6 files changed, 322 insertions, 71 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 26058d0bebb..4a88f1d5156 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4371,7 +4371,7 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
 	struct task_struct *curr = current;
 	struct rq *rq, *p_rq;
 	unsigned long flags;
-	bool yielded = 0;
+	int yielded = 0;
 
 	local_irq_save(flags);
 	rq = this_rq();
@@ -4667,6 +4667,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 */
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
+	vtime_init_idle(idle);
 #if defined(CONFIG_SMP)
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif
@@ -7508,6 +7509,25 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/* make sure that internally we keep jiffies */
+	/* also, writing zero resets timeslice to default */
+	if (!ret && write) {
+		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
+
 int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 23aa789c53e..1095e878a46 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -28,6 +28,8 @@
  */
 
 #include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
 #include "cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 293b202fcf7..9857329ed28 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -3,6 +3,7 @@
 #include <linux/tsacct_kern.h>
 #include <linux/kernel_stat.h>
 #include <linux/static_key.h>
+#include <linux/context_tracking.h>
 #include "sched.h"
 
 
@@ -163,7 +164,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 	task_group_account_field(p, index, (__force u64) cputime);
 
 	/* Account for user time used */
-	acct_update_integrals(p);
+	acct_account_cputime(p);
 }
 
 /*
@@ -213,7 +214,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
 	task_group_account_field(p, index, (__force u64) cputime);
 
 	/* Account for system time used */
-	acct_update_integrals(p);
+	acct_account_cputime(p);
 }
 
 /*
@@ -295,6 +296,7 @@ static __always_inline bool steal_account_process_tick(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct signal_struct *sig = tsk->signal;
+	cputime_t utime, stime;
 	struct task_struct *t;
 
 	times->utime = sig->utime;
@@ -308,16 +310,15 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
 	t = tsk;
 	do {
-		times->utime += t->utime;
-		times->stime += t->stime;
+		task_cputime(tsk, &utime, &stime);
+		times->utime += utime;
+		times->stime += stime;
 		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
 }
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 /*
  * Account a tick to a process and cpustat
@@ -382,11 +383,12 @@ static void irqtime_account_idle_ticks(int ticks)
 		irqtime_account_process_tick(current, 0, rq);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static void irqtime_account_idle_ticks(int ticks) {}
-static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+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) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Account a single tick of cpu time.
  * @p: the process that the cpu time gets accounted to
@@ -397,6 +399,9 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
+	if (vtime_accounting_enabled())
+		return;
+
 	if (sched_clock_irqtime) {
 		irqtime_account_process_tick(p, user_tick, rq);
 		return;
@@ -438,8 +443,7 @@ void account_idle_ticks(unsigned long ticks)
 
 	account_idle_time(jiffies_to_cputime(ticks));
 }
-
-#endif
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 /*
  * Use precise platform statistics if available:
@@ -461,25 +465,20 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 	*st = cputime.stime;
 }
 
-void vtime_account_system_irqsafe(struct task_struct *tsk)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	vtime_account_system(tsk);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe);
-
 #ifndef __ARCH_HAS_VTIME_TASK_SWITCH
 void vtime_task_switch(struct task_struct *prev)
 {
+	if (!vtime_accounting_enabled())
+		return;
+
 	if (is_idle_task(prev))
 		vtime_account_idle(prev);
 	else
 		vtime_account_system(prev);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	vtime_account_user(prev);
+#endif
 	arch_vtime_task_switch(prev);
 }
 #endif
@@ -493,27 +492,40 @@ void vtime_task_switch(struct task_struct *prev)
  * vtime_account().
  */
 #ifndef __ARCH_HAS_VTIME_ACCOUNT
-void vtime_account(struct task_struct *tsk)
+void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	if (in_interrupt() || !is_idle_task(tsk))
-		vtime_account_system(tsk);
-	else
-		vtime_account_idle(tsk);
+	if (!vtime_accounting_enabled())
+		return;
+
+	if (!in_interrupt()) {
+		/*
+		 * If we interrupted user, context_tracking_in_user()
+		 * is 1 because the context tracking don't hook
+		 * on irq entry/exit. This way we know if
+		 * we need to flush user time on kernel entry.
+		 */
+		if (context_tracking_in_user()) {
+			vtime_account_user(tsk);
+			return;
+		}
+
+		if (is_idle_task(tsk)) {
+			vtime_account_idle(tsk);
+			return;
+		}
+	}
+	vtime_account_system(tsk);
 }
-EXPORT_SYMBOL_GPL(vtime_account);
+EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
 
