Commit 0b3e9f3f 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.

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Remove NULL assignment of dattr_cur
  sched: Remove the last NULL entry from sched_feat_names
  sched: Make sched_feat_names const
  sched/rt: Fix SCHED_RR across cgroups
  sched: Move nr_cpus_allowed out of 'struct sched_rt_entity'
  sched: Make sure to not re-read variables after validation
  sched: Fix SD_OVERLAP
  sched: Don't try allocating memory from offline nodes
  sched/nohz: Fix rq->cpu_load calculations some more
  sched/x86: Use cpu_llc_shared_mask(cpu) for coregroup_mask
parents 99becf13 6a4c96ee

arch/blackfin/kernel/process.c

+1 −1
Original line number Diff line number Diff line
@@ -173,7 +173,7 @@ asmlinkage int bfin_clone(struct pt_regs *regs) 
	unsigned long newsp;



#ifdef __ARCH_SYNC_CORE_DCACHE

	if (current->rt.nr_cpus_allowed == num_possible_cpus())

	if (current->nr_cpus_allowed == num_possible_cpus())

		set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));

#endif

arch/x86/kernel/smpboot.c

+1 −9
Original line number Diff line number Diff line
@@ -410,14 +410,6 @@ void __cpuinit set_cpu_sibling_map(int cpu) 
/* maps the cpu to the sched domain representing multi-core */

const struct cpumask *cpu_coregroup_mask(int cpu)

{

	struct cpuinfo_x86 *c = &cpu_data(cpu);

	/*

	 * For perf, we return last level cache shared map.

	 * And for power savings, we return cpu_core_map

	 */

	if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))

		return cpu_core_mask(cpu);

	else

	return cpu_llc_shared_mask(cpu);

}

include/linux/init_task.h

+1 −1
Original line number Diff line number Diff line
@@ -149,6 +149,7 @@ extern struct cred init_cred; 
	.normal_prio	= MAX_PRIO-20,					\

	.policy		= SCHED_NORMAL,					\

	.cpus_allowed	= CPU_MASK_ALL,					\

	.nr_cpus_allowed= NR_CPUS,					\

	.mm		= NULL,						\

	.active_mm	= &init_mm,					\

	.se		= {						\
@@ -157,7 +158,6 @@ extern struct cred init_cred; 
	.rt		= {						\

		.run_list	= LIST_HEAD_INIT(tsk.rt.run_list),	\

		.time_slice	= RR_TIMESLICE,				\

		.nr_cpus_allowed = NR_CPUS,				\

	},								\

	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\

	INIT_PUSHABLE_TASKS(tsk)					\

include/linux/sched.h

+2 −1
Original line number Diff line number Diff line
@@ -145,6 +145,7 @@ extern unsigned long this_cpu_load(void); 




extern void calc_global_load(unsigned long ticks);

extern void update_cpu_load_nohz(void);



extern unsigned long get_parent_ip(unsigned long addr);
@@ -1187,7 +1188,6 @@ struct sched_rt_entity { 
	struct list_head run_list;

	unsigned long timeout;

	unsigned int time_slice;

	int nr_cpus_allowed;



	struct sched_rt_entity *back;

#ifdef CONFIG_RT_GROUP_SCHED
@@ -1252,6 +1252,7 @@ struct task_struct { 
#endif



	unsigned int policy;

	int nr_cpus_allowed;

	cpumask_t cpus_allowed;



#ifdef CONFIG_PREEMPT_RCU

kernel/sched/core.c

+51 −17
Original line number Diff line number Diff line
@@ -142,9 +142,8 @@ const_debug unsigned int sysctl_sched_features = 
#define SCHED_FEAT(name, enabled)	\

	#name ,



static __read_mostly char *sched_feat_names[] = {

static const char * const sched_feat_names[] = {

#include "features.h"

	NULL

};



#undef SCHED_FEAT
@@ -2517,25 +2516,32 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, 
	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.

 */

void update_idle_cpu_load(struct rq *this_rq)

{

	unsigned long curr_jiffies = jiffies;

	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);

	unsigned long load = this_rq->load.weight;

	unsigned long pending_updates;



	/*

	 * Bloody broken means of dealing with nohz, but better than nothing..

	 * jiffies is updated by one cpu, another cpu can drift wrt the jiffy

	 * update and see 0 difference the one time and 2 the next, even though

	 * we ticked at roughtly the same rate.

	 *

	 * Hence we only use this from nohz_idle_balance() and skip this

	 * nonsense when called from the scheduler_tick() since that's

	 * guaranteed a stable rate.

	 * bail if there's load or we're actually up-to-date.

	 */

	if (load || curr_jiffies == this_rq->last_load_update_tick)

		return;
@@ -2546,13 +2552,39 @@ void update_idle_cpu_load(struct rq *this_rq) 
	__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)

{

	/*

	 * See the mess in update_idle_cpu_load().

	 * 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);
@@ -4982,7 +5014,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) 
		p->sched_class->set_cpus_allowed(p, new_mask);



	cpumask_copy(&p->cpus_allowed, new_mask);

	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);

	p->nr_cpus_allowed = cpumask_weight(new_mask);

}



/*
@@ -5997,11 +6029,14 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) 


		cpumask_or(covered, covered, sg_span);



		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));

		sg->sgp = *per_cpu_ptr(sdd->sgp, i);

		atomic_inc(&sg->sgp->ref);



		if (cpumask_test_cpu(cpu, sg_span))

		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||

			       cpumask_first(sg_span) == cpu) {

			WARN_ON_ONCE(!cpumask_test_cpu(cpu, sg_span));

			groups = sg;

		}



		if (!first)

			first = sg;
@@ -6403,7 +6438,7 @@ static void sched_init_numa(void) 
			return;



		for (j = 0; j < nr_node_ids; j++) {

			struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);

			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);

			if (!mask)

				return;
@@ -6691,7 +6726,6 @@ static int init_sched_domains(const struct cpumask *cpu_map) 
	if (!doms_cur)

		doms_cur = &fallback_doms;

	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);

	dattr_cur = NULL;

	err = build_sched_domains(doms_cur[0], NULL);

	register_sched_domain_sysctl();

CRA Git | Maintained and supported by SUSTech CRA and CCSE