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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  sched/tracing: Add a new tracepoint for sleeptime
  sched: Disable scheduler warnings during oopses
  sched: Fix cgroup movement of waking process
  sched: Fix cgroup movement of newly created process
  sched: Fix cgroup movement of forking process
  sched: Remove cfs bandwidth period check in tg_set_cfs_period()
  sched: Fix load-balance lock-breaking
  sched: Replace all_pinned with a generic flags field
  sched: Only queue remote wakeups when crossing cache boundaries
  sched: Add missing rcu_dereference() around ->real_parent usage
  [S390] fix cputime overflow in uptime_proc_show
  [S390] cputime: add sparse checking and cleanup
  sched: Mark parent and real_parent as __rcu
  sched, nohz: Fix missing RCU read lock
  sched, nohz: Set the NOHZ_BALANCE_KICK flag for idle load balancer
  sched, nohz: Fix the idle cpu check in nohz_idle_balance
  sched: Use jump_labels for sched_feat
  sched/accounting: Fix parameter passing in task_group_account_field
  sched/accounting: Fix user/system tick double accounting
  sched/accounting: Re-use scheduler statistics for the root cgroup
  ...

Fix up conflicts in
 - arch/ia64/include/asm/cputime.h, include/asm-generic/cputime.h
	usecs_to_cputime64() vs the sparse cleanups
 - kernel/sched/fair.c, kernel/time/tick-sched.c
	scheduler changes in multiple branches

27 files changed, 2687 insertions, 2463 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index e898c5b9d02..f70396e5a24 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -2,16 +2,15 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
+obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o sched_clock.o cred.o \
-	    async.o range.o
-obj-y += groups.o
+	    notifier.o ksysfs.o cred.o \
+	    async.o range.o groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -20,10 +19,11 @@ CFLAGS_REMOVE_lockdep_proc.o = -pg
 CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
-CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+obj-y += sched/
+
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
@@ -99,7 +99,6 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
-obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 
@@ -110,15 +109,6 @@ obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 
-ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
-# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
-# needed for x86 only.  Why this used to be enabled for all architectures is beyond
-# me.  I suspect most platforms don't need this, but until we know that for sure
-# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
-# to get a correct value for the wait-channel (WCHAN in ps). --davidm
-CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer
-endif
-
 $(obj)/configs.o: $(obj)/config_data.h
 
 # config_data.h contains the same information as ikconfig.h but gzipped.
diff --git a/kernel/acct.c b/kernel/acct.c
index fa7eb3de2dd..203dfead2e0 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -613,8 +613,8 @@ void acct_collect(long exitcode, int group_dead)
 		pacct->ac_flag |= ACORE;
 	if (current->flags & PF_SIGNALED)
 		pacct->ac_flag |= AXSIG;
-	pacct->ac_utime = cputime_add(pacct->ac_utime, current->utime);
-	pacct->ac_stime = cputime_add(pacct->ac_stime, current->stime);
+	pacct->ac_utime += current->utime;
+	pacct->ac_stime += current->stime;
 	pacct->ac_minflt += current->min_flt;
 	pacct->ac_majflt += current->maj_flt;
 	spin_unlock_irq(&current->sighand->siglock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9d448ddb224..5ca38d5d238 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -178,8 +178,7 @@ static inline void check_for_tasks(int cpu)
 	write_lock_irq(&tasklist_lock);
 	for_each_process(p) {
 		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
-		    (!cputime_eq(p->utime, cputime_zero) ||
-		     !cputime_eq(p->stime, cputime_zero)))
+		    (p->utime || p->stime))
 			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
 				"(state = %ld, flags = %x)\n",
 				p->comm, task_pid_nr(p), cpu,
diff --git a/kernel/exit.c b/kernel/exit.c
index e6e01b959a0..d579a459309 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -121,9 +121,9 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, tsk->utime);
-		sig->stime = cputime_add(sig->stime, tsk->stime);
-		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
+		sig->utime += tsk->utime;
+		sig->stime += tsk->stime;
+		sig->gtime += tsk->gtime;
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;
@@ -1255,19 +1255,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
-		psig->cutime =
-			cputime_add(psig->cutime,
-			cputime_add(tgutime,
-				    sig->cutime));
-		psig->cstime =
-			cputime_add(psig->cstime,
-			cputime_add(tgstime,
-				    sig->cstime));
-		psig->cgtime =
-			cputime_add(psig->cgtime,
-			cputime_add(p->gtime,
-			cputime_add(sig->gtime,
-				    sig->cgtime)));
+		psig->cutime += tgutime + sig->cutime;
+		psig->cstime += tgstime + sig->cstime;
+		psig->cgtime += p->gtime + sig->gtime + sig->cgtime;
 		psig->cmin_flt +=
 			p->min_flt + sig->min_flt + sig->cmin_flt;
 		psig->cmaj_flt +=
diff --git a/kernel/fork.c b/kernel/fork.c
index da4a6a10d08..b058c5820ec 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1023,8 +1023,8 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
-	tsk->cputime_expires.prof_exp = cputime_zero;
-	tsk->cputime_expires.virt_exp = cputime_zero;
+	tsk->cputime_expires.prof_exp = 0;
+	tsk->cputime_expires.virt_exp = 0;
 	tsk->cputime_expires.sched_exp = 0;
 	INIT_LIST_HEAD(&tsk->cpu_timers[0]);
 	INIT_LIST_HEAD(&tsk->cpu_timers[1]);
@@ -1132,14 +1132,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	init_sigpending(&p->pending);
 
