->cfs; +#endif + + if (!cfs_rq->nr_running) + goto idle; + + put_prev_task(rq, prev); + + do { + se = pick_next_entity(cfs_rq, NULL); + set_next_entity(cfs_rq, se); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; + +idle: + new_tasks = idle_balance(rq); + /* + * Because idle_balance() releases (and re-acquires) rq->lock, it is + * possible for any higher priority task to appear. In that case we + * must re-start the pick_next_entity() loop. + */ + if (new_tasks < 0) + return RETRY_TASK; + + if (new_tasks > 0) + goto again; + + return NULL; +} + +/* + * Account for a descheduled task: + */ +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +{ + struct sched_entity *se = &prev->se; + struct cfs_rq *cfs_rq; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + put_prev_entity(cfs_rq, se); + } +} + +/* + * sched_yield() is very simple + * + * The magic of dealing with the ->skip buddy is in pick_next_entity. + */ +static void yield_task_fair(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *se = &curr->se; + + /* + * Are we the only task in the tree? + */ + if (unlikely(rq->nr_running == 1)) + return; + + clear_buddies(cfs_rq, se); + + if (curr->policy != SCHED_BATCH) { + update_rq_clock(rq); + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); + } + + set_skip_buddy(se); +} + +static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt) +{ + struct sched_entity *se = &p->se; + + /* throttled hierarchies are not runnable */ + if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) + return false; + + /* Tell the scheduler that we'd really like pse to run next. */ + set_next_buddy(se); + + yield_task_fair(rq); + + return true; +} + +#ifdef CONFIG_SMP +/************************************************** + * Fair scheduling class load-balancing methods. + * + * BASICS + * + * The purpose of load-balancing is to achieve the same basic fairness the + * per-cpu scheduler provides, namely provide a proportional amount of compute + * time to each task. This is expressed in the following equation: + * + * W_i,n/P_i == W_j,n/P_j for all i,j (1) + * + * Where W_i,n is the n-th weight average for cpu i. The instantaneous weight + * W_i,0 is defined as: + * + * W_i,0 = \Sum_j w_i,j (2) + * + * Where w_i,j is the weight of the j-th runnable task on cpu i. This weight + * is derived from the nice value as per prio_to_weight[]. + * + * The weight average is an exponential decay average of the instantaneous + * weight: + * + * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) + * + * C_i is the compute capacity of cpu i, typically it is the + * fraction of 'recent' time available for SCHED_OTHER task execution. But it + * can also include other factors [XXX]. + * + * To achieve this balance we define a measure of imbalance which follows + * directly from (1): + * + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) + * + * We them move tasks around to minimize the imbalance. In the continuous + * function space it is obvious this converges, in the discrete case we get + * a few fun cases generally called infeasible weight scenarios. + * + * [XXX expand on: + * - infeasible weights; + * - local vs global optima in the discrete case. ] + * + * + * SCHED DOMAINS + * + * In order to solve the imbalance equation (4), and avoid the obvious O(n^2) + * for all i,j solution, we create a tree of cpus that follows the hardware + * topology where each level pairs two lower groups (or better). This results + * in O(log n) layers. Furthermore we reduce the number of cpus going up the + * tree to only the first of the previous level and we decrease the frequency + * of load-balance at each level inv. proportional to the number of cpus in + * the groups. + * + * This yields: + * + * log_2 n 1 n + * \Sum { --- * --- * 2^i } = O(n) (5) + * i = 0 2^i 2^i + * `- size of each group + * | | `- number of cpus doing load-balance + * | `- freq + * `- sum over all levels + * + * Coupled with a limit on how many tasks we can migrate every balance pass, + * this makes (5) the runtime complexity of the balancer. + * + * An important property here is that each CPU is still (indirectly) connected + * to every other cpu in at most O(log n) steps: + * + * The adjacency matrix of the resulting graph is given by: + * + * log_2 n + * A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6) + * k = 0 + * + * And you'll find that: + * + * A^(log_2 n)_i,j != 0 for all i,j (7) + * + * Showing there's indeed a path between every cpu in at most O(log n) steps. + * The task movement gives a factor of O(m), giving a convergence complexity + * of: + * + * O(nm log n), n := nr_cpus, m := nr_tasks (8) + * + * + * WORK CONSERVING + * + * In order to avoid CPUs going idle while there's still work to do, new idle + * balancing is more aggressive and has the newly idle cpu iterate up the domain + * tree itself instead of relying on other CPUs to bring it work. + * + * This adds some complexity to both (5) and (8) but it reduces the total idle + * time. + * + * [XXX more?] + * + * + * CGROUPS + * + * Cgroups make a horror show out of (2), instead of a simple sum we get: + * + * s_k,i + * W_i,0 = \Sum_j \Prod_k w_k * ----- (9) + * S_k + * + * Where + * + * s_k,i = \Sum_j w_i,j,k and S_k = \Sum_i s_k,i (10) + * + * w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on cpu i. + * + * The big problem is S_k, its a global sum needed to compute a local (W_i) + * property. + * + * [XXX write more on how we solve this.. _after_ merging pjt's patches that + * rewrite all of this once again.] + */ + +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +enum fbq_type { regular, remote, all }; + +#define LBF_ALL_PINNED 0x01 +#define LBF_NEED_BREAK 0x02 +#define LBF_DST_PINNED 0x04 +#define LBF_SOME_PINNED 0x08 + +struct lb_env { + struct sched_domain *sd; + + struct rq *src_rq; + int src_cpu; + + int dst_cpu; + struct rq *dst_rq; + + struct cpumask *dst_grpmask; + int new_dst_cpu; + enum cpu_idle_type idle; + long imbalance; + /* The set of CPUs under consideration for load-balancing */ + struct cpumask *cpus; + + unsigned int flags; + + unsigned int loop; + unsigned int loop_break; + unsigned int loop_max; + + enum fbq_type fbq_type; + struct list_head tasks; +}; + +/* + * Is this task likely cache-hot: + */ +static int task_hot(struct task_struct *p, struct lb_env *env) +{ + s64 delta; + + lockdep_assert_held(&env->src_rq->lock); + + if (p->sched_class != &fair_sched_class) + return 0; + + if (unlikely(p->policy == SCHED_IDLE)) + return 0; + + /* + * Buddy candidates are cache hot: + */ + if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running && + (&p->se == cfs_rq_of(&p->se)->next || + &p->se == cfs_rq_of(&p->se)->last)) + return 1; + + if (sysctl_sched_migration_cost == -1) + return 1; + if (sysctl_sched_migration_cost == 0) + return 0; + + delta = rq_clock_task(env->src_rq) - p->se.exec_start; + + return delta < (s64)sysctl_sched_migration_cost; +} + +#ifdef CONFIG_NUMA_BALANCING +/* Returns true if the destination node has incurred more faults */ +static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || + !(env->sd->flags & SD_NUMA)) { + return false; + } + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is already in the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return false; + + /* Task is moving into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) > group_faults(p, src_nid); + } + + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) > task_faults(p, src_nid); +} + + +static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) + return false; + + if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) + return false; + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is moving within/into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return false; + + /* Task is moving out of the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) < group_faults(p, src_nid); + } + + /* Migrating away from the preferred node is always bad. */ + if (src_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) < task_faults(p, src_nid); +} + +#else +static inline bool migrate_improves_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} + +static inline bool migrate_degrades_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} +#endif + +/* + * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + */ +static +int can_migrate_task(struct task_struct *p, struct lb_env *env) +{ + int tsk_cache_hot = 0; + + lockdep_assert_held(&env->src_rq->lock); + + /* + * We do not migrate tasks that are: + * 1) throttled_lb_pair, or + * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. + */ + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + return 0; + + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { + int cpu; + + schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + + env->flags |= LBF_SOME_PINNED; + + /* + * Remember if this task can be migrated to any other cpu in + * our sched_group. We may want to revisit it if we couldn't + * meet load balance goals by pulling other tasks on src_cpu. + * + * Also avoid computing new_dst_cpu if we have already computed + * one in current iteration. + */ + if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED)) + return 0; + + /* Prevent to re-select dst_cpu via env's cpus */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { + if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) { + env->flags |= LBF_DST_PINNED; + env->new_dst_cpu = cpu; + break; + } + } + + return 0; + } + + /* Record that we found atleast one task that could run on dst_cpu */ + 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) destination numa is preferred + * 2) task is cache cold, or + * 3) too many balance attempts have failed. + */ + tsk_cache_hot = task_hot(p, env); + if (!tsk_cache_hot) + tsk_cache_hot = migrate_degrades_locality(p, env); + + if (migrate_improves_locality(p, env) || !tsk_cache_hot || + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { + if (tsk_cache_hot) { + schedstat_inc(env->sd, lb_hot_gained[env->idle]); + schedstat_inc(p, se.statistics.nr_forced_migrations); + } + return 1; + } + + schedstat_inc(p, se.statistics.nr_failed_migrations_hot); + return 0; +} + +/* + * detach_task() -- detach the task for the migration specified in env + */ +static void detach_task(struct task_struct *p, struct lb_env *env) +{ + lockdep_assert_held(&env->src_rq->lock); + + deactivate_task(env->src_rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; + set_task_cpu(p, env->dst_cpu); +} + +/* + * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as + * part of active balancing operations within "domain". + * + * Returns a task if successful and NULL otherwise. + */ +static struct task_struct *detach_one_task(struct lb_env *env) +{ + struct task_struct *p, *n; + + lockdep_assert_held(&env->src_rq->lock); + + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + if (!can_migrate_task(p, env)) + continue; + + detach_task(p, env); + + /* + * Right now, this is only the second place where + * lb_gained[env->idle] is updated (other is detach_tasks) + * so we can safely collect stats here rather than + * inside detach_tasks(). + */ + schedstat_inc(env->sd, lb_gained[env->idle]); + return p; + } + return NULL; +} + +static const unsigned int sched_nr_migrate_break = 32; + +/* + * detach_tasks() -- tries to detach up to imbalance weighted load from + * busiest_rq, as part of a balancing operation within domain "sd". + * + * Returns number of detached tasks if successful and 0 otherwise. + */ +static int detach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->src_rq->cfs_tasks; + struct task_struct *p; + unsigned long load; + int detached = 0; + + lockdep_assert_held(&env->src_rq->lock); + + if (env->imbalance <= 0) + return 0; + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + + env->loop++; + /* We've more or less seen every task there is, call it quits */ + if (env->loop > env->loop_max) + break; + + /* take a breather every nr_migrate tasks */ + if (env->loop > env->loop_break) { + env->loop_break += sched_nr_migrate_break; + env->flags |= LBF_NEED_BREAK; + break; + } + + if (!can_migrate_task(p, env)) + goto next; + + load = task_h_load(p); + + if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) + goto next; + + if ((load / 2) > env->imbalance) + goto next; + + detach_task(p, env); + list_add(&p->se.group_node, &env->tasks); + + detached++; + env->imbalance -= load; + +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is detached to minimize + * the critical section. + */ + if (env->idle == CPU_NEWLY_IDLE) + break; +#endif + + /* + * We only want to steal up to the prescribed amount of + * weighted load. + */ + if (env->imbalance <= 0) + break; + + continue; +next: + list_move_tail(&p->se.group_node, tasks); + } + + /* + * Right now, this is one of only two places we collect this stat + * so we can safely collect detach_one_task() stats here rather + * than inside detach_one_task(). + */ + schedstat_add(env->sd, lb_gained[env->idle], detached); + + return detached; +} + +/* + * attach_task() -- attach the task detached by detach_task() to its new rq. + */ +static void attach_task(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_held(&rq->lock); + + BUG_ON(task_rq(p) != rq); + p->on_rq = TASK_ON_RQ_QUEUED; + activate_task(rq, p, 0); + check_preempt_curr(rq, p, 0); +} + +/* + * attach_one_task() -- attaches the task returned from detach_one_task() to + * its new rq. + */ +static void attach_one_task(struct rq *rq, struct task_struct *p) +{ + raw_spin_lock(&rq->lock); + attach_task(rq, p); + raw_spin_unlock(&rq->lock); +} + +/* + * attach_tasks() -- attaches all tasks detached by detach_tasks() to their + * new rq. + */ +static void attach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->tasks; + struct task_struct *p; + + raw_spin_lock(&env->dst_rq->lock); + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + list_del_init(&p->se.group_node); + + attach_task(env->dst_rq, p); + } + + raw_spin_unlock(&env->dst_rq->lock); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * update tg->load_weight by folding this cpu's load_avg + */ +static void __update_blocked_averages_cpu(struct task_group *tg, int cpu) +{ + struct sched_entity *se = tg->se[cpu]; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu]; + + /* throttled entities do not contribute to load */ + if (throttled_hierarchy(cfs_rq)) + return; + + update_cfs_rq_blocked_load(cfs_rq, 1); + + if (se) { + update_entity_load_avg(se, 1); + /* + * We pivot on our runnable average having decayed to zero for + * list removal. This generally implies that all our children + * have also been removed (modulo rounding error or bandwidth + * control); however, such cases are rare and we can fix these + * at enqueue. + * + * TODO: fix up out-of-order children on enqueue. + */ + if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running) + list_del_leaf_cfs_rq(cfs_rq); + } else { + struct rq *rq = rq_of(cfs_rq); + update_rq_runnable_avg(rq, rq->nr_running); + } +} + +static void update_blocked_averages(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct cfs_rq *cfs_rq; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); + /* + * Iterates the task_group tree in a bottom up fashion, see + * list_add_leaf_cfs_rq() for details. + */ + for_each_leaf_cfs_rq(rq, cfs_rq) { + /* + * Note: We may want to consider periodically releasing + * rq->lock about these updates so that creating many task + * groups does not result in continually extending hold time. + */ + __update_blocked_averages_cpu(cfs_rq->tg, rq->cpu); + } + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +/* + * Compute the hierarchical load factor for cfs_rq and all its ascendants. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)]; + unsigned long now = jiffies; + unsigned long load; + + if (cfs_rq->last_h_load_update == now) + return; + + cfs_rq->h_load_next = NULL; + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + cfs_rq->h_load_next = se; + if (cfs_rq->last_h_load_update == now) + break; + } + + if (!se) { + cfs_rq->h_load = cfs_rq->runnable_load_avg; + cfs_rq->last_h_load_update = now; + } + + while ((se = cfs_rq->h_load_next) != NULL) { + load = cfs_rq->h_load; + load = div64_ul(load * se->avg.load_avg_contrib, + cfs_rq->runnable_load_avg + 1); + cfs_rq = group_cfs_rq(se); + cfs_rq->h_load = load; + cfs_rq->last_h_load_update = now; + } +} + +static unsigned long task_h_load(struct task_struct *p) +{ + struct cfs_rq *cfs_rq = task_cfs_rq(p); + + update_cfs_rq_h_load(cfs_rq); + return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load, + cfs_rq->runnable_load_avg + 1); +} +#else +static inline void update_blocked_averages(int cpu) +{ +} + +static unsigned long task_h_load(struct task_struct *p) +{ + return p->se.avg.load_avg_contrib; +} +#endif + +/********** Helpers for find_busiest_group ************************/ + +enum group_type { + group_other = 0, + group_imbalanced, + group_overloaded, +}; + +/* + * sg_lb_stats - stats of a sched_group required for load_balancing + */ +struct sg_lb_stats { + unsigned long avg_load; /*Avg load across the CPUs of the group */ + unsigned long group_load; /* Total load over the CPUs of the group */ + unsigned long sum_weighted_load; /* Weighted load of group's tasks */ + unsigned long load_per_task; + unsigned long group_capacity; + unsigned long group_usage; /* Total usage of the group */ + unsigned int sum_nr_running; /* Nr tasks running in the group */ + unsigned int idle_cpus; + unsigned int group_weight; + enum group_type group_type; + int group_no_capacity; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif +}; + +/* + * sd_lb_stats - Structure to store the statistics of a sched_domain + * during load balancing. + */ +struct sd_lb_stats { + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *local; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + + struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ + struct sg_lb_stats local_stat; /* Statistics of the local group */ +}; + +static inline void init_sd_lb_stats(struct sd_lb_stats *sds) +{ + /* + * Skimp on the clearing to avoid duplicate work. We can avoid clearing + * local_stat because update_sg_lb_stats() does a full clear/assignment. + * We must however clear busiest_stat::avg_load because + * update_sd_pick_busiest() reads this before assignment. + */ + *sds = (struct sd_lb_stats){ + .busiest = NULL, + .local = NULL, + .total_load = 0UL, + .total_capacity = 0UL, + .busiest_stat = { + .avg_load = 0UL, + .sum_nr_running = 0, + .group_type = group_other, + }, + }; +} + +/** + * get_sd_load_idx - Obtain the load index for a given sched domain. + * @sd: The sched_domain whose load_idx is to be obtained. + * @idle: The idle status of the CPU for whose sd load_idx is obtained. + * + * Return: The load index. + */ +static inline int get_sd_load_idx(struct sched_domain *sd, + enum cpu_idle_type idle) +{ + int load_idx; + + switch (idle) { + case CPU_NOT_IDLE: + load_idx = sd->busy_idx; + break; + + case CPU_NEWLY_IDLE: + load_idx = sd->newidle_idx; + break; + default: + load_idx = sd->idle_idx; + break; + } + + return load_idx; +} + +static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu) +{ + if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) + return sd->smt_gain / sd->span_weight; + + return SCHED_CAPACITY_SCALE; +} + +unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) +{ + return default_scale_cpu_capacity(sd, cpu); +} + +static unsigned long scale_rt_capacity(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + u64 total, used, age_stamp, avg; + s64 delta; + + /* + * Since we're reading these variables without serialization make sure + * we read them once before doing sanity checks on them. + */ + age_stamp = ACCESS_ONCE(rq->age_stamp); + avg = ACCESS_ONCE(rq->rt_avg); + delta = __rq_clock_broken(rq) - age_stamp; + + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; + + used = div_u64(avg, total); + + if (likely(used < SCHED_CAPACITY_SCALE)) + return SCHED_CAPACITY_SCALE - used; + + return 1; +} + +static void update_cpu_capacity(struct sched_domain *sd, int cpu) +{ + unsigned long capacity = SCHED_CAPACITY_SCALE; + struct sched_group *sdg = sd->groups; + + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_cpu_capacity(sd, cpu); + else + capacity *= default_scale_cpu_capacity(sd, cpu); + + capacity >>= SCHED_CAPACITY_SHIFT; + + cpu_rq(cpu)->cpu_capacity_orig = capacity; + + capacity *= scale_rt_capacity(cpu); + capacity >>= SCHED_CAPACITY_SHIFT; + + if (!capacity) + capacity = 1; + + cpu_rq(cpu)->cpu_capacity = capacity; + sdg->sgc->capacity = capacity; +} + +void update_group_capacity(struct sched_domain *sd, int cpu) +{ + struct sched_domain *child = sd->child; + struct sched_group *group, *sdg = sd->groups; + unsigned long capacity; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgc->next_update = jiffies + interval; + + if (!child) { + update_cpu_capacity(sd, cpu); + return; + } + + capacity = 0; + + if (child->flags & SD_OVERLAP) { + /* + * SD_OVERLAP domains cannot assume that child groups + * span the current group. + */ + + for_each_cpu(cpu, sched_group_cpus(sdg)) { + struct sched_group_capacity *sgc; + struct rq *rq = cpu_rq(cpu); + + /* + * build_sched_domains() -> init_sched_groups_capacity() + * gets here before we've attached the domains to the + * runqueues. + * + * Use capacity_of(), which is set irrespective of domains + * in update_cpu_capacity(). + * + * This avoids capacity from being 0 and + * causing divide-by-zero issues on boot. + */ + if (unlikely(!rq->sd)) { + capacity += capacity_of(cpu); + continue; + } + + sgc = rq->sd->groups->sgc; + capacity += sgc->capacity; + } + } else { + /* + * !SD_OVERLAP domains can assume that child groups + * span the current group. + */ + + group = child->groups; + do { + capacity += group->sgc->capacity; + group = group->next; + } while (group != child->groups); + } + + sdg->sgc->capacity = capacity; +} + +/* + * Check whether the capacity of the rq has been noticeably reduced by side + * activity. The imbalance_pct is used for the threshold. + * Return true is the capacity is reduced + */ +static inline int +check_cpu_capacity(struct rq *rq, struct sched_domain *sd) +{ + return ((rq->cpu_capacity * sd->imbalance_pct) < + (rq->cpu_capacity_orig * 100)); +} + +/* + * Group imbalance indicates (and tries to solve) the problem where balancing + * groups is inadequate due to tsk_cpus_allowed() constraints. + * + * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a + * cpumask covering 1 cpu of the first group and 3 cpus of the second group. + * Something like: + * + * { 0 1 2 3 } { 4 5 6 7 } + * * * * * + * + * If we were to balance group-wise we'd place two tasks in the first group and + * two tasks in the second group. Clearly this is undesired as it will overload + * cpu 3 and leave one of the cpus in the second group unused. + * + * The current solution to this issue is detecting the skew in the first group + * by noticing the lower domain failed to reach balance and had difficulty + * moving tasks due to affinity constraints. + * + * When this is so detected; this group becomes a candidate for busiest; see + * update_sd_pick_busiest(). And calculate_imbalance() and + * find_busiest_group() avoid some of the usual balance conditions to allow it + * to create an effective group imbalance. + * + * This is a somewhat tricky proposition since the next run might not find the + * group imbalance and decide the groups need to be balanced again. A most + * subtle and fragile situation. + */ + +static inline int sg_imbalanced(struct sched_group *group) +{ + return group->sgc->imbalance; +} + +/* + * group_has_capacity returns true if the group has spare capacity that could + * be used by some tasks. + * We consider that a group has spare capacity if the * number of task is + * smaller than the number of CPUs or if the usage is lower than the available + * capacity for CFS tasks. + * For the latter, we use a threshold to stabilize the state, to take into + * account the variance of the tasks' load and to return true if the available + * capacity in meaningful for the load balancer. + * As an example, an available capacity of 1% can appear but it doesn't make + * any benefit for the load balance. + */ +static inline bool +group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running < sgs->group_weight) + return true; + + if ((sgs->group_capacity * 100) > + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} + +/* + * group_is_overloaded returns true if the group has more tasks than it can + * handle. + * group_is_overloaded is not equals to !group_has_capacity because a group + * with the exact right number of tasks, has no more spare capacity but is not + * overloaded so both group_has_capacity and group_is_overloaded return + * false. + */ +static inline bool +group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false; + + if ((sgs->group_capacity * 100) < + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} + +static enum group_type group_classify(struct lb_env *env, + struct sched_group *group, + struct sg_lb_stats *sgs) +{ + if (sgs->group_no_capacity) + return group_overloaded; + + if (sg_imbalanced(group)) + return group_imbalanced; + + return group_other; +} + +/** + * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @env: The load balancing environment. + * @group: sched_group whose statistics are to be updated. + * @load_idx: Load index of sched_domain of this_cpu for load calc. + * @local_group: Does group contain this_cpu. + * @sgs: variable to hold the statistics for this group. + * @overload: Indicate more than one runnable task for any CPU. + */ +static inline void update_sg_lb_stats(struct lb_env *env, + struct sched_group *group, int load_idx, + int local_group, struct sg_lb_stats *sgs, + bool *overload) +{ + unsigned long load; + int i; + + memset(sgs, 0, sizeof(*sgs)); + + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + struct rq *rq = cpu_rq(i); + + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = target_load(i, load_idx); + else + load = source_load(i, load_idx); + + sgs->group_load += load; + sgs->group_usage += get_cpu_usage(i); + sgs->sum_nr_running += rq->cfs.h_nr_running; + + if (rq->nr_running > 1) + *overload = true; + +#ifdef CONFIG_NUMA_BALANCING + sgs->nr_numa_running += rq->nr_numa_running; + sgs->nr_preferred_running += rq->nr_preferred_running; +#endif + sgs->sum_weighted_load += weighted_cpuload(i); + if (idle_cpu(i)) + sgs->idle_cpus++; + } + + /* Adjust by relative CPU capacity of the group */ + sgs->group_capacity = group->sgc->capacity; + sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; + + if (sgs->sum_nr_running) + sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + + sgs->group_weight = group->group_weight; + + sgs->group_no_capacity = group_is_overloaded(env, sgs); + sgs->group_type = group_classify(env, group, sgs); +} + +/** + * update_sd_pick_busiest - return 1 on busiest group + * @env: The load balancing environment. + * @sds: sched_domain statistics + * @sg: sched_group candidate to be checked for being the busiest + * @sgs: sched_group statistics + * + * Determine if @sg is a busier group than the previously selected + * busiest group. + * + * Return: %true if @sg is a busier group than the previously selected + * busiest group. %false otherwise. + */ +static bool update_sd_pick_busiest(struct lb_env *env, + struct sd_lb_stats *sds, + struct sched_group *sg, + struct sg_lb_stats *sgs) +{ + struct sg_lb_stats *busiest = &sds->busiest_stat; + + if (sgs->group_type > busiest->group_type) + return true; + + if (sgs->group_type < busiest->group_type) + return false; + + if (sgs->avg_load <= busiest->avg_load) + return false; + + /* This is the busiest node in its class. */ + if (!