diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 2 | ||||
| -rw-r--r-- | kernel/sched/auto_group.c | 3 | ||||
| -rw-r--r-- | kernel/sched/core.c | 925 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.c | 51 | ||||
| -rw-r--r-- | kernel/sched/cpupri.c | 4 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 13 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 37 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 801 | ||||
| -rw-r--r-- | kernel/sched/proc.c | 591 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 132 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 85 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 47 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 8 |
13 files changed, 1440 insertions, 1259 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index deaf90e4a1de..54adcf35f495 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o +obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o obj-$(CONFIG_SMP) += cpupri.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 64de5f8b0c9e..4a073539c58e 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -77,8 +77,6 @@ static inline struct autogroup *autogroup_create(void) if (IS_ERR(tg)) goto out_free; - sched_online_group(tg, &root_task_group); - kref_init(&ag->kref); init_rwsem(&ag->lock); ag->id = atomic_inc_return(&autogroup_seq_nr); @@ -98,6 +96,7 @@ static inline struct autogroup *autogroup_create(void) #endif tg->autogroup = ag; + sched_online_group(tg, &root_task_group); return ag; out_free: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..b8e2162fc803 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -370,13 +370,6 @@ static struct rq *this_rq_lock(void) #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. - * - * Its all a bit involved since we cannot program an hrt while holding the - * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a - * reschedule event. - * - * When we get rescheduled we reprogram the hrtick_timer outside of the - * rq->lock. */ static void hrtick_clear(struct rq *rq) @@ -404,6 +397,15 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) } #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 */ @@ -412,7 +414,7 @@ static void __hrtick_start(void *arg) struct rq *rq = arg; raw_spin_lock(&rq->lock); - hrtimer_restart(&rq->hrtick_timer); + __hrtick_restart(rq); rq->hrtick_csd_pending = 0; raw_spin_unlock(&rq->lock); } @@ -430,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_set_expires(timer, time); if (rq == this_rq()) { - hrtimer_restart(timer); + __hrtick_restart(rq); } else if (!rq->hrtick_csd_pending) { __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); rq->hrtick_csd_pending = 1; @@ -633,7 +635,19 @@ void wake_up_nohz_cpu(int cpu) static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); - return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + + 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 */ @@ -667,7 +681,7 @@ void sched_avg_update(struct rq *rq) { s64 period = sched_avg_period(); - while ((s64)(rq->clock - rq->age_stamp) > period) { + while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { /* * Inline assembly required to prevent the compiler * optimising this loop into a divmod call. @@ -919,6 +933,8 @@ static int effective_prio(struct task_struct *p) /** * 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) { @@ -1328,7 +1344,7 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) p->sched_class->task_woken(rq, p); if (rq->idle_stamp) { - u64 delta = rq->clock - rq->idle_stamp; + u64 delta = rq_clock(rq) - rq->idle_stamp; u64 max = 2*sysctl_sched_migration_cost; if (delta > max) @@ -1365,6 +1381,8 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) rq = __task_rq_lock(p); if (p->on_rq) { + /* check_preempt_curr() may use rq clock */ + update_rq_clock(rq); ttwu_do_wakeup(rq, p, wake_flags); ret = 1; } @@ -1393,8 +1411,9 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() - && !tick_nohz_full_cpu(smp_processor_id())) + if (llist_empty(&this_rq()->wake_list) + && !tick_nohz_full_cpu(smp_processor_id()) + && !got_nohz_idle_kick()) return; /* @@ -1417,7 +1436,7 @@ void scheduler_ipi(void) /* * Check if someone kicked us for doing the nohz idle load balance. */ - if (unlikely(got_nohz_idle_kick() && !need_resched())) { + if (unlikely(got_nohz_idle_kick())) { this_rq()->idle_balance = 1; raise_softirq_irqoff(SCHED_SOFTIRQ); } @@ -1465,7 +1484,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * Returns %true if @p was woken up, %false if it was already running + * Return: %true if @p was woken up, %false if it was already running. * or @state didn't match @p's state. */ static int @@ -1474,7 +1493,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; - smp_wmb(); + /* + * 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; @@ -1560,8 +1585,9 @@ out: * @p: The process to be woken up. * * Attempt to wake up the nominated process and move it to the set of runnable - * processes. Returns 1 if the process was woken up, 0 if it was already - * running. + * 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. @@ -1596,15 +1622,6 @@ static void __sched_fork(struct task_struct *p) p->se.vruntime = 0; INIT_LIST_HEAD(&p->se.group_node); -/* - * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be - * removed when useful for applications beyond shares distribution (e.g. - * load-balance). - */ -#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED) - p->se.avg.runnable_avg_period = 0; - p->se.avg.runnable_avg_sum = 0; -#endif #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif @@ -1748,6 +1765,8 @@ void wake_up_new_task(struct task_struct *p) set_task_cpu(p, select_task_rq(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 = 1; @@ -2056,575 +2075,6 @@ unsigned long nr_iowait_cpu(int cpu) return atomic_read(&this->nr_iowait); } -unsigned long this_cpu_load(void) -{ - struct rq *this = this_rq(); - return this->cpu_load[0]; -} - - -/* - * 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 */ -static atomic_long_t calc_load_tasks; -static 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; -} - -static 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_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 = this_rq->load.weight; - 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_COMMON */ - -/* - * Called from scheduler_tick() - */ -static void update_cpu_load_active(struct rq *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, this_rq->load.weight, 1); - - calc_load_account_active(this_rq); -} - #ifdef CONFIG_SMP /* @@ -2673,7 +2123,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) if (task_current(rq, p)) { update_rq_clock(rq); - ns = rq->clock_task - p->se.exec_start; + ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) ns = 0; } @@ -2726,8 +2176,8 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); - update_cpu_load_active(rq); curr->sched_class->task_tick(rq, curr, 0); + update_cpu_load_active(rq); raw_spin_unlock(&rq->lock); perf_event_task_tick(); @@ -2750,6 +2200,8 @@ void scheduler_tick(void) * 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) { @@ -2953,6 +2405,12 @@ need_resched: 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); switch_count = &prev->nivcsw; @@ -3219,7 +2677,7 @@ void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, if (unlikely(!q)) return; - if (unlikely(!nr_exclusive)) + if (unlikely(nr_exclusive != 1)) wake_flags = 0; spin_lock_irqsave(&q->lock, flags); @@ -3355,8 +2813,8 @@ EXPORT_SYMBOL(wait_for_completion); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * 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) @@ -3388,8 +2846,8 @@ EXPORT_SYMBOL(wait_for_completion_io); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. The caller is accounted as waiting for IO. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * 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) @@ -3405,7 +2863,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout); * This waits for completion of a specific task to be signaled. It is * interruptible. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_interruptible(struct completion *x) { @@ -3424,8 +2882,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * 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. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * 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, @@ -3442,7 +2900,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); * This waits to be signaled for completion of a specific task. It can be * interrupted by a kill signal. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_killable(struct completion *x) { @@ -3462,8 +2920,8 @@ EXPORT_SYMBOL(wait_for_completion_killable); * signaled or for a specified timeout to expire. It can be * interrupted by a kill signal. The timeout is in jiffies. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * 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, @@ -3477,7 +2935,7 @@ EXPORT_SYMBOL(wait_for_completion_killable_timeout); * try_wait_for_completion - try to decrement a completion without blocking * @x: completion structure * - * Returns: 0 if a decrement cannot be done without blocking + * 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, @@ -3504,7 +2962,7 @@ EXPORT_SYMBOL(try_wait_for_completion); * completion_done - Test to see if a completion has any waiters * @x: completion structure * - * Returns: 0 if there are waiters (wait_for_completion() in progress) + * Return: 0 if there are waiters (wait_for_completion() in progress) * 1 if there are no waiters. * */ @@ -3741,7 +3199,7 @@ SYSCALL_DEFINE1(nice, int, increment) * task_prio - return the priority value of a given task. * @p: the task in question. * - * This is the priority value as seen by users in /proc. + * 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. */ @@ -3753,6 +3211,8 @@ int task_prio(const struct task_struct *p) /** * task_nice - return the nice value of a given task. * @p: the task in question. + * + * Return: The nice value [ -20 ... 