-	p->utime = cputime_zero;
-	p->stime = cputime_zero;
-	p->gtime = cputime_zero;
-	p->utimescaled = cputime_zero;
-	p->stimescaled = cputime_zero;
+	p->utime = p->stime = p->gtime = 0;
+	p->utimescaled = p->stimescaled = 0;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	p->prev_utime = cputime_zero;
-	p->prev_stime = cputime_zero;
+	p->prev_utime = p->prev_stime = 0;
 #endif
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
diff --git a/kernel/itimer.c b/kernel/itimer.c
index d802883153d..22000c3db0d 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -52,22 +52,22 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 
 	cval = it->expires;
 	cinterval = it->incr;
-	if (!cputime_eq(cval, cputime_zero)) {
+	if (cval) {
 		struct task_cputime cputime;
 		cputime_t t;
 
 		thread_group_cputimer(tsk, &cputime);
 		if (clock_id == CPUCLOCK_PROF)
-			t = cputime_add(cputime.utime, cputime.stime);
+			t = cputime.utime + cputime.stime;
 		else
 			/* CPUCLOCK_VIRT */
 			t = cputime.utime;
 
-		if (cputime_le(cval, t))
+		if (cval < t)
 			/* about to fire */
 			cval = cputime_one_jiffy;
 		else
-			cval = cputime_sub(cval, t);
+			cval = cval - t;
 	}
 
 	spin_unlock_irq(&tsk->sighand->siglock);
@@ -161,10 +161,9 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 
 	cval = it->expires;
 	cinterval = it->incr;
-	if (!cputime_eq(cval, cputime_zero) ||
-	    !cputime_eq(nval, cputime_zero)) {
-		if (cputime_gt(nval, cputime_zero))
-			nval = cputime_add(nval, cputime_one_jiffy);
+	if (cval || nval) {
+		if (nval > 0)
+			nval += cputime_one_jiffy;
 		set_process_cpu_timer(tsk, clock_id, &nval, &cval);
 	}
 	it->expires = nval;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e7cb76dc18f..125cb67daa2 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -78,7 +78,7 @@ static inline int cpu_time_before(const clockid_t which_clock,
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
 		return now.sched < then.sched;
 	}  else {
-		return cputime_lt(now.cpu, then.cpu);
+		return now.cpu < then.cpu;
 	}
 }
 static inline void cpu_time_add(const clockid_t which_clock,
@@ -88,7 +88,7 @@ static inline void cpu_time_add(const clockid_t which_clock,
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
 		acc->sched += val.sched;
 	}  else {
-		acc->cpu = cputime_add(acc->cpu, val.cpu);
+		acc->cpu += val.cpu;
 	}
 }
 static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
@@ -98,25 +98,12 @@ static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
 		a.sched -= b.sched;
 	}  else {
-		a.cpu = cputime_sub(a.cpu, b.cpu);
+		a.cpu -= b.cpu;
 	}
 	return a;
 }
 
