diff options
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r-- | kernel/sched/fair.c | 556 |
1 files changed, 298 insertions, 258 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 036be95a87e9..d4bbf68c3161 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -96,12 +96,12 @@ int __weak arch_asym_cpu_priority(int cpu) } /* - * The margin used when comparing utilization with CPU capacity: - * util * margin < capacity * 1024 + * The margin used when comparing utilization with CPU capacity. * * (default: ~20%) */ -static unsigned int capacity_margin = 1280; +#define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024) + #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -1086,6 +1086,21 @@ struct numa_group { unsigned long faults[0]; }; +/* + * For functions that can be called in multiple contexts that permit reading + * ->numa_group (see struct task_struct for locking rules). + */ +static struct numa_group *deref_task_numa_group(struct task_struct *p) +{ + return rcu_dereference_check(p->numa_group, p == current || + (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu))); +} + +static struct numa_group *deref_curr_numa_group(struct task_struct *p) +{ + return rcu_dereference_protected(p->numa_group, p == current); +} + static inline unsigned long group_faults_priv(struct numa_group *ng); static inline unsigned long group_faults_shared(struct numa_group *ng); @@ -1129,10 +1144,12 @@ static unsigned int task_scan_start(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long period = smin; + struct numa_group *ng; /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); @@ -1140,6 +1157,7 @@ static unsigned int task_scan_start(struct task_struct *p) period *= shared + 1; period /= private + shared + 1; } + rcu_read_unlock(); return max(smin, period); } @@ -1148,13 +1166,14 @@ static unsigned int task_scan_max(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long smax; + struct numa_group *ng; /* Watch for min being lower than max due to floor calculations */ smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + ng = deref_curr_numa_group(p); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); unsigned long period = smax; @@ -1169,47 +1188,6 @@ static unsigned int task_scan_max(struct task_struct *p) return max(smin, smax); } -void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) -{ - int mm_users = 0; - struct mm_struct *mm = p->mm; - - if (mm) { - mm_users = atomic_read(&mm->mm_users); - if (mm_users == 1) { - mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); - mm->numa_scan_seq = 0; - } - } - p->node_stamp = 0; - p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; - p->numa_scan_period = sysctl_numa_balancing_scan_delay; - p->numa_work.next = &p->numa_work; - p->numa_faults = NULL; - p->numa_group = NULL; - p->last_task_numa_placement = 0; - p->last_sum_exec_runtime = 0; - - /* New address space, reset the preferred nid */ - if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = NUMA_NO_NODE; - return; - } - - /* - * New thread, keep existing numa_preferred_nid which should be copied - * already by arch_dup_task_struct but stagger when scans start. - */ - if (mm) { - unsigned int delay; - - delay = min_t(unsigned int, task_scan_max(current), - current->numa_scan_period * mm_users * NSEC_PER_MSEC); - delay += 2 * TICK_NSEC; - p->node_stamp = delay; - } -} - static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); @@ -1233,7 +1211,16 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p) pid_t task_numa_group_id(struct task_struct *p) { - return p->numa_group ? p->numa_group->gid : 0; + struct numa_group *ng; + pid_t gid = 0; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) + gid = ng->gid; + rcu_read_unlock(); + + return gid; } /* @@ -1258,11 +1245,13 @@ static inline unsigned long task_faults(struct task_struct *p, int nid) static inline unsigned long group_faults(struct task_struct *p, int nid) { - if (!p->numa_group) + struct numa_group *ng = deref_task_numa_group(p); + + if (!ng) return 0; - return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + - p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; + return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + ng->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) @@ -1400,12 +1389,13 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, static inline unsigned long group_weight(struct task_struct *p, int nid, int dist) { + struct numa_group *ng = deref_task_numa_group(p); unsigned long faults, total_faults; - if (!p->numa_group) + if (!ng) return 0; - total_faults = p->numa_group->total_faults; + total_faults = ng->total_faults; if (!total_faults) return 0; @@ -1419,7 +1409,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { - struct numa_group *ng = p->numa_group; + struct numa_group *ng = deref_curr_numa_group(p); int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; @@ -1600,13 +1590,14 @@ static bool load_too_imbalanced(long src_load, long dst_load, static