X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=blobdiff_plain;f=kernel%2Fsched.c;h=4b3e12ec5a601401c918bdcd979917e83e848c70;hp=d6b149ccf925c320841e8a42f31fd23b6ee64dc6;hb=13d541b057418b886a2951ccb5ebdc56c57dfff9;hpb=34a9d2c39afe74a941b9e88efe2762afc4d82443 diff --git a/kernel/sched.c b/kernel/sched.c index d6b149ccf925..4b3e12ec5a60 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -746,22 +746,19 @@ static inline int cpu_of(struct rq *rq) /* * Return the group to which this tasks belongs. * - * We use task_subsys_state_check() and extend the RCU verification with - * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each - * task it moves into the cgroup. Therefore by holding either of those locks, - * we pin the task to the current cgroup. + * 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. + * + * The same is true for autogroup's p->signal->autogroup->tg, the autogroup + * core changes this before calling sched_move_task(). + * + * Instead we use a 'copy' which is updated from sched_move_task() while + * holding both task_struct::pi_lock and rq::lock. */ static inline struct task_group *task_group(struct task_struct *p) { - struct task_group *tg; - struct cgroup_subsys_state *css; - - css = task_subsys_state_check(p, cpu_cgroup_subsys_id, - lockdep_is_held(&p->pi_lock) || - lockdep_is_held(&task_rq(p)->lock)); - tg = container_of(css, struct task_group, css); - - return autogroup_task_group(p, tg); + return p->sched_task_group; } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ @@ -1019,8 +1016,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. + * + * Pairs with the control dependency and rmb in try_to_wake_up(). */ - smp_wmb(); + smp_mb(); prev->on_cpu = 0; #endif #ifdef CONFIG_DEBUG_SPINLOCK @@ -1885,10 +1884,9 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) #endif -static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); -static void update_cpu_load(struct rq *this_rq); +static void update_idle_cpu_load(struct rq *this_rq); static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { @@ -2193,6 +2191,10 @@ static int irqtime_account_si_update(void) #endif +#ifdef CONFIG_SMP +static void unthrottle_offline_cfs_rqs(struct rq *rq); +#endif + #include "sched_idletask.c" #include "sched_fair.c" #include "sched_rt.c" @@ -2373,7 +2375,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. * * sched_move_task() holds both and thus holding either pins the cgroup, - * see set_task_rq(). + * see task_group(). * * Furthermore, all task_rq users should acquire both locks, see * task_rq_lock(). @@ -2831,6 +2833,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) success = 1; /* we're going to change ->state */ cpu = task_cpu(p); + /* + * Ensure we load p->on_rq _after_ p->state, otherwise it would + * be possible to, falsely, observe p->on_rq == 0 and get stuck + * in smp_cond_load_acquire() below. + * + * sched_ttwu_pending() try_to_wake_up() + * [S] p->on_rq = 1; [L] P->state + * UNLOCK rq->lock -----. + * \ + * +--- RMB + * schedule() / + * LOCK rq->lock -----' + * UNLOCK rq->lock + * + * [task p] + * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq + * + * Pairs with the UNLOCK+LOCK on rq->lock from the + * last wakeup of our task and the schedule that got our task + * current. + */ + smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) goto stat; @@ -2893,8 +2917,10 @@ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - BUG_ON(rq != this_rq()); - BUG_ON(p == current); + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { @@ -2928,7 +2954,7 @@ out: */ int wake_up_process(struct task_struct *p) { - return try_to_wake_up(p, TASK_ALL, 0); + return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); @@ -3188,11 +3214,11 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * If a task dies, then it sets TASK_DEAD in tsk->state and calls * schedule one last time. The schedule call will never return, and * the scheduled task must drop that reference. - * The test for TASK_DEAD must occur while the runqueue locks are - * still held, otherwise prev could be scheduled on another cpu, die - * there before we look at prev->state, and then the reference would - * be dropped twice. - * Manfred Spraul + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_lock_switch), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. */ prev_state = prev->state; finish_arch_switch(prev); @@ -3401,11 +3427,73 @@ unsigned long this_cpu_load(void) } +/* + * 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); +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) { @@ -3422,41 +3510,135 @@ static long calc_load_fold_active(struct rq *this_rq) 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; + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; } #ifdef CONFIG_NO_HZ /* - * For NO_HZ we delay the active fold to the next LOAD_FREQ update. + * 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_tasks_idle; +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 void