(env->sd->flags & SD_ASYM_PACKING)) + return true; + + /* + * ASYM_PACKING needs to move all the work to the lowest + * numbered CPUs in the group, therefore mark all groups + * higher than ourself as busy. + */ + if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) { + if (!sds->busiest) + return true; + + if (group_first_cpu(sds->busiest) > group_first_cpu(sg)) + return true; + } + + return false; +} + +#ifdef CONFIG_NUMA_BALANCING +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running > sgs->nr_numa_running) + return regular; + if (sgs->sum_nr_running > sgs->nr_preferred_running) + return remote; + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + if (rq->nr_running > rq->nr_numa_running) + return regular; + if (rq->nr_running > rq->nr_preferred_running) + return remote; + return all; +} +#else +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + return regular; +} +#endif /* CONFIG_NUMA_BALANCING */ + +/** + * update_sd_lb_stats - Update sched_domain's statistics for load balancing. + * @env: The load balancing environment. + * @sds: variable to hold the statistics for this sched_domain. + */ +static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) +{ + struct sched_domain *child = env->sd->child; + struct sched_group *sg = env->sd->groups; + struct sg_lb_stats tmp_sgs; + int load_idx, prefer_sibling = 0; + bool overload = false; + + if (child && child->flags & SD_PREFER_SIBLING) + prefer_sibling = 1; + + load_idx = get_sd_load_idx(env->sd, env->idle); + + do { + struct sg_lb_stats *sgs = &tmp_sgs; + int local_group; + + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); + if (local_group) { + sds->local = sg; + sgs = &sds->local_stat; + + if (env->idle != CPU_NEWLY_IDLE || + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); + } + + update_sg_lb_stats(env, sg, load_idx, local_group, sgs, + &overload); + + if (local_group) + goto next_group; + + /* + * In case the child domain prefers tasks go to siblings + * first, lower the sg capacity so that we'll try + * and move all the excess tasks away. We lower the capacity + * of a group only if the local group has the capacity to fit + * these excess tasks. The extra check prevents the case where + * you always pull from the heaviest group when it is already + * under-utilized (possible with a large weight task outweighs + * the tasks on the system). + */ + if (prefer_sibling && sds->local && + group_has_capacity(env, &sds->local_stat) && + (sgs->sum_nr_running > 1)) { + sgs->group_no_capacity = 1; + sgs->group_type = group_overloaded; + } + + if (update_sd_pick_busiest(env, sds, sg, sgs)) { + sds->busiest = sg; + sds->busiest_stat = *sgs; + } + +next_group: + /* Now, start updating sd_lb_stats */ + sds->total_load += sgs->group_load; + sds->total_capacity += sgs->group_capacity; + + sg = sg->next; + } while (sg != env->sd->groups); + + if (env->sd->flags & SD_NUMA) + env->fbq_type = fbq_classify_group(&sds->busiest_stat); + + if (!env->sd->parent) { + /* update overload indicator if we are at root domain */ + if (env->dst_rq->rd->overload != overload) + env->dst_rq->rd->overload = overload; + } + +} + +/** + * check_asym_packing - Check to see if the group is packed into the + * sched doman. + * + * This is primarily intended to used at the sibling level. Some + * cores like POWER7 prefer to use lower numbered SMT threads. In the + * case of POWER7, it can move to lower SMT modes only when higher + * threads are idle. When in lower SMT modes, the threads will + * perform better since they share less core resources. Hence when we + * have idle threads, we want them to be the higher ones. + * + * This packing function is run on idle threads. It checks to see if + * the busiest CPU in this domain (core in the P7 case) has a higher + * CPU number than the packing function is being run on. Here we are + * assuming lower CPU number will be equivalent to lower a SMT thread + * number. + * + * Return: 1 when packing is required and a task should be moved to + * this CPU. The amount of the imbalance is returned in *imbalance. + * + * @env: The load balancing environment. + * @sds: Statistics of the sched_domain which is to be packed + */ +static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) +{ + int busiest_cpu; + + if (!(env->sd->flags & SD_ASYM_PACKING)) + return 0; + + if (!sds->busiest) + return 0; + + busiest_cpu = group_first_cpu(sds->busiest); + if (env->dst_cpu > busiest_cpu) + return 0; + + env->imbalance = DIV_ROUND_CLOSEST( + sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, + SCHED_CAPACITY_SCALE); + + return 1; +} + +/** + * fix_small_imbalance - Calculate the minor imbalance that exists + * amongst the groups of a sched_domain, during + * load balancing. + * @env: The load balancing environment. + * @sds: Statistics of the sched_domain whose imbalance is to be calculated. + */ +static inline +void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) +{ + unsigned long tmp, capa_now = 0, capa_move = 0; + unsigned int imbn = 2; + unsigned long scaled_busy_load_per_task; + struct sg_lb_stats *local, *busiest; + + local = &sds->local_stat; + busiest = &sds->busiest_stat; + + if (!local->sum_nr_running) + local->load_per_task = cpu_avg_load_per_task(env->dst_cpu); + else if (busiest->load_per_task > local->load_per_task) + imbn = 1; + + scaled_busy_load_per_task = + (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + busiest->group_capacity; + + if (busiest->avg_load + scaled_busy_load_per_task >= + local->avg_load + (scaled_busy_load_per_task * imbn)) { + env->imbalance = busiest->load_per_task; + return; + } + + /* + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU capacity used by + * moving them. + */ + + capa_now += busiest->group_capacity * + min(busiest->load_per_task, busiest->avg_load); + capa_now += local->group_capacity * + min(local->load_per_task, local->avg_load); + capa_now /= SCHED_CAPACITY_SCALE; + + /* Amount of load we'd subtract */ + if (busiest->avg_load > scaled_busy_load_per_task) { + capa_move += busiest->group_capacity * + min(busiest->load_per_task, + busiest->avg_load - scaled_busy_load_per_task); + } + + /* Amount of load we'd add */ + if (busiest->avg_load * busiest->group_capacity < + busiest->load_per_task * SCHED_CAPACITY_SCALE) { + tmp = (busiest->avg_load * busiest->group_capacity) / + local->group_capacity; + } else { + tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + local->group_capacity; + } + capa_move += local->group_capacity * + min(local->load_per_task, local->avg_load + tmp); + capa_move /= SCHED_CAPACITY_SCALE; + + /* Move if we gain throughput */ + if (capa_move > capa_now) + env->imbalance = busiest->load_per_task; +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @env: load balance environment + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + */ +static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds) +{ + unsigned long max_pull, load_above_capacity = ~0UL; + struct sg_lb_stats *local, *busiest; + + local = &sds->local_stat; + busiest = &sds->busiest_stat; + + if (busiest->group_type == group_imbalanced) { + /* + * In the group_imb case we cannot rely on group-wide averages + * to ensure cpu-load equilibrium, look at wider averages. XXX + */ + busiest->load_per_task = + min(busiest->load_per_task, sds->avg_load); + } + + /* + * In the presence of smp nice balancing, certain scenarios can have + * max load less than avg load(as we skip the groups at or below + * its cpu_capacity, while calculating max_load..) + */ + if (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load) { + env->imbalance = 0; + return fix_small_imbalance(env, sds); + } + + /* + * If there aren't any idle cpus, avoid creating some. + */ + if (busiest->group_type == group_overloaded && + local->group_type == group_overloaded) { + load_above_capacity = busiest->sum_nr_running * + SCHED_LOAD_SCALE; + if (load_above_capacity > busiest->group_capacity) + load_above_capacity -= busiest->group_capacity; + else + load_above_capacity = ~0UL; + } + + /* + * We're trying to get all the cpus to the average_load, so we don't + * want to push ourselves above the average load, nor do we wish to + * reduce the max loaded cpu below the average load. At the same time, + * we also don't want to reduce the group load below the group capacity + * (so that we can implement power-savings policies etc). Thus we look + * for the minimum possible imbalance. + */ + max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity); + + /* How much load to actually move to equalise the imbalance */ + env->imbalance = min( + max_pull * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; + + /* + * if *imbalance is less than the average load per runnable task + * there is no guarantee that any tasks will be moved so we'll have + * a think about bumping its value to force at least one task to be + * moved + */ + if (env->imbalance < busiest->load_per_task) + return fix_small_imbalance(env, sds); +} + +/******* find_busiest_group() helpers end here *********************/ + +/** + * find_busiest_group - Returns the busiest group within the sched_domain + * if there is an imbalance. If there isn't an imbalance, and + * the user has opted for power-savings, it returns a group whose + * CPUs can be put to idle by rebalancing those tasks elsewhere, if + * such a group exists. + * + * Also calculates the amount of weighted load which should be moved + * to restore balance. + * + * @env: The load balancing environment. + * + * Return: - The busiest group if imbalance exists. + * - If no imbalance and user has opted for power-savings balance, + * return the least loaded group whose CPUs can be + * put to idle by rebalancing its tasks onto our group. + */ +static struct sched_group *find_busiest_group(struct lb_env *env) +{ + struct sg_lb_stats *local, *busiest; + struct sd_lb_stats sds; + + init_sd_lb_stats(&sds); + + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(env, &sds); + local = &sds.local_stat; + busiest = &sds.busiest_stat; + + /* ASYM feature bypasses nice load balance check */ + if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && + check_asym_packing(env, &sds)) + return sds.busiest; + + /* There is no busy sibling group to pull tasks from */ + if (!sds.busiest || busiest->sum_nr_running == 0) + goto out_balanced; + + sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load) + / sds.total_capacity; + + /* + * If the busiest group is imbalanced the below checks don't + * work because they assume all things are equal, which typically + * isn't true due to cpus_allowed constraints and the like. + */ + if (busiest->group_type == group_imbalanced) + goto force_balance; + + /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ + if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) && + busiest->group_no_capacity) + goto force_balance; + + /* + * If the local group is busier than the selected busiest group + * don't try and pull any tasks. + */ + if (local->avg_load >= busiest->avg_load) + goto out_balanced; + + /* + * Don't pull any tasks if this group is already above the domain + * average load. + */ + if (local->avg_load >= sds.avg_load) + goto out_balanced; + + if (env->idle == CPU_IDLE) { + /* + * This cpu is idle. If the busiest group is not overloaded + * and there is no imbalance between this and busiest group + * wrt idle cpus, it is balanced. The imbalance becomes + * significant if the diff is greater than 1 otherwise we + * might end up to just move the imbalance on another group + */ + if ((busiest->group_type != group_overloaded) && + (local->idle_cpus <= (busiest->idle_cpus + 1))) + goto out_balanced; + } else { + /* + * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use + * imbalance_pct to be conservative. + */ + if (100 * busiest->avg_load <= + env->sd->imbalance_pct * local->avg_load) + goto out_balanced; + } + +force_balance: + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(env, &sds); + return sds.busiest; + +out_balanced: + env->imbalance = 0; + return NULL; +} + +/* + * find_busiest_queue - find the busiest runqueue among the cpus in group. + */ +static struct rq *find_busiest_queue(struct lb_env *env, + struct sched_group *group) +{ + struct rq *busiest = NULL, *rq; + unsigned long busiest_load = 0, busiest_capacity = 1; + int i; + + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { + unsigned long capacity, wl; + enum fbq_type rt; + + rq = cpu_rq(i); + rt = fbq_classify_rq(rq); + + /* + * We classify groups/runqueues into three groups: + * - regular: there are !numa tasks + * - remote: there are numa tasks that run on the 'wrong' node + * - all: there is no distinction + * + * In order to avoid migrating ideally placed numa tasks, + * ignore those when there's better options. + * + * If we ignore the actual busiest queue to migrate another + * task, the next balance pass can still reduce the busiest + * queue by moving tasks around inside the node. + * + * If we cannot move enough load due to this classification + * the next pass will adjust the group classification and + * allow migration of more tasks. + * + * Both cases only affect the total convergence complexity. + */ + if (rt > env->fbq_type) + continue; + + capacity = capacity_of(i); + + wl = weighted_cpuload(i); + + /* + * When comparing with imbalance, use weighted_cpuload() + * which is not scaled with the cpu capacity. + */ + + if (rq->nr_running == 1 && wl > env->imbalance && + !check_cpu_capacity(rq, env->sd)) + continue; + + /* + * For the load comparisons with the other cpu's, consider + * the weighted_cpuload() scaled with the cpu capacity, so + * that the load can be moved away from the cpu that is + * potentially running at a lower capacity. + * + * Thus we're looking for max(wl_i / capacity_i), crosswise + * multiplication to rid ourselves of the division works out + * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * our previous maximum. + */ + if (wl * busiest_capacity > busiest_load * capacity) { + busiest_load = wl; + busiest_capacity = capacity; + busiest = rq; + } + } + + return busiest; +} + +/* + * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but + * so long as it is large enough. + */ +#define MAX_PINNED_INTERVAL 512 + +/* Working cpumask for load_balance and load_balance_newidle. */ +DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); + +static int need_active_balance(struct lb_env *env) +{ + struct sched_domain *sd = env->sd; + + if (env->idle == CPU_NEWLY_IDLE) { + + /* + * ASYM_PACKING needs to force migrate tasks from busy but + * higher numbered CPUs in order to pack all tasks in the + * lowest numbered CPUs. + */ + if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) + return 1; + } + + /* + * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. + * It's worth migrating the task if the src_cpu's capacity is reduced + * because of other sched_class or IRQs if more capacity stays + * available on dst_cpu. + */ + if ((env->idle != CPU_NOT_IDLE) && + (env->src_rq->cfs.h_nr_running == 1)) { + if ((check_cpu_capacity(env->src_rq, sd)) && + (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) + return 1; + } + + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); +} + +static int active_load_balance_cpu_stop(void *data); + +static int should_we_balance(struct lb_env *env) +{ + struct sched_group *sg = env->sd->groups; + struct cpumask *sg_cpus, *sg_mask; + int cpu, balance_cpu = -1; + + /* + * In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (env->idle == CPU_NEWLY_IDLE) + return 1; + + sg_cpus = sched_group_cpus(sg); + sg_mask = sched_group_mask(sg); + /* Try to find first idle cpu */ + for_each_cpu_and(cpu, sg_cpus, env->cpus) { + if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu)) + continue; + + balance_cpu = cpu; + break; + } + + if (balance_cpu == -1) + balance_cpu = group_balance_cpu(sg); + + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above domains. + */ + return balance_cpu == env->dst_cpu; +} + +/* + * Check this_cpu to ensure it is balanced within domain. Attempt to move + * tasks if there is an imbalance. + */ +static int load_balance(int this_cpu, struct rq *this_rq, + struct sched_domain *sd, enum cpu_idle_type idle, + int *continue_balancing) +{ + int ld_moved, cur_ld_moved, active_balance = 0; + struct sched_domain *sd_parent = sd->parent; + struct sched_group *group; + struct rq *busiest; + unsigned long flags; + struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask); + + struct lb_env env = { + .sd = sd, + .dst_cpu = this_cpu, + .dst_rq = this_rq, + .dst_grpmask = sched_group_cpus(sd->groups), + .idle = idle, + .loop_break = sched_nr_migrate_break, + .cpus = cpus, + .fbq_type = all, + .tasks = LIST_HEAD_INIT(env.tasks), + }; + + /* + * For NEWLY_IDLE load_balancing, we don't need to consider + * other cpus in our group + */ + if (idle == CPU_NEWLY_IDLE) + env.dst_grpmask = NULL; + + cpumask_copy(cpus, cpu_active_mask); + + schedstat_inc(sd, lb_count[idle]); + +redo: + if (!should_we_balance(&env)) { + *continue_balancing = 0; + goto out_balanced; + } + + group = find_busiest_group(&env); + if (!group) { + schedstat_inc(sd, lb_nobusyg[idle]); + goto out_balanced; + } + + busiest = find_busiest_queue(&env, group); + if (!busiest) { + schedstat_inc(sd, lb_nobusyq[idle]); + goto out_balanced; + } + + BUG_ON(busiest == env.dst_rq); + + schedstat_add(sd, lb_imbalance[idle], env.imbalance); + + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + + ld_moved = 0; + if (busiest->nr_running > 1) { + /* + * Attempt to move tasks. If find_busiest_group has found + * an imbalance but busiest->nr_running <= 1, the group is + * still unbalanced. ld_moved simply stays zero, so it is + * correctly treated as an imbalance. + */ + env.flags |= LBF_ALL_PINNED; + env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); + +more_balance: + raw_spin_lock_irqsave(&busiest->lock, flags); + + /* + * cur_ld_moved - load moved in current iteration + * ld_moved - cumulative load moved across iterations + */ + cur_ld_moved = detach_tasks(&env); + + /* + * We've detached some tasks from busiest_rq. Every + * task is masked "TASK_ON_RQ_MIGRATING", so we can safely + * unlock busiest->lock, and we are able to be sure + * that nobody can manipulate the tasks in parallel. + * See task_rq_lock() family for the details. + */ + + raw_spin_unlock(&busiest->lock); + + if (cur_ld_moved) { + attach_tasks(&env); + ld_moved += cur_ld_moved; + } + + local_irq_restore(flags); + + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + + /* + * Revisit (affine) tasks on src_cpu that couldn't be moved to + * us and move them to an alternate dst_cpu in our sched_group + * where they can run. The upper limit on how many times we + * iterate on same src_cpu is dependent on number of cpus in our + * sched_group. + * + * This changes load balance semantics a bit on who can move + * load to a given_cpu. In addition to the given_cpu itself + * (or a ilb_cpu acting on its behalf where given_cpu is + * nohz-idle), we now have balance_cpu in a position to move + * load to given_cpu. In rare situations, this may cause + * conflicts (balance_cpu and given_cpu/ilb_cpu deciding + * _independently_ and at _same_ time to move some load to + * given_cpu) causing exceess load to be moved to given_cpu. + * This however should not happen so much in practice and + * moreover subsequent load balance cycles should correct the + * excess load moved. + */ + if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) { + + /* Prevent to re-select dst_cpu via env's cpus */ + cpumask_clear_cpu(env.dst_cpu, env.cpus); + + env.dst_rq = cpu_rq(env.new_dst_cpu); + env.dst_cpu = env.new_dst_cpu; + env.flags &= ~LBF_DST_PINNED; + env.loop = 0; + env.loop_break = sched_nr_migrate_break; + + /* + * Go back to "more_balance" rather than "redo" since we + * need to continue with same src_cpu. + */ + goto more_balance; + } + + /* + * We failed to reach balance because of affinity. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) + *group_imbalance = 1; + } + + /* All tasks on this runqueue were pinned by CPU affinity */ + if (unlikely(env.flags & LBF_ALL_PINNED)) { + cpumask_clear_cpu(cpu_of(busiest), cpus); + if (!cpumask_empty(cpus)) { + env.loop = 0; + env.loop_break = sched_nr_migrate_break; + goto redo; + } + goto out_all_pinned; + } + } + + if (!ld_moved) { + schedstat_inc(sd, lb_failed[idle]); + /* + * Increment the failure counter only on periodic balance. + * We do not want newidle balance, which can be very + * frequent, pollute the failure counter causing + * excessive cache_hot migrations and active balances. + */ + if (idle != CPU_NEWLY_IDLE) + sd->nr_balance_failed++; + + if (need_active_balance(&env)) { + raw_spin_lock_irqsave(&busiest->lock, flags); + + /* don't kick the active_load_balance_cpu_stop, + * if the curr task on busiest cpu can't be + * moved to this_cpu + */ + if (!cpumask_test_cpu(this_cpu, + tsk_cpus_allowed(busiest->curr))) { + raw_spin_unlock_irqrestore(&busiest->lock, + flags); + env.flags |= LBF_ALL_PINNED; + goto out_one_pinned; + } + + /* + * ->active_balance synchronizes accesses to + * ->active_balance_work. Once set, it's cleared + * only after active load balance is finished. + */ + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + raw_spin_unlock_irqrestore(&busiest->lock, flags); + + if (active_balance) { + stop_one_cpu_nowait(cpu_of(busiest), + active_load_balance_cpu_stop, busiest, + &busiest->active_balance_work); + } + + /* + * We've kicked active balancing, reset the failure + * counter. + */ + sd->nr_balance_failed = sd->cache_nice_tries+1; + } + } else + sd->nr_balance_failed = 0; + + if (likely(!active_balance)) { + /* We were unbalanced, so reset the balancing interval */ + sd->balance_interval = sd->min_interval; + } else { + /* + * If we've begun active balancing, start to back off. This + * case may not be covered by the all_pinned logic if there + * is only 1 task on the busy runqueue (because we don't call + * detach_tasks). + */ + if (sd->balance_interval < sd->max_interval) + sd->balance_interval *= 2; + } + + goto out; + +out_balanced: + /* + * We reach balance although we may have faced some affinity + * constraints. Clear the imbalance flag if it was set. