Merge tag 'cputime-adjustment-cleanups' of git://git.kernel.org/pub/s…

…cm/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>

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;
 	}
 

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)
 {
@@ -2657,9 +2582,6 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("limits",	  S_IRUGO, proc_pid_limits),
 #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

include/linux/sched.h

@@ -433,14 +433,29 @@ struct cpu_itimer {
 	u32 incr_error;
 };
 
+/**
+ * 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

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;

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));

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)

kernel/sched/auto_group.c

@@ -110,6 +110,9 @@ static inline struct autogroup *autogroup_create(void)
 
 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)
 {

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;