0 ... 19 ]. */ int task_nice(const struct task_struct *p) { @@ -3763,6 +3223,8 @@ EXPORT_SYMBOL(task_nice); /** * 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) { @@ -3785,6 +3247,8 @@ int idle_cpu(int cpu) /** * 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) { @@ -3794,6 +3258,8 @@ struct task_struct *idle_task(int cpu) /** * 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) { @@ -3991,6 +3457,8 @@ recheck: * @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, @@ -4010,6 +3478,8 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * 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) @@ -4044,6 +3514,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) * @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) @@ -4059,6 +3531,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, * 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) { @@ -4068,6 +3542,9 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) /** * 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) { @@ -4094,6 +3571,9 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) * 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) { @@ -4218,6 +3698,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, * @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) @@ -4269,6 +3751,8 @@ out_unlock: * @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) @@ -4303,6 +3787,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, * * 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) { @@ -4428,7 +3914,7 @@ EXPORT_SYMBOL(yield); * 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. * - * Returns: + * 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. @@ -4531,8 +4017,9 @@ long __sched io_schedule_timeout(long timeout) * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. * - * this syscall returns the maximum rt_priority that can be used - * by a given 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) { @@ -4556,8 +4043,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) * sys_sched_get_priority_min - return minimum RT priority. * @policy: scheduling class. * - * this syscall returns the minimum rt_priority that can be used - * by a given 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) { @@ -4583,6 +4071,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) * * 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) @@ -4692,7 +4183,7 @@ void show_state_filter(unsigned long state_filter) debug_show_all_locks(); } -void __cpuinit init_idle_bootup_task(struct task_struct *idle) +void init_idle_bootup_task(struct task_struct *idle) { idle->sched_class = &idle_sched_class; } @@ -4705,7 +4196,7 @@ void __cpuinit init_idle_bootup_task(struct task_struct *idle) * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. */ -void __cpuinit init_idle(struct task_struct *idle, int cpu) +void init_idle(struct task_struct *idle, int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -4745,7 +4236,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); - vtime_init_idle(idle); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif @@ -4947,6 +4438,13 @@ static void migrate_tasks(unsigned int dead_cpu) */ 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 @@ -5080,7 +4578,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return table; } -static ctl_table *sd_alloc_ctl_cpu_table(int cpu) +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; @@ -5182,7 +4680,7 @@ static void set_rq_offline(struct rq *rq) * 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 __cpuinit +static int migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { int cpu = (long)hcpu; @@ -5236,12 +4734,12 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) * happens before everything else. This has to be lower priority than * the notifier in the perf_event subsystem, though. */ -static struct notifier_block __cpuinitdata migration_notifier = { +static struct notifier_block migration_notifier = { .notifier_call = migration_call, .priority = CPU_PRI_MIGRATION, }; -static int __cpuinit sched_cpu_active(struct notifier_block *nfb, +static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { @@ -5254,7 +4752,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb, } } -static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, +static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { @@ -5466,7 +4964,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_FORK | SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES); + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5635,18 +5134,23 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) * 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); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; int id = cpu; + int size = 1; sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); - if (sd) + if (sd) { id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + } rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; per_cpu(sd_llc_id, cpu) = id; } @@ -5670,6 +5174,13 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) 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; @@ -5894,7 +5405,7 @@ build_sched_groups(struct sched_domain *sd, int cpu) get_group(cpu, sdd, &sd->groups); atomic_inc(&sd->groups->ref); - if (cpu != cpumask_first(sched_domain_span(sd))) + if (cpu != cpumask_first(span)) return 0; lockdep_assert_held(&sched_domains_mutex); @@ -5904,12 +5415,12 @@ build_sched_groups(struct sched_domain *sd, int cpu) for_each_cpu(i, span) { struct sched_group *sg; - int group = get_group(i, sdd, &sg); - int j; + int group, j; if (cpumask_test_cpu(i, covered)) continue; + group = get_group(i, sdd, &sg); cpumask_clear(sched_group_cpus(sg)); sg->sgp->power = 0; cpumask_setall(sched_group_mask(sg)); @@ -5947,7 +5458,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) { struct sched_group *sg = sd->groups; - WARN_ON(!sd || !sg); + WARN_ON(!sg); do { sg->group_weight = cpumask_weight(sched_group_cpus(sg)); @@ -6112,6 +5623,9 @@ static struct sched_domain_topology_level default_topology[] = { static struct sched_domain_topology_level *sched_domain_topology = default_topology; +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->init; tl++) + #ifdef CONFIG_NUMA static int sched_domains_numa_levels; @@ -6409,7 +5923,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map) struct sched_domain_topology_level *tl; int j; - for (tl = sched_domain_topology; tl->init; tl++) { + for_each_sd_topology(tl) { struct sd_data *sdd = &tl->data; sdd->sd = alloc_percpu(struct sched_domain *); @@ -6462,7 +5976,7 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sched_domain_topology_level *tl; int j; - for (tl = sched_domain_topology; tl->init; tl++) { + for_each_sd_topology(tl) { struct sd_data *sdd = &tl->data; for_each_cpu(j, cpu_map) { @@ -6490,9 +6004,8 @@ static void __sdt_free(const struct cpumask *cpu_map) } struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, - struct s_data *d, const struct cpumask *cpu_map, - struct sched_domain_attr *attr, struct sched_domain *child, - int cpu) + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) { struct sched_domain *sd = tl->init(tl, cpu); if (!sd) @@ -6503,8 +6016,8 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, sd->level = child->level + 1; sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; + sd->child = child; } - sd->child = child; set_domain_attribute(sd, attr); return sd; @@ -6517,7 +6030,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) { - enum s_alloc alloc_state = sa_none; + enum s_alloc alloc_state; struct sched_domain *sd; struct s_data d; int i, ret = -ENOMEM; @@ -6531,18 +6044,15 @@ static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_topology_level *tl; sd = NULL; - for (tl = sched_domain_topology; tl->init; tl++) { - sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i); + 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; } - - while (sd->child) - sd = sd->child; - - *per_cpu_ptr(d.sd, i) = sd; } /* Build the groups for the domains */ @@ -6737,8 +6247,9 @@ match1: ; } + n = ndoms_cur; if (doms_new == NULL) { - ndoms_cur = 0; + n = 0; doms_new = &fallback_doms; cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); WARN_ON_ONCE(dattr_new); @@ -6746,7 +6257,7 @@ match1: /* Build new domains */ for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < ndoms_cur && !new_topology; j++) { + 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; @@ -6854,9 +6365,6 @@ void __init sched_init_smp(void) hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); - /* RT runtime code needs to handle some hotplug events */ - hotcpu_notifier(update_runtime, 0); - init_hrtick(); /* Move init over to a non-isolated CPU */ @@ -7188,6 +6696,8 @@ void normalize_rt_tasks(void) * @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) { @@ -7319,7 +6829,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id, + tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id, lockdep_is_held(&tsk->sighand->siglock)), struct task_group, css); tg = autogroup_task_group(tsk, tg); @@ -7641,23 +7151,22 @@ int sched_rt_handler(struct ctl_table *table, int write, #ifdef CONFIG_CGROUP_SCHED -/* return corresponding task_group object of a cgroup */ -static inline struct task_group *cgroup_tg(struct cgroup *cgrp) +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) { - return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), - struct task_group, css); + return css ? container_of(css, struct task_group, css) : NULL; } -static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { - struct task_group *tg, *parent; + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; - if (!cgrp->parent) { + if (!parent) { /* This is early initialization for the top cgroup */ return &root_task_group.css; } - parent = cgroup_tg(cgrp->parent); tg = sched_create_group(parent); if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); @@ -7665,41 +7174,38 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) return &tg->css; } -static int cpu_cgroup_css_online(struct cgroup *cgrp) +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); - struct task_group *parent; + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css_parent(css)); - if (!cgrp->parent) - return 0; - - parent = cgroup_tg(cgrp->parent); - sched_online_group(tg, parent); + if (parent) + sched_online_group(tg, parent); return 0; } -static void cpu_cgroup_css_free(struct cgroup *cgrp) +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); sched_destroy_group(tg); } -static void cpu_cgroup_css_offline(struct cgroup *cgrp) +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); sched_offline_group(tg); } -static int cpu_cgroup_can_attach(struct cgroup *cgrp, +static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED - if (!sched_rt_can_attach(cgroup_tg(cgrp), task)) + if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ @@ -7710,18 +7216,18 @@ static int cpu_cgroup_can_attach(struct cgroup *cgrp, return 0; } -static void cpu_cgroup_attach(struct cgroup *cgrp, +static void cpu_cgroup_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } -static void -cpu_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, - struct task_struct *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. @@ -7735,15 +7241,16 @@ cpu_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, } #ifdef CONFIG_FAIR_GROUP_SCHED -static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 shareval) +static int cpu_shares_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 shareval) { - return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval)); + return sched_group_set_shares(css_tg(css), scale_load(shareval)); } -static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); return (u64) scale_load_down(tg->shares); } @@ -7865,26 +7372,28 @@ long tg_get_cfs_period(struct task_group *tg) return cfs_period_us; } -static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_quota(cgroup_tg(cgrp)); + return tg_get_cfs_quota(css_tg(css)); } -static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype, - s64 cfs_quota_us) +static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 cfs_quota_us) { - return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us); + return tg_set_cfs_quota(css_tg(css), cfs_quota_us); } -static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_period(cgroup_tg(cgrp)); + return tg_get_cfs_period(css_tg(css)); } -static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 cfs_period_us) +static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 cfs_period_us) { - return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us); + return tg_set_cfs_period(css_tg(css), cfs_period_us); } struct cfs_schedulable_data { @@ -7965,10 +7474,10 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) return ret; } -static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, +static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; cb->fill(cb, "nr_periods", cfs_b->nr_periods); @@ -7981,26 +7490,28 @@ static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED -static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, - s64 val) +static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) { - return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); + return sched_group_set_rt_runtime(css_tg(css), val); } -static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_runtime(cgroup_tg(cgrp)); + return sched_group_rt_runtime(css_tg(css)); } -static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, - u64 rt_period_us) +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(cgroup_tg(cgrp), rt_period_us); + return sched_group_set_rt_period(css_tg(css), rt_period_us); } -static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_period(cgroup_tg(cgrp)); + return sched_group_rt_period(css_tg(css)); } #endif /* CONFIG_RT_GROUP_SCHED */ diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index dbb7e2cd95eb..f64722ff0299 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -33,30 +33,20 @@ struct cpuacct { struct kernel_cpustat __percpu *cpustat; }; -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) +static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) { - return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), - struct cpuacct, 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 container_of(task_subsys_state(tsk, cpuacct_subsys_id), - struct cpuacct, css); -} - -static inline struct cpuacct *__parent_ca(struct cpuacct *ca) -{ - return cgroup_ca(ca->css.cgroup->parent); + return css_ca(task_css(tsk, cpuacct_subsys_id)); } static inline struct cpuacct *parent_ca(struct cpuacct *ca) { - if (!ca->css.cgroup->parent) - return NULL; - return cgroup_ca(ca->css.cgroup->parent); + return css_ca(css_parent(&ca->css)); } static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); @@ -66,11 +56,12 @@ static struct cpuacct root_cpuacct = { }; /* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cpuacct_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuacct *ca; - if (!cgrp->parent) + if (!parent_css) return &root_cpuacct.css; ca = kzalloc(sizeof(*ca), GFP_KERNEL); @@ -96,9 +87,9 @@ out: } /* destroy an existing cpu accounting group */ -static void cpuacct_css_free(struct cgroup *cgrp) +static void cpuacct_css_free(struct cgroup_subsys_state *css) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); free_percpu(ca->cpustat); free_percpu(ca->cpuusage); @@ -141,9 +132,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) } /* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) +static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); u64 totalcpuusage = 0; int i; @@ -153,10 +144,10 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) return totalcpuusage; } -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) +static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, + u64 reset) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); int err = 0; int i; @@ -172,10 +163,10 @@ out: return err; } -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) +static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m) { - struct cpuacct *ca = cgroup_ca(cgroup); + struct cpuacct *ca = css_ca(css); u64 percpu; int i; @@ -192,10 +183,10 @@ static const char * const cpuacct_stat_desc[] = { [CPUACCT_STAT_SYSTEM] = "system", }; -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) +static int cpuacct_stats_show(struct cgroup_subsys_state *css, + struct cftype *cft, struct cgroup_map_cb *cb) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); int cpu; s64 val = 0; @@ -281,7 +272,7 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) while (ca != &root_cpuacct) { kcpustat = this_cpu_ptr(ca->cpustat); kcpustat->cpustat[index] += val; - ca = __parent_ca(ca); + ca = parent_ca(ca); } rcu_read_unlock(); } diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 1095e878a46f..8b836b376d91 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -62,7 +62,7 @@ static int convert_prio(int prio) * any discrepancies created by racing against the uncertainty of the current * priority configuration. * - * Returns: (int)bool - CPUs were found + * Return: (int)bool - CPUs were found */ int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask) @@ -203,7 +203,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * cpupri_init - initialize the cpupri structure * @cp: The cpupri context * - * Returns: -ENOMEM if memory fails. + * Return: -ENOMEM on memory allocation failure. */ int cpupri_init(struct cpupri *cp) { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cc2dc3eea8a3..e89ccefef278 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -121,7 +121,7 @@ static inline void task_group_account_field(struct task_struct *p, int index, * is the only cgroup, then nothing else should be necessary. * */ - __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; + __this_cpu_add(kernel_cpustat.cpustat[index], tmp); cpuacct_account_field(p, index, tmp); } @@ -515,9 +515,8 @@ static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) for (;;) { /* Make sure "rtime" is the bigger of stime/rtime */ - if (stime > rtime) { - u64 tmp = rtime; rtime = stime; stime = tmp; - } + if (stime > rtime) + swap(rtime, stime); /* Make sure 'total' fits in 32 bits */ if (total >> 32) @@ -747,17 +746,17 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqlock(¤t->vtime_seqlock); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock(); + current->vtime_snap = sched_clock_cpu(smp_processor_id()); write_sequnlock(¤t->vtime_seqlock); } -void vtime_init_idle(struct task_struct *t) +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(); + t->vtime_snap = sched_clock_cpu(cpu); write_sequnlock_irqrestore(&t->vtime_seqlock, flags); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 75024a673520..e076bddd4c66 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -209,22 +209,24 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) 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_FAIR_GROUP_SCHED #ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lld\n", "runnable_load_avg", + SEQ_printf(m, " .%-30s: %ld\n", "runnable_load_avg", cfs_rq->runnable_load_avg); - SEQ_printf(m, " .%-30s: %lld\n", "blocked_load_avg", + SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", cfs_rq->blocked_load_avg); - SEQ_printf(m, " .%-30s: %lld\n", "tg_load_avg", - (unsigned long long)atomic64_read(&cfs_rq->tg->load_avg)); - SEQ_printf(m, " .