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if (*group_imbalance) + *group_imbalance = 0; + } + +out_all_pinned: + /* + * We reach balance because all tasks are pinned at this level so + * we can't migrate them. Let the imbalance flag set so parent level + * can try to migrate them. + */ + schedstat_inc(sd, lb_balanced[idle]); + + sd->nr_balance_failed = 0; + +out_one_pinned: + /* tune up the balancing interval */ + if (((env.flags & LBF_ALL_PINNED) && + sd->balance_interval < MAX_PINNED_INTERVAL) || + (sd->balance_interval < sd->max_interval)) + sd->balance_interval *= 2; + + ld_moved = 0; +out: + return ld_moved; +} + +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + + return interval; +} + +static inline void +update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +{ + unsigned long interval, next; + + interval = get_sd_balance_interval(sd, cpu_busy); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + +/* + * idle_balance is called by schedule() if this_cpu is about to become + * idle. Attempts to pull tasks from other CPUs. + */ +static int idle_balance(struct rq *this_rq) +{ + unsigned long next_balance = jiffies + HZ; + int this_cpu = this_rq->cpu; + struct sched_domain *sd; + int pulled_task = 0; + u64 curr_cost = 0; + + idle_enter_fair(this_rq); + + /* + * We must set idle_stamp _before_ calling idle_balance(), such that we + * measure the duration of idle_balance() as idle time. + */ + this_rq->idle_stamp = rq_clock(this_rq); + + if (this_rq->avg_idle < sysctl_sched_migration_cost || + !this_rq->rd->overload) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (sd) + update_next_balance(sd, 0, &next_balance); + rcu_read_unlock(); + + goto out; + } + + /* + * Drop the rq->lock, but keep IRQ/preempt disabled. + */ + raw_spin_unlock(&this_rq->lock); + + update_blocked_averages(this_cpu); + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + int continue_balancing = 1; + u64 t0, domain_cost; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { + update_next_balance(sd, 0, &next_balance); + break; + } + + if (sd->flags & SD_BALANCE_NEWIDLE) { + t0 = sched_clock_cpu(this_cpu); + + pulled_task = load_balance(this_cpu, this_rq, + sd, CPU_NEWLY_IDLE, + &continue_balancing); + + domain_cost = sched_clock_cpu(this_cpu) - t0; + if (domain_cost > sd->max_newidle_lb_cost) + sd->max_newidle_lb_cost = domain_cost; + + curr_cost += domain_cost; + } + + update_next_balance(sd, 0, &next_balance); + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0) + break; + } + rcu_read_unlock(); + + raw_spin_lock(&this_rq->lock); + + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + + /* + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. + */ + if (this_rq->cfs.h_nr_running && !pulled_task) + pulled_task = 1; + +out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) + this_rq->next_balance = next_balance; + + /* Is there a task of a high priority class? */ + if (this_rq->nr_running != this_rq->cfs.h_nr_running) + pulled_task = -1; + + if (pulled_task) { + idle_exit_fair(this_rq); + this_rq->idle_stamp = 0; + } + + return pulled_task; +} + +/* + * active_load_balance_cpu_stop is run by cpu stopper. It pushes + * running tasks off the busiest CPU onto idle CPUs. It requires at + * least 1 task to be running on each physical CPU where possible, and + * avoids physical / logical imbalances. + */ +static int active_load_balance_cpu_stop(void *data) +{ + struct rq *busiest_rq = data; + 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; + struct task_struct *p = NULL; + + 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; + + /* + * 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); + + /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); + for_each_domain(target_cpu, sd) { + if ((sd->flags & SD_LOAD_BALANCE) && + 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); + + p = detach_one_task(&env); + if (p) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } + rcu_read_unlock(); +out_unlock: + busiest_rq->active_balance = 0; + raw_spin_unlock(&busiest_rq->lock); + + if (p) + attach_one_task(target_rq, p); + + local_irq_enable(); + + return 0; +} + +static inline int on_null_domain(struct rq *rq) +{ + return unlikely(!rcu_dereference_sched(rq->sd)); +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * idle load balancing details + * - When one of the busy CPUs notice that there may be an idle rebalancing + * needed, they will kick the idle load balancer, which then does idle + * load balancing for all the idle CPUs. + */ +static struct { + cpumask_var_t idle_cpus_mask; + atomic_t nr_cpus; + unsigned long next_balance; /* in jiffy units */ +} nohz ____cacheline_aligned; + +static inline int find_new_ilb(void) +{ + int ilb = cpumask_first(nohz.idle_cpus_mask); + + if (ilb < nr_cpu_ids && idle_cpu(ilb)) + return ilb; + + return nr_cpu_ids; +} + +/* + * Kick a CPU to do the nohz balancing, if it is time for it. We pick the + * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle + * CPU (if there is one). + */ +static void nohz_balancer_kick(void) +{ + int ilb_cpu; + + nohz.next_balance++; + + ilb_cpu = find_new_ilb(); + + if (ilb_cpu >= nr_cpu_ids) + return; + + if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu))) + return; + /* + * Use smp_send_reschedule() instead of resched_cpu(). + * This way we generate a sched IPI on the target cpu which + * is idle. And the softirq performing nohz idle load balance + * will be run before returning from the IPI. + */ + smp_send_reschedule(ilb_cpu); + return; +} + +static inline void nohz_balance_exit_idle(int cpu) +{ + if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { + /* + * Completely isolated CPUs don't ever set, so we must test. + */ + if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) { + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); + atomic_dec(&nohz.nr_cpus); + } + clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); + } +} + +static inline void set_cpu_sd_state_busy(void) +{ + struct sched_domain *sd; + int cpu = smp_processor_id(); + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + + if (!sd || !sd->nohz_idle) + goto unlock; + sd->nohz_idle = 0; + + atomic_inc(&sd->groups->sgc->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +void set_cpu_sd_state_idle(void) +{ + struct sched_domain *sd; + int cpu = smp_processor_id(); + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + + if (!sd || sd->nohz_idle) + goto unlock; + sd->nohz_idle = 1; + + atomic_dec(&sd->groups->sgc->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +/* + * This routine will record that the cpu is going idle with tick stopped. + * This info will be used in performing idle load balancing in the future. + */ +void nohz_balance_enter_idle(int cpu) +{ + /* + * If this cpu is going down, then nothing needs to be done. + */ + if (!cpu_active(cpu)) + return; + + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) + return; + + /* + * If we're a completely isolated CPU, we don't play. + */ + if (on_null_domain(cpu_rq(cpu))) + return; + + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); + atomic_inc(&nohz.nr_cpus); + set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); +} + +static int sched_ilb_notifier(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DYING: + nohz_balance_exit_idle(smp_processor_id()); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} +#endif + +static DEFINE_SPINLOCK(balancing); + +/* + * Scale the max load_balance interval with the number of CPUs in the system. + * This trades load-balance latency on larger machines for less cross talk. + */ +void update_max_interval(void) +{ + max_load_balance_interval = HZ*num_online_cpus()/10; +} + +/* + * It checks each scheduling domain to see if it is due to be balanced, + * and initiates a balancing operation if so. + * + * Balancing parameters are set up in init_sched_domains. + */ +static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) +{ + int continue_balancing = 1; + int cpu = rq->cpu; + unsigned long interval; + struct sched_domain *sd; + /* Earliest time when we have to do rebalance again */ + unsigned long next_balance = jiffies + 60*HZ; + int update_next_balance = 0; + int need_serialize, need_decay = 0; + u64 max_cost = 0; + + update_blocked_averages(cpu); + + rcu_read_lock(); + for_each_domain(cpu, sd) { + /* + * Decay the newidle max times here because this is a regular + * visit to all the domains. Decay ~1% per second. + */ + if (time_after(jiffies, sd->next_decay_max_lb_cost)) { + sd->max_newidle_lb_cost = + (sd->max_newidle_lb_cost * 253) / 256; + sd->next_decay_max_lb_cost = jiffies + HZ; + need_decay = 1; + } + max_cost += sd->max_newidle_lb_cost; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!continue_balancing) { + if (need_decay) + continue; + break; + } + + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + + need_serialize = sd->flags & SD_SERIALIZE; + if (need_serialize) { + if (!spin_trylock(&balancing)) + goto out; + } + + if (time_after_eq(jiffies, sd->last_balance + interval)) { + if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { + /* + * The LBF_DST_PINNED logic could have changed + * env->dst_cpu, so we can't know our idle + * state even if we migrated tasks. Update it. + */ + idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; + } + sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + } + if (need_serialize) + spin_unlock(&balancing); +out: + if (time_after(next_balance, sd->last_balance + interval)) { + next_balance = sd->last_balance + interval; + update_next_balance = 1; + } + } + if (need_decay) { + /* + * Ensure the rq-wide value also decays but keep it at a + * reasonable floor to avoid funnies with rq->avg_idle. + */ + rq->max_idle_balance_cost = + max((u64)sysctl_sched_migration_cost, max_cost); + } + rcu_read_unlock(); + + /* + * next_balance will be updated only when there is a need. + * When the cpu is attached to null domain for ex, it will not be + * updated. + */ + if (likely(update_next_balance)) + rq->next_balance = next_balance; +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the + * rebalancing for all the cpus for whom scheduler ticks are stopped. + */ +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) +{ + int this_cpu = this_rq->cpu; + struct rq *rq; + int balance_cpu; + + if (idle != CPU_IDLE || + !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu))) + goto end; + + for_each_cpu(balance_cpu, nohz.idle_cpus_mask) { + if (balance_cpu == this_cpu || !idle_cpu(balance_cpu)) + continue; + + /* + * If this cpu gets work to do, stop the load balancing + * work being done for other cpus. Next load + * balancing owner will pick it up. + */ + if (need_resched()) + break; + + rq = cpu_rq(balance_cpu); + + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } + + if (time_after(this_rq->next_balance, rq->next_balance)) + this_rq->next_balance = rq->next_balance; + } + nohz.next_balance = this_rq->next_balance; +end: + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)); +} + +/* + * Current heuristic for kicking the idle load balancer in the presence + * of an idle cpu in the system. + * - This rq has more than one task. + * - This rq has at least one CFS task and the capacity of the CPU is + * significantly reduced because of RT tasks or IRQs. + * - At parent of LLC scheduler domain level, this cpu's scheduler group has + * multiple busy cpu. + * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler + * domain span are idle. + */ +static inline bool nohz_kick_needed(struct rq *rq) +{ + unsigned long now = jiffies; + struct sched_domain *sd; + struct sched_group_capacity *sgc; + int nr_busy, cpu = rq->cpu; + bool kick = false; + + if (unlikely(rq->idle_balance)) + return false; + + /* + * We may be recently in ticked or tickless idle mode. At the first + * busy tick after returning from idle, we will update the busy stats. + */ + set_cpu_sd_state_busy(); + nohz_balance_exit_idle(cpu); + + /* + * None are in tickless mode and hence no need for NOHZ idle load + * balancing. + */ + if (likely(!atomic_read(&nohz.nr_cpus))) + return false; + + if (time_before(now, nohz.next_balance)) + return false; + + if (rq->nr_running >= 2) + return true; + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); + if (sd) { + sgc = sd->groups->sgc; + nr_busy = atomic_read(&sgc->nr_busy_cpus); + + if (nr_busy > 1) { + kick = true; + goto unlock; + } + + } + + sd = rcu_dereference(rq->sd); + if (sd) { + if ((rq->cfs.h_nr_running >= 1) && + check_cpu_capacity(rq, sd)) { + kick = true; + goto unlock; + } + } + + sd = rcu_dereference(per_cpu(sd_asym, cpu)); + if (sd && (cpumask_first_and(nohz.idle_cpus_mask, + sched_domain_span(sd)) < cpu)) { + kick = true; + goto unlock; + } + +unlock: + rcu_read_unlock(); + return kick; +} +#else +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } +#endif + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * Also triggered for nohz idle balancing (with nohz_balancing_kick set). + */ +static void run_rebalance_domains(struct softirq_action *h) +{ + struct rq *this_rq = this_rq(); + enum cpu_idle_type idle = this_rq->idle_balance ? + CPU_IDLE : CPU_NOT_IDLE; + + /* + * If this cpu has a pending nohz_balance_kick, then do the + * balancing on behalf of the other idle cpus whose ticks are + * stopped. Do nohz_idle_balance *before* rebalance_domains to + * give the idle cpus a chance to load balance. Else we may + * load balance only within the local sched_domain hierarchy + * and abort nohz_idle_balance altogether if we pull some load. + */ + nohz_idle_balance(this_rq, idle); + rebalance_domains(this_rq, idle); +} + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + */ +void trigger_load_balance(struct rq *rq) +{ + /* Don't need to rebalance while attached to NULL domain */ + if (unlikely(on_null_domain(rq))) + return; + + if (time_after_eq(jiffies, rq->next_balance)) + raise_softirq(SCHED_SOFTIRQ); +#ifdef CONFIG_NO_HZ_COMMON + if (nohz_kick_needed(rq)) + nohz_balancer_kick(); +#endif +} + +static void rq_online_fair(struct rq *rq) +{ + update_sysctl(); + + update_runtime_enabled(rq); +} + +static void rq_offline_fair(struct rq *rq) +{ + update_sysctl(); + + /* Ensure any throttled groups are reachable by pick_next_task */ + unthrottle_offline_cfs_rqs(rq); +} + +#endif /* CONFIG_SMP */ + +/* + * scheduler tick hitting a task of our scheduling class: + */ +static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &curr->se; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + entity_tick(cfs_rq, se, queued); + } + + if (numabalancing_enabled) + task_tick_numa(rq, curr); + + update_rq_runnable_avg(rq, 1); +} + +/* + * called on fork with the child task as argument from the parent's context + * - child not yet on the tasklist + * - preemption disabled + */ +static void task_fork_fair(struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se, *curr; + int this_cpu = smp_processor_id(); + struct rq *rq = this_rq(); + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + update_rq_clock(rq); + + cfs_rq = task_cfs_rq(current); + curr = cfs_rq->curr; + + /* + * Not only the cpu but also the task_group of the parent might have + * been changed after parent->se.parent,cfs_rq were copied to + * child->se.parent,cfs_rq. So call __set_task_cpu() to make those + * of child point to valid ones. + */ + rcu_read_lock(); + __set_task_cpu(p, this_cpu); + rcu_read_unlock(); + + update_curr(cfs_rq); + + if (curr) + se->vruntime = curr->vruntime; + place_entity(cfs_rq, se, 1); + + if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) { + /* + * Upon rescheduling, sched_class::put_prev_task() will place + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); + resched_curr(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; + + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +/* + * Priority of the task has changed. Check to see if we preempt + * the current task. + */ +static void +prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) +{ + if (!task_on_rq_queued(p)) + return; + + /* + * Reschedule if we are currently running on this runqueue and + * our priority decreased, or if we are not currently running on + * this runqueue and our priority is higher than the current's + */ + if (rq->curr == p) { + if (p->prio > oldprio) + resched_curr(rq); + } else + check_preempt_curr(rq, p, 0); +} + +static void switched_from_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* + * Ensure the task's vruntime is normalized, so that when it's + * switched back to the fair class the enqueue_entity(.flags=0) will + * do the right thing. + * + * If it's queued, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !queued, then only when + * the task is sleeping will it still have non-normalized vruntime. + */ + if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) { + /* + * Fix up our vruntime so that the current sleep doesn't + * cause 'unlimited' sleep bonus. + */ + place_entity(cfs_rq, se, 0); + se->vruntime -= cfs_rq->min_vruntime; + } + +#ifdef CONFIG_SMP + /* + * Remove our load from contribution when we leave sched_fair + * and ensure we don't carry in an old decay_count if we + * switch back. + */ + if (se->avg.decay_count) { + __synchronize_entity_decay(se); + subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); + } +#endif +} + +/* + * We switched to the sched_fair class. + */ +static void switched_to_fair(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *se = &p->se; + /* + * Since the real-depth could have been changed (only FAIR + * class maintain depth value), reset depth properly. + */ + se->depth = se->parent ? se->parent->depth + 1 : 0; +#endif + if (!task_on_rq_queued(p)) + return; + + /* + * We were most likely switched from sched_rt, so + * kick off the schedule if running, otherwise just see + * if we can still preempt the current task. + */ + if (rq->curr == p) + resched_curr(rq); + else + check_preempt_curr(rq, p, 0); +} + +/* Account for a task changing its policy or group. + * + * This routine is mostly called to set cfs_rq->curr field when a task + * migrates between groups/classes. + */ +static void set_curr_task_fair(struct rq *rq) +{ + struct sched_entity *se = &rq->curr->se; + + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + set_next_entity(cfs_rq, se); + /* ensure bandwidth has been allocated on our new cfs_rq */ + account_cfs_rq_runtime(cfs_rq, 0); + } +} + +void init_cfs_rq(struct cfs_rq *cfs_rq) +{ + cfs_rq->tasks_timeline = RB_ROOT; + cfs_rq->min_vruntime = (u64)(-(1LL << 20)); +#ifndef CONFIG_64BIT + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif +#ifdef CONFIG_SMP + atomic64_set(&cfs_rq->decay_counter, 1); + atomic_long_set(&cfs_rq->removed_load, 0); +#endif +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void task_move_group_fair(struct task_struct *p, int queued) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq; + + /* + * If the task was not on the rq at the time of this cgroup movement + * it must have been asleep, sleeping tasks keep their ->vruntime + * absolute on their old rq until wakeup (needed for the fair sleeper + * bonus in place_entity()). + * + * If it was on the rq, we've just 'preempted' it, which does convert + * ->vruntime to a relative base. + * + * Make sure both cases convert their relative position when migrating + * to another cgroup's rq. This does somewhat interfere with the + * fair sleeper stuff for the first placement, but who cares. + */ + /* + * When !queued, vruntime of the task has usually NOT been normalized. + * But there are some cases where it has already been normalized: + * + * - Moving a forked child which is waiting for being woken up by + * wake_up_new_task(). + * - Moving a task which has been woken up by try_to_wake_up() and + * waiting for actually being woken up by sched_ttwu_pending(). + * + * To prevent boost or penalty in the new cfs_rq caused by delta + * min_vruntime between the two cfs_rqs, we skip vruntime adjustment. + */ + if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING)) + queued = 1; + + if (!queued) + se->vruntime -= cfs_rq_of(se)->min_vruntime; + set_task_rq(p, task_cpu(p)); + se->depth = se->parent ? se->parent->depth + 1 : 0; + if (!queued) { + cfs_rq = cfs_rq_of(se); + se->vruntime += cfs_rq->min_vruntime; +#ifdef CONFIG_SMP + /* + * migrate_task_rq_fair() will have removed our previous + * contribution, but we must synchronize for ongoing future + * decay. + */ + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; +#endif + } +} + +void free_fair_sched_group(struct task_group *tg) +{ + int i; + + destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); + + for_each_possible_cpu(i) { + if (tg->cfs_rq) + kfree(tg->cfs_rq[i]); + if (tg->se) + kfree(tg->se[i]); + } + + kfree(tg->cfs_rq); + kfree(tg->se); +} + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se; + int i; + + tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->cfs_rq) + goto err; + tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->se) + goto err; + + tg->shares = NICE_0_LOAD; + + init_cfs_bandwidth(tg_cfs_bandwidth(tg)); + + for_each_possible_cpu(i) { + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), + GFP_KERNEL, cpu_to_node(i)); + if (!cfs_rq) + goto err; + + se = kzalloc_node(sizeof(struct sched_entity), + GFP_KERNEL, cpu_to_node(i)); + if (!se) + goto err_free_rq; + + init_cfs_rq(cfs_rq); + init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); + } + + return 1; + +err_free_rq: + kfree(cfs_rq); +err: + return 0; +} + +void unregister_fair_sched_group(struct task_group *tg, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + +void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, + struct sched_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + cfs_rq->tg = tg; + cfs_rq->rq = rq; + init_cfs_rq_runtime(cfs_rq); + + tg->cfs_rq[cpu] = cfs_rq; + tg->se[cpu] = se; + + /* se could be NULL for root_task_group */ + if (!se) + return; + + if (!parent) { + se->cfs_rq = &rq->cfs; + se->depth = 0; + } else { + se->cfs_rq = parent->my_q; + se->depth = parent->depth + 1; + } + + se->my_q = cfs_rq; + /* guarantee group entities always have weight */ + update_load_set(&se->load, NICE_0_LOAD); + se->parent = parent; +} + +static DEFINE_MUTEX(shares_mutex); + +int sched_group_set_shares(struct task_group *tg, unsigned long shares) +{ + int i; + unsigned long flags; + + /* + * We can't change the weight of the root cgroup. + */ + if (!tg->se[0]) + return -EINVAL; + + shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); + + mutex_lock(&shares_mutex); + if (tg->shares == shares) + goto done; + + tg->shares = shares; + for_each_possible_cpu(i) { + struct rq *rq = cpu_rq(i); + struct sched_entity *se; + + se = tg->se[i]; + /* Propagate contribution to hierarchy */ + raw_spin_lock_irqsave(&rq->lock, flags); + + /* Possible calls to update_curr() need rq clock */ + update_rq_clock(rq); + for_each_sched_entity(se) + update_cfs_shares(group_cfs_rq(se)); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } + +done: + mutex_unlock(&shares_mutex); + return 0; +} +#else /* CONFIG_FAIR_GROUP_SCHED */ + +void free_fair_sched_group(struct task_group *tg) { } + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} + +void unregister_fair_sched_group(struct task_group *tg, int cpu) { } + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + +static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task) +{ + struct sched_entity *se = &task->se; + unsigned int rr_interval = 0; + + /* + * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise + * idle runqueue: + */ + if (rq->cfs.load.weight) + rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + + return rr_interval; +} + +/* + * All the scheduling class methods: + */ +const struct sched_class fair_sched_class = { + .next = &idle_sched_class, + .enqueue_task = enqueue_task_fair, + .dequeue_task = dequeue_task_fair, + .yield_task = yield_task_fair, + .yield_to_task = yield_to_task_fair, + + .check_preempt_curr = check_preempt_wakeup, + + .pick_next_task = pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_fair, + .migrate_task_rq = migrate_task_rq_fair, + + .rq_online = rq_online_fair, + .rq_offline = rq_offline_fair, + + .task_waking = task_waking_fair, +#endif + + .set_curr_task = set_curr_task_fair, + .task_tick = task_tick_fair, + .task_fork = task_fork_fair, + + .prio_changed = prio_changed_fair, + .switched_from = switched_from_fair, + .switched_to = switched_to_fair, + + .get_rr_interval = get_rr_interval_fair, + + .update_curr = update_curr_fair, + +#ifdef CONFIG_FAIR_GROUP_SCHED + .task_move_group = task_move_group_fair, +#endif +}; + +#ifdef CONFIG_SCHED_DEBUG +void print_cfs_stats(struct seq_file *m, int cpu) +{ + struct cfs_rq *cfs_rq; + + rcu_read_lock(); + for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) + print_cfs_rq(m, cpu, cfs_rq); + rcu_read_unlock(); +} +#endif + +__init void init_sched_fair_class(void) +{ +#ifdef CONFIG_SMP + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); + +#ifdef CONFIG_NO_HZ_COMMON + nohz.next_balance = jiffies; + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); + cpu_notifier(sched_ilb_notifier, 0); +#endif +#endif /* SMP */ + +} diff --git a/kernel/sched/features.h b/kernel/sched/features.h new file mode 100644 index 000000000..91e33cd48 --- /dev/null +++ b/kernel/sched/features.h @@ -0,0 +1,98 @@ +/* + * Only give sleepers 50% of their service deficit. This allows + * them to run sooner, but does not allow tons of sleepers to + * rip the spread apart. + */ +SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true) + +/* + * Place new tasks ahead so that they do not starve already running + * tasks + */ +SCHED_FEAT(START_DEBIT, true) + +/* + * Prefer to schedule the task we woke last (assuming it failed + * wakeup-preemption), since its likely going to consume data we + * touched, increases cache locality. + */ +SCHED_FEAT(NEXT_BUDDY, false) + +/* + * Prefer to schedule the task that ran last (when we did + * wake-preempt) as that likely will touch the same data, increases + * cache locality. + */ +SCHED_FEAT(LAST_BUDDY, true) + +/* + * Consider buddies to be cache hot, decreases the likelyness of a + * cache buddy being migrated away, increases cache locality. + */ +SCHED_FEAT(CACHE_HOT_BUDDY, true) + +/* + * Allow wakeup-time preemption of the current task: + */ +SCHED_FEAT(WAKEUP_PREEMPTION, true) + +/* + * Use arch dependent cpu capacity functions + */ +SCHED_FEAT(ARCH_CAPACITY, true) + +SCHED_FEAT(HRTICK, false) +SCHED_FEAT(DOUBLE_TICK, false) +SCHED_FEAT(LB_BIAS, true) + +/* + * Decrement CPU capacity based on time not spent running tasks + */ +SCHED_FEAT(NONTASK_CAPACITY, true) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, true) + +#ifdef HAVE_RT_PUSH_IPI +/* + * In order to avoid a thundering herd attack of CPUs that are + * lowering their priorities at the same time, and there being + * a single CPU that has an RT task that can migrate and is waiting + * to run, where the other CPUs will try to take that CPUs + * rq lock and possibly create a large contention, sending an + * IPI to that CPU and let that CPU push the RT task to where + * it should go may be a better scenario. + */ +SCHED_FEAT(RT_PUSH_IPI, true) +#endif + +SCHED_FEAT(FORCE_SD_OVERLAP, false) +SCHED_FEAT(RT_RUNTIME_SHARE, true) +SCHED_FEAT(LB_MIN, false) + +/* + * Apply the automatic NUMA scheduling policy. Enabled automatically + * at runtime if running on a NUMA machine. Can be controlled via + * numa_balancing= + */ +#ifdef CONFIG_NUMA_BALANCING +SCHED_FEAT(NUMA, false) + +/* + * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a + * higher number of hinting faults are recorded during active load + * balancing. + */ +SCHED_FEAT(NUMA_FAVOUR_HIGHER, true) + +/* + * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a + * lower number of hinting faults have been recorded. As this has + * the potential to prevent a task ever migrating to a new node + * due to CPU overload it is disabled by default. + */ +SCHED_FEAT(NUMA_RESIST_LOWER, false) +#endif diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c new file mode 100644 index 000000000..70e698d02 --- /dev/null +++ b/kernel/sched/idle.c @@ -0,0 +1,302 @@ +/* + * Generic entry point for the idle threads + */ +#include <linux/sched.