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

Pull scheduler changes from Ingo Molnar:
 "Main changes:

   - scheduler side full-dynticks (user-space execution is undisturbed
     and receives no timer IRQs) preparation changes that convert the
     cputime accounting code to be full-dynticks ready, from Frederic
     Weisbecker.

   - Initial sched.h split-up changes, by Clark Williams

   - select_idle_sibling() performance improvement by Mike Galbraith:

        " 1 tbench pair (worst case) in a 10 core + SMT package:

          pre   15.22 MB/sec 1 procs
          post 252.01 MB/sec 1 procs "

  - sched_rr_get_interval() ABI fix/change.  We think this detail is not
    used by apps (so it's not an ABI in practice), but lets keep it
    under observation.

  - misc RT scheduling cleanups, optimizations"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  sched/rt: Add <linux/sched/rt.h> header to <linux/init_task.h>
  cputime: Remove irqsave from seqlock readers
  sched, powerpc: Fix sched.h split-up build failure
  cputime: Restore CPU_ACCOUNTING config defaults for PPC64
  sched/rt: Move rt specific bits into new header file
  sched/rt: Add a tuning knob to allow changing SCHED_RR timeslice
  sched: Move sched.h sysctl bits into separate header
  sched: Fix signedness bug in yield_to()
  sched: Fix select_idle_sibling() bouncing cow syndrome
  sched/rt: Further simplify pick_rt_task()
  sched/rt: Do not account zero delta_exec in update_curr_rt()
  cputime: Safely read cputime of full dynticks CPUs
  kvm: Prepare to add generic guest entry/exit callbacks
  cputime: Use accessors to read task cputime stats
  cputime: Allow dynamic switch between tick/virtual based cputime accounting
  cputime: Generic on-demand virtual cputime accounting
  cputime: Move default nsecs_to_cputime() to jiffies based cputime file
  cputime: Librarize per nsecs resolution cputime definitions
  cputime: Avoid multiplication overflow on utime scaling
  context_tracking: Export context state for generic vtime
  ...

Fix up conflict in kernel/context_tracking.c due to comment additions.

1 files changed, 271 insertions, 43 deletions

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 */