diff options
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r-- | kernel/sched/fair.c | 90 |
1 files changed, 79 insertions, 11 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0c91d72f3e8f..5e65c7eea872 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1925,6 +1925,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) if (p->last_task_numa_placement) { delta = runtime - p->last_sum_exec_runtime; *period = now - p->last_task_numa_placement; + + /* Avoid time going backwards, prevent potential divide error: */ + if (unlikely((s64)*period < 0)) + *period = 0; } else { delta = p->se.avg.load_sum / p->se.load.weight; *period = LOAD_AVG_MAX; @@ -2253,13 +2257,23 @@ 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; + 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++) @@ -2272,8 +2286,14 @@ 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; + } } /* @@ -3862,6 +3882,8 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) 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 @@ -4057,6 +4079,9 @@ 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; @@ -4347,12 +4372,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); int overrun; int idle = 0; + int count = 0; raw_spin_lock(&cfs_b->lock); for (;;) { @@ -4360,6 +4388,36 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + /* + * Grow period by a factor of 2 to avoid losing precision. + * Precision loss in the quota/period ratio can cause __cfs_schedulable + * to fail. + */ + new = old * 2; + if (new < max_cfs_quota_period) { + cfs_b->period = ns_to_ktime(new); + cfs_b->quota *= 2; + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } else { + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(old, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun); } if (idle) @@ -6634,10 +6692,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) if (cfs_rq->last_h_load_update == now) return; - cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -6647,7 +6705,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) cfs_rq->last_h_load_update = now; } - while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1); @@ -7879,9 +7937,10 @@ 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) @@ -7899,13 +7958,22 @@ out_all_pinned: sd->nr_balance_failed = 0; 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. + */ + if (env.idle == CPU_NEWLY_IDLE) + goto out; + /* tune up the balancing interval */ if (((env.flags & LBF_ALL_PINNED) && sd->balance_interval < MAX_PINNED_INTERVAL) || (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; - - ld_moved = 0; out: return ld_moved; } |