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/tick.h> +#include <linux/mm.h> +#include <linux/stackprotector.h> +#include <linux/suspend.h> + +#include <asm/tlb.h> + +#include <trace/events/power.h> + +#ifdef CONFIG_SCHED_BFS +#include "bfs_sched.h" +#else +#include "sched.h" +#endif + +static int __read_mostly cpu_idle_force_poll; + +void cpu_idle_poll_ctrl(bool enable) +{ + if (enable) { + cpu_idle_force_poll++; + } else { + cpu_idle_force_poll--; + WARN_ON_ONCE(cpu_idle_force_poll < 0); + } +} + +#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP +static int __init cpu_idle_poll_setup(char *__unused) +{ + cpu_idle_force_poll = 1; + return 1; +} +__setup("nohlt", cpu_idle_poll_setup); + +static int __init cpu_idle_nopoll_setup(char *__unused) +{ + cpu_idle_force_poll = 0; + return 1; +} +__setup("hlt", cpu_idle_nopoll_setup); +#endif + +static inline int cpu_idle_poll(void) +{ + rcu_idle_enter(); + trace_cpu_idle_rcuidle(0, smp_processor_id()); + local_irq_enable(); + while (!tif_need_resched() && + (cpu_idle_force_poll || tick_check_broadcast_expired())) + cpu_relax(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + return 1; +} + +/* Weak implementations for optional arch specific functions */ +void __weak arch_cpu_idle_prepare(void) { } +void __weak arch_cpu_idle_enter(void) { } +void __weak arch_cpu_idle_exit(void) { } +void __weak arch_cpu_idle_dead(void) { } +void __weak arch_cpu_idle(void) +{ + cpu_idle_force_poll = 1; + local_irq_enable(); +} + +/** + * cpuidle_idle_call - the main idle function + * + * NOTE: no locks or semaphores should be used here + * + * On archs that support TIF_POLLING_NRFLAG, is called with polling + * set, and it returns with polling set. If it ever stops polling, it + * must clear the polling bit. + */ +static void cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int next_state, entered_state; + bool reflect; + + /* + * Check if the idle task must be rescheduled. If it is the + * case, exit the function after re-enabling the local irq. + */ + if (need_resched()) { + local_irq_enable(); + return; + } + + /* + * During the idle period, stop measuring the disabled irqs + * critical sections latencies + */ + stop_critical_timings(); + + /* + * Tell the RCU framework we are entering an idle section, + * so no more rcu read side critical sections and one more + * step to the grace period + */ + rcu_idle_enter(); + + if (cpuidle_not_available(drv, dev)) + goto use_default; + + /* + * Suspend-to-idle ("freeze") is a system state in which all user space + * has been frozen, all I/O devices have been suspended and the only + * activity happens here and in iterrupts (if any). In that case bypass + * the cpuidle governor and go stratight for the deepest idle state + * available. Possibly also suspend the local tick and the entire + * timekeeping to prevent timer interrupts from kicking us out of idle + * until a proper wakeup interrupt happens. + */ + if (idle_should_freeze()) { + entered_state = cpuidle_enter_freeze(drv, dev); + if (entered_state >= 0) { + local_irq_enable(); + goto exit_idle; + } + + reflect = false; + next_state = cpuidle_find_deepest_state(drv, dev); + } else { + reflect = true; + /* + * Ask the cpuidle framework to choose a convenient idle state. + */ + next_state = cpuidle_select(drv, dev); + } + /* Fall back to the default arch idle method on errors. */ + if (next_state < 0) + goto use_default; + + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + goto exit_idle; + } + + /* Take note of the planned idle state. */ + idle_set_state(this_rq(), &drv->states[next_state]); + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + entered_state = cpuidle_enter(drv, dev, next_state); + + /* The cpu is no longer idle or about to enter idle. */ + idle_set_state(this_rq(), NULL); + + if (entered_state == -EBUSY) + goto use_default; + + /* + * Give the governor an opportunity to reflect on the outcome + */ + if (reflect) + cpuidle_reflect(dev, entered_state); + +exit_idle: + __current_set_polling(); + + /* + * It is up to the idle functions to reenable local interrupts + */ + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); + + rcu_idle_exit(); + start_critical_timings(); + return; + +use_default: + /* + * We can't use the cpuidle framework, let's use the default + * idle routine. + */ + if (current_clr_polling_and_test()) + local_irq_enable(); + else + arch_cpu_idle(); + + goto exit_idle; +} + +DEFINE_PER_CPU(bool, cpu_dead_idle); + +/* + * Generic idle loop implementation + * + * Called with polling cleared. + */ +static void cpu_idle_loop(void) +{ + while (1) { + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if + * rq->curr != rq->idle). This means that, if rq->idle has + * the polling bit set, then setting need_resched is + * guaranteed to cause the cpu to reschedule. + */ + + __current_set_polling(); + tick_nohz_idle_enter(); + + while (!need_resched()) { + check_pgt_cache(); + rmb(); + + if (cpu_is_offline(smp_processor_id())) { + rcu_cpu_notify(NULL, CPU_DYING_IDLE, + (void *)(long)smp_processor_id()); + smp_mb(); /* all activity before dead. */ + this_cpu_write(cpu_dead_idle, true); + arch_cpu_idle_dead(); + } + + local_irq_disable(); + arch_cpu_idle_enter(); + + /* + * In poll mode we reenable interrupts and spin. + * + * Also if we detected in the wakeup from idle + * path that the tick broadcast device expired + * for us, we don't want to go deep idle as we + * know that the IPI is going to arrive right + * away + */ + if (cpu_idle_force_poll || tick_check_broadcast_expired()) + cpu_idle_poll(); + else + cpuidle_idle_call(); + + arch_cpu_idle_exit(); + } + + /* + * Since we fell out of the loop above, we know + * TIF_NEED_RESCHED must be set, propagate it into + * PREEMPT_NEED_RESCHED. + * + * This is required because for polling idle loops we will + * not have had an IPI to fold the state for us. + */ + preempt_set_need_resched(); + tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending and reschedule + * if need_resched is set while polling is set. That + * means that clearing polling needs to be visible + * before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); + schedule_preempt_disabled(); + } +} + +void cpu_startup_entry(enum cpuhp_state state) +{ + /* + * This #ifdef needs to die, but it's too late in the cycle to + * make this generic (arm and sh have never invoked the canary + * init for the non boot cpus!). Will be fixed in 3.11 + */ +#ifdef CONFIG_X86 + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. The boot CPU already has it initialized but no harm + * in doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); +#endif + arch_cpu_idle_prepare(); + cpu_idle_loop(); +} diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c new file mode 100644 index 000000000..c65dac8c9 --- /dev/null +++ b/kernel/sched/idle_task.c @@ -0,0 +1,109 @@ +#include "sched.h" + +/* + * idle-task scheduling class. + * + * (NOTE: these are not related to SCHED_IDLE tasks which are + * handled in sched/fair.c) + */ + +#ifdef CONFIG_SMP +static int +select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + return task_cpu(p); /* IDLE tasks as never migrated */ +} +#endif /* CONFIG_SMP */ + +/* + * Idle tasks are unconditionally rescheduled: + */ +static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags) +{ + resched_curr(rq); +} + +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev) +{ + put_prev_task(rq, prev); + + schedstat_inc(rq, sched_goidle); + return rq->idle; +} + +/* + * It is not legal to sleep in the idle task - print a warning + * message if some code attempts to do it: + */ +static void +dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) +{ + raw_spin_unlock_irq(&rq->lock); + printk(KERN_ERR "bad: scheduling from the idle thread!\n"); + dump_stack(); + raw_spin_lock_irq(&rq->lock); +} + +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) +{ + idle_exit_fair(rq); + rq_last_tick_reset(rq); +} + +static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) +{ +} + +static void set_curr_task_idle(struct rq *rq) +{ +} + +static void switched_to_idle(struct rq *rq, struct task_struct *p) +{ + BUG(); +} + +static void +prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio) +{ + BUG(); +} + +static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task) +{ + return 0; +} + +static void update_curr_idle(struct rq *rq) +{ +} + +/* + * Simple, special scheduling class for the per-CPU idle tasks: + */ +const struct sched_class idle_sched_class = { + /* .next is NULL */ + /* no enqueue/yield_task for idle tasks */ + + /* dequeue is not valid, we print a debug message there: */ + .dequeue_task = dequeue_task_idle, + + .check_preempt_curr = check_preempt_curr_idle, + + .pick_next_task = pick_next_task_idle, + .put_prev_task = put_prev_task_idle, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_idle, +#endif + + .set_curr_task = set_curr_task_idle, + .task_tick = task_tick_idle, + + .get_rr_interval = get_rr_interval_idle, + + .prio_changed = prio_changed_idle, + .switched_to = switched_to_idle, + .update_curr = update_curr_idle, +}; diff --git a/kernel/sched/proc.c b/kernel/sched/proc.c new file mode 100644 index 000000000..8ecd552fe --- /dev/null +++ b/kernel/sched/proc.c @@ -0,0 +1,584 @@ +/* + * kernel/sched/proc.c + * + * Kernel load calculations, forked from sched/core.c + */ + +#include <linux/export.h> + +#include "sched.h" + +/* + * Global load-average calculations + * + * We take a distributed and async approach to calculating the global load-avg + * in order to minimize overhead. + * + * The global load average is an exponentially decaying average of nr_running + + * nr_uninterruptible. + * + * Once every LOAD_FREQ: + * + * nr_active = 0; + * for_each_possible_cpu(cpu) + * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible; + * + * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n) + * + * Due to a number of reasons the above turns in the mess below: + * + * - for_each_possible_cpu() is prohibitively expensive on machines with + * serious number of cpus, therefore we need to take a distributed approach + * to calculating nr_active. + * + * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0 + * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) } + * + * So assuming nr_active := 0 when we start out -- true per definition, we + * can simply take per-cpu deltas and fold those into a global accumulate + * to obtain the same result. See calc_load_fold_active(). + * + * Furthermore, in order to avoid synchronizing all per-cpu delta folding + * across the machine, we assume 10 ticks is sufficient time for every + * cpu to have completed this task. + * + * This places an upper-bound on the IRQ-off latency of the machine. Then + * again, being late doesn't loose the delta, just wrecks the sample. + * + * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because + * this would add another cross-cpu cacheline miss and atomic operation + * to the wakeup path. Instead we increment on whatever cpu the task ran + * when it went into uninterruptible state and decrement on whatever cpu + * did the wakeup. This means that only the sum of nr_uninterruptible over + * all cpus yields the correct result. + * + * This covers the NO_HZ=n code, for extra head-aches, see the comment below. + */ + +/* Variables and functions for calc_load */ +atomic_long_t calc_load_tasks; +unsigned long calc_load_update; +unsigned long avenrun[3]; +EXPORT_SYMBOL(avenrun); /* should be removed */ + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} + +long calc_load_fold_active(struct rq *this_rq) +{ + long nr_active, delta = 0; + + nr_active = this_rq->nr_running; + nr_active += (long) this_rq->nr_uninterruptible; + + if (nr_active != this_rq->calc_load_active) { + delta = nr_active - this_rq->calc_load_active; + this_rq->calc_load_active = nr_active; + } + + return delta; +} + +/* + * a1 = a0 * e + a * (1 - e) + */ +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * Handle NO_HZ for the global load-average. + * + * Since the above described distributed algorithm to compute the global + * load-average relies on per-cpu sampling from the tick, it is affected by + * NO_HZ. + * + * The basic idea is to fold the nr_active delta into a global idle-delta upon + * entering NO_HZ state such that we can include this as an 'extra' cpu delta + * when we read the global state. + * + * Obviously reality has to ruin such a delightfully simple scheme: + * + * - When we go NO_HZ idle during the window, we can negate our sample + * contribution, causing under-accounting. + * + * We avoid this by keeping two idle-delta counters and flipping them + * when the window starts, thus separating old and new NO_HZ load. + * + * The only trick is the slight shift in index flip for read vs write. + * + * 0s 5s 10s 15s + * +10 +10 +10 +10 + * |-|-----------|-|-----------|-|-----------|-| + * r:0 0 1 1 0 0 1 1 0 + * w:0 1 1 0 0 1 1 0 0 + * + * This ensures we'll fold the old idle contribution in this window while + * accumlating the new one. + * + * - When we wake up from NO_HZ idle during the window, we push up our + * contribution, since we effectively move our sample point to a known + * busy state. + * + * This is solved by pushing the window forward, and thus skipping the + * sample, for this cpu (effectively using the idle-delta for this cpu which + * was in effect at the time the window opened). This also solves the issue + * of having to deal with a cpu having been in NOHZ idle for multiple + * LOAD_FREQ intervals. + * + * When making the ILB scale, we should try to pull this in as well. + */ +static atomic_long_t calc_load_idle[2]; +static int calc_load_idx; + +static inline int calc_load_write_idx(void) +{ + int idx = calc_load_idx; + + /* + * See calc_global_nohz(), if we observe the new index, we also + * need to observe the new update time. + */ + smp_rmb(); + + /* + * If the folding window started, make sure we start writing in the + * next idle-delta. + */ + if (!time_before(jiffies, calc_load_update)) + idx++; + + return idx & 1; +} + +static inline int calc_load_read_idx(void) +{ + return calc_load_idx & 1; +} + +void calc_load_enter_idle(void) +{ + struct rq *this_rq = this_rq(); + long delta; + + /* + * We're going into NOHZ mode, if there's any pending delta, fold it + * into the pending idle delta. + */ + delta = calc_load_fold_active(this_rq); + if (delta) { + int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); + } +} + +void calc_load_exit_idle(void) +{ + struct rq *this_rq = this_rq(); + + /* + * If we're still before the sample window, we're done. + */ + if (time_before(jiffies, this_rq->calc_load_update)) + return; + + /* + * We woke inside or after the sample window, this means we're already + * accounted through the nohz accounting, so skip the entire deal and + * sync up for the next window. + */ + this_rq->calc_load_update = calc_load_update; + if (time_before(jiffies, this_rq->calc_load_update + 10)) + this_rq->calc_load_update += LOAD_FREQ; +} + +static long calc_load_fold_idle(void) +{ + int idx = calc_load_read_idx(); + long delta = 0; + + if (atomic_long_read(&calc_load_idle[idx])) + delta = atomic_long_xchg(&calc_load_idle[idx], 0); + + return delta; +} + +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + +/* + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. + * + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. + */ +static void calc_global_nohz(void) +{ + long delta, active, n; + + if (!time_before(jiffies, calc_load_update + 10)) { + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + + calc_load_update += n * LOAD_FREQ; + } + + /* + * Flip the idle index... + * + * Make sure we first write the new time then flip the index, so that + * calc_load_write_idx() will see the new time when it reads the new + * index, this avoids a double flip messing things up. + */ + smp_wmb(); + calc_load_idx++; +} +#else /* !CONFIG_NO_HZ_COMMON */ + +static inline long calc_load_fold_idle(void) { return 0; } +static inline void calc_global_nohz(void) { } + +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * calc_load - update the avenrun load estimates 10 ticks after the + * CPUs have updated calc_load_tasks. + */ +void calc_global_load(unsigned long ticks) +{ + long active, delta; + + if (time_before(jiffies, calc_load_update + 10)) + return; + + /* + * Fold the 'old' idle-delta to include all NO_HZ cpus. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load(avenrun[0], EXP_1, active); + avenrun[1] = calc_load(avenrun[1], EXP_5, active); + avenrun[2] = calc_load(avenrun[2], EXP_15, active); + + calc_load_update += LOAD_FREQ; + + /* + * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. + */ + calc_global_nohz(); +} + +/* + * Called from update_cpu_load() to periodically update this CPU's + * active count. + */ +static void calc_load_account_active(struct rq *this_rq) +{ + long delta; + + if (time_before(jiffies, this_rq->calc_load_update)) + return; + + delta = calc_load_fold_active(this_rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + this_rq->calc_load_update += LOAD_FREQ; +} + +/* + * End of global load-average stuff + */ + +/* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). + * + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. + */ +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) +{ + int j = 0; + + if (!missed_updates) + return load; + + if (missed_updates >= degrade_zero_ticks[idx]) + return 0; + + if (idx == 1) + return load >> missed_updates; + + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; + + missed_updates >>= 1; + j++; + } + return load; +} + +/* + * Update rq->cpu_load[] statistics. This function is usually called every + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. + */ +static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) +{ + int i, scale; + + this_rq->nr_load_updates++; + + /* Update our load: */ + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + unsigned long old_load, new_load; + + /* scale is effectively 1 << i now, and >> i divides by scale */ + + old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); + new_load = this_load; + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; + } + + sched_avg_update(this_rq); +} + +#ifdef CONFIG_SMP +static inline unsigned long get_rq_runnable_load(struct rq *rq) +{ + return rq->cfs.runnable_load_avg; +} +#else +static inline unsigned long get_rq_runnable_load(struct rq *rq) +{ + return rq->load.weight; +} +#endif + +#ifdef CONFIG_NO_HZ_COMMON +/* + * There is no sane way to deal with nohz on smp when using jiffies because the + * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading + * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. + * + * Therefore we cannot use the delta approach from the regular tick since that + * would seriously skew the load calculation. However we'll make do for those + * updates happening while idle (nohz_idle_balance) or coming out of idle + * (tick_nohz_idle_exit). + * + * This means we might still be one tick off for nohz periods. + */ + +/* + * Called from nohz_idle_balance() to update the load ratings before doing the + * idle balance. + */ +void update_idle_cpu_load(struct rq *this_rq) +{ + unsigned long curr_jiffies = ACCESS_ONCE(jiffies); + unsigned long load = get_rq_runnable_load(this_rq); + unsigned long pending_updates; + + /* + * bail if there's load or we're actually up-to-date. + */ + if (load || curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + + __update_cpu_load(this_rq, load, pending_updates); +} + +/* + * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. + */ +void update_cpu_load_nohz(void) +{ + struct rq *this_rq = this_rq(); + unsigned long curr_jiffies = ACCESS_ONCE(jiffies); + unsigned long pending_updates; + + if (curr_jiffies == this_rq->last_load_update_tick) + return; + + raw_spin_lock(&this_rq->lock); + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * We were idle, this means load 0, the current load might be + * !0 due to remote wakeups and the sort. + */ + __update_cpu_load(this_rq, 0, pending_updates); + } + raw_spin_unlock(&this_rq->lock); +} +#endif /* CONFIG_NO_HZ */ + +/* + * Called from scheduler_tick() + */ +void update_cpu_load_active(struct rq *this_rq) +{ + unsigned long load = get_rq_runnable_load(this_rq); + /* + * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + */ + this_rq->last_load_update_tick = jiffies; + __update_cpu_load(this_rq, load, 1); + + calc_load_account_active(this_rq); +} diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c new file mode 100644 index 000000000..575da76a3 --- /dev/null +++ b/kernel/sched/rt.c @@ -0,0 +1,2346 @@ +/* + * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR + * policies) + */ + +#include "sched.h" + +#include <linux/slab.h> +#include <linux/irq_work.h> + +int sched_rr_timeslice = RR_TIMESLICE; + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); + +struct rt_bandwidth def_rt_bandwidth; + +static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) +{ + struct rt_bandwidth *rt_b = + container_of(timer, struct rt_bandwidth, rt_period_timer); + ktime_t now; + int overrun; + int idle = 0; + + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, rt_b->rt_period); + + if (!overrun) + break; + + idle = do_sched_rt_period_timer(rt_b, overrun); + } + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) +{ + rt_b->rt_period = ns_to_ktime(period); + rt_b->rt_runtime = runtime; + + raw_spin_lock_init(&rt_b->rt_runtime_lock); + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rt_b->rt_period_timer.function = sched_rt_period_timer; +} + +static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) + return; + + if (hrtimer_active(&rt_b->rt_period_timer)) + return; + + raw_spin_lock(&rt_b->rt_runtime_lock); + start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period); + raw_spin_unlock(&rt_b->rt_runtime_lock); +} + +#ifdef CONFIG_SMP +static void push_irq_work_func(struct irq_work *work); +#endif + +void init_rt_rq(struct rt_rq *rt_rq) +{ + struct rt_prio_array *array; + int i; + + array = &rt_rq->active; + for (i = 0; i < MAX_RT_PRIO; i++) { + INIT_LIST_HEAD(array->queue + i); + __clear_bit(i, array->bitmap); + } + /* delimiter for bitsearch: */ + __set_bit(MAX_RT_PRIO, array->bitmap); + +#if defined CONFIG_SMP + rt_rq->highest_prio.curr = MAX_RT_PRIO; + rt_rq->highest_prio.next = MAX_RT_PRIO; + rt_rq->rt_nr_migratory = 0; + rt_rq->overloaded = 0; + plist_head_init(&rt_rq->pushable_tasks); + +#ifdef HAVE_RT_PUSH_IPI + rt_rq->push_flags = 0; + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); +#endif +#endif /* CONFIG_SMP */ + /* We start is dequeued state, because no RT tasks are queued */ + rt_rq->rt_queued = 0; + + rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; + rt_rq->rt_runtime = 0; + raw_spin_lock_init(&rt_rq->rt_runtime_lock); +} + +#ifdef CONFIG_RT_GROUP_SCHED +static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + hrtimer_cancel(&rt_b->rt_period_timer); +} + +#define rt_entity_is_task(rt_se) (!(rt_se)->my_q) + +static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +{ +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(!rt_entity_is_task(rt_se)); +#endif + return container_of(rt_se, struct task_struct, rt); +} + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return rt_rq->rq; +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + return rt_se->rt_rq; +} + +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_se->rt_rq; + + return rt_rq->rq; +} + +void free_rt_sched_group(struct task_group *tg) +{ + int i; + + if (tg->rt_se) + destroy_rt_bandwidth(&tg->rt_bandwidth); + + for_each_possible_cpu(i) { + if (tg->rt_rq) + kfree(tg->rt_rq[i]); + if (tg->rt_se) + kfree(tg->rt_se[i]); + } + + kfree(tg->rt_rq); + kfree(tg->rt_se); +} + +void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, + struct sched_rt_entity *rt_se, int cpu, + struct sched_rt_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + rt_rq->highest_prio.curr = MAX_RT_PRIO; + rt_rq->rt_nr_boosted = 0; + rt_rq->rq = rq; + rt_rq->tg = tg; + + tg->rt_rq[cpu] = rt_rq; + tg->rt_se[cpu] = rt_se; + + if (!rt_se) + return; + + if (!parent) + rt_se->rt_rq = &rq->rt; + else + rt_se->rt_rq = parent->my_q; + + rt_se->my_q = rt_rq; + rt_se->parent = parent; + INIT_LIST_HEAD(&rt_se->run_list); +} + +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct rt_rq *rt_rq; + struct sched_rt_entity *rt_se; + int i; + + tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_rq) + goto err; + tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_se) + goto err; + + init_rt_bandwidth(&tg->rt_bandwidth, + ktime_to_ns(def_rt_bandwidth.rt_period), 0); + + for_each_possible_cpu(i) { + rt_rq = kzalloc_node(sizeof(struct rt_rq), + GFP_KERNEL, cpu_to_node(i)); + if (!rt_rq) + goto err; + + rt_se = kzalloc_node(sizeof(struct sched_rt_entity), + GFP_KERNEL, cpu_to_node(i)); + if (!rt_se) + goto err_free_rq; + + init_rt_rq(rt_rq); + rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; + init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); + } + + return 1; + +err_free_rq: + kfree(rt_rq); +err: + return 0; +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +#define rt_entity_is_task(rt_se) (1) + +static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se) +{ + return container_of(rt_se, struct task_struct, rt); +} + +static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) +{ + return container_of(rt_rq, struct rq, rt); +} + +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct task_struct *p = rt_task_of(rt_se); + + return task_rq(p); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + return &rq->rt; +} + +void free_rt_sched_group(struct task_group *tg) { } + +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_SMP + +static int pull_rt_task(struct rq *this_rq); + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + /* Try to pull RT tasks here if we lower this rq's prio */ + return rq->rt.highest_prio.curr > prev->prio; +} + +static inline int rt_overloaded(struct rq *rq) +{ + return atomic_read(&rq->rd->rto_count); +} + +static inline void rt_set_overload(struct rq *rq) +{ + if (!rq->online) + return; + + cpumask_set_cpu(rq->cpu, rq->rd->rto_mask); + /* + * Make sure the mask is visible before we set + * the overload count. That is checked to determine + * if we should look at the mask. It would be a shame + * if we looked at the mask, but the mask was not + * updated yet. + * + * Matched by the barrier in pull_rt_task(). + */ + smp_wmb(); + atomic_inc(&rq->rd->rto_count); +} + +static inline void rt_clear_overload(struct rq *rq) +{ + if (!rq->online) + return; + + /* the order here really doesn't matter */ + atomic_dec(&rq->rd->rto_count); + cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask); +} + +static void update_rt_migration(struct rt_rq *rt_rq) +{ + if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) { + if (!rt_rq->overloaded) { + rt_set_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 1; + } + } else if (rt_rq->overloaded) { + rt_clear_overload(rq_of_rt_rq(rt_rq)); + rt_rq->overloaded = 0; + } +} + +static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + struct task_struct *p; + + if (!rt_entity_is_task(rt_se)) + return; + + p = rt_task_of(rt_se); + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total++; + if (p->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory++; + + update_rt_migration(rt_rq); +} + +static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + struct task_struct *p; + + if (!rt_entity_is_task(rt_se)) + return; + + p = rt_task_of(rt_se); + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total--; + if (p->nr_cpus_allowed > 1) + rt_rq->rt_nr_migratory--; + + update_rt_migration(rt_rq); +} + +static inline int has_pushable_tasks(struct rq *rq) +{ + return !plist_head_empty(&rq->rt.pushable_tasks); +} + +static inline void set_post_schedule(struct rq *rq) +{ + /* + * We detect this state here so that we can avoid taking the RQ + * lock again later if there is no need to push + */ + rq->post_schedule = has_pushable_tasks(rq); +} + +static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); + plist_node_init(&p->pushable_tasks, p->prio); + plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks); + + /* Update the highest prio pushable task */ + if (p->prio < rq->rt.highest_prio.next) + rq->rt.highest_prio.next = p->prio; +} + +static void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ + plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); + + /* Update the new highest prio pushable task */ + if (has_pushable_tasks(rq)) { + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + rq->rt.highest_prio.next = p->prio; + } else + rq->rt.highest_prio.next = MAX_RT_PRIO; +} + +#else + +static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +static inline +void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ +} + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_rt_task(struct rq *this_rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} +#endif /* CONFIG_SMP */ + +static void enqueue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq); + +static inline int on_rt_rq(struct sched_rt_entity *rt_se) +{ + return !list_empty(&rt_se->run_list); +} + +#ifdef CONFIG_RT_GROUP_SCHED + +static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) +{ + if (!rt_rq->tg) + return RUNTIME_INF; + + return rt_rq->rt_runtime; +} + +static inline u64 sched_rt_period(struct rt_rq *rt_rq) +{ + return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); +} + +typedef struct task_group *rt_rq_iter_t; + +static inline struct task_group *next_task_group(struct task_group *tg) +{ + do { + tg = list_entry_rcu(tg->list.next, + typeof(struct task_group), list); + } while (&tg->list != &task_groups && task_group_is_autogroup(tg)); + + if (&tg->list == &task_groups) + tg = NULL; + + return tg; +} + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for (iter = container_of(&task_groups, typeof(*iter), list); \ + (iter = next_task_group(iter)) && \ + (rt_rq = iter->rt_rq[cpu_of(rq)]);) + +#define for_each_sched_rt_entity(rt_se) \ + for (; rt_se; rt_se = rt_se->parent) + +static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) +{ + return rt_se->my_q; +} + +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se); + +static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) +{ + struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; + struct rq *rq = rq_of_rt_rq(rt_rq); + struct sched_rt_entity *rt_se; + + int cpu = cpu_of(rq); + + rt_se = rt_rq->tg->rt_se[cpu]; + + if (rt_rq->rt_nr_running) { + if (!rt_se) + enqueue_top_rt_rq(rt_rq); + else if (!on_rt_rq(rt_se)) + enqueue_rt_entity(rt_se, false); + + if (rt_rq->highest_prio.curr < curr->prio) + resched_curr(rq); + } +} + +static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) +{ + struct sched_rt_entity *rt_se; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + + rt_se = rt_rq->tg->rt_se[cpu]; + + if (!rt_se) + dequeue_top_rt_rq(rt_rq); + else if (on_rt_rq(rt_se)) + dequeue_rt_entity(rt_se); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; +} + +static int rt_se_boosted(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = group_rt_rq(rt_se); + struct task_struct *p; + + if (rt_rq) + return !!rt_rq->rt_nr_boosted; + + p = rt_task_of(rt_se); + return p->prio != p->normal_prio; +} + +#ifdef CONFIG_SMP +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return this_rq()->rd->span; +} +#else +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return cpu_online_mask; +} +#endif + +static inline +struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) +{ + return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu]; +} + +static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) +{ + return &rt_rq->tg->rt_bandwidth; +} + +#else /* !CONFIG_RT_GROUP_SCHED */ + +static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) +{ + return rt_rq->rt_runtime; +} + +static inline u64 sched_rt_period(struct rt_rq *rt_rq) +{ + return ktime_to_ns(def_rt_bandwidth.rt_period); +} + +typedef struct rt_rq *rt_rq_iter_t; + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL) + +#define for_each_sched_rt_entity(rt_se) \ + for (; rt_se; rt_se = NULL) + +static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) +{ + return NULL; +} + +static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (!rt_rq->rt_nr_running) + return; + + enqueue_top_rt_rq(rt_rq); + resched_curr(rq); +} + +static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) +{ + dequeue_top_rt_rq(rt_rq); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled; +} + +static inline const struct cpumask *sched_rt_period_mask(void) +{ + return cpu_online_mask; +} + +static inline +struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu) +{ + return &cpu_rq(cpu)->rt; +} + +static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) +{ + return &def_rt_bandwidth; +} + +#endif /* CONFIG_RT_GROUP_SCHED */ + +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + +#ifdef CONFIG_SMP +/* + * We ran out of runtime, see if we can borrow some from our neighbours. + */ +static int do_balance_runtime(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd; + int i, weight, more = 0; + u64 rt_period; + + weight = cpumask_weight(rd->span); + + raw_spin_lock(&rt_b->rt_runtime_lock); + rt_period = ktime_to_ns(rt_b->rt_period); + for_each_cpu(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + if (iter == rt_rq) + continue; + + raw_spin_lock(&iter->rt_runtime_lock); + /* + * Either all rqs have inf runtime and there's nothing to steal + * or __disable_runtime() below sets a specific rq to inf to + * indicate its been disabled and disalow stealing. + */ + if (iter->rt_runtime == RUNTIME_INF) + goto next; + + /* + * From runqueues with spare time, take 1/n part of their + * spare time, but no more than our period. + */ + diff = iter->rt_runtime - iter->rt_time; + if (diff > 0) { + diff = div_u64((u64)diff, weight); + if (rt_rq->rt_runtime + diff > rt_period) + diff = rt_period - rt_rq->rt_runtime; + iter->rt_runtime -= diff; + rt_rq->rt_runtime += diff; + more = 1; + if (rt_rq->rt_runtime == rt_period) { + raw_spin_unlock(&iter->rt_runtime_lock); + break; + } + } +next: + raw_spin_unlock(&iter->rt_runtime_lock); + } + raw_spin_unlock(&rt_b->rt_runtime_lock); + + return more; +} + +/* + * Ensure this RQ takes back all the runtime it lend to its neighbours. + */ +static void __disable_runtime(struct rq *rq) +{ + struct root_domain *rd = rq->rd; + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_rt_rq(rt_rq, iter, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + s64 want; + int i; + + raw_spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * Either we're all inf and nobody needs to borrow, or we're + * already disabled and thus have nothing to do, or we have + * exactly the right amount of runtime to take out. + */ + if (rt_rq->rt_runtime == RUNTIME_INF || + rt_rq->rt_runtime == rt_b->rt_runtime) + goto balanced; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + + /* + * Calculate the difference between what we started out with + * and what we current have, that's the amount of runtime + * we lend and now have to reclaim. + */ + want = rt_b->rt_runtime - rt_rq->rt_runtime; + + /* + * Greedy reclaim, take back as much as we can. + */ + for_each_cpu(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + /* + * Can't reclaim from ourselves or disabled runqueues. + */ + if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF) + continue; + + raw_spin_lock(&iter->rt_runtime_lock); + if (want > 0) { + diff = min_t(s64, iter->rt_runtime, want); + iter->rt_runtime -= diff; + want -= diff; + } else { + iter->rt_runtime -= want; + want -= want; + } + raw_spin_unlock(&iter->rt_runtime_lock); + + if (!want) + break; + } + + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * We cannot be left wanting - that would mean some runtime + * leaked out of the system. + */ + BUG_ON(want); +balanced: + /* + * Disable all the borrow logic by pretending we have inf + * runtime - in which case borrowing doesn't make sense. + */ + rt_rq->rt_runtime = RUNTIME_INF; + rt_rq->rt_throttled = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); + + /* Make rt_rq available for pick_next_task() */ + sched_rt_rq_enqueue(rt_rq); + } +} + +static void __enable_runtime(struct rq *rq) +{ + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + /* + * Reset each runqueue's bandwidth settings + */ + for_each_rt_rq(rt_rq, iter, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + raw_spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_b->rt_runtime; + rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static int balance_runtime(struct rt_rq *rt_rq) +{ + int more = 0; + + if (!sched_feat(RT_RUNTIME_SHARE)) + return more; + + if (rt_rq->rt_time > rt_rq->rt_runtime) { + raw_spin_unlock(&rt_rq->rt_runtime_lock); + more = do_balance_runtime(rt_rq); + raw_spin_lock(&rt_rq->rt_runtime_lock); + } + + return more; +} +#else /* !CONFIG_SMP */ +static inline int balance_runtime(struct rt_rq *rt_rq) +{ + return 0; +} +#endif /* CONFIG_SMP */ + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) +{ + int i, idle = 1, throttled = 0; + const struct cpumask *span; + + span = sched_rt_period_mask(); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * FIXME: isolated CPUs should really leave the root task group, + * whether they are isolcpus or were isolated via cpusets, lest + * the timer run on a CPU which does not service all runqueues, + * potentially leaving other CPUs indefinitely throttled. If + * isolation is really required, the user will turn the throttle + * off to kill the perturbations it causes anyway. Meanwhile, + * this maintains functionality for boot and/or troubleshooting. + */ + if (rt_b == &root_task_group.rt_bandwidth) + span = cpu_online_mask; +#endif + for_each_cpu(i, span) { + int enqueue = 0; + struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); + struct rq *rq = rq_of_rt_rq(rt_rq); + + raw_spin_lock(&rq->lock); + if (rt_rq->rt_time) { + u64 runtime; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + if (rt_rq->rt_throttled) + balance_runtime(rt_rq); + runtime = rt_rq->rt_runtime; + rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime); + if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { + rt_rq->rt_throttled = 0; + enqueue = 1; + + /* + * When we're idle and a woken (rt) task is + * throttled check_preempt_curr() will set + * skip_update and the time between the wakeup + * and this unthrottle will get accounted as + * 'runtime'. + */ + if (rt_rq->rt_nr_running && rq->curr == rq->idle) + rq_clock_skip_update(rq, false); + } + if (rt_rq->rt_time || rt_rq->rt_nr_running) + idle = 0; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } else if (rt_rq->rt_nr_running) { + idle = 0; + if (!rt_rq_throttled(rt_rq)) + enqueue = 1; + } + if (rt_rq->rt_throttled) + throttled = 1; + + if (enqueue) + sched_rt_rq_enqueue(rt_rq); + raw_spin_unlock(&rq->lock); + } + + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + + return idle; +} + +static inline int rt_se_prio(struct sched_rt_entity *rt_se) +{ +#ifdef CONFIG_RT_GROUP_SCHED + struct rt_rq *rt_rq = group_rt_rq(rt_se); + + if (rt_rq) + return rt_rq->highest_prio.curr; +#endif + + return rt_task_of(rt_se)->prio; +} + +static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) +{ + u64 runtime = sched_rt_runtime(rt_rq); + + if (rt_rq->rt_throttled) + return rt_rq_throttled(rt_rq); + + if (runtime >= sched_rt_period(rt_rq)) + return 0; + + balance_runtime(rt_rq); + runtime = sched_rt_runtime(rt_rq); + if (runtime == RUNTIME_INF) + return 0; + + if (rt_rq->rt_time > runtime) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + rt_rq->rt_throttled = 1; + printk_deferred_once("sched: RT throttling activated\n"); + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + + if (rt_rq_throttled(rt_rq)) { + sched_rt_rq_dequeue(rt_rq); + return 1; + } + } + + return 0; +} + +/* + * Update the current task's runtime statistics. Skip current tasks that + * are not in our scheduling class. + */ +static void update_curr_rt(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_rt_entity *rt_se = &curr->rt; + u64 delta_exec; + + if (curr->sched_class != &rt_sched_class) + return; + + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); + + sched_rt_avg_update(rq, delta_exec); + + if (!rt_bandwidth_enabled()) + return; + + for_each_sched_rt_entity(rt_se) { + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + + if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { + raw_spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_time += delta_exec; + if (sched_rt_runtime_exceeded(rt_rq)) + resched_curr(rq); + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } + } +} + +static void +dequeue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (!rt_rq->rt_queued) + return; + + BUG_ON(!rq->nr_running); + + sub_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 0; +} + +static void +enqueue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (rt_rq->rt_queued) + return; + if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + return; + + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; +} + +#if defined CONFIG_SMP + +static void +inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif + if (rq->online && prio < prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, prio); +} + +static void +dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif + if (rq->online && rt_rq->highest_prio.curr != prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); +} + +#else /* CONFIG_SMP */ + +static inline +void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} +static inline +void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {} + +#endif /* CONFIG_SMP */ + +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED +static void +inc_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + + if (prio < prev_prio) + rt_rq->highest_prio.curr = prio; + + inc_rt_prio_smp(rt_rq, prio, prev_prio); +} + +static void +dec_rt_prio(struct rt_rq *rt_rq, int prio) +{ + int prev_prio = rt_rq->highest_prio.curr; + + if (rt_rq->rt_nr_running) { + + WARN_ON(prio < prev_prio); + + /* + * This may have been our highest task, and therefore + * we may have some recomputation to do + */ + if (prio == prev_prio) { + struct rt_prio_array *array = &rt_rq->active; + + rt_rq->highest_prio.curr = + sched_find_first_bit(array->bitmap); + } + + } else + rt_rq->highest_prio.curr = MAX_RT_PRIO; + + dec_rt_prio_smp(rt_rq, prio, prev_prio); +} + +#else + +static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {} +static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {} + +#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se_boosted(rt_se)) + rt_rq->rt_nr_boosted++; + + if (rt_rq->tg) + start_rt_bandwidth(&rt_rq->tg->rt_bandwidth); +} + +static void +dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + if (rt_se_boosted(rt_se)) + rt_rq->rt_nr_boosted--; + + WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted); +} + +#else /* CONFIG_RT_GROUP_SCHED */ + +static void +inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + start_rt_bandwidth(&def_rt_bandwidth); +} + +static inline +void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} + +#endif /* CONFIG_RT_GROUP_SCHED */ + +static inline +unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + + if (group_rq) + return group_rq->rt_nr_running; + else + return 1; +} + +static inline +void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + int prio = rt_se_prio(rt_se); + + WARN_ON(!rt_prio(prio)); + rt_rq->rt_nr_running += rt_se_nr_running(rt_se); + + inc_rt_prio(rt_rq, prio); + inc_rt_migration(rt_se, rt_rq); + inc_rt_group(rt_se, rt_rq); +} + +static inline +void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) +{ + WARN_ON(!rt_prio(rt_se_prio(rt_se))); + WARN_ON(!rt_rq->rt_nr_running); + rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); + + dec_rt_prio(rt_rq, rt_se_prio(rt_se)); + dec_rt_migration(rt_se, rt_rq); + dec_rt_group(rt_se, rt_rq); +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +{ + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + struct rt_prio_array *array = &rt_rq->active; + struct rt_rq *group_rq = group_rt_rq(rt_se); + struct list_head *queue = array->queue + rt_se_prio(rt_se); + + /* + * Don't enqueue the group if its throttled, or when empty. + * The latter is a consequence of the former when a child group + * get throttled and the current group doesn't have any other + * active members. + */ + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + return; + + if (head) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + __set_bit(rt_se_prio(rt_se), array->bitmap); + + inc_rt_tasks(rt_se, rt_rq); +} + +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + struct rt_prio_array *array = &rt_rq->active; + + list_del_init(&rt_se->run_list); + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + dec_rt_tasks(rt_se, rt_rq); +} + +/* + * Because the prio of an upper entry depends on the lower + * entries, we must remove entries top - down. + */ +static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +{ + struct sched_rt_entity *back = NULL; + + for_each_sched_rt_entity(rt_se) { + rt_se->back = back; + back = rt_se; + } + + dequeue_top_rt_rq(rt_rq_of_se(back)); + + for (rt_se = back; rt_se; rt_se = rt_se->back) { + if (on_rt_rq(rt_se)) + __dequeue_rt_entity(rt_se); + } +} + +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + dequeue_rt_stack(rt_se); + for_each_sched_rt_entity(rt_se) + __enqueue_rt_entity(rt_se, head); + enqueue_top_rt_rq(&rq->rt); +} + +static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); + + dequeue_rt_stack(rt_se); + + for_each_sched_rt_entity(rt_se) { + struct rt_rq *rt_rq = group_rt_rq(rt_se); + + if (rt_rq && rt_rq->rt_nr_running) + __enqueue_rt_entity(rt_se, false); + } + enqueue_top_rt_rq(&rq->rt); +} + +/* + * Adding/removing a task to/from a priority array: + */ +static void +enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) +{ + struct sched_rt_entity *rt_se = &p->rt; + + if (flags & ENQUEUE_WAKEUP) + rt_se->timeout = 0; + + enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); +} + +static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) +{ + struct sched_rt_entity *rt_se = &p->rt; + + update_curr_rt(rq); + dequeue_rt_entity(rt_se); + + dequeue_pushable_task(rq, p); +} + +/* + * Put task to the head or the end of the run list without the overhead of + * dequeue followed by enqueue. + */ +static void +requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head) +{ + if (on_rt_rq(rt_se)) { + struct rt_prio_array *array = &rt_rq->active; + struct list_head *queue = array->queue + rt_se_prio(rt_se); + + if (head) + list_move(&rt_se->run_list, queue); + else + list_move_tail(&rt_se->run_list, queue); + } +} + +static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head) +{ + struct sched_rt_entity *rt_se = &p->rt; + struct rt_rq *rt_rq; + + for_each_sched_rt_entity(rt_se) { + rt_rq = rt_rq_of_se(rt_se); + requeue_rt_entity(rt_rq, rt_se, head); + } +} + +static void yield_task_rt(struct rq *rq) +{ + requeue_task_rt(rq, rq->curr, 0); +} + +#ifdef CONFIG_SMP +static int find_lowest_rq(struct task_struct *task); + +static int +select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + struct task_struct *curr; + struct rq *rq; + + /* For anything but wake ups, just return the task_cpu */ + if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK) + goto out; + + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + + /* + * If the current task on @p's runqueue is an RT task, then + * try to see if we can wake this RT task up on another + * runqueue. Otherwise simply start this RT task + * on its current runqueue. + * + * We want to avoid overloading runqueues. If the woken + * task is a higher priority, then it will stay on this CPU + * and the lower prio task should be moved to another CPU. + * Even though this will probably make the lower prio task + * lose its cache, we do not want to bounce a higher task + * around just because it gave up its CPU, perhaps for a + * lock? + * + * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. + */ + if (curr && unlikely(rt_task(curr)) && + (curr->nr_cpus_allowed < 2 || + curr->prio <= p->prio)) { + int target = find_lowest_rq(p); + + /* + * Don't bother moving it if the destination CPU is + * not running a lower priority task. + */ + if (target != -1 && + p->prio < cpu_rq(target)->rt.highest_prio.curr) + cpu = target; + } + rcu_read_unlock(); + +out: + return cpu; +} + +static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) +{ + /* + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ + if (rq->curr->nr_cpus_allowed == 1 || + !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) + return; + + /* + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ + if (p->nr_cpus_allowed != 1 + && cpupri_find(&rq->rd->cpupri, p, NULL)) + return; + + /* + * There appears to be other cpus that can accept + * current and none to run 'p', so lets reschedule + * to try and push current away: + */ + requeue_task_rt(rq, p, 1); + resched_curr(rq); +} + +#endif /* CONFIG_SMP */ + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags) +{ + if (p->prio < rq->curr->prio) { + resched_curr(rq); + return; + } + +#ifdef CONFIG_SMP + /* + * If: + * + * - the newly woken task is of equal priority to the current task + * - the newly woken task is non-migratable while current is migratable + * - current will be preempted on the next reschedule + * + * we should check to see if current can readily move to a different + * cpu. If so, we will reschedule to allow the push logic to try + * to move current somewhere else, making room for our non-migratable + * task. + */ + if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr)) + check_preempt_equal_prio(rq, p); +#endif +} + +static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, + struct rt_rq *rt_rq) +{ + struct rt_prio_array *array = &rt_rq->active; + struct sched_rt_entity *next = NULL; + struct list_head *queue; + int idx; + + idx = sched_find_first_bit(array->bitmap); + BUG_ON(idx >= MAX_RT_PRIO); + + queue = array->queue + idx; + next = list_entry(queue->next, struct sched_rt_entity, run_list); + + return next; +} + +static struct task_struct *_pick_next_task_rt(struct rq *rq) +{ + struct sched_rt_entity *rt_se; + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + do { + rt_se = pick_next_rt_entity(rq, rt_rq); + BUG_ON(!rt_se); + rt_rq = group_rt_rq(rt_se); + } while (rt_rq); + + p = rt_task_of(rt_se); + p->se.exec_start = rq_clock_task(rq); + + return p; +} + +static struct task_struct * +pick_next_task_rt(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + if (need_pull_rt_task(rq, prev)) { + pull_rt_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a dl or stop task can slip in, in which case we need + * to re-start task selection. + */ + if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || + rq->dl.dl_nr_running)) + return RETRY_TASK; + } + + /* + * We may dequeue prev's rt_rq in put_prev_task(). + * So, we update time before rt_nr_running check. + */ + if (prev->sched_class == &rt_sched_class) + update_curr_rt(rq); + + if (!rt_rq->rt_queued) + return NULL; + + put_prev_task(rq, prev); + + p = _pick_next_task_rt(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); + + set_post_schedule(rq); + + return p; +} + +static void put_prev_task_rt(struct rq *rq, struct task_struct *p) +{ + update_curr_rt(rq); + + /* + * The previous task needs to be made eligible for pushing + * if it is still active + */ + if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) + enqueue_pushable_task(rq, p); +} + +#ifdef CONFIG_SMP + +/* Only try algorithms three times */ +#define RT_MAX_TRIES 3 + +static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) +{ + if (!task_running(rq, p) && + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + return 1; + return 0; +} + +/* + * Return the highest pushable rq's task, which is suitable to be executed + * on the cpu, NULL otherwise + */ +static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu) +{ + struct plist_head *head = &rq->rt.pushable_tasks; + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + plist_for_each_entry(p, head, pushable_tasks) { + if (pick_rt_task(rq, p, cpu)) + return p; + } + + return NULL; +} + +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); + +static int find_lowest_rq(struct task_struct *task) +{ + struct sched_domain *sd; + struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask); + int this_cpu = smp_processor_id(); + int cpu = task_cpu(task); + + /* Make sure the mask is initialized first */ + if (unlikely(!lowest_mask)) + return -1; + + if (task->nr_cpus_allowed == 1) + return -1; /* No other targets possible */ + + if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) + return -1; /* No targets found */ + + /* + * At this point we have built a mask of cpus representing the + * lowest priority tasks in the system. Now we want to elect + * the best one based on our affinity and topology. + * + * We prioritize the last cpu that the task executed on since + * it is most likely cache-hot in that location. + */ + if (cpumask_test_cpu(cpu, lowest_mask)) + return cpu; + + /* + * Otherwise, we consult the sched_domains span maps to figure + * out which cpu is logically closest to our hot cache data. + */ + if (!cpumask_test_cpu(this_cpu, lowest_mask)) + this_cpu = -1; /* Skip this_cpu opt if not among lowest */ + + rcu_read_lock(); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + int best_cpu; + + /* + * "this_cpu" is cheaper to preempt than a + * remote processor. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return this_cpu; + } + + best_cpu = cpumask_first_and(lowest_mask, + sched_domain_span(sd)); + if (best_cpu < nr_cpu_ids) { + rcu_read_unlock(); + return best_cpu; + } + } + } + rcu_read_unlock(); + + /* + * And finally, if there were no matches within the domains + * just give the caller *something* to work with from the compatible + * locations. + */ + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(lowest_mask); + if (cpu < nr_cpu_ids) + return cpu; + return -1; +} + +/* Will lock the rq it finds */ +static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) +{ + struct rq *lowest_rq = NULL; + int tries; + int cpu; + + for (tries = 0; tries < RT_MAX_TRIES; tries++) { + cpu = find_lowest_rq(task); + + if ((cpu == -1) || (cpu == rq->cpu)) + break; + + lowest_rq = cpu_rq(cpu); + + if (lowest_rq->rt.highest_prio.curr <= task->prio) { + /* + * Target rq has tasks of equal or higher priority, + * retrying does not release any lock and is unlikely + * to yield a different result. + */ + lowest_rq = NULL; + break; + } + + /* if the prio of this runqueue changed, try again */ + if (double_lock_balance(rq, lowest_rq)) { + /* + * We had to unlock the run queue. In + * the mean time, task could have + * migrated already or had its affinity changed. + * Also make sure that it wasn't scheduled on its rq. + */ + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(lowest_rq->cpu, + tsk_cpus_allowed(task)) || + task_running(rq, task) || + !task_on_rq_queued(task))) { + + double_unlock_balance(rq, lowest_rq); + lowest_rq = NULL; + break; + } + } + + /* If this rq is still suitable use it. */ + if (lowest_rq->rt.highest_prio.curr > task->prio) + break; + + /* try again */ + double_unlock_balance(rq, lowest_rq); + lowest_rq = NULL; + } + + return lowest_rq; +} + +static struct task_struct *pick_next_pushable_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!rt_task(p)); + + return p; +} + +/* + * If the current CPU has more than one RT task, see if the non + * running task can migrate over to a CPU that is running a task + * of lesser priority. + */ +static int push_rt_task(struct rq *rq) +{ + struct task_struct *next_task; + struct rq *lowest_rq; + int ret = 0; + + if (!rq->rt.overloaded) + return 0; + + next_task = pick_next_pushable_task(rq); + if (!next_task) + return 0; + +retry: + if (unlikely(next_task == rq->curr)) { + WARN_ON(1); + return 0; + } + + /* + * It's possible that the next_task slipped in of + * higher priority than current. If that's the case + * just reschedule current. + */ + if (unlikely(next_task->prio < rq->curr->prio)) { + resched_curr(rq); + return 0; + } + + /* We might release rq lock */ + get_task_struct(next_task); + + /* find_lock_lowest_rq locks the rq if found */ + lowest_rq = find_lock_lowest_rq(next_task, rq); + if (!lowest_rq) { + struct task_struct *task; + /* + * find_lock_lowest_rq releases rq->lock + * so it is possible that next_task has migrated. + * + * We need to make sure that the task is still on the same + * run-queue and is also still the next task eligible for + * pushing. + */ + task = pick_next_pushable_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * The task hasn't migrated, and is still the next + * eligible task, but we failed to find a run-queue + * to push it to. Do not retry in this case, since + * other cpus will pull from us when ready. + */ + goto out; + } + + if (!task) + /* No more tasks, just exit */ + goto out; + + /* + * Something has shifted, try again. + */ + put_task_struct(next_task); + next_task = task; + goto retry; + } + + deactivate_task(rq, next_task, 0); + set_task_cpu(next_task, lowest_rq->cpu); + activate_task(lowest_rq, next_task, 0); + ret = 1; + + resched_curr(lowest_rq); + + double_unlock_balance(rq, lowest_rq); + +out: + put_task_struct(next_task); + + return ret; +} + +static void push_rt_tasks(struct rq *rq) +{ + /* push_rt_task will return true if it moved an RT */ + while (push_rt_task(rq)) + ; +} + +#ifdef HAVE_RT_PUSH_IPI +/* + * The search for the next cpu always starts at rq->cpu and ends + * when we reach rq->cpu again. It will never return rq->cpu. + * This returns the next cpu to check, or nr_cpu_ids if the loop + * is complete. + * + * rq->rt.push_cpu holds the last cpu returned by this function, + * or if this is the first instance, it must hold rq->cpu. + */ +static int rto_next_cpu(struct rq *rq) +{ + int prev_cpu = rq->rt.push_cpu; + int cpu; + + cpu = cpumask_next(prev_cpu, rq->rd->rto_mask); + + /* + * If the previous cpu is less than the rq's CPU, then it already + * passed the end of the mask, and has started from the beginning. + * We end if the next CPU is greater or equal to rq's CPU. + */ + if (prev_cpu < rq->cpu) { + if (cpu >= rq->cpu) + return nr_cpu_ids; + + } else if (cpu >= nr_cpu_ids) { + /* + * We passed the end of the mask, start at the beginning. + * If the result is greater or equal to the rq's CPU, then + * the loop is finished. + */ + cpu = cpumask_first(rq->rd->rto_mask); + if (cpu >= rq->cpu) + return nr_cpu_ids; + } + rq->rt.push_cpu = cpu; + + /* Return cpu to let the caller know if the loop is finished or not */ + return cpu; +} + +static int find_next_push_cpu(struct rq *rq) +{ + struct rq *next_rq; + int cpu; + + while (1) { + cpu = rto_next_cpu(rq); + if (cpu >= nr_cpu_ids) + break; + next_rq = cpu_rq(cpu); + + /* Make sure the next rq can push to this rq */ + if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr) + break; + } + + return cpu; +} + +#define RT_PUSH_IPI_EXECUTING 1 +#define RT_PUSH_IPI_RESTART 2 + +static void tell_cpu_to_push(struct rq *rq) +{ + int cpu; + + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + raw_spin_lock(&rq->rt.push_lock); + /* Make sure it's still executing */ + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + /* + * Tell the IPI to restart the loop as things have + * changed since it started. + */ + rq->rt.push_flags |= RT_PUSH_IPI_RESTART; + raw_spin_unlock(&rq->rt.push_lock); + return; + } + raw_spin_unlock(&rq->rt.push_lock); + } + + /* When here, there's no IPI going around */ + + rq->rt.push_cpu = rq->cpu; + cpu = find_next_push_cpu(rq); + if (cpu >= nr_cpu_ids) + return; + + rq->rt.push_flags = RT_PUSH_IPI_EXECUTING; + + irq_work_queue_on(&rq->rt.push_work, cpu); +} + +/* Called from hardirq context */ +static void try_to_push_tasks(void *arg) +{ + struct rt_rq *rt_rq = arg; + struct rq *rq, *src_rq; + int this_cpu; + int cpu; + + this_cpu = rt_rq->push_cpu; + + /* Paranoid check */ + BUG_ON(this_cpu != smp_processor_id()); + + rq = cpu_rq(this_cpu); + src_rq = rq_of_rt_rq(rt_rq); + +again: + if (has_pushable_tasks(rq)) { + raw_spin_lock(&rq->lock); + push_rt_task(rq); + raw_spin_unlock(&rq->lock); + } + + /* Pass the IPI to the next rt overloaded queue */ + raw_spin_lock(&rt_rq->push_lock); + /* + * If the source queue changed since the IPI went out, + * we need to restart the search from that CPU again. + */ + if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) { + rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART; + rt_rq->push_cpu = src_rq->cpu; + } + + cpu = find_next_push_cpu(src_rq); + + if (cpu >= nr_cpu_ids) + rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING; + raw_spin_unlock(&rt_rq->push_lock); + + if (cpu >= nr_cpu_ids) + return; + + /* + * It is possible that a restart caused this CPU to be + * chosen again. Don't bother with an IPI, just see if we + * have more to push. + */ + if (unlikely(cpu == rq->cpu)) + goto again; + + /* Try the next RT overloaded CPU */ + irq_work_queue_on(&rt_rq->push_work, cpu); +} + +static void push_irq_work_func(struct irq_work *work) +{ + struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work); + + try_to_push_tasks(rt_rq); +} +#endif /* HAVE_RT_PUSH_IPI */ + +static int pull_rt_task(struct rq *this_rq) +{ + int this_cpu = this_rq->cpu, ret = 0, cpu; + struct task_struct *p; + struct rq *src_rq; + + if (likely(!rt_overloaded(this_rq))) + return 0; + + /* + * Match the barrier from rt_set_overloaded; this guarantees that if we + * see overloaded we must also see the rto_mask bit. + */ + smp_rmb(); + +#ifdef HAVE_RT_PUSH_IPI + if (sched_feat(RT_PUSH_IPI)) { + tell_cpu_to_push(this_rq); + return 0; + } +#endif + + for_each_cpu(cpu, this_rq->rd->rto_mask) { + if (this_cpu == cpu) + continue; + + src_rq = cpu_rq(cpu); + + /* + * Don't bother taking the src_rq->lock if the next highest + * task is known to be lower-priority than our current task. + * This may look racy, but if this value is about to go + * logically higher, the src_rq will push this task away. + * And if its going logically lower, we do not care + */ + if (src_rq->rt.highest_prio.next >= + this_rq->rt.highest_prio.curr) + continue; + + /* + * We can potentially drop this_rq's lock in + * double_lock_balance, and another CPU could + * alter this_rq + */ + double_lock_balance(this_rq, src_rq); + + /* + * We can pull only a task, which is pushable + * on its rq, and no others. + */ + p = pick_highest_pushable_task(src_rq, this_cpu); + + /* + * Do we have an RT task that preempts + * the to-be-scheduled task? + */ + if (p && (p->prio < this_rq->rt.highest_prio.curr)) { + WARN_ON(p == src_rq->curr); + WARN_ON(!task_on_rq_queued(p)); + + /* + * There's a chance that p is higher in priority + * than what's currently running on its cpu. + * This is just that p is wakeing up and hasn't + * had a chance to schedule. We only pull + * p if it is lower in priority than the + * current task on the run queue + */ + if (p->prio < src_rq->curr->prio) + goto skip; + + ret = 1; + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + /* + * We continue with the search, just in + * case there's an even higher prio task + * in another runqueue. (low likelihood + * but possible) + */ + } +skip: + double_unlock_balance(this_rq, src_rq); + } + + return ret; +} + +static void post_schedule_rt(struct rq *rq) +{ + push_rt_tasks(rq); +} + +/* + * If we are not running and we are not going to reschedule soon, we should + * try to push tasks away now + */ +static void task_woken_rt(struct rq *rq, struct task_struct *p) +{ + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + has_pushable_tasks(rq) && + p->nr_cpus_allowed > 1 && + (dl_task(rq->curr) || rt_task(rq->curr)) && + (rq->curr->nr_cpus_allowed < 2 || + rq->curr->prio <= p->prio)) + push_rt_tasks(rq); +} + +static void set_cpus_allowed_rt(struct task_struct *p, + const struct cpumask *new_mask) +{ + struct rq *rq; + int weight; + + BUG_ON(!rt_task(p)); + + if (!task_on_rq_queued(p)) + return; + + weight = cpumask_weight(new_mask); + + /* + * Only update if the process changes its state from whether it + * can migrate or not. + */ + if ((p->nr_cpus_allowed > 1) == (weight > 1)) + return; + + rq = task_rq(p); + + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_task(rq, p); + BUG_ON(!rq->rt.rt_nr_migratory); + rq->rt.rt_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_task(rq, p); + rq->rt.rt_nr_migratory++; + } + + update_rt_migration(&rq->rt); +} + +/* Assumes rq->lock is held */ +static void rq_online_rt(struct rq *rq) +{ + if (rq->rt.overloaded) + rt_set_overload(rq); + + __enable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); +} + +/* Assumes rq->lock is held */ +static void rq_offline_rt(struct rq *rq) +{ + if (rq->rt.overloaded) + rt_clear_overload(rq); + + __disable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID); +} + +/* + * When switch from the rt queue, we bring ourselves to a position + * that we might want to pull RT tasks from other runqueues. + */ +static void switched_from_rt(struct rq *rq, struct task_struct *p) +{ + /* + * If there are other RT tasks then we will reschedule + * and the scheduling of the other RT tasks will handle + * the balancing. But if we are the last RT task + * we may need to handle the pulling of RT tasks + * now. + */ + if (!task_on_rq_queued(p) || rq->rt.rt_nr_running) + return; + + if (pull_rt_task(rq)) + resched_curr(rq); +} + +void __init init_sched_rt_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) { + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i), + GFP_KERNEL, cpu_to_node(i)); + } +} +#endif /* CONFIG_SMP */ + +/* + * When switching a task to RT, we may overload the runqueue + * with RT tasks. In this case we try to push them off to + * other runqueues. + */ +static void switched_to_rt(struct rq *rq, struct task_struct *p) +{ + int check_resched = 1; + + /* + * If we are already running, then there's nothing + * that needs to be done. But if we are not running + * we may need to preempt the current running task. + * If that current running task is also an RT task + * then see if we can move to another run queue. + */ + if (task_on_rq_queued(p) && rq->curr != p) { +#ifdef CONFIG_SMP + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && + /* Don't resched if we changed runqueues */ + push_rt_task(rq) && rq != task_rq(p)) + check_resched = 0; +#endif /* CONFIG_SMP */ + if (check_resched && p->prio < rq->curr->prio) + resched_curr(rq); + } +} + +/* + * Priority of the task has changed. This may cause + * us to initiate a push or pull. + */ +static void +prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) +{ + if (!task_on_rq_queued(p)) + return; + + if (rq->curr == p) { +#ifdef CONFIG_SMP + /* + * If our priority decreases while running, we + * may need to pull tasks to this runqueue. + */ + if (oldprio < p->prio) + pull_rt_task(rq); + /* + * If there's a higher priority task waiting to run + * then reschedule. Note, the above pull_rt_task + * can release the rq lock and p could migrate. + * Only reschedule if p is still on the same runqueue. + */ + if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) + resched_curr(rq); +#else + /* For UP simply resched on drop of prio */ + if (oldprio < p->prio) + resched_curr(rq); +#endif /* CONFIG_SMP */ + } else { + /* + * This task is not running, but if it is + * greater than the current running task + * then reschedule. + */ + if (p->prio < rq->curr->prio) + resched_curr(rq); + } +} + +static void watchdog(struct rq *rq, struct task_struct *p) +{ + unsigned long soft, hard; + + /* max may change after cur was read, this will be fixed next tick */ + soft = task_rlimit(p, RLIMIT_RTTIME); + hard = task_rlimit_max(p, RLIMIT_RTTIME); + + if (soft != RLIM_INFINITY) { + unsigned long next; + + if (p->rt.watchdog_stamp != jiffies) { + p->rt.timeout++; + p->rt.watchdog_stamp = jiffies; + } + + next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); + if (p->rt.timeout > next) + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; + } +} + +static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) +{ + struct sched_rt_entity *rt_se = &p->rt; + + update_curr_rt(rq); + + watchdog(rq, p); + + /* + * RR tasks need a special form of timeslice management. + * FIFO tasks have no timeslices. + */ + if (p->policy != SCHED_RR) + return; + + if (--p->rt.time_slice) + return; + + p->rt.time_slice = sched_rr_timeslice; + + /* + * Requeue to the end of queue if we (and all of our ancestors) are not + * the only element on the queue + */ + for_each_sched_rt_entity(rt_se) { + if (rt_se->run_list.prev != rt_se->run_list.next) { + requeue_task_rt(rq, p, 0); + resched_curr(rq); + return; + } + } +} + +static void set_curr_task_rt(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + p->se.exec_start = rq_clock_task(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); +} + +static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) +{ + /* + * Time slice is 0 for SCHED_FIFO tasks + */ + if (task->policy == SCHED_RR) + return sched_rr_timeslice; + else + return 0; +} + +const struct sched_class rt_sched_class = { + .next = &fair_sched_class, + .enqueue_task = enqueue_task_rt, + .dequeue_task = dequeue_task_rt, + .yield_task = yield_task_rt, + + .check_preempt_curr = check_preempt_curr_rt, + + .pick_next_task = pick_next_task_rt, + .put_prev_task = put_prev_task_rt, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_rt, + + .set_cpus_allowed = set_cpus_allowed_rt, + .rq_online = rq_online_rt, + .rq_offline = rq_offline_rt, + .post_schedule = post_schedule_rt, + .task_woken = task_woken_rt, + .switched_from = switched_from_rt, +#endif + + .set_curr_task = set_curr_task_rt, + .task_tick = task_tick_rt, + + .get_rr_interval = get_rr_interval_rt, + + .prio_changed = prio_changed_rt, + .switched_to = switched_to_rt, + + .update_curr = update_curr_rt, +}; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); + +void print_rt_stats(struct seq_file *m, int cpu) +{ + rt_rq_iter_t iter; + struct rt_rq *rt_rq; + + rcu_read_lock(); + for_each_rt_rq(rt_rq, iter, cpu_rq(cpu)) + print_rt_rq(m, cpu, rt_rq); + rcu_read_unlock(); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h new file mode 100644 index 000000000..e0e129993 --- /dev/null +++ b/kernel/sched/sched.h @@ -0,0 +1,1736 @@ + +#include <linux/sched.h> +#include <linux/sched/sysctl.h> +#include <linux/sched/rt.h> +#include <linux/sched/deadline.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/stop_machine.h> +#include <linux/irq_work.h> +#include <linux/tick.h> +#include <linux/slab.h> + +#include "cpupri.h" +#include "cpudeadline.h" +#include "cpuacct.h" + +struct rq; +struct cpuidle_state; + +/* task_struct::on_rq states: */ +#define TASK_ON_RQ_QUEUED 1 +#define TASK_ON_RQ_MIGRATING 2 + +extern __read_mostly int scheduler_running; + +extern unsigned long calc_load_update; +extern atomic_long_t calc_load_tasks; + +extern long calc_load_fold_active(struct rq *this_rq); +extern void update_cpu_load_active(struct rq *this_rq); + +/* + * Helpers for converting nanosecond timing to jiffy resolution + */ +#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) + +/* + * Increase resolution of nice-level calculations for 64-bit architectures. + * The extra resolution improves shares distribution and load balancing of + * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup + * hierarchies, especially on larger systems. This is not a user-visible change + * and does not change the user-interface for setting shares/weights. + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution + * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the + * increased costs. + */ +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ +# define SCHED_LOAD_RESOLUTION 10 +# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) +# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#else +# define SCHED_LOAD_RESOLUTION 0 +# define scale_load(w) (w) +# define scale_load_down(w) (w) +#endif + +#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + +#define NICE_0_LOAD SCHED_LOAD_SCALE +#define NICE_0_SHIFT SCHED_LOAD_SHIFT + +/* + * Single value that decides SCHED_DEADLINE internal math precision. + * 10 -> just above 1us + * 9 -> just above 0.5us + */ +#define DL_SCALE (10) + +/* + * These are the 'tuning knobs' of the scheduler: + */ + +/* + * single value that denotes runtime == period, ie unlimited time. + */ +#define RUNTIME_INF ((u64)~0ULL) + +static inline int fair_policy(int policy) +{ + return policy == SCHED_NORMAL || policy == SCHED_BATCH; +} + +static inline int rt_policy(int policy) +{ + return policy == SCHED_FIFO || policy == SCHED_RR; +} + +static inline int dl_policy(int policy) +{ + return policy == SCHED_DEADLINE; +} + +static inline int task_has_rt_policy(struct task_struct *p) +{ + return rt_policy(p->policy); +} + +static inline int task_has_dl_policy(struct task_struct *p) +{ + return dl_policy(p->policy); +} + +static inline bool dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +/* + * Tells if entity @a should preempt entity @b. + */ +static inline bool +dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) +{ + return dl_time_before(a->deadline, b->deadline); +} + +/* + * This is the priority-queue data structure of the RT scheduling class: + */ +struct rt_prio_array { + DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ + struct list_head queue[MAX_RT_PRIO]; +}; + +struct rt_bandwidth { + /* nests inside the rq lock: */ + raw_spinlock_t rt_runtime_lock; + ktime_t rt_period; + u64 rt_runtime; + struct hrtimer rt_period_timer; +}; + +void __dl_clear_params(struct task_struct *p); + +/* + * To keep the bandwidth of -deadline tasks and groups under control + * we need some place where: + * - store the maximum -deadline bandwidth of the system (the group); + * - cache the fraction of that bandwidth that is currently allocated. + * + * This is all done in the data structure below. It is similar to the + * one used for RT-throttling (rt_bandwidth), with the main difference + * that, since here we are only interested in admission control, we + * do not decrease any runtime while the group "executes", neither we + * need a timer to replenish it. + * + * With respect to SMP, the bandwidth is given on a per-CPU basis, + * meaning that: + * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU; + * - dl_total_bw array contains, in the i-eth element, the currently + * allocated bandwidth on the i-eth CPU. + * Moreover, groups consume bandwidth on each CPU, while tasks only + * consume bandwidth on the CPU they're running on. + * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw + * that will be shown the next time the proc or cgroup controls will + * be red. It on its turn can be changed by writing on its own + * control. + */ +struct dl_bandwidth { + raw_spinlock_t dl_runtime_lock; + u64 dl_runtime; + u64 dl_period; +}; + +static inline int dl_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + +extern struct dl_bw *dl_bw_of(int i); + +struct dl_bw { + raw_spinlock_t lock; + u64 bw, total_bw; +}; + +static inline +void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw -= tsk_bw; +} + +static inline +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw += tsk_bw; +} + +static inline +bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) +{ + return dl_b->bw != -1 && + dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; +} + +extern struct mutex sched_domains_mutex; + +#ifdef CONFIG_CGROUP_SCHED + +#include <linux/cgroup.h> + +struct cfs_rq; +struct rt_rq; + +extern struct list_head task_groups; + +struct cfs_bandwidth { +#ifdef CONFIG_CFS_BANDWIDTH + raw_spinlock_t lock; + ktime_t period; + u64 quota, runtime; + s64 hierarchical_quota; + u64 runtime_expires; + + int idle, timer_active; + struct hrtimer period_timer, slack_timer; + struct list_head throttled_cfs_rq; + + /* statistics */ + int nr_periods, nr_throttled; + u64 throttled_time; +#endif +}; + +/* task group related information */ +struct task_group { + struct cgroup_subsys_state css; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* schedulable entities of this group on each cpu */ + struct sched_entity **se; + /* runqueue "owned" by this group on each cpu */ + struct cfs_rq **cfs_rq; + unsigned long shares; + +#ifdef CONFIG_SMP + atomic_long_t load_avg; + atomic_t runnable_avg; +#endif +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + struct sched_rt_entity **rt_se; + struct rt_rq **rt_rq; + + struct rt_bandwidth rt_bandwidth; +#endif + + struct rcu_head rcu; + struct list_head list; + + struct task_group *parent; + struct list_head siblings; + struct list_head children; + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif + + struct cfs_bandwidth cfs_bandwidth; +}; + +#ifdef CONFIG_FAIR_GROUP_SCHED +#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD + +/* + * A weight of 0 or 1 can cause arithmetics problems. + * A weight of a cfs_rq is the sum of weights of which entities + * are queued on this cfs_rq, so a weight of a entity should not be + * too large, so as the shares value of a task group. + * (The default weight is 1024 - so there's no practical + * limitation from this.) + */ +#define MIN_SHARES (1UL << 1) +#define MAX_SHARES (1UL << 18) +#endif + +typedef int (*tg_visitor)(struct task_group *, void *); + +extern int walk_tg_tree_from(struct task_group *from, + tg_visitor down, tg_visitor up, void *data); + +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. + */ +static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) +{ + return walk_tg_tree_from(&root_task_group, down, up, data); +} + +extern int tg_nop(struct task_group *tg, void *data); + +extern void free_fair_sched_group(struct task_group *tg); +extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent); +extern void unregister_fair_sched_group(struct task_group *tg, int cpu); +extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, + struct sched_entity *parent); +extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); + +extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); +extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force); +extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); + +extern void free_rt_sched_group(struct task_group *tg); +extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent); +extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, + struct sched_rt_entity *rt_se, int cpu, + struct sched_rt_entity *parent); + +extern struct task_group *sched_create_group(struct task_group *parent); +extern void sched_online_group(struct task_group *tg, + struct task_group *parent); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_offline_group(struct task_group *tg); + +extern void sched_move_task(struct task_struct *tsk); + +#ifdef CONFIG_FAIR_GROUP_SCHED +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +#endif + +#else /* CONFIG_CGROUP_SCHED */ + +struct cfs_bandwidth { }; + +#endif /* CONFIG_CGROUP_SCHED */ + +/* CFS-related fields in a runqueue */ +struct cfs_rq { + struct load_weight load; + unsigned int nr_running, h_nr_running; + + u64 exec_clock; + u64 min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; +#endif + + struct rb_root tasks_timeline; + struct rb_node *rb_leftmost; + + /* + * 'curr' points to currently running entity on this cfs_rq. + * It is set to NULL otherwise (i.e when none are currently running). + */ + struct sched_entity *curr, *next, *last, *skip; + +#ifdef CONFIG_SCHED_DEBUG + unsigned int nr_spread_over; +#endif + +#ifdef CONFIG_SMP + /* + * CFS Load tracking + * Under CFS, load is tracked on a per-entity basis and aggregated up. + * This allows for the description of both thread and group usage (in + * the FAIR_GROUP_SCHED case). + * runnable_load_avg is the sum of the load_avg_contrib of the + * sched_entities on the rq. + * blocked_load_avg is similar to runnable_load_avg except that its + * the blocked sched_entities on the rq. + * utilization_load_avg is the sum of the average running time of the + * sched_entities on the rq. + */ + unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg; + atomic64_t decay_counter; + u64 last_decay; + atomic_long_t removed_load; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* Required to track per-cpu representation of a