 /*
- * Divide and limit the result to res >= 1
- *
- * This is necessary to prevent signal delivery starvation, when the result of
- * the division would be rounded down to 0.
- */
-static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
-{
-	cputime_t res = cputime_div(time, div);
-
-	return max_t(cputime_t, res, 1);
-}
-
-/*
  * Update expiry time from increment, and increase overrun count,
  * given the current clock sample.
  */
@@ -148,28 +135,26 @@ static void bump_cpu_timer(struct k_itimer *timer,
 	} else {
 		cputime_t delta, incr;
 
-		if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
+		if (now.cpu < timer->it.cpu.expires.cpu)
 			return;
 		incr = timer->it.cpu.incr.cpu;
-		delta = cputime_sub(cputime_add(now.cpu, incr),
-				    timer->it.cpu.expires.cpu);
+		delta = now.cpu + incr - timer->it.cpu.expires.cpu;
 		/* Don't use (incr*2 < delta), incr*2 might overflow. */
-		for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
-			     incr = cputime_add(incr, incr);
-		for (; i >= 0; incr = cputime_halve(incr), i--) {
-			if (cputime_lt(delta, incr))
+		for (i = 0; incr < delta - incr; i++)
+			     incr += incr;
+		for (; i >= 0; incr = incr >> 1, i--) {
+			if (delta < incr)
 				continue;
-			timer->it.cpu.expires.cpu =
-				cputime_add(timer->it.cpu.expires.cpu, incr);
+			timer->it.cpu.expires.cpu += incr;
 			timer->it_overrun += 1 << i;
-			delta = cputime_sub(delta, incr);
+			delta -= incr;
 		}
 	}
 }
 
 static inline cputime_t prof_ticks(struct task_struct *p)
 {
-	return cputime_add(p->utime, p->stime);
+	return p->utime + p->stime;
 }
 static inline cputime_t virt_ticks(struct task_struct *p)
 {
@@ -248,8 +233,8 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
 	t = tsk;
 	do {
-		times->utime = cputime_add(times->utime, t->utime);
-		times->stime = cputime_add(times->stime, t->stime);
+		times->utime += t->utime;
+		times->stime += t->stime;
 		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
@@ -258,10 +243,10 @@ out:
 
 static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
 {
-	if (cputime_gt(b->utime, a->utime))
+	if (b->utime > a->utime)
 		a->utime = b->utime;
 
-	if (cputime_gt(b->stime, a->stime))
+	if (b->stime > a->stime)
 		a->stime = b->stime;
 
 	if (b->sum_exec_runtime > a->sum_exec_runtime)
@@ -306,7 +291,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		return -EINVAL;
 	case CPUCLOCK_PROF:
 		thread_group_cputime(p, &cputime);
-		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+		cpu->cpu = cputime.utime + cputime.stime;
 		break;
 	case CPUCLOCK_VIRT:
 		thread_group_cputime(p, &cputime);
@@ -470,26 +455,24 @@ static void cleanup_timers(struct list_head *head,
 			   unsigned long long sum_exec_runtime)
 {
 	struct cpu_timer_list *timer, *next;
-	cputime_t ptime = cputime_add(utime, stime);
+	cputime_t ptime = utime + stime;
 
 	list_for_each_entry_safe(timer, next, head, entry) {
 		list_del_init(&timer->entry);
-		if (cputime_lt(timer->expires.cpu, ptime)) {
-			timer->expires.cpu = cputime_zero;
+		if (timer->expires.cpu < ptime) {
+			timer->expires.cpu = 0;
 		} else {
-			timer->expires.cpu = cputime_sub(timer->expires.cpu,
-							 ptime);
+			timer->expires.cpu -= ptime;
 		}
 	}
 