calc_load_account_idle(struct rq *this_rq) +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) - atomic_long_add(delta, &calc_load_tasks_idle); + if (delta) { + int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); + } } -static long calc_load_fold_idle(void) +void calc_load_exit_idle(void) { - long delta = 0; + struct rq *this_rq = this_rq(); + + /* + * If we're still before the pending sample window, we're done. + */ + this_rq->calc_load_update = calc_load_update; + if (time_before(jiffies, this_rq->calc_load_update)) + return; /* - * Its got a race, we don't care... + * 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. */ - if (atomic_long_read(&calc_load_tasks_idle)) - delta = atomic_long_xchg(&calc_load_tasks_idle, 0); + 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; } @@ -3538,28 +3720,16 @@ calc_load_n(unsigned long load, unsigned long exp, * 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(unsigned long ticks) +static void calc_global_nohz(void) { long delta, active, n; - if (time_before(jiffies, calc_load_update)) - return; - - /* - * If we crossed a calc_load_update boundary, make sure to fold - * any pending idle changes, the respective CPUs might have - * missed the tick driven calc_load_account_active() update - * due to NO_HZ. - */ - delta = calc_load_fold_idle(); - if (delta) - atomic_long_add(delta, &calc_load_tasks); - - /* - * If we were idle for multiple load cycles, apply them. - */ - if (ticks >= LOAD_FREQ) { - n = ticks / LOAD_FREQ; + 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; @@ -3572,45 +3742,21 @@ static void calc_global_nohz(unsigned long ticks) } /* - * Its possible the remainder of the above division also crosses - * a LOAD_FREQ period, the regular check in calc_global_load() - * which comes after this will take care of that. + * Flip the idle index... * - * Consider us being 11 ticks before a cycle completion, and us - * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will - * age us 4 cycles, and the test in calc_global_load() will - * pick up the final one. + * 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 -static void calc_load_account_idle(struct rq *this_rq) -{ -} - -static inline long calc_load_fold_idle(void) -{ - return 0; -} +#else /* !CONFIG_NO_HZ */ -static void calc_global_nohz(unsigned long ticks) -{ -} -#endif +static inline long calc_load_fold_idle(void) { return 0; } +static inline void calc_global_nohz(void) { } -/** - * 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; -} +#endif /* CONFIG_NO_HZ */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -3618,13 +3764,18 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) */ void calc_global_load(unsigned long ticks) { - long active; - - calc_global_nohz(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; @@ -3633,6 +3784,11 @@ void calc_global_load(unsigned long ticks) 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(); } /* @@ -3647,13 +3803,16 @@ static void calc_load_account_active(struct rq *this_rq) return; delta = calc_load_fold_active(this_rq); - delta += calc_load_fold_idle(); 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 @@ -3726,22 +3885,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) * 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) +static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) { - unsigned long this_load = this_rq->load.weight; - unsigned long curr_jiffies = jiffies; - unsigned long pending_updates; int i, scale; this_rq->nr_load_updates++; - /* Avoid repeated calls on same jiffy, when moving in and out of idle */ - if (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 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) { @@ -3766,9 +3916,78 @@ static void update_cpu_load(struct rq *this_rq) sched_avg_update(this_rq); } +#ifdef CONFIG_NO_HZ +/* + * 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. + */ +static 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 */ + +/* + * Called from scheduler_tick() + */ static void update_cpu_load_active(struct rq *this_rq) { - update_cpu_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, this_rq->load.weight, 1); calc_load_account_active(this_rq); } @@ -4169,6 +4388,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) # define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) #endif +static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) +{ + u64 temp = (__force u64) rtime; + + temp *= (__force u64) utime; + + if (sizeof(cputime_t) == 4) + temp = div_u64(temp, (__force u32) total); + else + temp = div64_u64(temp, (__force u64) total); + + return (__force cputime_t) temp; +} + void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); @@ -4178,13 +4411,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) */ rtime = nsecs_to_cputime(p->se.sum_exec_runtime); - if (total) { - u64 temp = rtime; - - temp *= utime; - do_div(temp, total); - utime = (cputime_t)temp; - } else + if (total) + utime = scale_utime(utime, rtime, total); + else