task_group */ + u32 tg_runnable_contrib; + unsigned long tg_load_contrib; + + /* + * h_load = weight * f(tg) + * + * Where f(tg) is the recursive weight fraction assigned to + * this group. + */ + unsigned long h_load; + u64 last_h_load_update; + struct sched_entity *h_load_next; +#endif /* CONFIG_FAIR_GROUP_SCHED */ +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_FAIR_GROUP_SCHED + struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ + + /* + * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in + * a hierarchy). Non-leaf lrqs hold other higher schedulable entities + * (like users, containers etc.) + * + * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This + * list is used during load balance. + */ + int on_list; + struct list_head leaf_cfs_rq_list; + struct task_group *tg; /* group that "owns" this runqueue */ + +#ifdef CONFIG_CFS_BANDWIDTH + int runtime_enabled; + u64 runtime_expires; + s64 runtime_remaining; + + u64 throttled_clock, throttled_clock_task; + u64 throttled_clock_task_time; + int throttled, throttle_count; + struct list_head throttled_list; +#endif /* CONFIG_CFS_BANDWIDTH */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ +}; + +static inline int rt_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + +/* RT IPI pull logic requires IRQ_WORK */ +#ifdef CONFIG_IRQ_WORK +# define HAVE_RT_PUSH_IPI +#endif + +/* Real-Time classes' related field in a runqueue: */ +struct rt_rq { + struct rt_prio_array active; + unsigned int rt_nr_running; +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED + struct { + int curr; /* highest queued rt task prio */ +#ifdef CONFIG_SMP + int next; /* next highest */ +#endif + } highest_prio; +#endif +#ifdef CONFIG_SMP + unsigned long rt_nr_migratory; + unsigned long rt_nr_total; + int overloaded; + struct plist_head pushable_tasks; +#ifdef HAVE_RT_PUSH_IPI + int push_flags; + int push_cpu; + struct irq_work push_work; + raw_spinlock_t push_lock; +#endif +#endif /* CONFIG_SMP */ + int rt_queued; + + int rt_throttled; + u64 rt_time; + u64 rt_runtime; + /* Nests inside the rq lock: */ + raw_spinlock_t rt_runtime_lock; + +#ifdef CONFIG_RT_GROUP_SCHED + unsigned long rt_nr_boosted; + + struct rq *rq; + struct task_group *tg; +#endif +}; + +/* Deadline class' related fields in a runqueue */ +struct dl_rq { + /* runqueue is an rbtree, ordered by deadline */ + struct rb_root rb_root; + struct rb_node *rb_leftmost; + + unsigned long dl_nr_running; + +#ifdef CONFIG_SMP + /* + * Deadline values of the currently executing and the + * earliest ready task on this rq. Caching these facilitates + * the decision wether or not a ready but not running task + * should migrate somewhere else. + */ + struct { + u64 curr; + u64 next; + } earliest_dl; + + unsigned long dl_nr_migratory; + int overloaded; + + /* + * Tasks on this rq that can be pushed away. They are kept in + * an rb-tree, ordered by tasks' deadlines, with caching + * of the leftmost (earliest deadline) element. + */ + struct rb_root pushable_dl_tasks_root; + struct rb_node *pushable_dl_tasks_leftmost; +#else + struct dl_bw dl_bw; +#endif +}; + +#ifdef CONFIG_SMP + +/* + * We add the notion of a root-domain which will be used to define per-domain + * variables. Each exclusive cpuset essentially defines an island domain by + * fully partitioning the member cpus from any other cpuset. Whenever a new + * exclusive cpuset is created, we also create and attach a new root-domain + * object. + * + */ +struct root_domain { + atomic_t refcount; + atomic_t rto_count; + struct rcu_head rcu; + cpumask_var_t span; + cpumask_var_t online; + + /* Indicate more than one runnable task for any CPU */ + bool overload; + + /* + * The bit corresponding to a CPU gets set here if such CPU has more + * than one runnable -deadline task (as it is below for RT tasks). + */ + cpumask_var_t dlo_mask; + atomic_t dlo_count; + struct dl_bw dl_bw; + struct cpudl cpudl; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_var_t rto_mask; + struct cpupri cpupri; +}; + +extern struct root_domain def_root_domain; + +#endif /* CONFIG_SMP */ + +/* + * This is the main, per-CPU runqueue data structure. + * + * Locking rule: those places that want to lock multiple runqueues + * (such as the load balancing or the thread migration code), lock + * acquire operations must be ordered by ascending &runqueue. + */ +struct rq { + /* runqueue lock: */ + raw_spinlock_t lock; + + /* + * nr_running and cpu_load should be in the same cacheline because + * remote CPUs use both these fields when doing load calculation. + */ + unsigned int nr_running; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif + #define CPU_LOAD_IDX_MAX 5 + unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long last_load_update_tick; +#ifdef CONFIG_NO_HZ_COMMON + u64 nohz_stamp; + unsigned long nohz_flags; +#endif +#ifdef CONFIG_NO_HZ_FULL + unsigned long last_sched_tick; +#endif + /* capture load from *all* tasks on this cpu: */ + struct load_weight load; + unsigned long nr_load_updates; + u64 nr_switches; + + struct cfs_rq cfs; + struct rt_rq rt; + struct dl_rq dl; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* list of leaf cfs_rq on this cpu: */ + struct list_head leaf_cfs_rq_list; + + struct sched_avg avg; +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + /* + * This is part of a global counter where only the total sum + * over all CPUs matters. A task can increase this counter on + * one CPU and if it got migrated afterwards it may decrease + * it on another CPU. Always updated under the runqueue lock: + */ + unsigned long nr_uninterruptible; + + struct task_struct *curr, *idle, *stop; + unsigned long next_balance; + struct mm_struct *prev_mm; + + unsigned int clock_skip_update; + u64 clock; + u64 clock_task; + + atomic_t nr_iowait; + +#ifdef CONFIG_SMP + struct root_domain *rd; + struct sched_domain *sd; + + unsigned long cpu_capacity; + unsigned long cpu_capacity_orig; + + unsigned char idle_balance; + /* For active balancing */ + int post_schedule; + int active_balance; + int push_cpu; + struct cpu_stop_work active_balance_work; + /* cpu of this runqueue: */ + int cpu; + int online; + + struct list_head cfs_tasks; + + u64 rt_avg; + u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; + + /* This is used to determine avg_idle's max value */ + u64 max_idle_balance_cost; +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif + + /* calc_load related fields */ + unsigned long calc_load_update; + long calc_load_active; + +#ifdef CONFIG_SCHED_HRTICK +#ifdef CONFIG_SMP + int hrtick_csd_pending; + struct call_single_data hrtick_csd; +#endif + struct hrtimer hrtick_timer; +#endif + +#ifdef CONFIG_SCHEDSTATS + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; +#endif + +#ifdef CONFIG_SMP + struct llist_head wake_list; +#endif + +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif +}; + +static inline int cpu_of(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq->cpu; +#else + return 0; +#endif +} + +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) +#define this_rq() this_cpu_ptr(&runqueues) +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) +#define raw_rq() raw_cpu_ptr(&runqueues) + +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return ACCESS_ONCE(rq->clock); +} + +static inline u64 rq_clock(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + return rq->clock_task; +} + +#define RQCF_REQ_SKIP 0x01 +#define RQCF_ACT_SKIP 0x02 + +static inline void rq_clock_skip_update(struct rq *rq, bool skip) +{ + lockdep_assert_held(&rq->lock); + if (skip) + rq->clock_skip_update |= RQCF_REQ_SKIP; + else + rq->clock_skip_update &= ~RQCF_REQ_SKIP; +} + +#ifdef CONFIG_NUMA +enum numa_topology_type { + NUMA_DIRECT, + NUMA_GLUELESS_MESH, + NUMA_BACKPLANE, +}; +extern enum numa_topology_type sched_numa_topology_type; +extern int sched_max_numa_distance; +extern bool find_numa_distance(int distance); +#endif + +#ifdef CONFIG_NUMA_BALANCING +/* The regions in numa_faults array from task_struct */ +enum numa_faults_stats { + NUMA_MEM = 0, + NUMA_CPU, + NUMA_MEMBUF, + NUMA_CPUBUF +}; +extern void sched_setnuma(struct task_struct *p, int node); +extern int migrate_task_to(struct task_struct *p, int cpu); +extern int migrate_swap(struct task_struct *, struct task_struct *); +#endif /* CONFIG_NUMA_BALANCING */ + +#ifdef CONFIG_SMP + +extern void sched_ttwu_pending(void); + +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + lockdep_is_held(&sched_domains_mutex)) + +/* + * The domain tree (rq->sd) is protected by RCU's quiescent state transition. + * See detach_destroy_domains: synchronize_sched for details. + * + * The domain tree of any CPU may only be accessed from within + * preempt-disabled sections. + */ +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \ + __sd; __sd = __sd->parent) + +#define for_each_lower_domain(sd) for (; sd; sd = sd->child) + +/** + * highest_flag_domain - Return highest sched_domain containing flag. + * @cpu: The cpu whose highest level of sched domain is to + * be returned. + * @flag: The flag to check for the highest sched_domain + * for the given cpu. + * + * Returns the highest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *highest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd, *hsd = NULL; + + for_each_domain(cpu, sd) { + if (!(sd->flags & flag)) + break; + hsd = sd; + } + + return hsd; +} + +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + if (sd->flags & flag) + break; + } + + return sd; +} + +DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(int, sd_llc_size); +DECLARE_PER_CPU(int, sd_llc_id); +DECLARE_PER_CPU(struct sched_domain *, sd_numa); +DECLARE_PER_CPU(struct sched_domain *, sd_busy); +DECLARE_PER_CPU(struct sched_domain *, sd_asym); + +struct sched_group_capacity { + atomic_t ref; + /* + * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * for a single CPU. + */ + unsigned int capacity; + unsigned long next_update; + int imbalance; /* XXX unrelated to capacity but shared group state */ + /* + * Number of busy cpus in this group. + */ + atomic_t nr_busy_cpus; + + unsigned long cpumask[0]; /* iteration mask */ +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + + unsigned int group_weight; + struct sched_group_capacity *sgc; + + /* + * The CPUs this group covers. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long cpumask[0]; +}; + +static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +{ + return to_cpumask(sg->cpumask); +} + +/* + * cpumask masking which cpus in the group are allowed to iterate up the domain + * tree. + */ +static inline struct cpumask *sched_group_mask(struct sched_group *sg) +{ + return to_cpumask(sg->sgc->cpumask); +} + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. + */ +static inline unsigned int group_first_cpu(struct sched_group *group) +{ + return cpumask_first(sched_group_cpus(group)); +} + +extern int group_balance_cpu(struct sched_group *sg); + +#else + +static inline void sched_ttwu_pending(void) { } + +#endif /* CONFIG_SMP */ + +#include "stats.h" +#include "auto_group.h" + +#ifdef CONFIG_CGROUP_SCHED + +/* + * Return the group to which this tasks belongs. + * + * We cannot use task_css() and friends because the cgroup subsystem + * changes that value before the cgroup_subsys::attach() method is called, + * therefore we cannot pin it and might observe the wrong value. + * + * The same is true for autogroup's p->signal->autogroup->tg, the autogroup + * core changes this before calling sched_move_task(). + * + * Instead we use a 'copy' which is updated from sched_move_task() while + * holding both task_struct::pi_lock and rq::lock. + */ +static inline struct task_group *task_group(struct task_struct *p) +{ + return p->sched_task_group; +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) +{ +#if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED) + struct task_group *tg = task_group(p); +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = tg->cfs_rq[cpu]; + p->se.parent = tg->se[cpu]; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + p->rt.rt_rq = tg->rt_rq[cpu]; + p->rt.parent = tg->rt_se[cpu]; +#endif +} + +#else /* CONFIG_CGROUP_SCHED */ + +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} + +#endif /* CONFIG_CGROUP_SCHED */ + +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + set_task_rq(p, cpu); +#ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + task_thread_info(p)->cpu = cpu; + p->wake_cpu = cpu; +#endif +} + +/* + * Tunables that become constants when CONFIG_SCHED_DEBUG is off: + */ +#ifdef CONFIG_SCHED_DEBUG +# include <linux/static_key.h> +# define const_debug __read_mostly +#else +# define const_debug const +#endif + +extern const_debug unsigned int sysctl_sched_features; + +#define SCHED_FEAT(name, enabled) \ + __SCHED_FEAT_##name , + +enum { +#include "features.h" + __SCHED_FEAT_NR, +}; + +#undef SCHED_FEAT + +#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) +#define SCHED_FEAT(name, enabled) \ +static __always_inline bool static_branch_##name(struct static_key *key) \ +{ \ + return static_key_##enabled(key); \ +} + +#include "features.h" + +#undef SCHED_FEAT + +extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; +#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) +#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */ +#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) +#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ + +#ifdef CONFIG_NUMA_BALANCING +#define sched_feat_numa(x) sched_feat(x) +#ifdef CONFIG_SCHED_DEBUG +#define numabalancing_enabled sched_feat_numa(NUMA) +#else +extern bool numabalancing_enabled; +#endif /* CONFIG_SCHED_DEBUG */ +#else +#define sched_feat_numa(x) (0) +#define numabalancing_enabled (0) +#endif /* CONFIG_NUMA_BALANCING */ + +static inline u64 global_rt_period(void) +{ + return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; +} + +static inline u64 global_rt_runtime(void) +{ + if (sysctl_sched_rt_runtime < 0) + return RUNTIME_INF; + + return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; +} + +static inline int task_current(struct rq *rq, struct task_struct *p) +{ + return rq->curr == p; +} + +static inline int task_running(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_SMP + return p->on_cpu; +#else + return task_current(rq, p); +#endif +} + +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_QUEUED; +} + +static inline int task_on_rq_migrating(struct task_struct *p) +{ + return p->on_rq == TASK_ON_RQ_MIGRATING; +} + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_switch +# define finish_arch_switch(prev) do { } while (0) +#endif +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + rq->lock.owner = current; +#endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); + + raw_spin_unlock_irq(&rq->lock); +} + +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ + +/* + * To aid in avoiding the subversion of "niceness" due to uneven distribution + * of tasks with abnormal "nice" values across CPUs the contribution that + * each task makes to its run queue's load is weighted according to its + * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a + * scaled version of the new time slice allocation that they receive on time + * slice expiry etc. + */ + +#define WEIGHT_IDLEPRIO 3 +#define WMULT_IDLEPRIO 1431655765 + +/* + * Nice levels are multiplicative, with a gentle 10% change for every + * nice level changed. I.e. when a CPU-bound task goes from nice 0 to + * nice 1, it will get ~10% less CPU time than another CPU-bound task + * that remained on nice 0. + * + * The "10% effect" is relative and cumulative: from _any_ nice level, + * if you go up 1 level, it's -10% CPU usage, if you go down 1 level + * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. + * If a task goes up by ~10% and another task goes down by ~10% then + * the relative distance between them is ~25%.) + */ +static const int prio_to_weight[40] = { + /* -20 */ 88761, 71755, 56483, 46273, 36291, + /* -15 */ 29154, 23254, 18705, 14949, 11916, + /* -10 */ 9548, 7620, 6100, 4904, 3906, + /* -5 */ 3121, 2501, 1991, 1586, 1277, + /* 0 */ 1024, 820, 655, 526, 423, + /* 5 */ 335, 272, 215, 172, 137, + /* 10 */ 110, 87, 70, 56, 45, + /* 15 */ 36, 29, 23, 18, 15, +}; + +/* + * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. + * + * In cases where the weight does not change often, we can use the + * precalculated inverse to speed up arithmetics by turning divisions + * into multiplications: + */ +static const u32 prio_to_wmult[40] = { + /* -20 */ 48388, 59856, 76040, 92818, 118348, + /* -15 */ 147320, 184698, 229616, 287308, 360437, + /* -10 */ 449829, 563644, 704093, 875809, 1099582, + /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, + /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, + /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, + /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, + /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, +}; + +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif +#define ENQUEUE_REPLENISH 8 + +#define DEQUEUE_SLEEP 1 + +#define RETRY_TASK ((void *)-1UL) + +struct sched_class { + const struct sched_class *next; + + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*yield_task) (struct rq *rq); + bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); + + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); + + /* + * It is the responsibility of the pick_next_task() method that will + * return the next task to call put_prev_task() on the @prev task or + * something equivalent. + * + * May return RETRY_TASK when it finds a higher prio class has runnable + * tasks. + */ + struct task_struct * (*pick_next_task) (struct rq *rq, + struct task_struct *prev); + void (*put_prev_task) (struct rq *rq, struct task_struct *p); + +#ifdef CONFIG_SMP + int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); + void (*migrate_task_rq)(struct task_struct *p, int next_cpu); + + void (*post_schedule) (struct rq *this_rq); + void (*task_waking) (struct task_struct *task); + void (*task_woken) (struct rq *this_rq, struct task_struct *task); + + void (*set_cpus_allowed)(struct task_struct *p, + const struct cpumask *newmask); + + void (*rq_online)(struct rq *rq); + void (*rq_offline)(struct rq *rq); +#endif + + void (*set_curr_task) (struct rq *rq); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); + void (*task_fork) (struct task_struct *p); + void (*task_dead) (struct task_struct *p); + + /* + * The switched_from() call is allowed to drop rq->lock, therefore we + * cannot assume the switched_from/switched_to pair is serliazed by + * rq->lock. They are however serialized by p->pi_lock. + */ + void (*switched_from) (struct rq *this_rq, struct task_struct *task); + void (*switched_to) (struct rq *this_rq, struct task_struct *task); + void (*prio_changed) (struct rq *this_rq, struct task_struct *task, + int oldprio); + + unsigned int (*get_rr_interval) (struct rq *rq, + struct task_struct *task); + + void (*update_curr) (struct rq *rq); + +#ifdef CONFIG_FAIR_GROUP_SCHED + void (*task_move_group) (struct task_struct *p, int on_rq); +#endif +}; + +static inline void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + prev->sched_class->put_prev_task(rq, prev); +} + +#define sched_class_highest (&stop_sched_class) +#define for_each_class(class) \ + for (class = sched_class_highest; class; class = class->next) + +extern const struct sched_class stop_sched_class; +extern const struct sched_class dl_sched_class; +extern const struct sched_class rt_sched_class; +extern const struct sched_class fair_sched_class; +extern const struct sched_class idle_sched_class; + + +#ifdef CONFIG_SMP + +extern void update_group_capacity(struct sched_domain *sd, int cpu); + +extern void trigger_load_balance(struct rq *rq); + +extern void idle_enter_fair(struct rq *this_rq); +extern void idle_exit_fair(struct rq *this_rq); + +#else + +static inline void idle_enter_fair(struct rq *rq) { } +static inline void idle_exit_fair(struct rq *rq) { } + +#endif + +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif + +extern void sysrq_sched_debug_show(void); +extern void sched_init_granularity(void); +extern void update_max_interval(void); + +extern void init_sched_dl_class(void); +extern void init_sched_rt_class(void); +extern void init_sched_fair_class(void); +extern void init_sched_dl_class(void); + +extern void resched_curr(struct rq *rq); +extern void resched_cpu(int cpu); + +extern struct rt_bandwidth def_rt_bandwidth; +extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +extern struct dl_bandwidth def_dl_bandwidth; +extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); +extern void init_dl_task_timer(struct sched_dl_entity *dl_se); + +unsigned long to_ratio(u64 period, u64 runtime); + +extern void update_idle_cpu_load(struct rq *this_rq); + +extern void init_task_runnable_average(struct task_struct *p); + +static inline void add_nr_running(struct rq *rq, unsigned count) +{ + unsigned prev_nr = rq->nr_running; + + rq->nr_running = prev_nr + count; + + if (prev_nr < 2 && rq->nr_running >= 2) { +#ifdef CONFIG_SMP + if (!rq->rd->overload) + rq->rd->overload = true; +#endif + +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(rq->cpu)) { + /* + * Tick is needed if more than one task runs on a CPU. + * Send the target an IPI to kick it out of nohz mode. + * + * We assume that IPI implies full memory barrier and the + * new value of rq->nr_running is visible on reception + * from the target. + */ + tick_nohz_full_kick_cpu(rq->cpu); + } +#endif + } +} + +static inline void sub_nr_running(struct rq *rq, unsigned count) +{ + rq->nr_running -= count; +} + +static inline void rq_last_tick_reset(struct rq *rq) +{ +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = jiffies; +#endif +} + +extern void update_rq_clock(struct rq *rq); + +extern void activate_task(struct rq *rq, struct task_struct *p, int flags); +extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); + +extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); + +extern const_debug unsigned int sysctl_sched_time_avg; +extern const_debug unsigned int sysctl_sched_nr_migrate; +extern const_debug unsigned int sysctl_sched_migration_cost; + +static inline u64 sched_avg_period(void) +{ + return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; +} + +#ifdef CONFIG_SCHED_HRTICK + +/* + * Use hrtick when: + * - enabled by features + * - hrtimer is actually high res + */ +static inline int hrtick_enabled(struct rq *rq) +{ + if (!sched_feat(HRTICK)) + return 0; + if (!cpu_active(cpu_of(rq))) + return 0; + return hrtimer_is_hres_active(&rq->hrtick_timer); +} + +void hrtick_start(struct rq *rq, u64 delay); + +#else + +static inline int hrtick_enabled(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SCHED_HRTICK */ + +#ifdef CONFIG_SMP +extern void sched_avg_update(struct rq *rq); + +#ifndef arch_scale_freq_capacity +static __always_inline +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); + sched_avg_update(rq); +} +#else +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } +static inline void sched_avg_update(struct rq *rq) { } +#endif + +extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period); + +/* + * __task_rq_lock - lock the rq @p resides on. + */ +static inline struct rq *__task_rq_lock(struct task_struct *p) + __acquires(rq->lock) +{ + struct rq *rq; + + lockdep_assert_held(&p->pi_lock); + + for (;;) { + rq = task_rq(p); + raw_spin_lock(&rq->lock); + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +/* + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. + */ +static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + raw_spin_lock_irqsave(&p->pi_lock, *flags); + rq = task_rq(p); + raw_spin_lock(&rq->lock); + /* + * move_queued_task() task_rq_lock() + * + * ACQUIRE (rq->lock) + * [S] ->on_rq = MIGRATING [L] rq = task_rq() + * WMB (__set_task_cpu()) ACQUIRE (rq->lock); + * [S] ->cpu = new_cpu [L] task_rq() + * [L] ->on_rq + * RELEASE (rq->lock) + * + * If we observe the old cpu in task_rq_lock, the acquire of + * the old rq->lock will fully serialize against the stores. + * + * If we observe the new cpu in task_rq_lock, the acquire will + * pair with the WMB to ensure we must then also see migrating. + */ + if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) + return rq; + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); + + while (unlikely(task_on_rq_migrating(p))) + cpu_relax(); + } +} + +static inline void __task_rq_unlock(struct rq *rq) + __releases(rq->lock) +{ + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) + __releases(rq->lock) + __releases(p->pi_lock) +{ + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_PREEMPT + +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); + +/* + * fair double_lock_balance: Safely acquires both rq->locks in a fair + * way at the expense of forcing extra atomic operations in all + * invocations. This assures that the double_lock is acquired using the + * same underlying policy as the spinlock_t on this architecture, which + * reduces latency compared to the unfair variant below. However, it + * also adds more overhead and therefore may reduce throughput. + */ +static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + raw_spin_unlock(&this_rq->lock); + double_rq_lock(this_rq, busiest); + + return 1; +} + +#else +/* + * Unfair double_lock_balance: Optimizes throughput at the expense of + * latency by eliminating extra atomic operations when the locks are + * already in proper order on entry. This favors lower cpu-ids and will + * grant the double lock to lower cpus over higher ids under contention, + * regardless of entry order into the function. + */ +static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + int ret = 0; + + if (unlikely(!raw_spin_trylock(&busiest->lock))) { + if (busiest < this_rq) { + raw_spin_unlock(&this_rq->lock); + raw_spin_lock(&busiest->lock); + raw_spin_lock_nested(&this_rq->lock, + SINGLE_DEPTH_NESTING); + ret = 1; + } else + raw_spin_lock_nested(&busiest->lock, + SINGLE_DEPTH_NESTING); + } + return ret; +} + +#endif /* CONFIG_PREEMPT */ + +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest) +{ + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + raw_spin_unlock(&this_rq->lock); + BUG_ON(1); + } + + return _double_lock_balance(this_rq, busiest); +} + +static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + raw_spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} + +static inline void