%-30s: %lld\n", "tg_load_contrib", +#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_FAIR_GROUP_SCHED print_cfs_group_stats(m, cpu, cfs_rq->tg); #endif } @@ -493,15 +495,16 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, get_nr_threads(p)); SEQ_printf(m, - "---------------------------------------------------------\n"); + "---------------------------------------------------------" + "----------\n"); #define __P(F) \ - SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)F) + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) #define P(F) \ - SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)p->F) + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) #define __PN(F) \ - SEQ_printf(m, "%-35s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) #define PN(F) \ - SEQ_printf(m, "%-35s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) PN(se.exec_start); PN(se.vruntime); @@ -560,12 +563,18 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) } #endif __P(nr_switches); - SEQ_printf(m, "%-35s:%21Ld\n", + SEQ_printf(m, "%-45s:%21Ld\n", "nr_voluntary_switches", (long long)p->nvcsw); - SEQ_printf(m, "%-35s:%21Ld\n", + 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.runnable_avg_period); + P(se.avg.load_avg_contrib); + P(se.avg.decay_count); +#endif P(policy); P(prio); #undef PN @@ -579,7 +588,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) t0 = cpu_clock(this_cpu); t1 = cpu_clock(this_cpu); - SEQ_printf(m, "%-35s:%21Ld\n", + SEQ_printf(m, "%-45s:%21Ld\n", "clock-delta", (long long)(t1-t0)); } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c61a614465c8..7f0a5e6cdae0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -113,6 +113,24 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; #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 @@ -662,6 +680,26 @@ 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 inline void __update_task_entity_contrib(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; + + p->se.avg.decay_count = 0; + slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; + p->se.avg.runnable_avg_sum = slice; + p->se.avg.runnable_avg_period = slice; + __update_task_entity_contrib(&p->se); +} +#else +void init_task_runnable_average(struct task_struct *p) +{ +} +#endif + /* * Update the current task's runtime statistics. Skip current tasks that * are not in our scheduling class. @@ -686,7 +724,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_of(cfs_rq)->clock_task; + u64 now = rq_clock_task(rq_of(cfs_rq)); unsigned long delta_exec; if (unlikely(!curr)) @@ -718,7 +756,7 @@ static void update_curr(struct cfs_rq *cfs_rq) static inline void update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) { - schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock); + schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq))); } /* @@ -738,14 +776,14 @@ 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_of(cfs_rq)->clock - se->statistics.wait_start)); + 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_of(cfs_rq)->clock - se->statistics.wait_start); + 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_of(cfs_rq)->clock - se->statistics.wait_start); + rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); } #endif schedstat_set(se->statistics.wait_start, 0); @@ -771,7 +809,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) /* * We are starting a new run period: */ - se->exec_start = rq_of(cfs_rq)->clock_task; + se->exec_start = rq_clock_task(rq_of(cfs_rq)); } /************************************************** @@ -813,7 +851,7 @@ void task_numa_fault(int node, int pages, bool migrated) { struct task_struct *p = current; - if (!sched_feat_numa(NUMA)) + if (!numabalancing_enabled) return; /* FIXME: Allocate task-specific structure for placement policy here */ @@ -1037,7 +1075,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) * to gain a more accurate current total weight. See * update_cfs_rq_load_contribution(). */ - tg_weight = atomic64_read(&tg->load_avg); + tg_weight = atomic_long_read(&tg->load_avg); tg_weight -= cfs_rq->tg_load_contrib; tg_weight += cfs_rq->load.weight; @@ -1110,8 +1148,7 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq) } #endif /* CONFIG_FAIR_GROUP_SCHED */ -/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */ -#if defined(CONFIG_SMP) && defined(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. @@ -1319,13 +1356,13 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, int force_update) { struct task_group *tg = cfs_rq->tg; - s64 tg_contrib; + long tg_contrib; tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg; tg_contrib -= cfs_rq->tg_load_contrib; - if (force_update || abs64(tg_contrib) > cfs_rq->tg_load_contrib / 8) { - atomic64_add(tg_contrib, &tg->load_avg); + 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; } } @@ -1360,8 +1397,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) u64 contrib; contrib = cfs_rq->tg_load_contrib * tg->shares; - se->avg.load_avg_contrib = div64_u64(contrib, - atomic64_read(&tg->load_avg) + 1); + 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 @@ -1480,8 +1517,9 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) if (!decays && !force_update) return; - if (atomic64_read(&cfs_rq->removed_load)) { - u64 removed_load = atomic64_xchg(&cfs_rq->removed_load, 0); + 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); } @@ -1497,7 +1535,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) static inline void update_rq_runnable_avg(struct rq *rq, int runnable) { - __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable); + __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); __update_tg_runnable_avg(&rq->avg, &rq->cfs); } @@ -1510,9 +1548,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, * 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_of(cfs_rq)->clock_task; + 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 @@ -1530,7 +1572,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, } wakeup = 0; } else { - __synchronize_entity_decay(se); + /* + * Task re-woke on same cpu (or else migrate_task_rq_fair() + * would have made count negative); we must be careful to avoid + * double-accounting blocked time after synchronizing decays. + */ + se->avg.last_runnable_update += __synchronize_entity_decay(se) + << 20; } /* migrated tasks did not contribute to our blocked load */ @@ -1607,7 +1655,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) tsk = task_of(se); if (se->statistics.sleep_start) { - u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start; + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start; if ((s64)delta < 0) delta = 0; @@ -1624,7 +1672,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) } } if (se->statistics.block_start) { - u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start; + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start; if ((s64)delta < 0) delta = 0; @@ -1712,7 +1760,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* * Update the normalized vruntime before updating min_vruntime - * through callig update_curr(). + * through calling update_curr(). */ if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) se->vruntime += cfs_rq->min_vruntime; @@ -1805,9 +1853,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) struct task_struct *tsk = task_of(se); if (tsk->state & TASK_INTERRUPTIBLE) - se->statistics.sleep_start = rq_of(cfs_rq)->clock; + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); if (tsk->state & TASK_UNINTERRUPTIBLE) - se->statistics.block_start = rq_of(cfs_rq)->clock; + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); } #endif } @@ -1984,6 +2032,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) */ update_entity_load_avg(curr, 1); update_cfs_rq_blocked_load(cfs_rq, 1); + update_cfs_shares(cfs_rq); #ifdef CONFIG_SCHED_HRTICK /* @@ -2082,7 +2131,7 @@ 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_of(cfs_rq)->clock_task - cfs_rq->throttled_clock_task_time; + return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; } /* returns 0 on failure to allocate runtime */ @@ -2138,10 +2187,9 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) { struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - struct rq *rq = rq_of(cfs_rq); /* if the deadline is ahead of our clock, nothing to do */ - if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0)) + if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) return; if (cfs_rq->runtime_remaining < 0) @@ -2230,7 +2278,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) #ifdef CONFIG_SMP if (!cfs_rq->throttle_count) { /* adjust cfs_rq_clock_task() */ - cfs_rq->throttled_clock_task_time += rq->clock_task - + cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task; } #endif @@ -2245,7 +2293,7 @@ static int tg_throttle_down(struct task_group *tg, void *data) /* group is entering throttled state, stop time */ if (!cfs_rq->throttle_count) - cfs_rq->throttled_clock_task = rq->clock_task; + cfs_rq->throttled_clock_task = rq_clock_task(rq); cfs_rq->throttle_count++; return 0; @@ -2284,7 +2332,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) rq->nr_running -= task_delta; cfs_rq->throttled = 1; - cfs_rq->throttled_clock = rq->clock; + cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); raw_spin_unlock(&cfs_b->lock); @@ -2298,15 +2346,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) int enqueue = 1; long task_delta; - se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; + 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 - cfs_rq->throttled_clock; + 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_rq_clock(rq); /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); @@ -2599,10 +2649,6 @@ static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) throttle_cfs_rq(cfs_rq); } -static inline u64 default_cfs_period(void); -static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun); -static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b); - static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -2706,7 +2752,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) #else /* CONFIG_CFS_BANDWIDTH */ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) { - return rq_of(cfs_rq)->clock_task; + return rq_clock_task(rq_of(cfs_rq)); } static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, @@ -2919,7 +2965,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* Used instead of source_load when we know the type == 0 */ static unsigned long weighted_cpuload(const int cpu) { - return cpu_rq(cpu)->load.weight; + return cpu_rq(cpu)->cfs.runnable_load_avg; } /* @@ -2964,13 +3010,31 @@ static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long nr_running = ACCESS_ONCE(rq->nr_running); + unsigned long load_avg = rq->cfs.runnable_load_avg; if (nr_running) - return rq->load.weight / 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 (jiffies > current->wakee_flip_decay_ts + HZ) { + current->wakee_flips = 0; + 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) { @@ -2991,6 +3055,7 @@ static void task_waking_fair(struct task_struct *p) #endif se->vruntime -= min_vruntime; + record_wakee(p); } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -3109,6 +3174,28 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, #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; @@ -3118,6 +3205,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) 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); @@ -3416,12 +3510,6 @@ unlock: } /* - * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be - * removed when useful for applications beyond shares distribution (e.g. - * load-balance). - */ -#ifdef CONFIG_FAIR_GROUP_SCHED -/* * 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 @@ -3441,10 +3529,10 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu) */ if (se->avg.decay_count) { se->avg.decay_count = -__synchronize_entity_decay(se); - atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load); + atomic_long_add(se->avg.load_avg_contrib, + &cfs_rq->removed_load); } } -#endif #endif /* CONFIG_SMP */ static unsigned long @@ -3946,7 +4034,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 2) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); + tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd); if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { @@ -4131,118 +4219,120 @@ static void update_blocked_averages(int cpu) } /* - * Compute the cpu's hierarchical load factor for each task group. + * 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 int tg_load_down(struct task_group *tg, void *data) +static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) { - unsigned long load; - long cpu = (long)data; - - if (!tg->parent) { - load = cpu_rq(cpu)->load.weight; - } else { - load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->se[cpu]->load.weight; - load /= tg->parent->cfs_rq[cpu]->load.weight + 1; - } - - tg->cfs_rq[cpu]->h_load = load; - - return 0; -} - -static void update_h_load(long cpu) -{ - struct rq *rq = cpu_rq(cpu); + 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 (rq->h_load_throttle == now) + if (cfs_rq->last_h_load_update == now) return; - rq->h_load_throttle = now; + 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; + } - rcu_read_lock(); - walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); - rcu_read_unlock(); + if (!se) { + cfs_rq->h_load = rq->avg.load_avg_contrib; + 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); - unsigned long load; - - load = p->se.load.weight; - load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1); - return load; + 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 inline void update_h_load(long cpu) -{ -} - static unsigned long task_h_load(struct task_struct *p) { - return p->se.load.weight; + return p->se.avg.load_avg_contrib; } #endif /********** Helpers for find_busiest_group ************************/ /* - * 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 *this; /* Local group in this sd */ - unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ - unsigned long avg_load; /* Average load across all groups in sd */ - - /** Statistics of this group */ - unsigned long this_load; - unsigned long this_load_per_task; - unsigned long this_nr_running; - unsigned long this_has_capacity; - unsigned int this_idle_cpus; - - /* Statistics of the busiest group */ - unsigned int busiest_idle_cpus; - unsigned long max_load; - unsigned long busiest_load_per_task; - unsigned long busiest_nr_running; - unsigned long busiest_group_capacity; - unsigned long busiest_has_capacity; - unsigned int busiest_group_weight; - - int group_imb; /* Is there imbalance in this sd */ -}; - -/* * 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_nr_running; /* Nr tasks running in the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ - unsigned long group_capacity; - unsigned long idle_cpus; - unsigned long group_weight; + unsigned long load_per_task; + unsigned long group_power; + unsigned int sum_nr_running; /* Nr tasks running in the group */ + unsigned int group_capacity; + unsigned int idle_cpus; + unsigned int group_weight; int group_imb; /* Is there an imbalance in the group ? */ int group_has_capacity; /* Is there extra capacity in the group? */ }; +/* + * 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_pwr; /* Total power 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_pwr = 0UL, + .busiest_stat = { + .avg_load = 0UL, + }, + }; +} + /** * 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_icx is obtained. + * + * Return: The load index. */ static inline int get_sd_load_idx(struct sched_domain *sd, enum cpu_idle_type idle) @@ -4302,7 +4392,7 @@ static unsigned long scale_rt_power(int cpu) age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); - total = sched_avg_period() + (rq->clock - age_stamp); + total = sched_avg_period() + (rq_clock(rq) - age_stamp); if (unlikely(total < avg)) { /* Ensures that power won't end up being negative */ @@ -4420,33 +4510,99 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) return 0; } +/* + * 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 it has a cpu that is overloaded while the remaining cpus are + * idle -- or rather, there's a distinct imbalance in the cpus; see + * sg_imbalanced(). + * + * When this is so detected; this group becomes a candidate for busiest; see + * update_sd_pick_busiest(). And calculcate_imbalance() and + * find_busiest_group() avoid some of the usual balance conditional 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. + */ + +struct sg_imb_stats { + unsigned long max_nr_running, min_nr_running; + unsigned long max_cpu_load, min_cpu_load; +}; + +static inline void init_sg_imb_stats(struct sg_imb_stats *sgi) +{ + sgi->max_cpu_load = sgi->max_nr_running = 0UL; + sgi->min_cpu_load = sgi->min_nr_running = ~0UL; +} + +static inline void +update_sg_imb_stats(struct sg_imb_stats *sgi, + unsigned long load, unsigned long nr_running) +{ + if (load > sgi->max_cpu_load) + sgi->max_cpu_load = load; + if (sgi->min_cpu_load > load) + sgi->min_cpu_load = load; + + if (nr_running > sgi->max_nr_running) + sgi->max_nr_running = nr_running; + if (sgi->min_nr_running > nr_running) + sgi->min_nr_running = nr_running; +} + +static inline int +sg_imbalanced(struct sg_lb_stats *sgs, struct sg_imb_stats *sgi) +{ + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of a task. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + if ((sgi->max_cpu_load - sgi->min_cpu_load) >= sgs->load_per_task && + (sgi->max_nr_running - sgi->min_nr_running) > 1) + return 1; + + return 0; +} + /** * 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. - * @balance: Should we balance. * @sgs: variable to hold the statistics for this group. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, - int local_group, int *balance, struct sg_lb_stats *sgs) + int local_group, struct sg_lb_stats *sgs) { - unsigned long nr_running, max_nr_running, min_nr_running; - unsigned long load, max_cpu_load, min_cpu_load; - unsigned int balance_cpu = -1, first_idle_cpu = 0; - unsigned long avg_load_per_task = 0; + struct sg_imb_stats sgi; + unsigned long nr_running; + unsigned long load; int i; - if (local_group) - balance_cpu = group_balance_cpu(group); - - /* Tally up the load of all CPUs in the group */ - max_cpu_load = 0; - min_cpu_load = ~0UL; - max_nr_running = 0; - min_nr_running = ~0UL; + init_sg_imb_stats(&sgi); for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { struct rq *rq = cpu_rq(i); @@ -4455,24 +4611,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, /* Bias balancing toward cpus of our domain */ if (local_group) { - if (idle_cpu(i) && !first_idle_cpu && - cpumask_test_cpu(i, sched_group_mask(group))) { - first_idle_cpu = 1; - balance_cpu = i; - } - load = target_load(i, load_idx); } else { load = source_load(i, load_idx); - if (load > max_cpu_load) - max_cpu_load = load; - if (min_cpu_load > load) - min_cpu_load = load; - - if (nr_running > max_nr_running) - max_nr_running = nr_running; - if (min_nr_running > nr_running) - min_nr_running = nr_running; + update_sg_imb_stats(&sgi, load, nr_running); } sgs->group_load += load; @@ -4482,46 +4624,25 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->idle_cpus++; } - /* - * First idle cpu or the first cpu(busiest) in this sched group - * is eligible for doing load balancing at this and above - * domains. In the newly idle case, we will allow all the cpu's - * to do the newly idle load balance. - */ - if (local_group) { - if (env->idle != CPU_NEWLY_IDLE) { - if (balance_cpu != env->dst_cpu) { - *balance = 0; - return; - } - update_group_power(env->sd, env->dst_cpu); - } else if (time_after_eq(jiffies, group->sgp->next_update)) - update_group_power(env->sd, env->dst_cpu); - } + if (local_group && (env->idle != CPU_NEWLY_IDLE || + time_after_eq(jiffies, group->sgp->next_update))) + update_group_power(env->sd, env->dst_cpu); /* Adjust by relative CPU power of the group */ - sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power; + sgs->group_power = group->sgp->power; + sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power; - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of a task. - * - * APZ: with cgroup the avg task weight can vary wildly