aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJan Beulich <jbeulich@novell.com>2006-05-30 16:47:54 -0400
committerLinus Torvalds <torvalds@g5.osdl.org>2006-05-30 23:31:05 -0400
commitb2468e525f29882f866cb0b832956e69328f9647 (patch)
tree7a48afb9933732c6fccb2baa1e928e3508a3c940
parent2ba567cbd7626700b800d4ce9503bd3cd78ed7ef (diff)
[PATCH] x86_64: fix last_tsc calculation of PM timer
From: "Jan Beulich" <jbeulich@novell.com> The PM timer code updates vxtime.last_tsc, but this update was done incorrectly in two ways: - offset_delay being in microseconds requires multiplying with cpu_mhz rather than cpu_khz - the multiplication of offset_delay and cpu_khz (both being 32-bit values) on most current CPUs would overflow (observed value of the delay was approximately 4000us, yielding an overflow for frequencies starting a little above 1GHz) Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--arch/x86_64/kernel/pmtimer.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86_64/kernel/pmtimer.c b/arch/x86_64/kernel/pmtimer.c
index b0444a415bd6..bf421ed26808 100644
--- a/arch/x86_64/kernel/pmtimer.c
+++ b/arch/x86_64/kernel/pmtimer.c
@@ -68,7 +68,7 @@ int pmtimer_mark_offset(void)
68 offset_delay = delta % (USEC_PER_SEC / HZ); 68 offset_delay = delta % (USEC_PER_SEC / HZ);
69 69
70 rdtscll(tsc); 70 rdtscll(tsc);
71 vxtime.last_tsc = tsc - offset_delay * cpu_khz; 71 vxtime.last_tsc = tsc - offset_delay * (u64)cpu_khz / 1000;
72 72
73 /* don't calculate delay for first run, 73 /* don't calculate delay for first run,
74 or if we've got less then a tick */ 74 or if we've got less then a tick */