diff options
| author | Russell King <rmk+kernel@armlinux.org.uk> | 2016-10-06 08:56:43 +0100 |
|---|---|---|
| committer | Russell King <rmk+kernel@armlinux.org.uk> | 2016-10-06 08:56:43 +0100 |
| commit | 301a36fa700f9add6e14f5a95c7573e01578343a (patch) | |
| tree | 6ff94ff3b08b838353b9127eb5f8055b3de6b25f /kernel/sched/core.c | |
| parent | b828f960215f02e5d2c88bbd27565c694254a15a (diff) | |
| parent | b60752f2b20c167859943e001727f0d4da419b23 (diff) | |
| download | linux-301a36fa700f9add6e14f5a95c7573e01578343a.tar.bz2 | |
Merge branches 'misc' and 'sa1111-base' into for-linus
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 41 |
1 files changed, 41 insertions, 0 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5c883fe8e440..44817c640e99 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -74,6 +74,7 @@ #include <linux/context_tracking.h> #include <linux/compiler.h> #include <linux/frame.h> +#include <linux/prefetch.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2015,6 +2016,28 @@ 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; @@ -2972,6 +2995,23 @@ EXPORT_PER_CPU_SYMBOL(kstat); EXPORT_PER_CPU_SYMBOL(kernel_cpustat); /* + * The function fair_sched_class.update_curr accesses the struct curr + * and its field curr->exec_start; when called from task_sched_runtime(), + * we observe a high rate of cache misses in practice. + * Prefetching this data results in improved performance. + */ +static inline void prefetch_curr_exec_start(struct task_struct *p) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *curr = (&p->se)->cfs_rq->curr; +#else + struct sched_entity *curr = (&task_rq(p)->cfs)->curr; +#endif + prefetch(curr); + prefetch(&curr->exec_start); +} + +/* * Return accounted runtime for the task. * In case the task is currently running, return the runtime plus current's * pending runtime that have not been accounted yet. @@ -3005,6 +3045,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) * thread, breaking clock_gettime(). */ if (task_current(rq, p) && task_on_rq_queued(p)) { + prefetch_curr_exec_start(p); update_rq_clock(rq); p->sched_class->update_curr(rq); } |