From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Thu, 19 Feb 2009 14:19:00 +0000 (+0100)
Subject: [S390] Fix timeval regression on s390
X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=d5cd0343d2878b66e25e044f644563c6bf708833;p=linux-2.6-omap-h63xx.git

[S390] Fix timeval regression on s390

commit aa5e97ce4bbc9d5daeec16b1d15bb3f6b7b4f4d4
[PATCH] improve precision of process accounting.

Introduced a timing regression:
-bash-3.2# time ls
real    0m0.006s
user    0m1.754s
sys     0m1.094s

The problem was introduced by an error in cputime_to_timeval.
Cputime is now 1/4096 microsecond, therefore, we have to divide
the remainder with 4096 to get the microseconds.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 521726430af..95b0f7db3c6 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -145,7 +145,7 @@ cputime_to_timeval(const cputime_t cputime, struct timeval *value)
 	value->tv_usec = rp.subreg.even / 4096;
 	value->tv_sec = rp.subreg.odd;
 #else
-	value->tv_usec = cputime % 4096000000ULL;
+	value->tv_usec = (cputime % 4096000000ULL) / 4096;
 	value->tv_sec = cputime / 4096000000ULL;
 #endif
 }