double_lock(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock_irq(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + raw_spin_lock(l1); + raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + if (rq1 == rq2) { + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ + } else { + if (rq1 < rq2) { + raw_spin_lock(&rq1->lock); + raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); + } else { + raw_spin_lock(&rq2->lock); + raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); + } + } +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + raw_spin_unlock(&rq1->lock); + if (rq1 != rq2) + raw_spin_unlock(&rq2->lock); + else + __release(rq2->lock); +} + +#else /* CONFIG_SMP */ + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + BUG_ON(rq1 != rq2); + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + BUG_ON(rq1 != rq2); + raw_spin_unlock(&rq1->lock); + __release(rq2->lock); +} + +#endif + +extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); +extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); +extern void print_cfs_stats(struct seq_file *m, int cpu); +extern void print_rt_stats(struct seq_file *m, int cpu); +extern void print_dl_stats(struct seq_file *m, int cpu); + +extern void init_cfs_rq(struct cfs_rq *cfs_rq); +extern void init_rt_rq(struct rt_rq *rt_rq); +extern void init_dl_rq(struct dl_rq *dl_rq); + +extern void cfs_bandwidth_usage_inc(void); +extern void cfs_bandwidth_usage_dec(void); + +#ifdef CONFIG_NO_HZ_COMMON +enum rq_nohz_flag_bits { + NOHZ_TICK_STOPPED, + NOHZ_BALANCE_KICK, +}; + +#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +DECLARE_PER_CPU(u64, cpu_hardirq_time); +DECLARE_PER_CPU(u64, cpu_softirq_time); + +#ifndef CONFIG_64BIT +DECLARE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c new file mode 100644 index 000000000..7466a0bb2 --- /dev/null +++ b/kernel/sched/stats.c @@ -0,0 +1,142 @@ + +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> + +#ifndef CONFIG_SCHED_BFS +#include "sched.h" +#else +#include "bfs_sched.h" +#endif + +/* + * bump this up when changing the output format or the meaning of an existing + * format, so that tools can adapt (or abort) + */ +#define SCHEDSTAT_VERSION 15 + +static int show_schedstat(struct seq_file *seq, void *v) +{ + int cpu; + + if (v == (void *)1) { + seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); + seq_printf(seq, "timestamp %lu\n", jiffies); + } else { + struct rq *rq; +#ifdef CONFIG_SMP + struct sched_domain *sd; + int dcount = 0; +#endif + cpu = (unsigned long)(v - 2); + rq = cpu_rq(cpu); + + /* runqueue-specific stats */ + seq_printf(seq, + "cpu%d %u 0 %u %u %u %u %llu %llu %lu", + cpu, rq->yld_count, + rq->sched_count, rq->sched_goidle, + rq->ttwu_count, rq->ttwu_local, + rq->rq_cpu_time, + rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount); + + seq_printf(seq, "\n"); + +#ifdef CONFIG_SMP + /* domain-specific stats */ + rcu_read_lock(); + for_each_domain(cpu, sd) { + enum cpu_idle_type itype; + + seq_printf(seq, "domain%d %*pb", dcount++, + cpumask_pr_args(sched_domain_span(sd))); + for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; + itype++) { + seq_printf(seq, " %u %u %u %u %u %u %u %u", + sd->lb_count[itype], + sd->lb_balanced[itype], + sd->lb_failed[itype], + sd->lb_imbalance[itype], + sd->lb_gained[itype], + sd->lb_hot_gained[itype], + sd->lb_nobusyq[itype], + sd->lb_nobusyg[itype]); + } + seq_printf(seq, + " %u %u %u %u %u %u %u %u %u %u %u %u\n", + sd->alb_count, sd->alb_failed, sd->alb_pushed, + sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed, + sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed, + sd->ttwu_wake_remote, sd->ttwu_move_affine, + sd->ttwu_move_balance); + } + rcu_read_unlock(); +#endif + } + return 0; +} + +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *schedstat_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *schedstat_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return schedstat_start(file, offset); +} + +static void schedstat_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations schedstat_sops = { + .start = schedstat_start, + .next = schedstat_next, + .stop = schedstat_stop, + .show = show_schedstat, +}; + +static int schedstat_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &schedstat_sops); +} + +static const struct file_operations proc_schedstat_operations = { + .open = schedstat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_schedstat_init(void) +{ + proc_create("schedstat", 0, NULL, &proc_schedstat_operations); + return 0; +} +subsys_initcall(proc_schedstat_init); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h new file mode 100644 index 000000000..4ab704339 --- /dev/null +++ b/kernel/sched/stats.h @@ -0,0 +1,267 @@ + +#ifdef CONFIG_SCHEDSTATS + +/* + * Expects runqueue lock to be held for atomicity of update + */ +static inline void +rq_sched_info_arrive(struct rq *rq, unsigned long long delta) +{ + if (rq) { + rq->rq_sched_info.run_delay += delta; + rq->rq_sched_info.pcount++; + } +} + +/* + * Expects runqueue lock to be held for atomicity of update + */ +static inline void +rq_sched_info_depart(struct rq *rq, unsigned long long delta) +{ + if (rq) + rq->rq_cpu_time += delta; +} + +static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{ + if (rq) + rq->rq_sched_info.run_delay += delta; +} +# define schedstat_inc(rq, field) do { (rq)->field++; } while (0) +# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) +# define schedstat_set(var, val) do { var = (val); } while (0) +#else /* !CONFIG_SCHEDSTATS */ +static inline void +rq_sched_info_arrive(struct rq *rq, unsigned long long delta) +{} +static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{} +static inline void +rq_sched_info_depart(struct rq *rq, unsigned long long delta) +{} +# define schedstat_inc(rq, field) do { } while (0) +# define schedstat_add(rq, field, amt) do { } while (0) +# define schedstat_set(var, val) do { } while (0) +#endif + +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +static inline void sched_info_reset_dequeued(struct task_struct *t) +{ + t->sched_info.last_queued = 0; +} + +/* + * We are interested in knowing how long it was from the *first* time a + * task was queued to the time that it finally hit a cpu, we call this routine + * from dequeue_task() to account for possible rq->clock skew across cpus. The + * delta taken on each cpu would annul the skew. + */ +static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t) +{ + unsigned long long now = rq_clock(rq), delta = 0; + + if (unlikely(sched_info_on())) + if (t->sched_info.last_queued) + delta = now - t->sched_info.last_queued; + sched_info_reset_dequeued(t); + t->sched_info.run_delay += delta; + + rq_sched_info_dequeued(rq, delta); +} + +/* + * Called when a task finally hits the cpu. We can now calculate how + * long it was waiting to run. We also note when it began so that we + * can keep stats on how long its timeslice is. + */ +static void sched_info_arrive(struct rq *rq, struct task_struct *t) +{ + unsigned long long now = rq_clock(rq), delta = 0; + + if (t->sched_info.last_queued) + delta = now - t->sched_info.last_queued; + sched_info_reset_dequeued(t); + t->sched_info.run_delay += delta; + t->sched_info.last_arrival = now; + t->sched_info.pcount++; + + rq_sched_info_arrive(rq, delta); +} + +/* + * This function is only called from enqueue_task(), but also only updates + * the timestamp if it is already not set. It's assumed that + * sched_info_dequeued() will clear that stamp when appropriate. + */ +static inline void sched_info_queued(struct rq *rq, struct task_struct *t) +{ + if (unlikely(sched_info_on())) + if (!t->sched_info.last_queued) + t->sched_info.last_queued = rq_clock(rq); +} + +/* + * Called when a process ceases being the active-running process involuntarily + * due, typically, to expiring its time slice (this may also be called when + * switching to the idle task). Now we can calculate how long we ran. + * Also, if the process is still in the TASK_RUNNING state, call + * sched_info_queued() to mark that it has now again started waiting on + * the runqueue. + */ +static inline void sched_info_depart(struct rq *rq, struct task_struct *t) +{ + unsigned long long delta = rq_clock(rq) - + t->sched_info.last_arrival; + + rq_sched_info_depart(rq, delta); + + if (t->state == TASK_RUNNING) + sched_info_queued(rq, t); +} + +/* + * Called when tasks are switched involuntarily due, typically, to expiring + * their time slice. (This may also be called when switching to or from + * the idle task.) We are only called when prev != next. + */ +static inline void +__sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) +{ + /* + * prev now departs the cpu. It's not interesting to record + * stats about how efficient we were at scheduling the idle + * process, however. + */ + if (prev != rq->idle) + sched_info_depart(rq, prev); + + if (next != rq->idle) + sched_info_arrive(rq, next); +} +static inline void +sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) +{ + if (unlikely(sched_info_on())) + __sched_info_switch(rq, prev, next); +} +#else +#define sched_info_queued(rq, t) do { } while (0) +#define sched_info_reset_dequeued(t) do { } while (0) +#define sched_info_dequeued(rq, t) do { } while (0) +#define sched_info_depart(rq, t) do { } while (0) +#define sched_info_arrive(rq, next) do { } while (0) +#define sched_info_switch(rq, t, next) do { } while (0) +#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ + +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +/** + * cputimer_running - return true if cputimer is running + * + * @tsk: Pointer to target task. + */ +static inline bool cputimer_running(struct task_struct *tsk) + +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer->running) + return false; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return false; + + return true; +} + +/** + * account_group_user_time - Maintain utime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.utime += cputime; + raw_spin_unlock(&cputimer->lock); +} + +/** + * account_group_system_time - Maintain stime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.stime += cputime; + raw_spin_unlock(&cputimer->lock); +} + +/** + * account_group_exec_runtime - Maintain exec runtime for a thread group. + * + * @tsk: Pointer to task structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of the thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer_running(tsk)) + return; + + raw_spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + raw_spin_unlock(&cputimer->lock); +} diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c new file mode 100644 index 000000000..79ffec45a --- /dev/null +++ b/kernel/sched/stop_task.c @@ -0,0 +1,136 @@ +#include "sched.h" + +/* + * stop-task scheduling class. + * + * The stop task is the highest priority task in the system, it preempts + * everything and will be preempted by nothing. + * + * See kernel/stop_machine.c + */ + +#ifdef CONFIG_SMP +static int +select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + return task_cpu(p); /* stop tasks as never migrate */ +} +#endif /* CONFIG_SMP */ + +static void +check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) +{ + /* we're never preempted */ +} + +static struct task_struct * +pick_next_task_stop(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *stop = rq->stop; + + if (!stop || !task_on_rq_queued(stop)) + return NULL; + + put_prev_task(rq, prev); + + stop->se.exec_start = rq_clock_task(rq); + + return stop; +} + +static void +enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) +{ + add_nr_running(rq, 1); +} + +static void +dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) +{ + sub_nr_running(rq, 1); +} + +static void yield_task_stop(struct rq *rq) +{ + BUG(); /* the stop task should never yield, its pointless. */ +} + +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) +{ + struct task_struct *curr = rq->curr; + u64 delta_exec; + + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec < 0)) + delta_exec = 0; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); +} + +static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) +{ +} + +static void set_curr_task_stop(struct rq *rq) +{ + struct task_struct *stop = rq->stop; + + stop->se.exec_start = rq_clock_task(rq); +} + +static void switched_to_stop(struct rq *rq, struct task_struct *p) +{ + BUG(); /* its impossible to change to this class */ +} + +static void +prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio) +{ + BUG(); /* how!?, what priority? */ +} + +static unsigned int +get_rr_interval_stop(struct rq *rq, struct task_struct *task) +{ + return 0; +} + +static void update_curr_stop(struct rq *rq) +{ +} + +/* + * Simple, special scheduling class for the per-CPU stop tasks: + */ +const struct sched_class stop_sched_class = { + .next = &dl_sched_class, + + .enqueue_task = enqueue_task_stop, + .dequeue_task = dequeue_task_stop, + .yield_task = yield_task_stop, + + .check_preempt_curr = check_preempt_curr_stop, + + .pick_next_task = pick_next_task_stop, + .put_prev_task = put_prev_task_stop, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_stop, +#endif + + .set_curr_task = set_curr_task_stop, + .task_tick = task_tick_stop, + + .get_rr_interval = get_rr_interval_stop, + + .prio_changed = prio_changed_stop, + .switched_to = switched_to_stop, + .update_curr = update_curr_stop, +}; diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c new file mode 100644 index 000000000..852143a79 --- /dev/null +++ b/kernel/sched/wait.c @@ -0,0 +1,624 @@ +/* + * Generic waiting primitives. + * + * (C) 2004 Nadia Yvette Chambers, Oracle + */ +#include <linux/init.h> +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/wait.h> +#include <linux/hash.h> +#include <linux/kthread.h> + +void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) +{ + spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} + +EXPORT_SYMBOL(__init_waitqueue_head); + +void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue); + +void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue_tail(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue_exclusive); + +void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __remove_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(remove_wait_queue); + + +/* + * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just + * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve + * number) then we wake all the non-exclusive tasks and one exclusive task. + * + * There are circumstances in which we can try to wake a task which has already + * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns + * zero in this (rare) case, and we handle it by continuing to scan the queue. + */ +static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int wake_flags, void *key) +{ + wait_queue_t *curr, *next; + + list_for_each_entry_safe(curr, next, &q->task_list, task_list) { + unsigned flags = curr->flags; + + if (curr->func(curr, mode, wake_flags, key) && + (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + break; + } +} + +/** + * __wake_up - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: is directly passed to the wakeup function + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void __wake_up(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(__wake_up); + +/* + * Same as __wake_up but called with the spinlock in wait_queue_head_t held. + */ +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) +{ + __wake_up_common(q, mode, nr, 0, NULL); +} +EXPORT_SYMBOL_GPL(__wake_up_locked); + +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +{ + __wake_up_common(q, mode, 1, 0, key); +} +EXPORT_SYMBOL_GPL(__wake_up_locked_key); + +/** + * __wake_up_sync_key - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: opaque value to be passed to wakeup targets + * + * The sync wakeup differs that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + int wake_flags = 1; /* XXX WF_SYNC */ + + if (unlikely(!q)) + return; + + if (unlikely(nr_exclusive != 1)) + wake_flags = 0; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, wake_flags, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(__wake_up_sync_key); + +/* + * __wake_up_sync - see __wake_up_sync_key() + */ +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + __wake_up_sync_key(q, mode, nr_exclusive, NULL); +} +EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ + +/* + * Note: we use "set_current_state()" _after_ the wait-queue add, + * because we need a memory barrier there on SMP, so that any + * wake-function that tests for the wait-queue being active + * will be guaranteed to see waitqueue addition _or_ subsequent + * tests in this thread will see the wakeup having taken place. + * + * The spin_unlock() itself is semi-permeable and only protects + * one way (it only protects stuff inside the critical region and + * stops them from bleeding out - it would still allow subsequent + * loads to move into the critical region). + */ +void +prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait); + +void +prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue_tail(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait_exclusive); + +long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + wait->private = current; + wait->func = autoremove_wake_function; + + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) { + if (wait->flags & WQ_FLAG_EXCLUSIVE) + __add_wait_queue_tail(q, wait); + else + __add_wait_queue(q, wait); + } + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); + + return 0; +} +EXPORT_SYMBOL(prepare_to_wait_event); + +/** + * finish_wait - clean up after waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + */ +void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + /* + * We can check for list emptiness outside the lock + * IFF: + * - we use the "careful" check that verifies both + * the next and prev pointers, so that there cannot + * be any half-pending updates in progress on other + * CPU's that we haven't seen yet (and that might + * still change the stack area. + * and + * - all other users take the lock (ie we can only + * have _one_ other CPU that looks at or modifies + * the list). + */ + if (!list_empty_careful(&wait->task_list)) { + spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_wait); + +/** + * abort_exclusive_wait - abort exclusive waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * @mode: runstate of the waiter to be woken + * @key: key to identify a wait bit queue or %NULL + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + * + * Wakes up the next waiter if the caller is concurrently + * woken up through the queue. + * + * This prevents waiter starvation where an exclusive waiter + * aborts and is woken up concurrently and no one wakes up + * the next waiter. + */ +void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, + unsigned int mode, void *key) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + spin_lock_irqsave(&q->lock, flags); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); + else if (waitqueue_active(q)) + __wake_up_locked_key(q, mode, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(abort_exclusive_wait); + +int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + + if (ret) + list_del_init(&wait->task_list); + return ret; +} +EXPORT_SYMBOL(autoremove_wake_function); + +static inline bool is_kthread_should_stop(void) +{ + return (current->flags & PF_KTHREAD) && kthread_should_stop(); +} + +/* + * DEFINE_WAIT_FUNC(wait, woken_wake_func); + * + * add_wait_queue(&wq, &wait); + * for (;;) { + * if (condition) + * break; + * + * p->state = mode; condition = true; + * smp_mb(); // A smp_wmb(); // C + * if (!wait->flags & WQ_FLAG_WOKEN) wait->flags |= WQ_FLAG_WOKEN; + * schedule() try_to_wake_up(); + * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ + * wait->flags &= ~WQ_FLAG_WOKEN; condition = true; + * smp_mb() // B smp_wmb(); // C + * wait->flags |= WQ_FLAG_WOKEN; + * } + * remove_wait_queue(&wq, &wait); + * + */ +long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) +{ + set_current_state(mode); /* A */ + /* + * The above implies an smp_mb(), which matches with the smp_wmb() from + * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must + * also observe all state before the wakeup. + */ + if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) + timeout = schedule_timeout(timeout); + __set_current_state(TASK_RUNNING); + + /* + * The below implies an smp_mb(), it too pairs with the smp_wmb() from + * woken_wake_function() such that we must either observe the wait + * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss + * an event. + */ + set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ + + return timeout; +} +EXPORT_SYMBOL(wait_woken); + +int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + /* + * Although this function is called under waitqueue lock, LOCK + * doesn't imply write barrier and the users expects write + * barrier semantics on wakeup functions. The following + * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() + * and is paired with set_mb() in wait_woken(). + */ + smp_wmb(); /* C */ + wait->flags |= WQ_FLAG_WOKEN; + + return default_wake_function(wait, mode, sync, key); +} +EXPORT_SYMBOL(woken_wake_function); + +int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + test_bit(key->bit_nr, key->flags)) + return 0; + else + return autoremove_wake_function(wait, mode, sync, key); +} +EXPORT_SYMBOL(wake_bit_function); + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) + * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are + * permitted return codes. Nonzero return codes halt waiting and return. + */ +int __sched +__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, + wait_bit_action_f *action, unsigned mode) +{ + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + if (test_bit(q->key.bit_nr, q->key.flags)) + ret = (*action)(&q->key); + } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); + finish_wait(wq, &q->wait); + return ret; +} +EXPORT_SYMBOL(__wait_on_bit); + +int __sched out_of_line_wait_on_bit(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit); + +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + wait.key.timeout = jiffies + timeout; + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + +int __sched +__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, + wait_bit_action_f *action, unsigned mode) +{ + do { + int ret; + + prepare_to_wait_exclusive(wq, &q->wait, mode); + if (!test_bit(q->key.bit_nr, q->key.flags)) + continue; + ret = action(&q->key); + if (!ret) + continue; + abort_exclusive_wait(wq, &q->wait, mode, &q->key); + return ret; + } while (test_and_set_bit(q->key.bit_nr, q->key.flags)); + finish_wait(wq, &q->wait); + return 0; +} +EXPORT_SYMBOL(__wait_on_bit_lock); + +int __sched out_of_line_wait_on_bit_lock(void *word, int bit, + wait_bit_action_f *action, unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit_lock(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); + +void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit) +{ + struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &key); +} +EXPORT_SYMBOL(__wake_up_bit); + +/** + * wake_up_bit - wake up a waiter on a bit + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that wakes up waiters + * on a bit. For instance, if one were to have waiters on a bitflag, + * one would call wake_up_bit() after clearing the bit. + * + * In order for this to function properly, as it uses waitqueue_active() + * internally, some kind of memory barrier must be done prior to calling + * this. Typically, this will be smp_mb__after_atomic(), but in some + * cases where bitflags are manipulated non-atomically under a lock, one + * may need to use a less regular barrier, such fs/inode.c's smp_mb(), + * because spin_unlock() does not guarantee a memory barrier. + */ +void wake_up_bit(void *word, int bit) +{ + __wake_up_bit(bit_waitqueue(word, bit), word, bit); +} +EXPORT_SYMBOL(wake_up_bit); + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + const struct zone *zone = page_zone(virt_to_page(word)); + unsigned long val = (unsigned long)word << shift | bit; + + return &zone->wait_table[hash_long(val, zone->wait_table_bits)]; +} +EXPORT_SYMBOL(bit_waitqueue); + +/* + * Manipulate the atomic_t address to produce a better bit waitqueue table hash + * index (we're keying off bit -1, but that would produce a horrible hash + * value). + */ +static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) +{ + if (BITS_PER_LONG == 64) { + unsigned long q = (unsigned long)p; + return bit_waitqueue((void *)(q & ~1), q & 1); + } + return bit_waitqueue(p, 0); +} + +static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync, + void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + atomic_t *val = key->flags; + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + atomic_read(val) != 0) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, + * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero + * return codes halt waiting and return. + */ +static __sched +int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, + int (*action)(atomic_t *), unsigned mode) +{ + atomic_t *val; + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + val = q->key.flags; + if (atomic_read(val) == 0) + break; + ret = (*action)(val); + } while (!ret && atomic_read(val) != 0); + finish_wait(wq, &q->wait); + return ret; +} + +#define DEFINE_WAIT_ATOMIC_T(name, p) \ + struct wait_bit_queue name = { \ + .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ + .wait = { \ + .private = current, \ + .func = wake_atomic_t_function, \ + .task_list = \ + LIST_HEAD_INIT((name).wait.task_list), \ + }, \ + } + +__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), + unsigned mode) +{ + wait_queue_head_t *wq = atomic_t_waitqueue(p); + DEFINE_WAIT_ATOMIC_T(wait, p); + + return __wait_on_atomic_t(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); + +/** + * wake_up_atomic_t - Wake up a waiter on a atomic_t + * @p: The atomic_t being waited on, a kernel virtual address + * + * Wake up anyone waiting for the atomic_t to go to zero. + * + * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t + * check is done by the waiter's wake function, not the by the waker itself). + */ +void wake_up_atomic_t(atomic_t *p) +{ + __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); +} +EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + io_schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); |