void task_numa_compare(struct task_numa_env *env, long taskimp, long groupimp, bool maymove) { + struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p); struct rq *dst_rq = cpu_rq(env->dst_cpu); + long imp = p_ng ? groupimp : taskimp; struct task_struct *cur; long src_load, dst_load; - long load; - long imp = env->p->numa_group ? groupimp : taskimp; - long moveimp = imp; int dist = env->dist; + long moveimp = imp; + long load; if (READ_ONCE(dst_rq->numa_migrate_on)) return; @@ -1645,21 +1636,22 @@ static void task_numa_compare(struct task_numa_env *env, * If dst and source tasks are in the same NUMA group, or not * in any group then look only at task weights. */ - if (cur->numa_group == env->p->numa_group) { + cur_ng = rcu_dereference(cur->numa_group); + if (cur_ng == p_ng) { imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* * Add some hysteresis to prevent swapping the * tasks within a group over tiny differences. */ - if (cur->numa_group) + if (cur_ng) imp -= imp / 16; } else { /* * Compare the group weights. If a task is all by itself * (not part of a group), use the task weight instead. */ - if (cur->numa_group && env->p->numa_group) + if (cur_ng && p_ng) imp += group_weight(cur, env->src_nid, dist) - group_weight(cur, env->dst_nid, dist); else @@ -1757,11 +1749,12 @@ static int task_numa_migrate(struct task_struct *p) .best_imp = 0, .best_cpu = -1, }; + unsigned long taskweight, groupweight; struct sched_domain *sd; + long taskimp, groupimp; + struct numa_group *ng; struct rq *best_rq; - unsigned long taskweight, groupweight; int nid, ret, dist; - long taskimp, groupimp; /* * Pick the lowest SD_NUMA domain, as that would have the smallest @@ -1807,7 +1800,8 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { + ng = deref_curr_numa_group(p); + if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1840,7 +1834,7 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group) { + if (ng) { if (env.best_cpu == -1) nid = env.src_nid; else @@ -2135,6 +2129,7 @@ static void task_numa_placement(struct task_struct *p) unsigned long total_faults; u64 runtime, period; spinlock_t *group_lock = NULL; + struct numa_group *ng; /* * The p->mm->numa_scan_seq field gets updated without @@ -2152,8 +2147,9 @@ static void task_numa_placement(struct task_struct *p) runtime = numa_get_avg_runtime(p, &period); /* If the task is part of a group prevent parallel updates to group stats */ - if (p->numa_group) { - group_lock = &p->numa_group->lock; + ng = deref_curr_numa_group(p); + if (ng) { + group_lock = &ng->lock; spin_lock_irq(group_lock); } @@ -2194,7 +2190,7 @@ static void task_numa_placement(struct task_struct *p) p->numa_faults[cpu_idx] += f_diff; faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; - if (p->numa_group) { + if (ng) { /* * safe because we can only change our own group * @@ -2202,14 +2198,14 @@ static void task_numa_placement(struct task_struct *p) * nid and priv in a specific region because it * is at the beginning of the numa_faults array. */ - p->numa_group->faults[mem_idx] += diff; - p->numa_group->faults_cpu[mem_idx] += f_diff; - p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[mem_idx]; + ng->faults[mem_idx] += diff; + ng->faults_cpu[mem_idx] += f_diff; + ng->total_faults += diff; + group_faults += ng->faults[mem_idx]; } } - if (!p->numa_group) { + if (!ng) { if (faults > max_faults) { max_faults = faults; max_nid = nid; @@ -2220,8 +2216,8 @@ static void task_numa_placement(struct task_struct *p) } } - if (p->numa_group) { - numa_group_count_active_nodes(p->numa_group); + if (ng) { + numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_nid); } @@ -2255,7 +2251,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, int cpu = cpupid_to_cpu(cpupid); int i; - if (unlikely(!p->numa_group)) { + if (unlikely(!deref_curr_numa_group(p))) { unsigned int size = sizeof(struct numa_group) + 4*nr_node_ids*sizeof(unsigned long); @@ -2291,7 +2287,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!grp) goto no_join; - my_grp = p->numa_group; + my_grp = deref_curr_numa_group(p); if (grp == my_grp) goto no_join; @@ -2353,13 +2349,24 @@ no_join: return; } -void task_numa_free(struct task_struct *p) +/* + * Get rid of NUMA staticstics associated with a task (either current or dead). + * If @final is set, the task is dead and has reached refcount zero, so we can + * safely free all relevant data structures. Otherwise, there might be + * concurrent reads from places like load balancing and procfs, and we should + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) { - struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults; + /* safe: p either is current or is being freed by current */ + struct numa_group *grp = rcu_dereference_raw(p->numa_group); + unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; + if (!numa_faults) + return; + if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) @@ -2372,8 +2379,14 