[PATCH] x86_64: fix cpu MHz reporting on constant_tsc cpus

From: Joerg Roedel
Date: Tue Mar 13 2007 - 06:01:45 EST

Next message: Nick Piggin: "Re: SMP performance degradation with sysbench"
Previous message: Maximus: "Porting V4L2 drivers to 2.6.20"
Next in thread: Andi Kleen: "Re: [discuss] [PATCH] x86_64: fix cpu MHz reporting on constant_tsc cpus"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

From: Mark Langsdorf <mark.langsdorf@xxxxxxx>
From: Joerg Roedel <joerg.roedel@xxxxxxx>

This patch fixes the reporting of cpu_mhz in /proc/cpuinfo on CPUs with
a constant TSC rate and a kernel with disabled cpufreq.

Signed-off-by: Mark Langsdorf <mark.langsdorf@xxxxxxx>
Signed-off-by: Joerg Roedel <joerg.roedel@xxxxxxx>

--
Joerg Roedel
Operating System Research Center
AMD Saxony LLC & Co. KG
diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c
index 723417d..5f291b2 100644
--- a/arch/x86_64/kernel/apic.c
+++ b/arch/x86_64/kernel/apic.c
@@ -839,7 +839,7 @@ static int __init calibrate_APIC_clock(void)
} while ((tsc - tsc_start) < TICK_COUNT &&
(apic - apic_start) < TICK_COUNT);

- result = (apic_start - apic) * 1000L * cpu_khz /
+ result = (apic_start - apic) * 1000L * tsc_khz /
(tsc - tsc_start);
}
printk("result %d\n", result);
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 486f4c6..0bbaeda 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -168,7 +168,7 @@ void release_evntsel_nmi(unsigned int msr)
clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner));
}

-static __cpuinit inline int nmi_known_cpu(void)
+__cpuinit inline int nmi_known_cpu(void)
{
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
@@ -225,8 +225,8 @@ static unsigned int adjust_for_32bit_ctr(unsigned int hz)
* 32nd bit should be 1, for 33.. to be 1.
* Find the appropriate nmi_hz
*/
- if ((((u64)cpu_khz * 1000) / retval) > 0x7fffffffULL) {
- retval = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1;
+ if ((((u64)tsc_khz * 1000) / retval) > 0x7fffffffULL) {
+ retval = ((u64)tsc_khz * 1000) / 0x7fffffffUL + 1;
}
return retval;
}
@@ -493,7 +493,7 @@ static int setup_k7_watchdog(void)

/* setup the timer */
wrmsr(evntsel_msr, evntsel, 0);
- wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
+ wrmsrl(perfctr_msr, -((u64)tsc_khz * 1000 / nmi_hz));
apic_write(APIC_LVTPC, APIC_DM_NMI);
evntsel |= K7_EVNTSEL_ENABLE;
wrmsr(evntsel_msr, evntsel, 0);
@@ -601,7 +601,7 @@ static int setup_p4_watchdog(void)

wrmsr(evntsel_msr, evntsel, 0);
wrmsr(cccr_msr, cccr_val, 0);
- wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
+ wrmsrl(perfctr_msr, -((u64)tsc_khz * 1000 / nmi_hz));
apic_write(APIC_LVTPC, APIC_DM_NMI);
cccr_val |= P4_CCCR_ENABLE;
wrmsr(cccr_msr, cccr_val, 0);
@@ -671,7 +671,7 @@ static int setup_intel_arch_watchdog(void)
wrmsr(evntsel_msr, evntsel, 0);

nmi_hz = adjust_for_32bit_ctr(nmi_hz);
- wrmsr(perfctr_msr, (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
+ wrmsr(perfctr_msr, (u32)(-((u64)tsc_khz * 1000 / nmi_hz)), 0);

apic_write(APIC_LVTPC, APIC_DM_NMI);
evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
@@ -894,7 +894,7 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
apic_write(APIC_LVTPC, APIC_DM_NMI);
/* start the cycle over again */
wrmsrl(wd->perfctr_msr,
- -((u64)cpu_khz * 1000 / nmi_hz));
+ -((u64)tsc_khz * 1000 / nmi_hz));
} else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
/*
* ArchPerfom/Core Duo needs to re-unmask
@@ -903,11 +903,11 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
apic_write(APIC_LVTPC, APIC_DM_NMI);
/* ARCH_PERFMON has 32 bit counter writes */
wrmsr(wd->perfctr_msr,
- (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
+ (u32)(-((u64)tsc_khz * 1000 / nmi_hz)), 0);
} else {
/* start the cycle over again */
wrmsrl(wd->perfctr_msr,
- -((u64)cpu_khz * 1000 / nmi_hz));
+ -((u64)tsc_khz * 1000 / nmi_hz));
}
rc = 1;
} else if (nmi_watchdog == NMI_IO_APIC) {
@@ -1003,6 +1003,7 @@ void __trigger_all_cpu_backtrace(void)
}

EXPORT_SYMBOL(nmi_active);
+EXPORT_SYMBOL(nmi_known_cpu);
EXPORT_SYMBOL(nmi_watchdog);
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 75d73a9..52b5dc1 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -43,6 +43,7 @@
#include <linux/hpet.h>
#include <asm/apic.h>
#include <asm/hpet.h>
+#include <asm/nmi.h>

extern void i8254_timer_resume(void);
extern int using_apic_timer;
@@ -252,6 +253,51 @@ static unsigned long get_cmos_time(void)
return mktime(year, mon, day, hour, min, sec);
}

