scheduler changes for v3.8

index 3deac95..7fcf7f0 100644
@@ -103,5 +103,7 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
 #define cputime64_to_clock_t(__ct)	\
 	cputime_to_clock_t((__force cputime_t)__ct)
 
+extern void arch_vtime_task_switch(struct task_struct *tsk);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */

index f638821..b1995ef 100644
@@ -83,7 +83,7 @@ static struct clocksource *itc_clocksource;
 
 extern cputime_t cycle_to_cputime(u64 cyc);
 
-static void vtime_account_user(struct task_struct *tsk)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_utime;
 	struct thread_info *ti = task_thread_info(tsk);

@@ -100,18 +100,11 @@ static void vtime_account_user(struct task_struct *tsk)
  * accumulated times to the current process, and to prepare accounting on
  * the next process.
  */
-void vtime_task_switch(struct task_struct *prev)
+void arch_vtime_task_switch(struct task_struct *prev)
 {
 	struct thread_info *pi = task_thread_info(prev);
 	struct thread_info *ni = task_thread_info(current);
 
-	if (idle_task(smp_processor_id()) != prev)
-		vtime_account_system(prev);
-	else
-		vtime_account_idle(prev);
-
-	vtime_account_user(prev);
-
 	pi->ac_stamp = ni->ac_stamp;
 	ni->ac_stime = ni->ac_utime = 0;
 }

@@ -126,6 +119,8 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 	cputime_t delta_stime;
 	__u64 now;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));

@@ -147,15 +142,6 @@ void vtime_account_idle(struct task_struct *tsk)
 	account_idle_time(vtime_delta(tsk));
 }
 
-/*
- * Called from the timer interrupt handler to charge accumulated user time
- * to the current process.  Must be called with interrupts disabled.
- */
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	vtime_account_user(p);
-}
-
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
 static irqreturn_t

index 487d46f..483733b 100644
@@ -228,6 +228,8 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 
 #define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
 
+static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
 #endif /* __KERNEL__ */
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __POWERPC_CPUTIME_H */

index ce4cb77..b3b1435 100644
@@ -297,6 +297,8 @@ static u64 vtime_delta(struct task_struct *tsk,
 	u64 now, nowscaled, deltascaled;
 	u64 udelta, delta, user_scaled;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	now = mftb();
 	nowscaled = read_spurr(now);
 	get_paca()->system_time += now - get_paca()->starttime;

@@ -355,15 +357,15 @@ void vtime_account_idle(struct task_struct *tsk)
 }
 
 /*
- * Transfer the user and system times accumulated in the paca
- * by the exception entry and exit code to the generic process
- * user and system time records.
+ * Transfer the user time accumulated in the paca
+ * by the exception entry and exit code to the generic
+ * process user time records.
  * Must be called with interrupts disabled.
- * Assumes that vtime_account() has been called recently
- * (i.e. since the last entry from usermode) so that
+ * Assumes that vtime_account_system/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void account_process_tick(struct task_struct *tsk, int user_tick)
+void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
 

@@ -375,12 +377,6 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	account_user_time(tsk, utime, utimescaled);
 }
 
-void vtime_task_switch(struct task_struct *prev)
-{
-	vtime_account(prev);
-	account_process_tick(prev, 0);
-}
-
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
 #endif

index 023d5ae..d2ff4137 100644
@@ -14,6 +14,7 @@
 
 
 #define __ARCH_HAS_VTIME_ACCOUNT
+#define __ARCH_HAS_VTIME_TASK_SWITCH
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 

index 7903344..e84b8b6 100644
@@ -112,7 +112,12 @@ void vtime_task_switch(struct task_struct *prev)
 	S390_lowcore.system_timer = ti->system_timer;
 }
 
-void account_process_tick(struct task_struct *tsk, int user_tick)
+/*
+ * In s390, accounting pending user time also implies
+ * accounting system time in order to correctly compute
+ * the stolen time accounting.
+ */
+void vtime_account_user(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk, HARDIRQ_OFFSET))
 		virt_timer_expire();

@@ -127,6 +132,8 @@ void vtime_account(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, system;
 
+	WARN_ON_ONCE(!irqs_disabled());
+
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;

@@ -140,6 +147,10 @@ void vtime_account(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 
+void vtime_account_system(struct task_struct *tsk)
+__attribute__((alias("vtime_account")));
+EXPORT_SYMBOL_GPL(vtime_account_system);
+
 void __kprobes vtime_stop_cpu(void)
 {
 	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);

index ecced9d..d91a955 100644
@@ -608,9 +608,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
-	local_irq_disable();
 	kvm_guest_enter();
-	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	trace_kvm_s390_sie_enter(vcpu,

@@ -629,9 +627,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
-	local_irq_disable();
 	kvm_guest_exit();
-	local_irq_enable();
 
 	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 	return rc;

index c1c207c..d369670 100644
@@ -438,7 +438,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			thread_group_times(task, &utime, &stime);
+			thread_group_cputime_adjusted(task, &utime, &stime);
 			gtime += sig->gtime;
 		}
 

@@ -454,7 +454,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (!whole) {
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_times(task, &utime, &stime);
+		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task->gtime;
 	}
 

index cab3da3..624ef3f 100644
@@ -4,6 +4,7 @@
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
+#include <linux/vtime.h>
 #include <asm/hardirq.h>
 
 /*

@@ -129,16 +130,6 @@ extern void synchronize_irq(unsigned int irq);
 # define synchronize_irq(irq)	barrier()
 #endif
 
-struct task_struct;
-
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
-#else
-extern void vtime_account(struct task_struct *tsk);
-#endif
-
 #if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 
 static inline void rcu_nmi_enter(void)

@@ -162,7 +153,7 @@ extern void rcu_nmi_exit(void);
  */
 #define __irq_enter()					\
 	do {						\
-		vtime_account(current);		\
+		vtime_account_irq_enter(current);	\
 		add_preempt_count(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)

@@ -178,7 +169,7 @@ extern void irq_enter(void);
 #define __irq_exit()					\
 	do {						\
 		trace_hardirq_exit();			\
-		vtime_account(current);		\
+		vtime_account_irq_exit(current);	\
 		sub_preempt_count(HARDIRQ_OFFSET);	\
 	} while (0)
 

index 36d12f0..66b7078 100644
@@ -7,6 +7,7 @@
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
+#include <linux/vtime.h>
 #include <asm/irq.h>
 #include <asm/cputime.h>
 

@@ -126,16 +127,16 @@ extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t)
 extern void account_steal_time(cputime_t);
 extern void account_idle_time(cputime_t);
 
-extern void account_process_tick(struct task_struct *, int user);
-extern void account_steal_ticks(unsigned long ticks);
-extern void account_idle_ticks(unsigned long ticks);
-
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void vtime_task_switch(struct task_struct *prev);
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
+static inline void account_process_tick(struct task_struct *tsk, int user)
+{
+	vtime_account_user(tsk);
+}
 #else
-static inline void vtime_task_switch(struct task_struct *prev) { }
+extern void account_process_tick(struct task_struct *, int user);
 #endif
 
+extern void account_steal_ticks(unsigned long ticks);
+extern void account_idle_ticks(unsigned long ticks);
+
 #endif /* _LINUX_KERNEL_STAT_H */

index ecc5543..d5cddd8 100644
@@ -726,7 +726,11 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 static inline void kvm_guest_enter(void)
 {
 	BUG_ON(preemptible());
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system_irqsafe(current);
 	current->flags |= PF_VCPU;
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode

@@ -740,7 +744,11 @@ static inline void kvm_guest_enter(void)
 
 static inline void kvm_guest_exit(void)
 {
-	vtime_account(current);
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system_irqsafe(current);
 	current->flags &= ~PF_VCPU;
 }
 

96 lines not on this page · raw message

48 lines not on this page · raw message

index 346616c..618f7ee 100644
@@ -1186,11 +1186,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
 		 *
-		 * We use thread_group_times() to get times for the thread
+		 * We use thread_group_cputime_adjusted() to get times for the thread
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
-		thread_group_times(p, &tgutime, &tgstime);
+		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;

index 8b20ab7..0e7cdb9 100644
@@ -1222,7 +1222,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	p->prev_utime = p->prev_stime = 0;
+	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));

index 125cb67..d738402 100644
@@ -217,30 +217,6 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
-void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
-{
-	struct signal_struct *sig = tsk->signal;
-	struct task_struct *t;
-
-	times->utime = sig->utime;
-	times->stime = sig->stime;
-	times->sum_exec_runtime = sig->sum_sched_runtime;
-
-	rcu_read_lock();
-	/* make sure we can trust tsk->thread_group list */
-	if (!likely(pid_alive(tsk)))
-		goto out;
-
-	t = tsk;
-	do {
-		times->utime += t->utime;
-		times->stime += t->stime;
-		times->sum_exec_runtime += task_sched_runtime(t);
-	} while_each_thread(tsk, t);
-out:
-	rcu_read_unlock();
-}
-
 static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
 {
 	if (b->utime > a->utime)