-#else
-
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs)	nsecs_to_jiffies(__nsecs)
-#endif
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
-static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
+static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total)
 {
 	u64 temp = (__force u64) rtime;
 
-	temp *= (__force u64) utime;
+	temp *= (__force u64) stime;
 
 	if (sizeof(cputime_t) == 4)
 		temp = div_u64(temp, (__force u32) total);
@@ -531,10 +543,10 @@ static void cputime_adjust(struct task_cputime *curr,
 			   struct cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, utime, total;
+	cputime_t rtime, stime, total;
 
-	utime = curr->utime;
-	total = utime + curr->stime;
+	stime = curr->stime;
+	total = stime + curr->utime;
 
 	/*
 	 * Tick based cputime accounting depend on random scheduling
@@ -549,17 +561,17 @@ static void cputime_adjust(struct task_cputime *curr,
 	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	if (total)
-		utime = scale_utime(utime, rtime, total);
+		stime = scale_stime(stime, rtime, total);
 	else
-		utime = rtime;
+		stime = rtime;
 
 	/*
 	 * If the tick based count grows faster than the scheduler one,
 	 * the result of the scaling may go backward.
 	 * Let's enforce monotonicity.
 	 */
-	prev->utime = max(prev->utime, utime);
-	prev->stime = max(prev->stime, rtime - prev->utime);
+	prev->stime = max(prev->stime, stime);
+	prev->utime = max(prev->utime, rtime - prev->stime);
 
