[PATCH] i386 and x86_64 TSC set_cyc2ns_scale imprecision
I just found out that some precision is unnecessarily lost in the
arch/i386/kernel/timers/timer_tsc.c:set_cyc2ns_scale function. It uses a
cpu_mhz parameter when it could use a cpu_khz. In the specific case of an
Intel P4 running at 3001.171 Mhz, the truncation to 3001 Mhz leads to an
imprecision of 19 microseconds per second : this is very sad for a timer with
nearly nanosecond accuracy.
Fix the x86_64 architecture too.
Cc: george anzinger <george@mvista.com>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 703acde..47d25ad 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -481,9 +481,9 @@
static unsigned int cyc2ns_scale;
#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-static inline void set_cyc2ns_scale(unsigned long cpu_mhz)
+static inline void set_cyc2ns_scale(unsigned long cpu_khz)
{
- cyc2ns_scale = (1000 << CYC2NS_SCALE_FACTOR)/cpu_mhz;
+ cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
}
static inline unsigned long long cycles_2_ns(unsigned long long cyc)
@@ -655,7 +655,7 @@
vxtime.tsc_quot = (1000L << 32) / cpu_khz;
}
- set_cyc2ns_scale(cpu_khz_ref / 1000);
+ set_cyc2ns_scale(cpu_khz_ref);
return 0;
}
@@ -939,7 +939,7 @@
rdtscll_sync(&vxtime.last_tsc);
setup_irq(0, &irq0);
- set_cyc2ns_scale(cpu_khz / 1000);
+ set_cyc2ns_scale(cpu_khz);
#ifndef CONFIG_SMP
time_init_gtod();