+/* calibrate_cpu is used on systems with fixed rate TSCs to determine
+ * processor frequency */
+#define TICK_COUNT 100000000
+static unsigned int __init tsc_calibrate_cpu_khz(void)
+{
+ int tsc_start, tsc_now;
+ int i, no_ctr_free;
+ unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
+ unsigned long flags;
+
+ for (i = 0; i < 4; i++)
+ if (avail_to_resrv_perfctr_nmi_bit(i))
+ break;
+ no_ctr_free = (i == 4);
+ if (no_ctr_free) {
+ i = 3;
+ rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ rdmsrl(MSR_K7_PERFCTR3, pmc3);
+ } else {
+ reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+ local_irq_save(flags);
+ /* start meauring cycles, incrementing from 0 */
+ wrmsrl(MSR_K7_PERFCTR0 + i, 0);
+ wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
+ rdtscl(tsc_start);
+ do {
+ rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+ tsc_now = get_cycles_sync();
+ } while ((tsc_now - tsc_start) < TICK_COUNT);
+
+ local_irq_restore(flags);
+ if (no_ctr_free) {
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ wrmsrl(MSR_K7_PERFCTR3, pmc3);
+ wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ } else {
+ release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ }
+
+ return pmc_now * tsc_khz / (tsc_now - tsc_start);
+}

/*
* pit_calibrate_tsc() uses the speaker output (channel 2) of
@@ -339,13 +385,19 @@ void __init time_init(void)
if (hpet_use_timer) {
/* set tick_nsec to use the proper rate for HPET */
tick_nsec = TICK_NSEC_HPET;
- cpu_khz = hpet_calibrate_tsc();
+ tsc_khz = hpet_calibrate_tsc();
timename = "HPET";
} else {
pit_init();
- cpu_khz = pit_calibrate_tsc();
+ tsc_khz = pit_calibrate_tsc();
timename = "PIT";
}
+
+ cpu_khz = tsc_khz;
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
+ nmi_known_cpu()) {
+ cpu_khz = tsc_calibrate_cpu_khz();
+ }

if (unsynchronized_tsc())
mark_tsc_unstable();
@@ -355,7 +407,7 @@ void __init time_init(void)
else
vgetcpu_mode = VGETCPU_LSL;

- set_cyc2ns_scale(cpu_khz);
+ set_cyc2ns_scale(tsc_khz);
printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
cpu_khz / 1000, cpu_khz % 1000);
init_tsc_clocksource();
diff --git a/arch/x86_64/kernel/tsc.c b/arch/x86_64/kernel/tsc.c
index 1a0edbb..5c84992 100644
--- a/arch/x86_64/kernel/tsc.c
+++ b/arch/x86_64/kernel/tsc.c
@@ -13,6 +13,8 @@ static int notsc __initdata = 0;

unsigned int cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
+unsigned int tsc_khz;
+EXPORT_SYMBOL(tsc_khz);

static unsigned int cyc2ns_scale __read_mostly;

@@ -77,7 +79,7 @@ static void handle_cpufreq_delayed_get(struct work_struct *v)
static unsigned int ref_freq = 0;
static unsigned long loops_per_jiffy_ref = 0;

-static unsigned long cpu_khz_ref = 0;
+static unsigned long tsc_khz_ref = 0;

static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
@@ -99,7 +101,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
if (!ref_freq) {
ref_freq = freq->old;
loops_per_jiffy_ref = *lpj;
- cpu_khz_ref = cpu_khz;
+ tsc_khz_ref = tsc_khz;
}
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
@@ -107,12 +109,12 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
*lpj =
cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);

- cpu_khz = cpufreq_scale(cpu_khz_ref, ref_freq, freq->new);
+ tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
mark_tsc_unstable();
}

- set_cyc2ns_scale(cpu_khz_ref);
+ set_cyc2ns_scale(tsc_khz_ref);

return 0;
}
@@ -213,7 +215,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
void __init init_tsc_clocksource(void)
{
if (!notsc) {
- clocksource_tsc.mult = clocksource_khz2mult(cpu_khz,
+ clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
clocksource_tsc.shift);
if (check_tsc_unstable())
clocksource_tsc.rating = 0;
diff --git a/arch/x86_64/kernel/tsc_sync.c b/arch/x86_64/kernel/tsc_sync.c
index 014f0db..72d444d 100644
--- a/arch/x86_64/kernel/tsc_sync.c
+++ b/arch/x86_64/kernel/tsc_sync.c
@@ -50,7 +50,7 @@ static __cpuinit void check_tsc_warp(void)
/*
* The measurement runs for 20 msecs:
*/
- end = start + cpu_khz * 20ULL;
+ end = start + tsc_khz * 20ULL;
now = start;

for (i = 0; ; i++) {
diff --git a/include/asm-x86_64/nmi.h b/include/asm-x86_64/nmi.h
index ceb3d8d..6b7520c 100644
--- a/include/asm-x86_64/nmi.h
+++ b/include/asm-x86_64/nmi.h
@@ -46,6 +46,7 @@ extern int unknown_nmi_panic;
extern int nmi_watchdog_enabled;

extern int check_nmi_watchdog(void);
+extern int nmi_known_cpu(void);
extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
extern int avail_to_resrv_perfctr_nmi(unsigned int);
extern int reserve_perfctr_nmi(unsigned int);
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index f54f3ab..e0b1fed 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -93,6 +93,7 @@ extern unsigned long table_start, table_end;

extern int exception_trace;
extern unsigned cpu_khz;
+extern unsigned tsc_khz;

extern void no_iommu_init(void);
extern int force_iommu, no_iommu;

Next message: Nick Piggin: "Re: SMP performance degradation with sysbench"
Previous message: Maximus: "Porting V4L2 drivers to 2.6.20"
Next in thread: Andi Kleen: "Re: [discuss] [PATCH] x86_64: fix cpu MHz reporting on constant_tsc cpus"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]