Division is done more carefully when scaling utime in mainline, match it.

-ck
---
 kernel/sched/bfs.c |   33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

Index: linux-3.7-bfs/kernel/sched/bfs.c
===================================================================
--- linux-3.7-bfs.orig/kernel/sched/bfs.c	2013-01-29 01:22:35.994785437 +1100
+++ linux-3.7-bfs/kernel/sched/bfs.c	2013-01-29 01:22:36.408780261 +1100
@@ -7477,6 +7477,19 @@ void thread_group_times(struct task_stru
 	*st = cputime.stime;
 }
 #else
+static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
+{
+	u64 temp = (__force u64) rtime;
+
+	temp *= (__force u64) utime;
+
+	if (sizeof(cputime_t) == 4)
+		temp = div_u64(temp, (__force u32) total);
+	else
+		temp = div64_u64(temp, (__force u64) total);
+
+	return (__force cputime_t) temp;
+}
 
 void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
@@ -7484,13 +7497,9 @@ void task_times(struct task_struct *p, c
 
 	rtime = nsecs_to_cputime(p->sched_time);
 
-	if (total) {
-		u64 temp = rtime;
-
-		temp *= utime;
-		do_div(temp, total);
-		utime = (cputime_t)temp;
-	} else
+	if (total)
+		utime = scale_utime(utime, rtime, total);
+	else
 		utime = rtime;
 
 	/*
@@ -7517,13 +7526,9 @@ void thread_group_times(struct task_stru
 	total = cputime.utime + cputime.stime;
 	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
-	if (total) {
-		u64 temp = rtime;
-
-		temp *= cputime.utime;
-		do_div(temp, total);
-		utime = (cputime_t)temp;
-	} else
+	if (total)
+		utime = scale_utime(cputime.utime, rtime, total);
+	else
 		utime = rtime;
 
 	sig->prev_utime = max(sig->prev_utime, utime);