 	++head;
 	list_for_each_entry_safe(timer, next, head, entry) {
 		list_del_init(&timer->entry);
-		if (cputime_lt(timer->expires.cpu, utime)) {
-			timer->expires.cpu = cputime_zero;
+		if (timer->expires.cpu < utime) {
+			timer->expires.cpu = 0;
 		} else {
-			timer->expires.cpu = cputime_sub(timer->expires.cpu,
-							 utime);
+			timer->expires.cpu -= utime;
 		}
 	}
 
@@ -520,8 +503,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 	struct signal_struct *const sig = tsk->signal;
 
 	cleanup_timers(tsk->signal->cpu_timers,
-		       cputime_add(tsk->utime, sig->utime),
-		       cputime_add(tsk->stime, sig->stime),
+		       tsk->utime + sig->utime, tsk->stime + sig->stime,
 		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
 }
 
@@ -540,8 +522,7 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
 
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 {
-	return cputime_eq(expires, cputime_zero) ||
-	       cputime_gt(expires, new_exp);
+	return expires == 0 || expires > new_exp;
 }
 
 /*
@@ -651,7 +632,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+		cpu->cpu = cputime.utime + cputime.stime;
 		break;
 	case CPUCLOCK_VIRT:
 		cpu->cpu = cputime.utime;
@@ -918,12 +899,12 @@ static void check_thread_timers(struct task_struct *tsk,
 	unsigned long soft;
 
 	maxfire = 20;
-	tsk->cputime_expires.prof_exp = cputime_zero;
+	tsk->cputime_expires.prof_exp = 0;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
+		if (!--maxfire || prof_ticks(tsk) < t->expires.cpu) {
 			tsk->cputime_expires.prof_exp = t->expires.cpu;
 			break;
 		}
@@ -933,12 +914,12 @@ static void check_thread_timers(struct task_struct *tsk,
 
 	++timers;
 	maxfire = 20;
-	tsk->cputime_expires.virt_exp = cputime_zero;
+	tsk->cputime_expires.virt_exp = 0;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
+		if (!--maxfire || virt_ticks(tsk) < t->expires.cpu) {
 			tsk->cputime_expires.virt_exp = t->expires.cpu;
 			break;
 		}
@@ -1009,20 +990,19 @@ static u32 onecputick;
 static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 			     cputime_t *expires, cputime_t cur_time, int signo)
 {
-	if (cputime_eq(it->expires, cputime_zero))
+	if (!it->expires)
 		return;
 
-	if (cputime_ge(cur_time, it->expires)) {
-		if (!cputime_eq(it->incr, cputime_zero)) {
-			it->expires = cputime_add(it->expires, it->incr);
+	if (cur_time >= it->expires) {
+		if (it->incr) {
+			it->expires += it->incr;
 			it->error += it->incr_error;
 			if (it->error >= onecputick) {
-				it->expires = cputime_sub(it->expires,
-							  cputime_one_jiffy);
+				it->expires -= cputime_one_jiffy;
 				it->error -= onecputick;
 			}
 		} else {
-			it->expires = cputime_zero;
+			it->expires = 0;
 		}
 
 		trace_itimer_expire(signo == SIGPROF ?
@@ -1031,9 +1011,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
 	}
 
-	if (!cputime_eq(it->expires, cputime_zero) &&
-	    (cputime_eq(*expires, cputime_zero) ||
-	     cputime_lt(it->expires, *expires))) {
+	if (it->expires && (!*expires || it->expires < *expires)) {
 		*expires = it->expires;
 	}
 }
@@ -1048,9 +1026,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
  */
 static inline int task_cputime_zero(const struct task_cputime *cputime)
 {
-	if (cputime_eq(cputime->utime, cputime_zero) &&
-	    cputime_eq(cputime->stime, cputime_zero) &&
-	    cputime->sum_exec_runtime == 0)
+	if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime)
 		return 1;
 	return 0;
 }
@@ -1076,15 +1052,15 @@ static void check_process_timers(struct task_struct *tsk,
 	 */
 	thread_group_cputimer(tsk, &cputime);
 	utime = cputime.utime;
-	ptime = cputime_add(utime, cputime.stime);
+	ptime = utime + cputime.stime;
 	sum_sched_runtime = cputime.sum_exec_runtime;
 	maxfire = 20;
-	prof_expires = cputime_zero;
+	prof_expires = 0;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *tl = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
+		if (!--maxfire || ptime < tl->expires.cpu) {
 			prof_expires = tl->expires.cpu;
 			break;
 		}
@@ -1094,12 +1070,12 @@ static void check_process_timers(struct task_struct *tsk,
 
 	++timers;
 	maxfire = 20;
-	virt_expires = cputime_zero;
+	virt_expires = 0;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *tl = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) {
+		if (!--maxfire || utime < tl->expires.cpu) {
 			virt_expires = tl->expires.cpu;
 			break;
 		}
@@ -1154,8 +1130,7 @@ static void check_process_timers(struct task_struct *tsk,
 			}
 		}
 		x = secs_to_cputime(soft);
-		if (cputime_eq(prof_expires, cputime_zero) ||
-		    cputime_lt(x, prof_expires)) {
+		if (!prof_expires || x < prof_expires) {
 			prof_expires = x;
 		}
 	}
@@ -1249,12 +1224,9 @@ out:
 static inline int task_cputime_expired(const struct task_cputime *sample,
 					const struct task_cputime *expires)
 {
-	if (!cputime_eq(expires->utime, cputime_zero) &&
-	    cputime_ge(sample->utime, expires->utime))
+	if (expires->utime && sample->utime >= expires->utime)
 		return 1;
-	if (!cputime_eq(expires->stime, cputime_zero) &&
-	    cputime_ge(cputime_add(sample->utime, sample->stime),
-		       expires->stime))
+	if (expires->stime && sample->utime + sample->stime >= expires->stime)
 		return 1;
 	if (expires->sum_exec_runtime != 0 &&
 	    sample->sum_exec_runtime >= expires->sum_exec_runtime)
@@ -1389,18 +1361,18 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		 * it to be relative, *newval argument is relative and we update
 		 * it to be absolute.
 		 */
-		if (!cputime_eq(*oldval, cputime_zero)) {
-			if (cputime_le(*oldval, now.cpu)) {
+		if (*oldval) {
+			if (*oldval <= now.cpu) {
 				/* Just about to fire. */
 				*oldval = cputime_one_jiffy;
 			} else {
-				*oldval = cputime_sub(*oldval, now.cpu);
+				*oldval -= now.cpu;
 			}
 		}
 
-		if (cputime_eq(*newval, cputime_zero))
+		if (!*newval)
 			return;
-		*newval = cputime_add(*newval, now.cpu);
+		*newval += now.cpu;
 	}
 
 	/*
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
new file mode 100644
index 00000000000..9a7dd35102a
--- /dev/null
+++ b/kernel/sched/Makefile
@@ -0,0 +1,20 @@
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_clock.o = -pg
+endif
+
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
+# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
+# needed for x86 only.  Why this used to be enabled for all architectures is beyond
+# me.  I suspect most platforms don't need this, but until we know that for sure
+# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
+# to get a correct value for the wait-channel (WCHAN in ps). --davidm
+CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
+endif
+
+obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
+obj-$(CONFIG_SCHED_DEBUG) += debug.o
+
+
diff --git a/kernel/sched_autogroup.c b/kernel/sched/auto_group.c
index 429242f3c48..e8a1f83ee0e 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched/auto_group.c
@@ -1,15 +1,19 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
+#include "sched.h"
+
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
+#include <linux/security.h>
+#include <linux/export.h>
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
 static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 
-static void __init autogroup_init(struct task_struct *init_task)
+void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
 	kref_init(&autogroup_default.kref);
@@ -17,7 +21,7 @@ static void __init autogroup_init(struct task_struct *init_task)
 	init_task->signal->autogroup = &autogroup_default;
 }
 
-static inline void autogroup_free(struct task_group *tg)
+void autogroup_free(struct task_group *tg)
 {
 	kfree(tg->autogroup);
 }
@@ -59,10 +63,6 @@ static inline struct autogroup *autogroup_task_get(struct task_struct *p)
 	return ag;
 }
 
-#ifdef CONFIG_RT_GROUP_SCHED
-static void free_rt_sched_group(struct task_group *tg);
-#endif
-
 static inline struct autogroup *autogroup_create(void)
 {
 	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
@@ -108,8 +108,7 @@ out_fail:
 	return autogroup_kref_get(&autogroup_default);
 }
 
-static inline bool
-task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
 	if (tg != &root_task_group)
 		return false;
@@ -127,22 +126,6 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	return true;
 }
 
-static inline bool task_group_is_autogroup(struct task_group *tg)
-{
-	return !!tg->autogroup;
-}
-
-static inline struct task_group *
-autogroup_task_group(struct task_struct *p, struct task_group *tg)
-{
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (enabled && task_wants_autogroup(p, tg))
-		return p->signal->autogroup->tg;
-
-	return tg;
-}
-
 static void
 autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 {
@@ -263,7 +246,7 @@ out:
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SCHED_DEBUG
-static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
 	if (!task_group_is_autogroup(tg))
 		return 0;
diff --git a/kernel/sched_autogroup.h b/kernel/sched/auto_group.h
index c2f0e7248dc..8bd04714281 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched/auto_group.h
@@ -1,5 +1,8 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
+#include <linux/kref.h>
+#include <linux/rwsem.h>
+
 struct autogroup {
 	/*
 	 * reference doesn't mean how many thread attach to this
@@ -13,9 +16,28 @@ struct autogroup {
 	int			nice;
 };
 
-static inline bool task_group_is_autogroup(struct task_group *tg);
+extern void autogroup_init(struct task_struct *init_task);
+extern void autogroup_free(struct task_group *tg);
+
+static inline bool task_group_is_autogroup(struct task_group *tg)
+{
+	return !!tg->autogroup;
+}
+
+extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
+
 static inline struct task_group *
-autogroup_task_group(struct task_struct *p, struct task_group *tg);
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+	if (enabled && task_wants_autogroup(p, tg))
+		return p->signal->autogroup->tg;
+
+	return tg;
+}
+
+extern int autogroup_path(struct task_group *tg, char *buf, int buflen);
 
 #else /* !CONFIG_SCHED_AUTOGROUP */
 
diff --git a/kernel/sched_clock.c b/kernel/sched/clock.c
index c685e31492d..c685e31492d 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched/clock.c
diff --git a/kernel/sched.c b/kernel/sched/core.c
index d6b149ccf92..4dbfd04a214 100644
--- a/kernel/sched.c
+++ b/kernel/sched/core.c
@@ -1,5 +1,5 @@
 /*
- *  kernel/sched.c
+ *  kernel/sched/core.c
  *
  *  Kernel scheduler and related syscalls
  *
@@ -56,7 +56,6 @@
 #include <linux/percpu.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
 #include <linux/times.h>
@@ -75,129 +74,17 @@
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
-#include <asm/mutex.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
 
-#include "sched_cpupri.h"
-#include "workqueue_sched.h"
-#include "sched_autogroup.h"
+#include "sched.h"
+#include "../workqueue_sched.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-/*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
-
-/*
- * Helpers for converting nanosecond timing to jiffy resolution
- */
-#define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
-
-#define NICE_0_LOAD		SCHED_LOAD_SCALE
-#define NICE_0_SHIFT		SCHED_LOAD_SHIFT
-
-/*
- * These are the 'tuning knobs' of the scheduler:
- *
- * default timeslice is 100 msecs (used only for SCHED_RR tasks).
- * Timeslices get refilled after they expire.
- */
-#define DEF_TIMESLICE		(100 * HZ / 1000)
-
-/*
- * single value that denotes runtime == period, ie unlimited time.
- */
-#define RUNTIME_INF	((u64)~0ULL)
-
-static inline int rt_policy(int policy)
-{
-	if (policy == SCHED_FIFO || policy == SCHED_RR)
-		return 1;
-	return 0;
-}
-
-static inline int task_has_rt_policy(struct task_struct *p)
-{
-	return rt_policy(p->policy);
-}
-
-/*
- * This is the priority-queue data structure of the RT scheduling class:
- */
-struct rt_prio_array {
-	DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1