index 15f60d0..0984a21 100644
@@ -143,11 +143,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
+out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }

index 443232e..8bd0471 100644
@@ -4,6 +4,11 @@
 #include <linux/rwsem.h>
 
 struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;

index 2d8927f..5dae0d2 100644
@@ -952,6 +952,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		if (p->sched_class->migrate_task_rq)
+			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
 	}

@@ -1524,6 +1526,15 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+	p->se.avg.runnable_avg_period = 0;
+	p->se.avg.runnable_avg_sum = 0;
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif

202 lines not on this page · raw message

index 6f79596..2cd3c1b 100644
@@ -61,14 +61,20 @@ static unsigned long nsec_low(unsigned long long nsec)
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
 	struct sched_entity *se = tg->se[cpu];
-	if (!se)
-		return;
 
 #define P(F) \
 	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
 #define PN(F) \
 	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
 
+	if (!se) {
+		struct sched_avg *avg = &cpu_rq(cpu)->avg;
+		P(avg->runnable_avg_sum);
+		P(avg->runnable_avg_period);
+		return;
+	}
+
+
 	PN(se->exec_start);
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);

@@ -85,6 +91,12 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
+#ifdef CONFIG_SMP
+	P(se->avg.runnable_avg_sum);
+	P(se->avg.runnable_avg_period);
+	P(se->avg.load_avg_contrib);
+	P(se->avg.decay_count);
+#endif
 #undef PN
 #undef P
 }

@@ -206,14 +218,18 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
-			SPLIT_NS(cfs_rq->load_avg));
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
-			SPLIT_NS(cfs_rq->load_period));
-	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
-			cfs_rq->load_contribution);
-	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
-			atomic_read(&cfs_rq->tg->load_weight));
+	SEQ_printf(m, "  .%-30s: %lld\n", "runnable_load_avg",
+			cfs_rq->runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
+			cfs_rq->blocked_load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
+			atomic64_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
+			cfs_rq->tg_load_contrib);
+	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
+			cfs_rq->tg_runnable_contrib);
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
+			atomic_read(&cfs_rq->tg->runnable_avg));
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);

1,188 lines not on this page · raw message

index eebefca..e68e69a 100644
@@ -32,6 +32,11 @@ SCHED_FEAT(LAST_BUDDY, true)
 SCHED_FEAT(CACHE_HOT_BUDDY, true)
 
 /*
+ * Allow wakeup-time preemption of the current task:
+ */
+SCHED_FEAT(WAKEUP_PREEMPTION, true)
+
+/*
  * Use arch dependent cpu power functions
  */
 SCHED_FEAT(ARCH_POWER, true)

101 lines not on this page · raw message

index cc96bdc..ed567ba 100644
@@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	vtime_account(current);
+	vtime_account_irq_enter(current);
 
 	__local_bh_disable((unsigned long)__builtin_return_address(0),
 				SOFTIRQ_OFFSET);

@@ -272,7 +272,7 @@ restart:
 
 	lockdep_softirq_exit();
 
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }

@@ -341,7 +341,7 @@ static inline void invoke_softirq(void)
  */
 void irq_exit(void)
 {
-	vtime_account(current);
+	vtime_account_irq_exit(current);
 	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())

index e6e0ece..265b376 100644
@@ -1046,7 +1046,7 @@ void do_sys_times(struct tms *tms)
 	cputime_t tgutime, tgstime, cutime, cstime;
 
 	spin_lock_irq(&current->sighand->siglock);
-	thread_group_times(current, &tgutime, &tgstime);
+	thread_group_cputime_adjusted(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);

@@ -1704,7 +1704,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	utime = stime = 0;
 
 	if (who == RUSAGE_THREAD) {
-		task_times(current, &utime, &stime);
+		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = p->signal->maxrss;
 		goto out;

@@ -1730,7 +1730,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			thread_group_times(p, &tgutime, &tgstime);
+			thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 			utime += tgutime;
 			stime += tgstime;
 			r->ru_nvcsw += p->signal->nvcsw;