utime = rtime; /* @@ -4211,13 +4440,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) total = cputime_add(cputime.utime, cputime.stime); rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - if (total) { - u64 temp = rtime; - - temp *= cputime.utime; - do_div(temp, total); - utime = (cputime_t)temp; - } else + if (total) + utime = scale_utime(cputime.utime, rtime, total); + else utime = rtime; sig->prev_utime = max(sig->prev_utime, utime); @@ -5025,8 +5250,11 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (rt_prio(prio)) p->sched_class = &rt_sched_class; - else + else { + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; + } p->prio = prio; @@ -6041,14 +6269,16 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } while_each_thread(g, p); - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG sysrq_sched_debug_show(); #endif @@ -6371,8 +6601,6 @@ static void unthrottle_offline_cfs_rqs(struct rq *rq) unthrottle_cfs_rq(cfs_rq); } } -#else -static void unthrottle_offline_cfs_rqs(struct rq *rq) {} #endif /* @@ -6400,9 +6628,6 @@ static void migrate_tasks(unsigned int dead_cpu) */ rq->stop = NULL; - /* Ensure any throttled groups are reachable by pick_next_task */ - unthrottle_offline_cfs_rqs(rq); - for ( ; ; ) { /* * There's this thread running, bail when that's the only @@ -6429,6 +6654,10 @@ static void migrate_tasks(unsigned int dead_cpu) #endif /* CONFIG_HOTPLUG_CPU */ +#if !defined(CONFIG_HOTPLUG_CPU) || !defined(CONFIG_CFS_BANDWIDTH) +static void unthrottle_offline_cfs_rqs(struct rq *rq) {} +#endif + #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) static struct ctl_table sd_ctl_dir[] = { @@ -6477,16 +6706,25 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - mode_t mode, proc_handler *proc_handler) + mode_t mode, proc_handler *proc_handler, + bool load_idx) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } } static struct ctl_table * @@ -6498,30 +6736,30 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return NULL; set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[9], "cache_nice_tries", &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring); + CORENAME_MAX_SIZE, 0444, proc_dostring, false); /* &table[12] is terminator */ return table; @@ -6959,11 +7197,11 @@ static int init_rootdomain(struct root_domain *rd) { memset(rd, 0, sizeof(*rd)); - if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_online; if (cpupri_init(&rd->cpupri) != 0) @@ -7430,11 +7668,8 @@ int sched_domain_level_max; static int __init setup_relax_domain_level(char *str) { - unsigned long val; - - val = simple_strtoul(str, NULL, 0); - if (val < sched_domain_level_max) - default_relax_domain_level = val; + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); return 1; } @@ -7605,16 +7840,26 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sd_data *sdd = &tl->data; for_each_cpu(j, cpu_map) { - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); - if (sd && (sd->flags & SD_OVERLAP)) - free_sched_groups(sd->groups, 0); - kfree(*per_cpu_ptr(sdd->sd, j)); - kfree(*per_cpu_ptr(sdd->sg, j)); - kfree(*per_cpu_ptr(sdd->sgp, j)); + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgp) + kfree(*per_cpu_ptr(sdd->sgp, j)); } free_percpu(sdd->sd); + sdd->sd = NULL; free_percpu(sdd->sg); + sdd->sg = NULL; free_percpu(sdd->sgp); + sdd->sgp = NULL; } } @@ -7627,7 +7872,6 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, if (!sd) return child; - set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); if (child) { sd->level = child->level + 1; @@ -7635,6 +7879,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, child->parent = sd; } sd->child = child; + set_domain_attribute(sd, attr); return sd; } @@ -7993,34 +8238,66 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. */ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + case CPU_ONLINE: case CPU_DOWN_FAILED: cpuset_update_active_cpus(); - return NOTIFY_OK; + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { case CPU_DOWN_PREPARE: cpuset_update_active_cpus(); - return NOTIFY_OK; + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } static int update_runtime(struct notifier_block *nfb, @@ -8756,6 +9033,7 @@ void sched_destroy_group(struct task_group *tg) */ void sched_move_task(struct task_struct *tsk) { + struct task_group *tg; int on_rq, running; unsigned long flags; struct rq *rq; @@ -8770,6 +9048,12 @@ 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, + lockdep_is_held(&tsk->sighand->siglock)), + struct task_group, css); + tg = autogroup_task_group(tsk, tg); + tsk->sched_task_group = tg; + #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_move_group) tsk->sched_class->task_move_group(tsk, on_rq); @@ -8851,6 +9135,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg) { struct task_struct *g, *p; + /* + * Autogroups do not have RT tasks; see autogroup_create(). + */ + if (task_group_is_autogroup(tg)) + return 0; + do_each_thread(g, p) { if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) return 1;