 	*ut = prev->utime;
 	*st = prev->stime;
@@ -568,11 +580,10 @@ static void cputime_adjust(struct task_cputime *curr,
 void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime = {
-		.utime = p->utime,
-		.stime = p->stime,
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
+	task_cputime(p, &cputime.utime, &cputime.stime);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
@@ -586,4 +597,221 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 	thread_group_cputime(p, &cputime);
 	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
 }
-#endif
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+static unsigned long long vtime_delta(struct task_struct *tsk)
+{
+	unsigned long long clock;
+
+	clock = sched_clock();
+	if (clock < tsk->vtime_snap)
+		return 0;
+
+	return clock - tsk->vtime_snap;
+}
+
+static cputime_t get_vtime_delta(struct task_struct *tsk)
+{
+	unsigned long long delta = vtime_delta(tsk);
+
+	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
+	tsk->vtime_snap += delta;
+
+	/* CHECKME: always safe to convert nsecs to cputime? */
+	return nsecs_to_cputime(delta);
+}
+
+static void __vtime_account_system(struct task_struct *tsk)
+{
+	cputime_t delta_cpu = get_vtime_delta(tsk);
+
+	account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu));
+}
+
+void vtime_account_system(struct task_struct *tsk)
+{
+	if (!vtime_accounting_enabled())
+		return;
+
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_account_irq_exit(struct task_struct *tsk)
+{
+	if (!vtime_accounting_enabled())
+		return;
+
+	write_seqlock(&tsk->vtime_seqlock);
+	if (context_tracking_in_user())
+		tsk->vtime_snap_whence = VTIME_USER;
+	__vtime_account_system(tsk);
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_account_user(struct task_struct *tsk)
+{
+	cputime_t delta_cpu;
+
+	if (!vtime_accounting_enabled())
+		return;
+
+	delta_cpu = get_vtime_delta(tsk);
+
+	write_seqlock(&tsk->vtime_seqlock);
+	tsk->vtime_snap_whence = VTIME_SYS;
+	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_user_enter(struct task_struct *tsk)
+{
+	if (!vtime_accounting_enabled())
+		return;
+
+	write_seqlock(&tsk->vtime_seqlock);
+	tsk->vtime_snap_whence = VTIME_USER;
+	__vtime_account_system(tsk);
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_guest_enter(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	current->flags |= PF_VCPU;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_guest_exit(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	current->flags &= ~PF_VCPU;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+	cputime_t delta_cpu = get_vtime_delta(tsk);
+
+	account_idle_time(delta_cpu);
+}
+
+bool vtime_accounting_enabled(void)
+{
+	return context_tracking_active();
+}
+
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+	write_seqlock(&prev->vtime_seqlock);
+	prev->vtime_snap_whence = VTIME_SLEEPING;
+	write_sequnlock(&prev->vtime_seqlock);
+
+	write_seqlock(&current->vtime_seqlock);
+	current->vtime_snap_whence = VTIME_SYS;
+	current->vtime_snap = sched_clock();
+	write_sequnlock(&current->vtime_seqlock);
+}
+
+void vtime_init_idle(struct task_struct *t)
+{
+	unsigned long flags;
+
+	write_seqlock_irqsave(&t->vtime_seqlock, flags);
+	t->vtime_snap_whence = VTIME_SYS;
+	t->vtime_snap = sched_clock();
+	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
+}
+
+cputime_t task_gtime(struct task_struct *t)
+{
+	unsigned int seq;
+	cputime_t gtime;
+
+	do {
+		seq = read_seqbegin(&t->vtime_seqlock);
+
+		gtime = t->gtime;
+		if (t->flags & PF_VCPU)
+			gtime += vtime_delta(t);
+
+	} while (read_seqretry(&t->vtime_seqlock, seq));
+
+	return gtime;
+}
+
+/*
+ * Fetch cputime raw values from fields of task_struct and
+ * add up the pending nohz execution time since the last
+ * cputime snapshot.
+ */
+static void
+fetch_task_cputime(struct task_struct *t,
+		   cputime_t *u_dst, cputime_t *s_dst,
+		   cputime_t *u_src, cputime_t *s_src,
+		   cputime_t *udelta, cputime_t *sdelta)
+{
+	unsigned int seq;
+	unsigned long long delta;
+
+	do {
+		*udelta = 0;
+		*sdelta = 0;
+
+		seq = read_seqbegin(&t->vtime_seqlock);
+
+		if (u_dst)
+			*u_dst = *u_src;
+		if (s_dst)
+			*s_dst = *s_src;
+
+		/* Task is sleeping, nothing to add */
+		if (t->vtime_snap_whence == VTIME_SLEEPING ||
+		    is_idle_task(t))
+			continue;
+
+		delta = vtime_delta(t);
+
+		/*
+		 * Task runs either in user or kernel space, add pending nohz time to
+		 * the right place.
+		 */
+		if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) {
+			*udelta = delta;
+		} else {
+			if (t->vtime_snap_whence == VTIME_SYS)
+				*sdelta = delta;
+		}
+	} while (read_seqretry(&t->vtime_seqlock, seq));
+}
+
+
+void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
+{
+	cputime_t udelta, sdelta;
+
+	fetch_task_cputime(t, utime, stime, &t->utime,
+			   &t->stime, &udelta, &sdelta);
+	if (utime)
+		*utime += udelta;
+	if (stime)
+		*stime += sdelta;
+}
+
+void task_cputime_scaled(struct task_struct *t,
+			 cputime_t *utimescaled, cputime_t *stimescaled)
+{
+	cputime_t udelta, sdelta;
+
+	fetch_task_cputime(t, utimescaled, stimescaled,
+			   &t->utimescaled, &t->stimescaled, &udelta, &sdelta);
+	if (utimescaled)
+		*utimescaled += cputime_to_scaled(udelta);
+	if (stimescaled)
+		*stimescaled += cputime_to_scaled(sdelta);
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 81fa5364340..7a33e5986fc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1680,9 +1680,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	}
 
 	/* ensure we never gain time by being placed backwards. */
-	vruntime = max_vruntime(se->vruntime, vruntime);
-
-	se->vruntime = vruntime;
+	se->vruntime = max_vruntime(se->vruntime, vruntime);
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -3254,25 +3252,18 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
  */
 static int select_idle_sibling(struct task_struct *p, int target)
 {
-	int cpu = smp_processor_id();
-	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
 	struct sched_group *sg;
-	int i;
+	int i = task_cpu(p);
 
-	/*
-	 * If the task is going to be woken-up on this cpu and if it is
-	 * already idle, then it is the right target.
-	 */
-	if (target == cpu && idle_cpu(cpu))
-		return cpu;
+	if (idle_cpu(target))
+		return target;
 
 	/*
-	 * If the task is going to be woken-up on the cpu where it previously
-	 * ran and if it is currently idle, then it the right target.
+	 * If the prevous cpu is cache affine and idle, don't be stupid.
 	 */
-	if (target == prev_cpu && idle_cpu(prev_cpu))
-		return prev_cpu;
+	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
+		return i;
 
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
@@ -3286,7 +3277,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 				goto next;
 
 			for_each_cpu(i, sched_group_cpus(sg)) {
-				if (!idle_cpu(i))
+				if (i == target || !idle_cpu(i))
 					goto next;
 			}
 
@@ -6101,7 +6092,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 	 * idle runqueue:
 	 */
 	if (rq->cfs.load.weight)
-		rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
+		rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
 
 	return rr_interval;
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4f02b284735..127a2c4cf4a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -7,6 +7,8 @@
 
 #include <linux/slab.h>
 
+int sched_rr_timeslice = RR_TIMESLICE;
+
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
 struct rt_bandwidth def_rt_bandwidth;
@@ -925,8 +927,8 @@ static void update_curr_rt(struct rq *rq)
 		return;
 
 	delta_exec = rq->clock_task - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
+	if (unlikely((s64)delta_exec <= 0))
+		return;
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
@@ -1427,8 +1429,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
-	    (p->nr_cpus_allowed > 1))
+	    cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
 		return 1;
 	return 0;
 }
@@ -1889,8 +1890,11 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (p->on_rq && !rq->rt.rt_nr_running)
-		pull_rt_task(rq);
+	if (!p->on_rq || rq->rt.rt_nr_running)
+		return;
+
+	if (pull_rt_task(rq))
+		resched_task(rq->curr);
 }
 
 void init_sched_rt_class(void)
@@ -1985,7 +1989,11 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 	if (soft != RLIM_INFINITY) {
 		unsigned long next;
 
-		p->rt.timeout++;
+		if (p->rt.watchdog_stamp != jiffies) {
+			p->rt.timeout++;
+			p->rt.watchdog_stamp = jiffies;
+		}
+
 		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
 		if (p->rt.timeout > next)
 			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
@@ -2010,7 +2018,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	if (--p->rt.time_slice)
 		return;
 
-	p->rt.time_slice = RR_TIMESLICE;
+	p->rt.time_slice = sched_rr_timeslice;
 
 	/*
 	 * Requeue to the end of queue if we (and all of our ancestors) are the
@@ -2041,7 +2049,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 	 * Time slice is 0 for SCHED_FIFO tasks
 	 */
 	if (task->policy == SCHED_RR)
-		return RR_TIMESLICE;
+		return sched_rr_timeslice;
 	else
 		return 0;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fc886441436..cc03cfdf469 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,5 +1,7 @@
 
 #include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>