summaryrefslogtreecommitdiffstats
path: root/include/asm-i386/timer.h
diff options
context:
space:
mode:
authorJeremy Fitzhardinge <jeremy@xensource.com>2007-07-17 18:37:04 -0700
committerJeremy Fitzhardinge <jeremy@goop.org>2007-07-18 08:47:42 -0700
commit688340ea34c61ad12473ccd837325b59aada9a93 (patch)
tree2862f4dca8d47fc4e6ecfaba2243d813344e3cd2 /include/asm-i386/timer.h
parentd572929cdd12a60732c3522f7cf011bfa29165cf (diff)
downloadtalos-op-linux-688340ea34c61ad12473ccd837325b59aada9a93.tar.gz
talos-op-linux-688340ea34c61ad12473ccd837325b59aada9a93.zip
Add a sched_clock paravirt_op
The tsc-based get_scheduled_cycles interface is not a good match for Xen's runstate accounting, which reports everything in nanoseconds. This patch replaces this interface with a sched_clock interface, which matches both Xen and VMI's requirements. In order to do this, we: 1. replace get_scheduled_cycles with sched_clock 2. hoist cycles_2_ns into a common header 3. update vmi accordingly One thing to note: because sched_clock is implemented as a weak function in kernel/sched.c, we must define a real function in order to override this weak binding. This means the usual paravirt_ops technique of using an inline function won't work in this case. Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Zachary Amsden <zach@vmware.com> Cc: Dan Hecht <dhecht@vmware.com> Cc: john stultz <johnstul@us.ibm.com>
Diffstat (limited to 'include/asm-i386/timer.h')
-rw-r--r--include/asm-i386/timer.h32
1 files changed, 31 insertions, 1 deletions
diff --git a/include/asm-i386/timer.h b/include/asm-i386/timer.h
index 153770e25faa..51a713e33a9e 100644
--- a/include/asm-i386/timer.h
+++ b/include/asm-i386/timer.h
@@ -15,8 +15,38 @@ extern int no_sync_cmos_clock;
extern int recalibrate_cpu_khz(void);
#ifndef CONFIG_PARAVIRT
-#define get_scheduled_cycles(val) rdtscll(val)
#define calculate_cpu_khz() native_calculate_cpu_khz()
#endif
+/* Accellerators for sched_clock()
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ * basic equation:
+ * ns = cycles / (freq / ns_per_sec)
+ * ns = cycles * (ns_per_sec / freq)
+ * ns = cycles * (10^9 / (cpu_khz * 10^3))
+ * ns = cycles * (10^6 / cpu_khz)
+ *
+ * Then we use scaling math (suggested by george@mvista.com) to get:
+ * ns = cycles * (10^6 * SC / cpu_khz) / SC
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * And since SC is a constant power of two, we can convert the div
+ * into a shift.
+ *
+ * We can use khz divisor instead of mhz to keep a better percision, since
+ * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ * (mathieu.desnoyers@polymtl.ca)
+ *
+ * -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ */
+extern unsigned long cyc2ns_scale __read_mostly;
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+ return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
+}
+
+
#endif
OpenPOWER on IntegriCloud