and - * might not be a suitable number - should we keep a - * normalized nr_running number somewhere that negates - * the hierarchy? - */ if (sgs->sum_nr_running) - avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + + sgs->group_imb = sg_imbalanced(sgs, &sgi); - if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && - (max_nr_running - min_nr_running) > 1) - sgs->group_imb = 1; + sgs->group_capacity = + DIV_ROUND_CLOSEST(sgs->group_power, SCHED_POWER_SCALE); - sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power, - SCHED_POWER_SCALE); if (!sgs->group_capacity) sgs->group_capacity = fix_small_capacity(env->sd, group); + sgs->group_weight = group->group_weight; if (sgs->group_capacity > sgs->sum_nr_running) @@ -4537,13 +4658,16 @@ static inline void update_sg_lb_stats(struct lb_env *env, * * 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) { - if (sgs->avg_load <= sds->max_load) + if (sgs->avg_load <= sds->busiest_stat.avg_load) return false; if (sgs->sum_nr_running > sgs->group_capacity) @@ -4576,11 +4700,11 @@ static bool update_sd_pick_busiest(struct lb_env *env, * @sds: variable to hold the statistics for this sched_domain. */ static inline void update_sd_lb_stats(struct lb_env *env, - int *balance, struct sd_lb_stats *sds) + struct sd_lb_stats *sds) { struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; - struct sg_lb_stats sgs; + struct sg_lb_stats tmp_sgs; int load_idx, prefer_sibling = 0; if (child && child->flags & SD_PREFER_SIBLING) @@ -4589,17 +4713,17 @@ static inline void update_sd_lb_stats(struct lb_env *env, 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)); - memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(env, sg, load_idx, local_group, balance, &sgs); - - if (local_group && !(*balance)) - return; + if (local_group) { + sds->local = sg; + sgs = &sds->local_stat; + } - sds->total_load += sgs.group_load; - sds->total_pwr += sg->sgp->power; + memset(sgs, 0, sizeof(*sgs)); + update_sg_lb_stats(env, sg, load_idx, local_group, sgs); /* * In case the child domain prefers tasks go to siblings @@ -4611,26 +4735,17 @@ static inline void update_sd_lb_stats(struct lb_env *env, * heaviest group when it is already under-utilized (possible * with a large weight task outweighs the tasks on the system). */ - if (prefer_sibling && !local_group && sds->this_has_capacity) - sgs.group_capacity = min(sgs.group_capacity, 1UL); + if (prefer_sibling && !local_group && + sds->local && sds->local_stat.group_has_capacity) + sgs->group_capacity = min(sgs->group_capacity, 1U); - if (local_group) { - sds->this_load = sgs.avg_load; - sds->this = sg; - sds->this_nr_running = sgs.sum_nr_running; - sds->this_load_per_task = sgs.sum_weighted_load; - sds->this_has_capacity = sgs.group_has_capacity; - sds->this_idle_cpus = sgs.idle_cpus; - } else if (update_sd_pick_busiest(env, sds, sg, &sgs)) { - sds->max_load = sgs.avg_load; + /* Now, start updating sd_lb_stats */ + sds->total_load += sgs->group_load; + sds->total_pwr += sgs->group_power; + + if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; - sds->busiest_nr_running = sgs.sum_nr_running; - sds->busiest_idle_cpus = sgs.idle_cpus; - sds->busiest_group_capacity = sgs.group_capacity; - sds->busiest_load_per_task = sgs.sum_weighted_load; - sds->busiest_has_capacity = sgs.group_has_capacity; - sds->busiest_group_weight = sgs.group_weight; - sds->group_imb = sgs.group_imb; + sds->busiest_stat = *sgs; } sg = sg->next; @@ -4654,7 +4769,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, * assuming lower CPU number will be equivalent to lower a SMT thread * number. * - * Returns 1 when packing is required and a task should be moved to + * 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. @@ -4675,7 +4790,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) return 0; env->imbalance = DIV_ROUND_CLOSEST( - sds->max_load * sds->busiest->sgp->power, SCHED_POWER_SCALE); + sds->busiest_stat.avg_load * sds->busiest_stat.group_power, + SCHED_POWER_SCALE); return 1; } @@ -4693,24 +4809,23 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) unsigned long tmp, pwr_now = 0, pwr_move = 0; unsigned int imbn = 2; unsigned long scaled_busy_load_per_task; + struct sg_lb_stats *local, *busiest; - if (sds->this_nr_running) { - sds->this_load_per_task /= sds->this_nr_running; - if (sds->busiest_load_per_task > - sds->this_load_per_task) - imbn = 1; - } else { - sds->this_load_per_task = - cpu_avg_load_per_task(env->dst_cpu); - } + 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 = sds->busiest_load_per_task - * SCHED_POWER_SCALE; - scaled_busy_load_per_task /= sds->busiest->sgp->power; + scaled_busy_load_per_task = + (busiest->load_per_task * SCHED_POWER_SCALE) / + busiest->group_power; - if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= - (scaled_busy_load_per_task * imbn)) { - env->imbalance = sds->busiest_load_per_task; + if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >= + (scaled_busy_load_per_task * imbn)) { + env->imbalance = busiest->load_per_task; return; } @@ -4720,34 +4835,37 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) * moving them. */ - pwr_now += sds->busiest->sgp->power * - min(sds->busiest_load_per_task, sds->max_load); - pwr_now += sds->this->sgp->power * - min(sds->this_load_per_task, sds->this_load); + pwr_now += busiest->group_power * + min(busiest->load_per_task, busiest->avg_load); + pwr_now += local->group_power * + min(local->load_per_task, local->avg_load); pwr_now /= SCHED_POWER_SCALE; /* Amount of load we'd subtract */ - tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / - sds->busiest->sgp->power; - if (sds->max_load > tmp) - pwr_move += sds->busiest->sgp->power * - min(sds->busiest_load_per_task, sds->max_load - tmp); + tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / + busiest->group_power; + if (busiest->avg_load > tmp) { + pwr_move += busiest->group_power * + min(busiest->load_per_task, + busiest->avg_load - tmp); + } /* Amount of load we'd add */ - if (sds->max_load * sds->busiest->sgp->power < - sds->busiest_load_per_task * SCHED_POWER_SCALE) - tmp = (sds->max_load * sds->busiest->sgp->power) / - sds->this->sgp->power; - else - tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / - sds->this->sgp->power; - pwr_move += sds->this->sgp->power * - min(sds->this_load_per_task, sds->this_load + tmp); + if (busiest->avg_load * busiest->group_power < + busiest->load_per_task * SCHED_POWER_SCALE) { + tmp = (busiest->avg_load * busiest->group_power) / + local->group_power; + } else { + tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / + local->group_power; + } + pwr_move += local->group_power * + min(local->load_per_task, local->avg_load + tmp); pwr_move /= SCHED_POWER_SCALE; /* Move if we gain throughput */ if (pwr_move > pwr_now) - env->imbalance = sds->busiest_load_per_task; + env->imbalance = busiest->load_per_task; } /** @@ -4759,11 +4877,18 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) 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; - sds->busiest_load_per_task /= sds->busiest_nr_running; - if (sds->group_imb) { - sds->busiest_load_per_task = - min(sds->busiest_load_per_task, sds->avg_load); + if (busiest->group_imb) { + /* + * 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); } /* @@ -4771,21 +4896,22 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * max load less than avg load(as we skip the groups at or below * its cpu_power, while calculating max_load..) */ - if (sds->max_load < sds->avg_load) { + if (busiest->avg_load < sds->avg_load) { env->imbalance = 0; return fix_small_imbalance(env, sds); } - if (!sds->group_imb) { + if (!busiest->group_imb) { /* * Don't want to pull so many tasks that a group would go idle. + * Except of course for the group_imb case, since then we might + * have to drop below capacity to reach cpu-load equilibrium. */ - load_above_capacity = (sds->busiest_nr_running - - sds->busiest_group_capacity); + load_above_capacity = + (busiest->sum_nr_running - busiest->group_capacity); load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - - load_above_capacity /= sds->busiest->sgp->power; + load_above_capacity /= busiest->group_power; } /* @@ -4795,15 +4921,14 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * 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. - * Be careful of negative numbers as they'll appear as very large values - * with unsigned longs. */ - max_pull = min(sds->max_load - sds->avg_load, load_above_capacity); + 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 * sds->busiest->sgp->power, - (sds->avg_load - sds->this_load) * sds->this->sgp->power) - / SCHED_POWER_SCALE; + env->imbalance = min( + max_pull * busiest->group_power, + (sds->avg_load - local->avg_load) * local->group_power + ) / SCHED_POWER_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -4811,9 +4936,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * a think about bumping its value to force at least one task to be * moved */ - if (env->imbalance < sds->busiest_load_per_task) + if (env->imbalance < busiest->load_per_task) return fix_small_imbalance(env, sds); - } /******* find_busiest_group() helpers end here *********************/ @@ -4829,69 +4953,62 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * to restore balance. * * @env: The load balancing environment. - * @balance: Pointer to a variable indicating if this_cpu - * is the appropriate cpu to perform load balancing at this_level. * - * Returns: - the busiest group if imbalance exists. + * 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, int *balance) +static struct sched_group *find_busiest_group(struct lb_env *env) { + struct sg_lb_stats *local, *busiest; struct sd_lb_stats sds; - memset(&sds, 0, sizeof(sds)); + init_sd_lb_stats(&sds); /* * Compute the various statistics relavent for load balancing at * this level. */ - update_sd_lb_stats(env, balance, &sds); - - /* - * this_cpu is not the appropriate cpu to perform load balancing at - * this level. - */ - if (!