Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "This fixes the cputime scaling overflow problems for good without
  having bad 32-bit overhead, and gets rid of the div64_u64_rem() helper
  as well."

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Revert "math64: New div64_u64_rem helper"
  sched: Avoid prev->stime underflow
  sched: Do not account bogus utime
  sched: Avoid cputime scaling overflow

1 files changed, 51 insertions, 29 deletions

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ea32f02bf2c..cc2dc3eea8a 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -506,34 +506,47 @@ void account_idle_ticks(unsigned long ticks)
 }
 
 /*
- * Perform (stime * rtime) / total with reduced chances
- * of multiplication overflows by using smaller factors
- * like quotient and remainders of divisions between
- * rtime and 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 rem, res, scaled;
+	u64 scaled;
 
-	if (rtime >= total) {
-		/*
-		 * Scale up to rtime / total then add
-		 * the remainder scaled to stime / total.
-		 */
-		res = div64_u64_rem(rtime, total, &rem);
-		scaled = stime * res;
-		scaled += div64_u64(stime * rem, total);
-	} else {
-		/*
-		 * Same in reverse: scale down to total / rtime
-		 * then substract that result scaled to
-		 * to the remaining part.
-		 */
-		res = div64_u64_rem(total, rtime, &rem);
-		scaled = div64_u64(stime, res);
-		scaled -= div64_u64(scaled * rem, total);
+	for (;;) {
+		/* Make sure "rtime" is the bigger of stime/rtime */
+		if (stime > rtime) {
+			u64 tmp = rtime; rtime = stime; stime = tmp;
+		}
+
+		/* 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;
+
+		/* 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;
 }
 
@@ -545,7 +558,7 @@ 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;
 
 	if (vtime_accounting_enabled()) {
 		*ut = curr->utime;
@@ -568,13 +581,21 @@ static void cputime_adjust(struct task_cputime *curr,
 	 */
 	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
-	if (!rtime) {
-		stime = 0;
-	} else if (!total) {
-		stime = rtime;
-	} 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;
 	}
 
 	/*
@@ -583,8 +604,9 @@ 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;
 }