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - kfree(numa_faults); + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } } /* @@ -2426,7 +2439,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - ng = p->numa_group; + ng = deref_curr_numa_group(p); if (!priv && !local && ng && ng->active_nodes > 1 && numa_is_active_node(cpu_node, ng) && numa_is_active_node(mem_node, ng)) @@ -2469,7 +2482,7 @@ static void reset_ptenuma_scan(struct task_struct *p) * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). */ -void task_numa_work(struct callback_head *work) +static void task_numa_work(struct callback_head *work) { unsigned long migrate, next_scan, now = jiffies; struct task_struct *p = current; @@ -2482,7 +2495,7 @@ void task_numa_work(struct callback_head *work) SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); - work->next = work; /* protect against double add */ + work->next = work; /* * Who cares about NUMA placement when they're dying. * @@ -2611,6 +2624,50 @@ out: } } +void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) +{ + int mm_users = 0; + struct mm_struct *mm = p->mm; + + if (mm) { + mm_users = atomic_read(&mm->mm_users); + if (mm_users == 1) { + mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + mm->numa_scan_seq = 0; + } + } + p->node_stamp = 0; + p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + /* Protect against double add, see task_tick_numa and task_numa_work */ + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + RCU_INIT_POINTER(p->numa_group, NULL); + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + init_task_work(&p->numa_work, task_numa_work); + + /* New address space, reset the preferred nid */ + if (!(clone_flags & CLONE_VM)) { + p->numa_preferred_nid = NUMA_NO_NODE; + return; + } + + /* + * New thread, keep existing numa_preferred_nid which should be copied + * already by arch_dup_task_struct but stagger when scans start. + */ + if (mm) { + unsigned int delay; + + delay = min_t(unsigned int, task_scan_max(current), + current->numa_scan_period * mm_users * NSEC_PER_MSEC); + delay += 2 * TICK_NSEC; + p->node_stamp = delay; + } +} + /* * Drive the periodic memory faults.. */ @@ -2639,10 +2696,8 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) curr->numa_scan_period = task_scan_start(curr); curr->node_stamp += period; - if (!time_before(jiffies, curr->mm->numa_next_scan)) { - init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + if (!time_before(jiffies, curr->mm->numa_next_scan)) task_work_add(curr, work, true); - } } } @@ -3635,8 +3690,6 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int idle_balance(struct rq *this_rq, struct rq_flags *rf); - static inline unsigned long task_util(struct task_struct *p) { return READ_ONCE(p->se.avg.util_avg); @@ -3753,7 +3806,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) static inline int task_fits_capacity(struct task_struct *p, long capacity) { - return capacity * 1024 > task_util_est(p) * capacity_margin; + return fits_capacity(task_util_est(p), capacity); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -4316,8 +4369,6 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; - cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4339,8 +4390,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) { struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount, expires; - int expires_seq; + u64 amount = 0, min_amount; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4357,65 +4407,23 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - expires_seq = cfs_b->expires_seq; - expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; - /* - * we may have advanced our local expiration to account for allowed - * spread between our sched_clock and the one on which runtime was - * issued. - */ - if (cfs_rq->expires_seq != expires_seq) { - cfs_rq->expires_seq = expires_seq; - cfs_rq->runtime_expires = expires; - } return cfs_rq->runtime_remaining > 0; } -/* - * Note: This depends on the synchronization provided by sched_clock and the - * fact that rq->clock snapshots this value. - */ -static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) -{ - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - - /* if the deadline is ahead of our clock, nothing to do */ - if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) - return; - - if (cfs_rq->runtime_remaining < 0) - return; - - /* - * If the local deadline has passed we have to consider the - * possibility that our sched_clock is 'fast' and the global deadline - * has not truly expired. - * - * Fortunately we can check determine whether this the case by checking - * whether the global deadline(cfs_b->expires_seq) has advanced. - */ - if (cfs_rq->expires_seq == cfs_b->expires_seq) { - /* extend local deadline, drift is bounded above by 2 ticks */ - cfs_rq->runtime_expires += TICK_NSEC; - } else { - /* global deadline is ahead, expiration has passed */ - cfs_rq->runtime_remaining = 0; - } -} - static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; - expire_cfs_rq_runtime(cfs_rq); if (likely(cfs_rq->runtime_remaining > 0)) return; + if (cfs_rq->throttled) + return; /* * if we're unable to extend our runtime we resched so that the active * hierarchy can be throttled @@ -4500,7 +4508,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, dequeue = 1; + long task_delta, idle_task_delta, dequeue = 1; bool empty; se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4511,6 +4519,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) rcu_read_unlock(); task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); /* throttled entity or throttle-on-deactivate */ @@ -4520,6 +4529,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) if (dequeue) dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); qcfs_rq->h_nr_running -= task_delta; + qcfs_rq->idle_h_nr_running -= idle_task_delta; if (qcfs_rq->load.weight) dequeue = 0; @@ -4559,7 +4569,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; int enqueue = 1; - long task_delta; + long task_delta, idle_task_delta; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -4579,6 +4589,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) return; task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { if (se->on_rq) enqueue = 0; @@ -4587,6 +4598,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) if (enqueue) enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); cfs_rq->h_nr_running += task_delta; + cfs_rq->idle_h_nr_running += idle_task_delta; if (cfs_rq_throttled(cfs_rq)) break; @@ -4602,8 +4614,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) resched_curr(rq); } -static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, - u64 remaining, u64 expires) +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) { struct cfs_rq *cfs_rq; u64 runtime; @@ -4619,13 +4630,15 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, if (!cfs_rq_throttled(cfs_rq)) goto next; + /* By the above check, this should never be true */ + SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); + runtime = -cfs_rq->runtime_remaining + 1; if (runtime > remaining) runtime = remaining; remaining -= runtime; cfs_rq->runtime_remaining += runtime; - cfs_rq->runtime_expires = expires; /* we check whether we're throttled above */ if (cfs_rq->runtime_remaining > 0) @@ -4650,7 +4663,7 @@ next: */ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { - u64 runtime, runtime_expires; + u64 runtime; int throttled; /* no need to continue the timer with no bandwidth constraint */ @@ -4678,8 +4691,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u /* account preceding periods in which throttling occurred */ cfs_b->nr_throttled += overrun; - runtime_expires = cfs_b->runtime_expires; - /* * This check is repeated as we are holding onto the new bandwidth while * we unthrottle. This can potentially race with an unthrottled group @@ -4692,8 +4703,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u cfs_b->distribute_running = 1; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ - runtime = distribute_cfs_runtime(cfs_b, runtime, - runtime_expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; @@ -4775,8 +4785,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) return; raw_spin_lock(&cfs_b->lock); - if (cfs_b->quota != RUNTIME_INF && - cfs_rq->runtime_expires == cfs_b->runtime_expires) { + if (cfs_b->quota != RUNTIME_INF) { cfs_b->runtime += slack_runtime; /* we are under rq->lock, defer unthrottling using a timer */ @@ -4809,7 +4818,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); unsigned long flags; - u64 expires; /* confirm we're still not at a refresh boundary */ raw_spin_lock_irqsave(&cfs_b->lock, flags); @@ -4827,7 +4835,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - expires = cfs_b->runtime_expires; if (runtime) cfs_b->distribute_running = 1; @@ -4836,11 +4843,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); - if (expires == cfs_b->runtime_expires) - lsub_positive(&cfs_b->runtime, runtime); + lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } @@ -4997,8 +5003,6 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period_active = 1; overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } @@ -5176,7 +5180,7 @@ static inline unsigned long cpu_util(int cpu); static inline bool cpu_overutilized(int cpu) { - return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); + return !fits_capacity(cpu_util(cpu), capacity_of(cpu)); } static inline void update_overutilized_status(struct rq *rq) @@ -5200,6 +5204,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int idle_h_nr_running = task_has_idle_policy(p); /* * The code below (indirectly) updates schedutil which looks at @@ -5232,6 +5237,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; flags = ENQUEUE_WAKEUP; } @@ -5239,6 +5245,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5300,6 +5307,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int task_sleep = flags & DEQUEUE_SLEEP; + int idle_h_nr_running = task_has_idle_policy(p); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); @@ -5314,6 +5322,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { @@ -5333,6 +5342,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5366,6 +5376,15 @@ static struct { #endif /* CONFIG_NO_HZ_COMMON */ +/* CPU only has SCHED_IDLE tasks enqueued */ +static int sched_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + rq->nr_running); +} + static unsigned long cpu_runnable_load(struct rq *rq) { return cfs_rq_runnable_load_avg(&rq->cfs); @@ -5688,7 +5707,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this unsigned int min_exit_latency = UINT_MAX; u64 latest_idle_timestamp = 0; int least_loaded_cpu = this_cpu; - int shallowest_idle_cpu = -1; + int shallowest_idle_cpu = -1, si_cpu = -1; int i; /* Check if we have any choice: */ @@ -5719,7 +5738,12 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this latest_idle_timestamp = rq->idle_stamp; shallowest_idle_cpu = i; } - } else if (shallowest_idle_cpu == -1) { + } else if (shallowest_idle_cpu == -1 && si_cpu == -1) { + if (sched_idle_cpu(i)) { + si_cpu = i; + continue; + } + load = cpu_runnable_load(cpu_rq(i)); if (load < min_load) { min_load = load; @@ -5728,7 +5752,11 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this } } - return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; + if (shallowest_idle_cpu != -1) + return shallowest_idle_cpu; + if (si_cpu != -1) + return si_cpu; + return least_loaded_cpu; } static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, @@ -5881,7 +5909,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int */ static int select_idle_smt(struct task_struct *p, int target) { - int cpu; + int cpu, si_cpu = -1; if (!static_branch_likely(&sched_smt_present)) return -1; @@ -5891,9 +5919,11 @@ static int select_idle_smt(struct task_struct *p, int target) continue; if (available_idle_cpu(cpu)) return cpu; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } - return -1; + return si_cpu; } #else /* CONFIG_SCHED_SMT */ @@ -5921,8 +5951,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t u64 avg_cost, avg_idle; u64 time, cost; s64 delta; - int cpu, nr = INT_MAX; int this = smp_processor_id(); + int cpu, nr = INT_MAX, si_cpu = -1; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -5950,11 +5980,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!--nr) - return -1; + return si_cpu; if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) break; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } time = cpu_clock(this) - time; @@ -5973,13 +6005,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) struct sched_domain *sd; int i, recent_used_cpu; - if (available_idle_cpu(target)) + if (available_idle_cpu(target) || sched_idle_cpu(target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ - if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev)) + if (prev != target && cpus_share_cache(prev, target) && + (available_idle_cpu(prev) || sched_idle_cpu(prev))) return prev; /* Check a recently used CPU as a potential idle candidate: */ @@ -5987,7 +6020,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (recent_used_cpu != prev && recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && - available_idle_cpu(recent_used_cpu) && + (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { /* * Replace recent_used_cpu with prev as it is a potential @@ -6223,69 +6256,55 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) } /* - * compute_energy(): Estimates the energy that would be consumed if @p was + * compute_energy(): Estimates the energy that @pd would consume if @p was * migrated to @dst_cpu. compute_energy() predicts what will be the utilization - * landscape of the * CPUs after the task migration, and uses the Energy Model + * landscape of @pd's CPUs after the task migration, and uses the Energy Model * to compute what would be the energy if we decided to actually migrate that * task. */ static long compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) { - unsigned int max_util, util_cfs, cpu_util, cpu_cap; - unsigned long sum_util, energy = 0; - struct task_struct *tsk; + struct cpumask *pd_mask = perf_domain_span(pd); + unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); + unsigned long max_util = 0, sum_util = 0; int cpu; - for (; pd; pd = pd->next) { - struct cpumask *pd_mask = perf_domain_span(pd); + /* + * The capacity state of CPUs of the current rd can be driven by CPUs + * of another rd if they belong to the same pd. So, account for the + * utilization of these CPUs too by masking pd with cpu_online_mask + * instead of the rd span. + * + * If an entire pd is outside of the current rd, it will not appear in + * its pd list and will not be accounted by compute_energy(). + */ + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu); + struct task_struct *tsk = cpu == dst_cpu ? p : NULL; /* - * The energy model mandates all the CPUs of a performance - * domain have the same capacity. + * Busy time computation: utilization