sched: Fix granularity of task_u/stime()

Originally task_s/utime() were designed to return clock_t but
later changed to return cputime_t by following commit:

  commit efe567fc82
  Author: Christian Borntraeger <borntraeger@de.ibm.com>
  Date:   Thu Aug 23 15:18:02 2007 +0200

It only changed the type of return value, but not the
implementation. As the result the granularity of task_s/utime()
is still that of clock_t, not that of cputime_t.

So using task_s/utime() in __exit_signal() makes values
accumulated to the signal struct to be rounded and coarse
grained.

This patch removes casts to clock_t in task_u/stime(), to keep
granularity of cputime_t over the calculation.

v2:
  Use div_u64() to avoid error "undefined reference to `__udivdi3`"
  on some 32bit systems.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: xiyou.wangcong@gmail.com
Cc: Spencer Candland <spencer@bluehost.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <4AFB9029.9000208@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -5156,41 +5156,45 @@ cputime_t task_stime(struct task_struct *p)
 	return p->stime;
 }
 #else
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) \
+	msecs_to_cputime(div_u64((__nsecs), NSEC_PER_MSEC))
+#endif
+
 cputime_t task_utime(struct task_struct *p)
 {
-	clock_t utime = cputime_to_clock_t(p->utime),
-		total = utime + cputime_to_clock_t(p->stime);
+	cputime_t utime = p->utime, total = utime + p->stime;
 	u64 temp;
 
 	/*
 	 * Use CFS's precise accounting:
 	 */
-	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+	temp = (u64)nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
 		temp *= utime;
 		do_div(temp, total);
 	}
-	utime = (clock_t)temp;
+	utime = (cputime_t)temp;
 
-	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+	p->prev_utime = max(p->prev_utime, utime);
 	return p->prev_utime;
 }
 
 cputime_t task_stime(struct task_struct *p)
 {
-	clock_t stime;
+	cputime_t stime;
 
 	/*
 	 * Use CFS's precise accounting. (we subtract utime from
 	 * the total, to make sure the total observed by userspace
 	 * grows monotonically - apps rely on that):
 	 */
-	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
-			cputime_to_clock_t(task_utime(p));
+	stime = nsecs_to_cputime(p->se.sum_exec_runtime) - task_utime(p);
 
 	if (stime >= 0)
-		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+		p->prev_stime = max(p->prev_stime, stime);
 
 	return p->prev_stime;
 }