[PATCH v2] sched/cputime: make scale_stime() more precise

[Oleg Nesterov <oleg@redhat.com>]

People report that utime and stime from /proc/<pid>/stat become very
wrong when the numbers are big enough, especially if you watch these
counters incrementally.

Say, if the monitored process runs 100 days 50/50 in user/kernel mode
it looks as if it runs 20 minutes entirely in kernel mode, then 20
minutes in user mode. See the test-case which tries to demonstrate this
behaviour:

	https://lore.kernel.org/lkml/20200124154215.GA14714@redhat.com/

The new implementation does the additional div64_u64_rem() but according
to my naive measurements it is faster on x86_64, much faster if rtime/etc
are big enough. See

	https://lore.kernel.org/lkml/20200123130541.GA30620@redhat.com/

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 kernel/sched/cputime.c | 65 +++++++++++++++++++++++++-------------------------
 1 file changed, 32 insertions(+), 33 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index d43318a..ae1ea09 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -528,42 +528,41 @@ void account_idle_ticks(unsigned long ticks)
  */
 static u64 scale_stime(u64 stime, u64 rtime, u64 total)
 {
-	u64 scaled;
+	u64 res = 0, div, rem;
+	int shift;
 
-	for (;;) {
-		/* Make sure "rtime" is the bigger of stime/rtime */
-		if (stime > rtime)
-			swap(rtime, stime);
-
-		/* 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;
+	/* can stime * rtime overflow ? */
+	if (ilog2(stime) + ilog2(rtime) > 62) {
+		/*
+		 * (rtime * stime) / total is equal to
+		 *
+		 *	(rtime / total) * stime +
+		 *	(rtime % total) * stime / total
+		 *
+		 * if nothing overflows. Can the 1st multiplication
+		 * overflow? Yes, but we do not care: this can only
+		 * happen if the end result can't fit in u64 anyway.
+		 *
+		 * So the code below does
+		 *
+		 *	res = (rtime / total) * stime;
+		 *	rtime = rtime % total;
+		 */
+		div = div64_u64_rem(rtime, total, &rem);
+		res = div * stime;
+		rtime = rem;
+
+		shift = ilog2(stime) + ilog2(rtime) - 62;
+		if (shift > 0) {
+			/* drop precision */
+			rtime >>= shift;
+			total >>= shift;
+			if (!total)
+				return res;
+		}
 	}
 
-	/*
-	 * 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 scaled;
+	return res + div64_u64(stime * rtime, total);
 }
 
 /*
-- 
2.5.0