clamping is not + * required since the ratio (sum_util / cpu_capacity) + * is already enough to scale the EM reported power + * consumption at the (eventually clamped) cpu_capacity. */ - cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); - max_util = sum_util = 0; + sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, + ENERGY_UTIL, NULL); /* - * The capacity state of CPUs of the current rd can be driven by - * CPUs of another rd if they belong to the same performance - * domain. So, account for the utilization of these CPUs too - * by masking pd with cpu_online_mask instead of the rd span. - * - * If an entire performance domain is outside of the current rd, - * it will not appear in its pd list and will not be accounted - * by compute_energy(). + * Performance domain frequency: utilization clamping + * must be considered since it affects the selection + * of the performance domain frequency. + * NOTE: in case RT tasks are running, by default the + * FREQUENCY_UTIL's utilization can be max OPP. */ - for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { - util_cfs = cpu_util_next(cpu, p, dst_cpu); - - /* - * Busy time computation: utilization clamping is not - * required since the ratio (sum_util / cpu_capacity) - * is already enough to scale the EM reported power - * consumption at the (eventually clamped) cpu_capacity. - */ - sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, - ENERGY_UTIL, NULL); - - /* - * Performance domain frequency: utilization clamping - * must be considered since it affects the selection - * of the performance domain frequency. - * NOTE: in case RT tasks are running, by default the - * FREQUENCY_UTIL's utilization can be max OPP. - */ - tsk = cpu == dst_cpu ? p : NULL; - cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, - FREQUENCY_UTIL, tsk); - max_util = max(max_util, cpu_util); - } - - energy += em_pd_energy(pd->em_pd, max_util, sum_util); + cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, + FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_util); } - return energy; + return em_pd_energy(pd->em_pd, max_util, sum_util); } /* @@ -6327,21 +6346,19 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * other use-cases too. So, until someone finds a better way to solve this, * let's keep things simple by re-using the existing slow path. */ - static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { - unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX; + unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + unsigned long cpu_cap, util, base_energy = 0; int cpu, best_energy_cpu = prev_cpu; - struct perf_domain *head, *pd; - unsigned long cpu_cap, util; struct sched_domain *sd; + struct perf_domain *pd; rcu_read_lock(); pd = rcu_dereference(rd->pd); if (!pd || READ_ONCE(rd->overutilized)) goto fail; - head = pd; /* * Energy-aware wake-up happens on the lowest sched_domain starting @@ -6358,9 +6375,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) goto unlock; for (; pd; pd = pd->next) { - unsigned long cur_energy, spare_cap, max_spare_cap = 0; + unsigned long cur_delta, spare_cap, max_spare_cap = 0; + unsigned long base_energy_pd; int max_spare_cap_cpu = -1; + /* Compute the 'base' energy of the pd, without @p */ + base_energy_pd = compute_energy(p, -1, pd); + base_energy += base_energy_pd; + for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6368,14 +6390,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Skip CPUs that will be overutilized. */ util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - if (cpu_cap * 1024 < util * capacity_margin) + if (!fits_capacity(util, cpu_cap)) continue; /* Always use prev_cpu as a candidate. */ if (cpu == prev_cpu) { - prev_energy = compute_energy(p, prev_cpu, head); - best_energy = min(best_energy, prev_energy); - continue; + prev_delta = compute_energy(p, prev_cpu, pd); + prev_delta -= base_energy_pd; + best_delta = min(best_delta, prev_delta); } /* @@ -6391,9 +6413,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Evaluate the energy impact of using this CPU. */ if (max_spare_cap_cpu >= 0) { - cur_energy = compute_energy(p, max_spare_cap_cpu, head); - if (cur_energy < best_energy) { - best_energy = cur_energy; + cur_delta = compute_energy(p, max_spare_cap_cpu, pd); + cur_delta -= base_energy_pd; + if (cur_delta < best_delta) { + best_delta = cur_delta; best_energy_cpu = max_spare_cap_cpu; } } @@ -6405,10 +6428,10 @@ unlock: * Pick the best CPU if prev_cpu cannot be used, or if it saves at * least 6% of the energy used by prev_cpu. */ - if (prev_energy == ULONG_MAX) + if (prev_delta == ULONG_MAX) return best_energy_cpu; - if ((prev_energy - best_energy) > (prev_energy >> 4)) + if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) return best_energy_cpu; return prev_cpu; @@ -6742,7 +6765,7 @@ again: goto idle; #ifdef CONFIG_FAIR_GROUP_SCHED - if (prev->sched_class != &fair_sched_class) + if (!prev || prev->sched_class != &fair_sched_class) goto simple; /* @@ -6819,8 +6842,8 @@ again: goto done; simple: #endif - - put_prev_task(rq, prev); + if (prev) + put_prev_task(rq, prev); do { se = pick_next_entity(cfs_rq, NULL); @@ -6848,11 +6871,13 @@ done: __maybe_unused; return p; idle: - update_misfit_status(NULL, rq); - new_tasks = idle_balance(rq, rf); + if (!rf) + return NULL; + + new_tasks = newidle_balance(rq, rf); /* - * Because idle_balance() releases (and re-acquires) rq->lock, it is + * Because newidle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we * must re-start the pick_next_entity() loop. */ @@ -6874,7 +6899,7 @@ idle: /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -7376,7 +7401,7 @@ static int detach_tasks(struct lb_env *env) detached++; env->imbalance -= load; -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * NEWIDLE balancing is a source of latency, so preemptible * kernels will stop after the first task is detached to minimize @@ -7923,8 +7948,7 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) static inline bool group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->min_capacity * capacity_margin < - ref->sgc->min_capacity * 1024; + return fits_capacity(sg->sgc->min_capacity, ref->sgc->min_capacity); } /* @@ -7934,8 +7958,7 @@ group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) static inline bool group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->max_capacity * capacity_margin < - ref->sgc->max_capacity * 1024; + return fits_capacity(sg->sgc->max_capacity, ref->sgc->max_capacity); } static inline enum @@ -8993,9 +9016,10 @@ more_balance: out_balanced: /* * We reach balance although we may have faced some affinity - * constraints. Clear the imbalance flag if it was set. + * constraints. Clear the imbalance flag only if other tasks got + * a chance to move and fix the imbalance. */ - if (sd_parent) { + if (sd_parent && !(env.flags & LBF_ALL_PINNED)) { int *group_imbalance = &sd_parent->groups->sgc->imbalance; if (*group_imbalance) @@ -9016,10 +9040,10 @@ out_one_pinned: ld_moved = 0; /* - * idle_balance() disregards balance intervals, so we could repeatedly - * reach this code, which would lead to balance_interval skyrocketting - * in a short amount of time. Skip the balance_interval increase logic - * to avoid that. + * newidle_balance() disregards balance intervals, so we could + * repeatedly reach this code, which would lead to balance_interval + * skyrocketting in a short amount of time. Skip the balance_interval + * increase logic to avoid that. */ if (env.idle == CPU_NEWLY_IDLE) goto out; @@ -9729,7 +9753,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static int idle_balance(struct rq *this_rq, struct rq_flags *rf) +int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; @@ -9737,6 +9761,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) int pulled_task = 0; u64 curr_cost = 0; + update_misfit_status(NULL, this_rq); /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -10121,9 +10146,19 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * This routine is mostly called to set cfs_rq->curr field when a task * migrates between groups/classes. */ -static void set_curr_task_fair(struct rq *rq) +static void set_next_task_fair(struct rq *rq, struct task_struct *p) { - struct sched_entity *se = &rq->curr->se; + struct sched_entity *se = &p->se; + +#ifdef CONFIG_SMP + if (task_on_rq_queued(p)) { + /* + * Move the next running task to the front of the list, so our + * cfs_tasks list becomes MRU one. + */ + list_move(&se->group_node, &rq->cfs_tasks); + } +#endif for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -10241,18 +10276,18 @@ err: void online_fair_sched_group(struct task_group *tg) { struct sched_entity *se; + struct rq_flags rf; struct rq *rq; int i; for_each_possible_cpu(i) { rq = cpu_rq(i); se = tg->se[i]; - - raw_spin_lock_irq(&rq->lock); + rq_lock_irq(rq, &rf); update_rq_clock(rq); attach_entity_cfs_rq(se); sync_throttle(tg, i); - raw_spin_unlock_irq(&rq->lock); + rq_unlock_irq(rq, &rf); } } @@ -10394,7 +10429,9 @@ const struct sched_class fair_sched_class = { .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_fair, @@ -10407,7 +10444,6 @@ const struct sched_class fair_sched_class = { .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_fair, .task_tick = task_tick_fair, .task_fork = task_fork_fair, @@ -10444,18 +10480,22 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m) { int node; unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + struct numa_group *ng; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); for_each_online_node(node) { if (p->numa_faults) { tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; } - if (p->numa_group) { - gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], - gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + if (ng) { + gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; } print_numa_stats(m, node, tsf, tpf, gsf, gpf); } + rcu_read_unlock(); } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ |