Merge tag 'cputime-adjustment-cleanups' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into sched/core

Pull cputime cleanups from Frederic Weisbecker:

 * Improve naming and code location

 * Consolidate adjustment code

 * Comment the adjustement code

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 119 insertions, 205 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index c1c207c36ca..d3696708fc1 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -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;
 	}
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9e28356a959..587631e1cd0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1272,81 +1272,6 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
-#ifdef CONFIG_SCHED_AUTOGROUP
-/*
- * Print out autogroup related information:
- */
-static int sched_autogroup_show(struct seq_file *m, void *v)
-{
-	struct inode *inode = m->private;
-	struct task_struct *p;
-
-	p = get_proc_task(inode);
-	if (!p)
-		return -ESRCH;
-	proc_sched_autogroup_show_task(p, m);
-
-	put_task_struct(p);
-
-	return 0;
-}
-
-static ssize_t
-sched_autogroup_write(struct file *file, const char __user *buf,
-	    size_t count, loff_t *offset)
-{
-	struct inode *inode = file->f_path.dentry->d_inode;
-	struct task_struct *p;
-	char buffer[PROC_NUMBUF];
-	int nice;
-	int err;
-
-	memset(buffer, 0, sizeof(buffer));
-	if (count > sizeof(buffer) - 1)
-		count = sizeof(buffer) - 1;
-	if (copy_from_user(buffer, buf, count))
-		return -EFAULT;
-
-	err = kstrtoint(strstrip(buffer), 0, &nice);
-	if (err < 0)
-		return err;
-
-	p = get_proc_task(inode);
-	if (!p)
-		return -ESRCH;
-
-	err = proc_sched_autogroup_set_nice(p, nice);
-	if (err)
-		count = err;
-
-	put_task_struct(p);
-
-	return count;
-}
-
-static int sched_autogroup_open(struct inode *inode, struct file *filp)
-{
-	int ret;
-
-	ret = single_open(filp, sched_autogroup_show, NULL);
-	if (!ret) {
-		struct seq_file *m = filp->private_data;
-
-		m->private = inode;
-	}
-	return ret;
-}
-
-static const struct file_operations proc_pid_sched_autogroup_operations = {
-	.open		= sched_autogroup_open,
-	.read		= seq_read,
-	.write		= sched_autogroup_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-#endif /* CONFIG_SCHED_AUTOGROUP */
-
 static ssize_t comm_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *offset)
 {
@@ -2658,9 +2583,6 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
-#ifdef CONFIG_SCHED_AUTOGROUP
-	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
-#endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 	INF("syscall",    S_IRUGO, proc_pid_syscall),
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e1581a029e3..5dafac36681 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -434,13 +434,28 @@ struct cpu_itimer {
 };
 
 /**
+ * struct cputime - snaphsot of system and user cputime
+ * @utime: time spent in user mode
+ * @stime: time spent in system mode
+ *
+ * Gathers a generic snapshot of user and system time.
+ */
+struct cputime {
+	cputime_t utime;
+	cputime_t stime;
+};
+
+/**
  * struct task_cputime - collected CPU time counts
  * @utime:		time spent in user mode, in &cputime_t units
  * @stime:		time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
  *
- * This structure groups together three kinds of CPU time that are
- * tracked for threads and thread groups.  Most things considering
+ * This is an extension of struct cputime that includes the total runtime
+ * spent by the task from the scheduler point of view.
+ *
+ * As a result, this structure groups together three kinds of CPU time
+ * that are tracked for threads and thread groups.  Most things considering
  * CPU time want to group these counts together and treat all three
  * of them in parallel.
  */
@@ -581,7 +596,7 @@ struct signal_struct {
 	cputime_t gtime;
 	cputime_t cgtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	cputime_t prev_utime, prev_stime;
+	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -1340,7 +1355,7 @@ struct task_struct {
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	cputime_t prev_utime, prev_stime;
+	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
@@ -1751,8 +1766,8 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
-extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
diff --git a/kernel/exit.c b/kernel/exit.c
index 346616c0092..618f7ee5600 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -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;
diff --git a/kernel/fork.c b/kernel/fork.c
index 8b20ab7d3aa..0e7cdb90476 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -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));
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 125cb67daa2..d73840271dc 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -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)
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 15f60d01198..0f1bacb005a 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -110,6 +110,9 @@ out_fail:
 
 bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return false;
+
 	if (tg != &root_task_group)
 		return false;
 
@@ -155,8 +158,11 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 /* Allocates GFP_KERNEL, cannot be called under any spinlock */
 void sched_autogroup_create_attach(struct task_struct *p)
 {
-	struct autogroup *ag = autogroup_create();
+	struct autogroup *ag;
 
+	if (!sysctl_sched_autogroup_enabled)
+		return;
+	ag = autogroup_create();
 	autogroup_move_group(p, ag);
 	/* drop extra reference added by autogroup_create() */
 	autogroup_kref_put(ag);
@@ -172,11 +178,15 @@ EXPORT_SYMBOL(sched_autogroup_detach);
 
 void sched_autogroup_fork(struct signal_struct *sig)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return;
 	sig->autogroup = autogroup_task_get(current);
 }
 
 void sched_autogroup_exit(struct signal_struct *sig)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return;
 	autogroup_kref_put(sig->autogroup);
 }
 
@@ -189,58 +199,6 @@ static int __init setup_autogroup(char *str)
 
 __setup("noautogroup", setup_autogroup);
 
-#ifdef CONFIG_PROC_FS
-
-int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
-{
-	static unsigned long next = INITIAL_JIFFIES;
-	struct autogroup *ag;
-	int err;
-
-	if (nice < -20 || nice > 19)
-		return -EINVAL;
-
-	err = security_task_setnice(current, nice);
-	if (err)
-		return err;
-
-	if (nice < 0 && !can_nice(current, nice))
-		return -EPERM;
-
-	/* this is a heavy operation taking global locks.. */
-	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
-		return -EAGAIN;
-
-	next = HZ / 10 + jiffies;
-	ag = autogroup_task_get(p);
-
-	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
-	if (!err)
-		ag->nice = nice;
-	up_write(&ag->lock);
-
-	autogroup_kref_put(ag);
-
-	return err;
-}
-
-void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
-{
-	struct autogroup *ag = autogroup_task_get(p);
-
-	if (!task_group_is_autogroup(ag->tg))
-		goto out;
-
-	down_read(&ag->lock);
-	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
-	up_read(&ag->lock);
-
-out:
-	autogroup_kref_put(ag);
-}
-#endif /* CONFIG_PROC_FS */
-
 #ifdef CONFIG_SCHED_DEBUG
 int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h
index 443232ebbb5..4552c6bf79d 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/auto_group.h
@@ -24,9 +24,7 @@ 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)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (enabled && task_wants_autogroup(p, tg))
+	if (task_wants_autogroup(p, tg))
 		return p->signal->autogroup->tg;
 
 	return tg;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 8d859dae5be..b7f73176862 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -288,6 +288,34 @@ static __always_inline bool steal_account_process_tick(void)
 	return false;
 }
 
+/*
+ * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
+ * tasks (sum on group iteration) belonging to @tsk's group.
+ */
+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();
+}
+
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -417,13 +445,13 @@ void account_idle_ticks(unsigned long ticks)
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	*ut = p->utime;
 	*st = p->stime;
 }
 
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime;
 
@@ -488,14 +516,30 @@ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
 	return (__force cputime_t) temp;
 }
 
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+/*
+ * Adjust tick based cputime random precision against scheduler
+ * runtime accounting.
+ */
+static void cputime_adjust(struct task_cputime *curr,
+			   struct cputime *prev,
+			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, utime = p->utime, total = utime + p->stime;
+	cputime_t rtime, utime, total;
+
+	utime = curr->utime;
+	total = utime + curr->stime;
 
 	/*
-	 * Use CFS's precise accounting:
+	 * Tick based cputime accounting depend on random scheduling
+	 * timeslices of a task to be interrupted or not by the timer.
+	 * Depending on these circumstances, the number of these interrupts
+	 * may be over or under-optimistic, matching the real user and system
+	 * cputime with a variable precision.
+	 *
+	 * Fix this by scaling these tick based values against the total
+	 * runtime accounted by the CFS scheduler.
 	 */
-	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
+	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	if (total)
 		utime = scale_utime(utime, rtime, total);
@@ -503,38 +547,36 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 		utime = rtime;
 
 	/*
-	 * Compare with previous values, to keep monotonicity:
+	 * If the tick based count grows faster than the scheduler one,
+	 * the result of the scaling may go backward.
+	 * Let's enforce monotonicity.
 	 */
-	p->prev_utime = max(p->prev_utime, utime);
-	p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+	prev->utime = max(prev->utime, utime);
+	prev->stime = max(prev->stime, rtime - prev->utime);
 
-	*ut = p->prev_utime;
-	*st = p->prev_stime;
+	*ut = prev->utime;
+	*st = prev->stime;
+}
+
+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,
+	};
+
+	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
 /*
  * Must be called with siglock held.
  */
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-	struct signal_struct *sig = p->signal;
 	struct task_cputime cputime;
-	cputime_t rtime, utime, total;
 
 	thread_group_cputime(p, &cputime);
-
-	total = cputime.utime + cputime.stime;
-	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
-
-	if (total)
-		utime = scale_utime(cputime.utime, rtime, total);
-	else
-		utime = rtime;
-
-	sig->prev_utime = max(sig->prev_utime, utime);
-	sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
-
-	*ut = sig->prev_utime;
-	*st = sig->prev_stime;
+	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
 }
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a319d56c760..59e072b2db9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3330,7 +3330,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
 	 * is driven by the tick):
 	 */
-	if (unlikely(p->policy != SCHED_NORMAL))
+	if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
 		return;
 
 	find_matching_se(&se, &pse);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index eebefcad702..e68e69ab917 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -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)
diff --git a/kernel/sys.c b/kernel/sys.c
index e6e0ece5f6a..265b3769042 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -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;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 26f65eaa01f..b0fa5ad0987 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -367,10 +367,8 @@ static struct ctl_table kern_table[] = {
 		.procname	= "sched_autogroup_enabled",
 		.data		= &sysctl_sched_autogroup_enabled,
 		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
 	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH