[PATCH v12 09/11] x86/tsc: prepare for early sched_clock

From: Pavel Tatashin
Date: Thu Jun 21 2018 - 17:27:49 EST


We will change sched_clock() to be called early. But, during boot
sched_clock() changes its output without notifying us about the change of
clock source.

This happens in tsc_init(), when static_branch_enable(&__use_tsc) is
called.

native_sched_clock() changes from outputing jiffies to reading tsc, but
sched is not notified in anyway. So, to preserve the continoutity in this
place we add the offset of sched_clock() to the calculation of cyc2ns.

Without this change, the output would look like this:

[ 0.004000] ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
[ 0.009000] tsc: Fast TSC calibration using PIT
[ 0.010000] tsc: Detected 3192.137 MHz processor
[ 0.011000] clocksource: tsc-early: mask: 0xffffffffffffffff max_cycles: 0x2e03465ceb2, max_idle_ns: 440795259855 ns

static_branch_enable(__use_tsc) is called, and timestamps became precise
but reduced:

[ 0.002233] Calibrating delay loop (skipped), value calculated using timer frequency.. 6384.27 BogoMIPS (lpj=3192137)
[ 0.002516] pid_max: default: 32768 minimum: 301

Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
---
arch/x86/kernel/tsc.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 186395041725..654a01cc0358 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -133,7 +133,9 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
return ns;
}

-static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+static void set_cyc2ns_scale(unsigned long khz, int cpu,
+ unsigned long long tsc_now,
+ unsigned long long sched_now)
{
unsigned long long ns_now;
struct cyc2ns_data data;
@@ -146,7 +148,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_
if (!khz)
goto done;

- ns_now = cycles_2_ns(tsc_now);
+ ns_now = cycles_2_ns(tsc_now) + sched_now;

/*
* Compute a new multiplier as per the above comment and ensure our
@@ -936,7 +938,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
mark_tsc_unstable("cpufreq changes");

- set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
+ set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc(), 0);
}

return 0;
@@ -1285,7 +1287,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)

/* Update the sched_clock() rate to match the clocksource one */
for_each_possible_cpu(cpu)
- set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
+ set_cyc2ns_scale(tsc_khz, cpu, tsc_stop, 0);

out:
if (tsc_unstable)
@@ -1356,7 +1358,7 @@ void __init tsc_early_delay_calibrate(void)

void __init tsc_init(void)
{
- u64 lpj, cyc;
+ u64 lpj, cyc, sch;
int cpu;

if (!boot_cpu_has(X86_FEATURE_TSC)) {
@@ -1403,9 +1405,10 @@ void __init tsc_init(void)
* up if their speed diverges)
*/
cyc = rdtsc();
+ sch = local_clock();
for_each_possible_cpu(cpu) {
cyc2ns_init(cpu);
- set_cyc2ns_scale(tsc_khz, cpu, cyc);
+ set_cyc2ns_scale(tsc_khz, cpu, cyc, sch);
}

static_branch_enable(&__use_tsc);
--
2.17.1