(*balance)) - goto ret; + update_sd_lb_stats(env, &sds); + local = &sds.local_stat; + busiest = &sds.busiest_stat; 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 || sds.busiest_nr_running == 0) + if (!sds.busiest || busiest->sum_nr_running == 0) goto out_balanced; sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; /* * If the busiest group is imbalanced the below checks don't - * work because they assumes all things are equal, which typically + * work because they assume all things are equal, which typically * isn't true due to cpus_allowed constraints and the like. */ - if (sds.group_imb) + if (busiest->group_imb) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && sds.this_has_capacity && - !sds.busiest_has_capacity) + if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity && + !busiest->group_has_capacity) goto force_balance; /* * If the local group is more busy than the selected busiest group * don't try and pull any tasks. */ - if (sds.this_load >= sds.max_load) + 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 (sds.this_load >= sds.avg_load) + if (local->avg_load >= sds.avg_load) goto out_balanced; if (env->idle == CPU_IDLE) { @@ -4901,15 +5018,16 @@ find_busiest_group(struct lb_env *env, int *balance) * there is no imbalance between this and busiest group * wrt to idle cpu's, it is balanced. */ - if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) && - sds.busiest_nr_running <= sds.busiest_group_weight) + if ((local->idle_cpus < busiest->idle_cpus) && + busiest->sum_nr_running <= busiest->group_weight) goto out_balanced; } else { /* * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use * imbalance_pct to be conservative. */ - if (100 * sds.max_load <= env->sd->imbalance_pct * sds.this_load) + if (100 * busiest->avg_load <= + env->sd->imbalance_pct * local->avg_load) goto out_balanced; } @@ -4919,7 +5037,6 @@ force_balance: return sds.busiest; out_balanced: -ret: env->imbalance = 0; return NULL; } @@ -4931,10 +5048,10 @@ static struct rq *find_busiest_queue(struct lb_env *env, struct sched_group *group) { struct rq *busiest = NULL, *rq; - unsigned long max_load = 0; + unsigned long busiest_load = 0, busiest_power = 1; int i; - for_each_cpu(i, sched_group_cpus(group)) { + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { unsigned long power = power_of(i); unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); @@ -4943,9 +5060,6 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (!capacity) capacity = fix_small_capacity(env->sd, group); - if (!cpumask_test_cpu(i, env->cpus)) - continue; - rq = cpu_rq(i); wl = weighted_cpuload(i); @@ -4961,11 +5075,15 @@ static struct rq *find_busiest_queue(struct lb_env *env, * the weighted_cpuload() scaled with the cpu power, 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 / power_i), crosswise + * multiplication to rid ourselves of the division works out + * to: wl_i * power_j > wl_j * power_i; where j is our + * previous maximum. */ - wl = (wl * SCHED_POWER_SCALE) / power; - - if (wl > max_load) { - max_load = wl; + if (wl * busiest_power > busiest_load * power) { + busiest_load = wl; + busiest_power = power; busiest = rq; } } @@ -5002,13 +5120,47 @@ static int need_active_balance(struct lb_env *env) 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 *balance) + int *continue_balancing) { int ld_moved, cur_ld_moved, active_balance = 0; struct sched_group *group; @@ -5038,11 +5190,12 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: - group = find_busiest_group(&env, balance); - - if (*balance == 0) + 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; @@ -5071,7 +5224,6 @@ redo: env.src_rq = busiest; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); - update_h_load(env.src_cpu); more_balance: local_irq_save(flags); double_rq_lock(env.dst_rq, busiest); @@ -5241,7 +5393,7 @@ void idle_balance(int this_cpu, struct rq *this_rq) int pulled_task = 0; unsigned long next_balance = jiffies + HZ; - this_rq->idle_stamp = this_rq->clock; + this_rq->idle_stamp = rq_clock(this_rq); if (this_rq->avg_idle < sysctl_sched_migration_cost) return; @@ -5255,7 +5407,7 @@ void idle_balance(int this_cpu, struct rq *this_rq) rcu_read_lock(); for_each_domain(this_cpu, sd) { unsigned long interval; - int balance = 1; + int continue_balancing = 1; if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -5263,7 +5415,8 @@ void idle_balance(int this_cpu, struct rq *this_rq) if (sd->flags & SD_BALANCE_NEWIDLE) { /* If we've pulled tasks over stop searching: */ pulled_task = load_balance(this_cpu, this_rq, - sd, CPU_NEWLY_IDLE, &balance); + sd, CPU_NEWLY_IDLE, + &continue_balancing); } interval = msecs_to_jiffies(sd->balance_interval); @@ -5418,10 +5571,9 @@ static inline void nohz_balance_exit_idle(int 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_check_sched_domain(cpu_rq(cpu)->sd); + sd = rcu_dereference_check_sched_domain(this_rq()->sd); if (!sd || !sd->nohz_idle) goto unlock; @@ -5436,10 +5588,9 @@ unlock: void set_cpu_sd_state_idle(void) { struct sched_domain *sd; - int cpu = smp_processor_id(); rcu_read_lock(); - sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); + sd = rcu_dereference_check_sched_domain(this_rq()->sd); if (!sd || sd->nohz_idle) goto unlock; @@ -5471,7 +5622,7 @@ void nohz_balance_enter_idle(int cpu) set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } -static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, +static int sched_ilb_notifier(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { @@ -5503,7 +5654,7 @@ void update_max_interval(void) */ static void rebalance_domains(int cpu, enum cpu_idle_type idle) { - int balance = 1; + int continue_balancing = 1; struct rq *rq = cpu_rq(cpu); unsigned long interval; struct sched_domain *sd; @@ -5535,7 +5686,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) } if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance)) { + if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { /* * The LBF_SOME_PINNED logic could have changed * env->dst_cpu, so we can't know our idle @@ -5558,7 +5709,7 @@ out: * CPU in our sched group which is doing load balancing more * actively. */ - if (!balance) + if (!continue_balancing) break; } rcu_read_unlock(); @@ -5751,7 +5902,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) entity_tick(cfs_rq, se, queued); } - if (sched_feat_numa(NUMA)) + if (numabalancing_enabled) task_tick_numa(rq, curr); update_rq_runnable_avg(rq, 1); @@ -5848,17 +5999,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) se->vruntime -= cfs_rq->min_vruntime; } -#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) +#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 (p->se.avg.decay_count) { - struct cfs_rq *cfs_rq = cfs_rq_of(&p->se); - __synchronize_entity_decay(&p->se); - subtract_blocked_load_contrib(cfs_rq, - p->se.avg.load_avg_contrib); + if (se->avg.decay_count) { + __synchronize_entity_decay(se); + subtract_blocked_load_contrib(cfs_rq, se->avg.load_avg_contrib); } #endif } @@ -5907,9 +6056,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) #ifndef CONFIG_64BIT cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; #endif -#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) +#ifdef CONFIG_SMP atomic64_set(&cfs_rq->decay_counter, 1); - atomic64_set(&cfs_rq->removed_load, 0); + atomic_long_set(&cfs_rq->removed_load, 0); #endif } @@ -6091,6 +6240,9 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) 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); @@ -6146,9 +6298,8 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_fair, -#ifdef CONFIG_FAIR_GROUP_SCHED .migrate_task_rq = migrate_task_rq_fair, -#endif + .rq_online = rq_online_fair, .rq_offline = rq_offline_fair, diff --git a/kernel/sched/proc.c b/kernel/sched/proc.c new file mode 100644 index 000000000000..16f5a30f9c88 --- /dev/null +++ b/kernel/sched/proc.c @@ -0,0 +1,591 @@ +/* + * kernel/sched/proc.c + * + * Kernel load calculations, forked from sched/core.c + */ + +#include <linux/export.h> + +#include "sched.h" + +unsigned long this_cpu_load(void) +{ + struct rq *this = this_rq(); + return this->cpu_load[0]; +} + + +/* + * 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 index 127a2c4cf4ab..01970c8e64df 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -399,20 +399,6 @@ static inline struct task_group *next_task_group(struct task_group *tg) (iter = next_task_group(iter)) && \ (rt_rq = iter->rt_rq[cpu_of(rq)]);) -static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) -{ - list_add_rcu(&rt_rq->leaf_rt_rq_list, - &rq_of_rt_rq(rt_rq)->leaf_rt_rq_list); -} - -static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq) -{ - list_del_rcu(&rt_rq->leaf_rt_rq_list); -} - -#define for_each_leaf_rt_rq(rt_rq, rq) \ - list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) - #define for_each_sched_rt_entity(rt_se) \ for (; rt_se; rt_se = rt_se->parent) @@ -472,7 +458,7 @@ static int rt_se_boosted(struct sched_rt_entity *rt_se) #ifdef CONFIG_SMP static inline const struct cpumask *sched_rt_period_mask(void) { - return cpu_rq(smp_processor_id())->rd->span; + return this_rq()->rd->span; } #else static inline const struct cpumask *sched_rt_period_mask(void) @@ -509,17 +495,6 @@ 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) -static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) -{ -} - -static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq) -{ -} - -#define for_each_leaf_rt_rq(rt_rq, rq) \ - for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL) - #define for_each_sched_rt_entity(rt_se) \ for (; rt_se; rt_se = NULL) @@ -699,15 +674,6 @@ balanced: } } -static void disable_runtime(struct rq *rq) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - __disable_runtime(rq); - raw_spin_unlock_irqrestore(&rq->lock, flags); -} - static void __enable_runtime(struct rq *rq) { rt_rq_iter_t iter; @@ -732,37 +698,6 @@ static void __enable_runtime(struct rq *rq) } } -static void enable_runtime(struct rq *rq) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - __enable_runtime(rq); - raw_spin_unlock_irqrestore(&rq->lock, flags); -} - -int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int cpu = (int)(long)hcpu; - - switch (action) { - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - disable_runtime(cpu_rq(cpu)); - return NOTIFY_OK; - - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - enable_runtime(cpu_rq(cpu)); - return NOTIFY_OK; - - default: - return NOTIFY_DONE; - } -} - static int balance_runtime(struct rt_rq *rt_rq) { int more = 0; @@ -926,7 +861,7 @@ static void update_curr_rt(struct rq *rq) if (curr->sched_class != &rt_sched_class) return; - delta_exec = rq->clock_task - curr->se.exec_start; + delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; @@ -936,7 +871,7 @@ static void update_curr_rt(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq->clock_task; + curr->se.exec_start = rq_clock_task(rq); cpuacct_charge(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); @@ -1106,9 +1041,6 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) return; - if (!rt_rq->rt_nr_running) - list_add_leaf_rt_rq(rt_rq); - if (head) list_add(&rt_se->run_list, queue); else @@ -1128,8 +1060,6 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) __clear_bit(rt_se_prio(rt_se), array->bitmap); dec_rt_tasks(rt_se, rt_rq); - if (!rt_rq->rt_nr_running) - list_del_leaf_rt_rq(rt_rq); } /* @@ -1385,7 +1315,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) } while (rt_rq); p = rt_task_of(rt_se); - p->se.exec_start = rq->clock_task; + p->se.exec_start = rq_clock_task(rq); return p; } @@ -1434,42 +1364,24 @@ static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) return 0; } -/* Return the second highest RT task, NULL otherwise */ -static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) +/* + * 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 task_struct *next = NULL; - struct sched_rt_entity *rt_se; - struct rt_prio_array *array; - struct rt_rq *rt_rq; - int idx; - - for_each_leaf_rt_rq(rt_rq, rq) { - array = &rt_rq->active; - idx = sched_find_first_bit(array->bitmap); -next_idx: - if (idx >= MAX_RT_PRIO) - continue; - if (next && next->prio <= idx) - continue; - list_for_each_entry(rt_se, array->queue + idx, run_list) { - struct task_struct *p; + struct plist_head *head = &rq->rt.pushable_tasks; + struct task_struct *p; - if (!rt_entity_is_task(rt_se)) - continue; + if (!has_pushable_tasks(rq)) + return NULL; - p = rt_task_of(rt_se); - if (pick_rt_task(rq, p, cpu)) { - next = p; - break; - } - } - if (!next) { - idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1); - goto next_idx; - } + plist_for_each_entry(p, head, pushable_tasks) { + if (pick_rt_task(rq, p, cpu)) + return p; } - return next; + return NULL; } static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); @@ -1743,12 +1655,10 @@ static int pull_rt_task(struct rq *this_rq) double_lock_balance(this_rq, src_rq); /* - * Are there still pullable RT tasks? + * We can pull only a task, which is pushable + * on its rq, and no others. */ - if (src_rq->rt.rt_nr_running <= 1) - goto skip; - - p = pick_next_highest_task_rt(src_rq, this_cpu); + p = pick_highest_pushable_task(src_rq, this_cpu); /* * Do we have an RT task that preempts @@ -2037,7 +1947,7 @@ static void set_curr_task_rt(struct rq *rq) { struct task_struct *p = rq->curr; - p->se.exec_start = rq->clock_task; + p->se.exec_start = rq_clock_task(rq); /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ce39224d6155..b3c5653e1dca 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -10,8 +10,16 @@ #include "cpupri.h" #include "cpuacct.h" +struct rq; + 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); + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -140,10 +148,11 @@ struct task_group { struct cfs_rq **cfs_rq; unsigned long shares; - atomic_t load_weight; - atomic64_t load_avg; +#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; @@ -261,27 +270,21 @@ struct cfs_rq { #endif #ifdef CONFIG_SMP -/* - * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be - * removed when useful for applications beyond shares distribution (e.g. - * load-balance). - */ -#ifdef CONFIG_FAIR_GROUP_SCHED /* * 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). */ - u64 runnable_load_avg, blocked_load_avg; - atomic64_t decay_counter, removed_load; + unsigned long runnable_load_avg, blocked_load_avg; + atomic64_t decay_counter; u64 last_decay; -#endif /* CONFIG_FAIR_GROUP_SCHED */ -/* These always depend on CONFIG_FAIR_GROUP_SCHED */ + atomic_long_t removed_load; + #ifdef CONFIG_FAIR_GROUP_SCHED + /* Required to track per-cpu representation of a task_group */ u32 tg_runnable_contrib; - u64 tg_load_contrib; -#endif /* CONFIG_FAIR_GROUP_SCHED */ + unsigned long tg_load_contrib; /* * h_load = weight * f(tg) @@ -290,6 +293,9 @@ struct cfs_rq { * 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 @@ -353,7 +359,6 @@ struct rt_rq { unsigned long rt_nr_boosted; struct rq *rq; - struct list_head leaf_rt_rq_list; struct task_group *tg; #endif }; @@ -426,9 +431,6 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; -#ifdef CONFIG_SMP - unsigned long h_load_throttle; -#endif /* CONFIG_SMP */ #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED @@ -540,6 +542,16 @@ DECLARE_PER_CPU(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() (&__raw_get_cpu_var(runqueues)) +static inline u64 rq_clock(struct rq *rq) +{ + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + return rq->clock_task; +} + #ifdef CONFIG_SMP #define rcu_dereference_check_sched_domain(p) \ @@ -582,6 +594,7 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) } DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); struct sched_group_power { @@ -652,9 +665,9 @@ extern int group_balance_cpu(struct sched_group *sg); /* * Return the group to which this tasks belongs. * - * We cannot use task_subsys_state() 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. + * 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(). @@ -884,24 +897,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #define WF_FORK 0x02 /* child wakeup after fork */ #define WF_MIGRATED 0x4 /* internal use, task got migrated */ -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; -} - /* * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that @@ -1028,17 +1023,8 @@ extern void update_group_power(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq, int cpu); extern void idle_balance(int this_cpu, struct rq *this_rq); -/* - * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg - * becomes useful in lb - */ -#if defined(CONFIG_FAIR_GROUP_SCHED) 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 *this_rq) {} -static inline void idle_exit_fair(struct rq *this_rq) {} -#endif #else /* CONFIG_SMP */ @@ -1051,7 +1037,6 @@ static inline void idle_balance(int cpu, struct rq *rq) extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); -extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); @@ -1063,6 +1048,8 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern void update_idle_cpu_load(struct rq *this_rq); +extern void init_task_runnable_average(struct task_struct *p); + #ifdef CONFIG_PARAVIRT static inline u64 steal_ticks(u64 steal) { diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 2ef90a51ec5e..5aef494fc8b4 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -61,7 +61,7 @@ static inline void sched_info_reset_dequeued(struct task_struct *t) */ static inline void sched_info_dequeued(struct task_struct *t) { - unsigned long long now = task_rq(t)->clock, delta = 0; + unsigned long long now = rq_clock(task_rq(t)), delta = 0; if (unlikely(sched_info_on())) if (t->sched_info.last_queued) @@ -79,7 +79,7 @@ static inline void sched_info_dequeued(struct task_struct *t) */ static void sched_info_arrive(struct task_struct *t) { - unsigned long long now = task_rq(t)->clock, delta = 0; + unsigned long long now = rq_clock(task_rq(t)), delta = 0; if (t->sched_info.last_queued) delta = now - t->sched_info.last_queued; @@ -100,7 +100,7 @@ static inline void sched_info_queued(struct task_struct *t) { if (unlikely(sched_info_on())) if (!t->sched_info.last_queued) - t->sched_info.last_queued = task_rq(t)->clock; + t->sched_info.last_queued = rq_clock(task_rq(t)); } /* @@ -112,7 +112,7 @@ static inline void sched_info_queued(struct task_struct *t) */ static inline void sched_info_depart(struct task_struct *t) { - unsigned long long delta = task_rq(t)->clock - + unsigned long long delta = rq_clock(task_rq(t)) - t->sched_info.last_arrival; rq_sched_info_depart(task_rq(t), delta); @@ -162,6 +162,39 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) */ /** + * 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. @@ -176,7 +209,7 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -199,7 +232,7 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -222,7 +255,7 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index da5eb5bed84a..e08fbeeb54b9 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -28,7 +28,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) struct task_struct *stop = rq->stop; if (stop && stop->on_rq) { - stop->se.exec_start = rq->clock_task; + stop->se.exec_start = rq_clock_task(rq); return stop; } @@ -57,7 +57,7 @@ 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 - curr->se.exec_start; + delta_exec = rq_clock_task(rq) - curr->se.exec_start; if (unlikely((s64)delta_exec < 0)) delta_exec = 0; @@ -67,7 +67,7 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq->clock_task; + curr->se.exec_start = rq_clock_task(rq); cpuacct_charge(curr, delta_exec); } @@ -79,7 +79,7 @@ static void set_curr_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - stop->se.exec_start = rq->clock_task; + stop->se.exec_start = rq_clock_task(rq); } static void switched_to_stop(struct rq *rq, struct task_struct *p) |