Commit f02f79db authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull scheduler fixes from Ingo Molnar:
 "The biggest commit is an irqtime accounting loop latency fix, the rest
  are misc fixes all over the place: deadline scheduling, docs, numa,
  balancer and a bad to-idle latency fix"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/numa: Initialize newidle balance stats in sd_numa_init()
  sched: Fix updating rq->max_idle_balance_cost and rq->next_balance in idle_balance()
  sched: Skip double execution of pick_next_task_fair()
  sched: Use CPUPRI_NR_PRIORITIES instead of MAX_RT_PRIO in cpupri check
  sched/deadline: Fix memory leak
  sched/deadline: Fix sched_yield() behavior
  sched: Sanitize irq accounting madness
  sched/docbook: Fix 'make htmldocs' warnings caused by missing description
parents e6a32c3a 2b4cfe64

include/linux/sched.h

+5 −2
Original line number Diff line number Diff line
@@ -1153,9 +1153,12 @@ struct sched_dl_entity { 
	 *

	 * @dl_boosted tells if we are boosted due to DI. If so we are

	 * outside bandwidth enforcement mechanism (but only until we

	 * exit the critical section).

	 * exit the critical section);

	 *

	 * @dl_yielded tells if task gave up the cpu before consuming

	 * all its available runtime during the last job.

	 */

	int dl_throttled, dl_new, dl_boosted;

	int dl_throttled, dl_new, dl_boosted, dl_yielded;



	/*

	 * Bandwidth enforcement timer. Each -deadline task has its

kernel/sched/core.c

+13 −2
Original line number Diff line number Diff line
@@ -2592,7 +2592,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev) 
	if (likely(prev->sched_class == class &&

		   rq->nr_running == rq->cfs.h_nr_running)) {

		p = fair_sched_class.pick_next_task(rq, prev);

		if (likely(p && p != RETRY_TASK))

		if (unlikely(p == RETRY_TASK))

			goto again;



		/* assumes fair_sched_class->next == idle_sched_class */

		if (unlikely(!p))

			p = idle_sched_class.pick_next_task(rq, prev);



		return p;

	}
@@ -3124,6 +3130,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) 
	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);

	dl_se->dl_throttled = 0;

	dl_se->dl_new = 1;

	dl_se->dl_yielded = 0;

}



static void __setscheduler_params(struct task_struct *p,
@@ -3639,6 +3646,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) 
 * sys_sched_setattr - same as above, but with extended sched_attr

 * @pid: the pid in question.

 * @uattr: structure containing the extended parameters.

 * @flags: for future extension.

 */

SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,

			       unsigned int, flags)
@@ -3783,6 +3791,7 @@ err_size: 
 * @pid: the pid in question.

 * @uattr: structure containing the extended parameters.

 * @size: sizeof(attr) for fwd/bwd comp.

 * @flags: for future extension.

 */

SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,

		unsigned int, size, unsigned int, flags)
@@ -6017,6 +6026,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) 
					,

		.last_balance		= jiffies,

		.balance_interval	= sd_weight,

		.max_newidle_lb_cost	= 0,

		.next_decay_max_lb_cost	= jiffies,

	};

	SD_INIT_NAME(sd, NUMA);

	sd->private = &tl->data;

kernel/sched/cpudeadline.c

+1 −3
Original line number Diff line number Diff line
@@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp) 
 */

void cpudl_cleanup(struct cpudl *cp)

{

	/*

	 * nothing to do for the moment

	 */

	free_cpumask_var(cp->free_cpus);

}

kernel/sched/cpupri.c

+1 −2
Original line number Diff line number Diff line
@@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, 
	int idx = 0;

	int task_pri = convert_prio(p->prio);



	if (task_pri >= MAX_RT_PRIO)

		return 0;

	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);



	for (idx = 0; idx < task_pri; idx++) {

		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];

kernel/sched/cputime.c

+16 −16
Original line number Diff line number Diff line
@@ -332,50 +332,50 @@ out: 
 * softirq as those do not count in task exec_runtime any more.

 */

static void irqtime_account_process_tick(struct task_struct *p, int user_tick,

						struct rq *rq)

					 struct rq *rq, int ticks)

{

	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);

	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);

	u64 cputime = (__force u64) cputime_one_jiffy;

	u64 *cpustat = kcpustat_this_cpu->cpustat;



	if (steal_account_process_tick())

		return;



	cputime *= ticks;

	scaled *= ticks;



	if (irqtime_account_hi_update()) {

		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;

		cpustat[CPUTIME_IRQ] += cputime;

	} else if (irqtime_account_si_update()) {

		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;

		cpustat[CPUTIME_SOFTIRQ] += cputime;

	} else if (this_cpu_ksoftirqd() == p) {

		/*

		 * ksoftirqd time do not get accounted in cpu_softirq_time.

		 * So, we have to handle it separately here.

		 * Also, p->stime needs to be updated for ksoftirqd.

		 */

		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,

					CPUTIME_SOFTIRQ);

		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);

	} else if (user_tick) {

		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);

		account_user_time(p, cputime, scaled);

	} else if (p == rq->idle) {

		account_idle_time(cputime_one_jiffy);

		account_idle_time(cputime);

	} else if (p->flags & PF_VCPU) { /* System time or guest time */

		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);

		account_guest_time(p, cputime, scaled);

	} else {

		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,

					CPUTIME_SYSTEM);

		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);

	}

}



static void irqtime_account_idle_ticks(int ticks)

{

	int i;

	struct rq *rq = this_rq();



	for (i = 0; i < ticks; i++)

		irqtime_account_process_tick(current, 0, rq);

	irqtime_account_process_tick(current, 0, rq, ticks);

}

#else /* CONFIG_IRQ_TIME_ACCOUNTING */

static inline void irqtime_account_idle_ticks(int ticks) {}

static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,

						struct rq *rq) {}

						struct rq *rq, int nr_ticks) {}

#endif /* CONFIG_IRQ_TIME_ACCOUNTING */



/*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick) 
		return;



	if (sched_clock_irqtime) {

		irqtime_account_process_tick(p, user_tick, rq);

		irqtime_account_process_tick(p, user_tick, rq, 1);

		return;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE