1 files changed, 57 insertions, 13 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index e93cca92f38b..6af50adcc0ff 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -521,18 +521,49 @@ EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
-static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total)
+/*
+ * Perform (stime * rtime) / total, but avoid multiplication overflow by
+ * loosing precision when the numbers are big.
+ */
+static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
 {
-	u64 temp = (__force u64) rtime;
+	u64 scaled;
 
-	temp *= (__force u64) stime;
+	for (;;) {
+		/* Make sure "rtime" is the bigger of stime/rtime */
+		if (stime > rtime) {
+			u64 tmp = rtime; rtime = stime; stime = tmp;
+		}
 
-	if (sizeof(cputime_t) == 4)
-		temp = div_u64(temp, (__force u32) total);
-	else
-		temp = div64_u64(temp, (__force u64) total);
+		/* Make sure 'total' fits in 32 bits */
+		if (total >> 32)
+			goto drop_precision;
+
+		/* Does rtime (and thus stime) fit in 32 bits? */
+		if (!(rtime >> 32))
+			break;
 
-	return (__force cputime_t) temp;
+		/* Can we just balance rtime/stime rather than dropping bits? */
+		if (stime >> 31)
+			goto drop_precision;
+
+		/* We can grow stime and shrink rtime and try to make them both fit */
+		stime <<= 1;
+		rtime >>= 1;
+		continue;
+
+drop_precision:
+		/* We drop from rtime, it has more bits than stime */
+		rtime >>= 1;
+		total >>= 1;
+	}
+
+	/*
+	 * Make sure gcc understands that this is a 32x32->64 multiply,
+	 * followed by a 64/32->64 divide.
+	 */
+	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
+	return (__force cputime_t) scaled;
 }
 
 /*
@@ -543,7 +574,7 @@ static void cputime_adjust(struct task_cputime *curr,
 			   struct cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, stime, total;
+	cputime_t rtime, stime, utime, total;
 
 	stime = curr->stime;
 	total = stime + curr->utime;
@@ -560,10 +591,22 @@ static void cputime_adjust(struct task_cputime *curr,
 	 */
 	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
-	if (total)
-		stime = scale_stime(stime, rtime, total);
-	else
+	/*
+	 * Update userspace visible utime/stime values only if actual execution
+	 * time is bigger than already exported. Note that can happen, that we
+	 * provided bigger values due to scaling inaccuracy on big numbers.
+	 */
+	if (prev->stime + prev->utime >= rtime)
+		goto out;
+
+	if (total) {
+		stime = scale_stime((__force u64)stime,
+				    (__force u64)rtime, (__force u64)total);
+		utime = rtime - stime;
+	} else {
 		stime = rtime;
+		utime = 0;
+	}
 
 	/*
 	 * If the tick based count grows faster than the scheduler one,
@@ -571,8 +614,9 @@ static void cputime_adjust(struct task_cputime *curr,
 	 * Let's enforce monotonicity.
 	 */
 	prev->stime = max(prev->stime, stime);
-	prev->utime = max(prev->utime, rtime - prev->stime);
+	prev->utime = max(prev->utime, utime);
 
+out:
 	*ut = prev->utime;
 	*st = prev->stime;
 }