The patch titled
replace get_scheduled_cycles with sched_clock paravirt_op
has been removed from the -mm tree. Its filename was
replace-get_scheduled_cycles-with-sched_clock-paravirt_op.patch
This patch was dropped because it had testing failures
------------------------------------------------------
Subject: replace get_scheduled_cycles with sched_clock paravirt_op
From: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
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@xxxxxxxxxxxxx>
Acked-by: Zachary Amsden <zach@xxxxxxxxxx>
Cc: Dan Hecht <dhecht@xxxxxxxxxx>
Cc: john stultz <johnstul@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/i386/kernel/paravirt.c | 2 +-
arch/i386/kernel/tsc.c | 23 +++++++++++++++--------
arch/i386/kernel/vmi.c | 2 +-
arch/i386/kernel/vmitime.c | 4 ++--
include/asm-i386/paravirt.h | 7 +++++--
include/asm-i386/timer.h | 32 +++++++++++++++++++++++++++++++-
include/asm-i386/vmi_time.h | 2 +-
7 files changed, 56 insertions(+), 16 deletions(-)
diff -puN arch/i386/kernel/paravirt.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op arch/i386/kernel/paravirt.c
--- a/arch/i386/kernel/paravirt.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/arch/i386/kernel/paravirt.c
@@ -521,7 +521,7 @@ struct paravirt_ops paravirt_ops = {
.write_msr = native_write_msr,
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
- .get_scheduled_cycles = native_read_tsc,
+ .sched_clock = native_sched_clock,
.get_cpu_khz = native_calculate_cpu_khz,
.load_tr_desc = native_load_tr_desc,
.set_ldt = native_set_ldt,
diff -puN arch/i386/kernel/tsc.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op arch/i386/kernel/tsc.c
--- a/arch/i386/kernel/tsc.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/arch/i386/kernel/tsc.c
@@ -81,7 +81,7 @@ static inline int check_tsc_unstable(voi
*
* -johnstul@xxxxxxxxxx "math is hard, lets go shopping!"
*/
-static unsigned long cyc2ns_scale __read_mostly;
+unsigned long cyc2ns_scale __read_mostly;
#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
@@ -90,15 +90,10 @@ static inline void set_cyc2ns_scale(unsi
cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
}
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
- return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
-}
-
/*
* Scheduler clock - returns current time in nanosec units.
*/
-unsigned long long sched_clock(void)
+unsigned long long native_sched_clock(void)
{
unsigned long long this_offset;
@@ -110,12 +105,24 @@ unsigned long long sched_clock(void)
return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
/* read the Time Stamp Counter: */
- get_scheduled_cycles(this_offset);
+ rdtscll(this_offset);
/* return the value in ns */
return cycles_2_ns(this_offset);
}
+/* We need to define a real function for sched_clock, to override the
+ weak default version */
+#ifdef CONFIG_PARAVIRT
+unsigned long long sched_clock(void)
+{
+ return paravirt_sched_clock();
+}
+#else
+unsigned long long sched_clock(void)
+ __attribute__((alias("native_sched_clock")));
+#endif
+
unsigned long native_calculate_cpu_khz(void)
{
unsigned long long start, end;
diff -puN arch/i386/kernel/vmi.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op arch/i386/kernel/vmi.c
--- a/arch/i386/kernel/vmi.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/arch/i386/kernel/vmi.c
@@ -900,7 +900,7 @@ static inline int __init activate_vmi(vo
paravirt_ops.setup_boot_clock = vmi_timer_setup_boot_alarm;
paravirt_ops.setup_secondary_clock = vmi_timer_setup_secondary_alarm;
#endif
- paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles;
+ paravirt_ops.sched_clock = vmi_sched_clock;
paravirt_ops.get_cpu_khz = vmi_cpu_khz;
/* We have true wallclock functions; disable CMOS clock sync */
diff -puN arch/i386/kernel/vmitime.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op arch/i386/kernel/vmitime.c
--- a/arch/i386/kernel/vmitime.c~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/arch/i386/kernel/vmitime.c
@@ -159,9 +159,9 @@ int vmi_set_wallclock(unsigned long now)
return -1;
}
-unsigned long long vmi_get_sched_cycles(void)
+unsigned long long vmi_sched_clock(void)
{
- return read_available_cycles();
+ return cycles_2_ns(read_available_cycles());
}
unsigned long vmi_cpu_khz(void)
diff -puN include/asm-i386/paravirt.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op include/asm-i386/paravirt.h
--- a/include/asm-i386/paravirt.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/include/asm-i386/paravirt.h
@@ -94,7 +94,7 @@ struct paravirt_ops
u64 (*read_tsc)(void);
u64 (*read_pmc)(void);
- u64 (*get_scheduled_cycles)(void);
+ unsigned long long (*sched_clock)(void);
unsigned long (*get_cpu_khz)(void);
void (*load_tr_desc)(void);
@@ -276,7 +276,10 @@ static inline void halt(void)
#define rdtscll(val) (val = paravirt_ops.read_tsc())
-#define get_scheduled_cycles(val) (val = paravirt_ops.get_scheduled_cycles())
+static inline unsigned long long paravirt_sched_clock(void)
+{
+ return PVOP_CALL0(unsigned long long, sched_clock);
+}
#define calculate_cpu_khz() (paravirt_ops.get_cpu_khz())
#define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
diff -puN include/asm-i386/timer.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op include/asm-i386/timer.h
--- a/include/asm-i386/timer.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/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@xxxxxxxxxx) 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@xxxxxxxxxx)
+ *
+ * -johnstul@xxxxxxxxxx "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
diff -puN include/asm-i386/vmi_time.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op include/asm-i386/vmi_time.h
--- a/include/asm-i386/vmi_time.h~replace-get_scheduled_cycles-with-sched_clock-paravirt_op
+++ a/include/asm-i386/vmi_time.h
@@ -49,7 +49,7 @@ extern struct vmi_timer_ops {
extern void __init vmi_time_init(void);
extern unsigned long vmi_get_wallclock(void);
extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_get_sched_cycles(void);
+extern unsigned long long vmi_sched_clock(void);
extern unsigned long vmi_cpu_khz(void);
#ifdef CONFIG_X86_LOCAL_APIC
_
Patches currently in -mm which might be from jeremy@xxxxxxxx are
replace-get_scheduled_cycles-with-sched_clock-paravirt_op.patch
fixes-and-cleanups-for-earlyprintk-aka-boot-console.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
