1 files changed, 150 insertions, 109 deletions

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 74392d9d51e0..1463468ba9a0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -33,16 +33,13 @@ EXPORT_SYMBOL(cpu_khz);
 unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
+#define KHZ	1000
+
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
 static int __read_mostly tsc_unstable;
 
-/* native_sched_clock() is called before tsc_init(), so
-   we must start with the TSC soft disabled to prevent
-   erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
-static int __read_mostly tsc_disabled = -1;
-
 static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
@@ -106,23 +103,6 @@ void cyc2ns_read_end(void)
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-static void cyc2ns_data_init(struct cyc2ns_data *data)
-{
-	data->cyc2ns_mul = 0;
-	data->cyc2ns_shift = 0;
-	data->cyc2ns_offset = 0;
-}
-
-static void __init cyc2ns_init(int cpu)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	cyc2ns_data_init(&c2n->data[0]);
-	cyc2ns_data_init(&c2n->data[1]);
-
-	seqcount_init(&c2n->seq);
-}
-
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	struct cyc2ns_data data;
@@ -138,18 +118,11 @@ 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 ns_now;
 	struct cyc2ns_data data;
 	struct cyc2ns *c2n;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sched_clock_idle_sleep_event();
-
-	if (!khz)
-		goto done;
 
 	ns_now = cycles_2_ns(tsc_now);
 
@@ -181,13 +154,56 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_
 	c2n->data[0] = data;
 	raw_write_seqcount_latch(&c2n->seq);
 	c2n->data[1] = data;
+}
+
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	sched_clock_idle_sleep_event();
+
+	if (khz)
+		__set_cyc2ns_scale(khz, cpu, tsc_now);
 
-done:
 	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
 
 /*
+ * Initialize cyc2ns for boot cpu
+ */
+static void __init cyc2ns_init_boot_cpu(void)
+{
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+
+	seqcount_init(&c2n->seq);
+	__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
+}
+
+/*
+ * Secondary CPUs do not run through tsc_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+static void __init cyc2ns_init_secondary_cpus(void)
+{
+	unsigned int cpu, this_cpu = smp_processor_id();
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+	struct cyc2ns_data *data = c2n->data;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu != this_cpu) {
+			seqcount_init(&c2n->seq);
+			c2n = per_cpu_ptr(&cyc2ns, cpu);
+			c2n->data[0] = data[0];
+			c2n->data[1] = data[1];
+		}
+	}
+}
+
+/*
  * Scheduler clock - returns current time in nanosec units.
  */
 u64 native_sched_clock(void)
@@ -248,8 +264,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable);
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
-	pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n");
-	tsc_disabled = 1;
+	mark_tsc_unstable("boot parameter notsc");
 	return 1;
 }
 #else
@@ -665,30 +680,17 @@ static unsigned long cpu_khz_from_cpuid(void)
 	return eax_base_mhz * 1000;
 }
 
-/**
- * native_calibrate_cpu - calibrate the cpu on boot
+/*
+ * calibrate cpu using pit, hpet, and ptimer methods. They are available
+ * later in boot after acpi is initialized.
  */
-unsigned long native_calibrate_cpu(void)
+static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate;
+	unsigned long flags, latch, ms;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	fast_calibrate = cpu_khz_from_cpuid();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	fast_calibrate = cpu_khz_from_msr();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	local_irq_save(flags);
-	fast_calibrate = quick_pit_calibrate();
-	local_irq_restore(flags);
-	if (fast_calibrate)
-		return fast_calibrate;
-
 	/*
 	 * Run 5 calibration loops to get the lowest frequency value
 	 * (the best estimate). We use two different calibration modes
@@ -831,6 +833,37 @@ unsigned long native_calibrate_cpu(void)
 	return tsc_pit_min;
 }
 
+/**
+ * native_calibrate_cpu_early - can calibrate the cpu early in boot
+ */
+unsigned long native_calibrate_cpu_early(void)
+{
+	unsigned long flags, fast_calibrate = cpu_khz_from_cpuid();
+
+	if (!fast_calibrate)
+		fast_calibrate = cpu_khz_from_msr();
+	if (!fast_calibrate) {
+		local_irq_save(flags);
+		fast_calibrate = quick_pit_calibrate();
+		local_irq_restore(flags);
+	}
+	return fast_calibrate;
+}
+
+
+/**
+ * native_calibrate_cpu - calibrate the cpu
+ */
+static unsigned long native_calibrate_cpu(void)
+{
+	unsigned long tsc_freq = native_calibrate_cpu_early();
+
+	if (!tsc_freq)
+		tsc_freq = pit_hpet_ptimer_calibrate_cpu();
+
+	return tsc_freq;
+}
+
 void recalibrate_cpu_khz(void)
 {
 #ifndef CONFIG_SMP
@@ -1307,7 +1340,7 @@ unreg:
 
 static int __init init_tsc_clocksource(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
 	if (tsc_unstable)
@@ -1341,40 +1374,22 @@ unreg:
  */
 device_initcall(init_tsc_clocksource);
 
-void __init tsc_early_delay_calibrate(void)
+static bool __init determine_cpu_tsc_frequencies(bool early)
 {
-	unsigned long lpj;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC))
-		return;
-
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
-	tsc_khz = tsc_khz ? : cpu_khz;
-	if (!tsc_khz)
-		return;
-
-	lpj = tsc_khz * 1000;
-	do_div(lpj, HZ);
-	loops_per_jiffy = lpj;
-}
-
-void __init tsc_init(void)
-{
-	u64 lpj, cyc;
-	int cpu;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC)) {
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
+	/* Make sure that cpu and tsc are not already calibrated */
+	WARN_ON(cpu_khz || tsc_khz);
+
+	if (early) {
+		cpu_khz = x86_platform.calibrate_cpu();
+		tsc_khz = x86_platform.calibrate_tsc();
+	} else {
+		/* We should not be here with non-native cpu calibration */
+		WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
+		cpu_khz = pit_hpet_ptimer_calibrate_cpu();
 	}
 
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
 	/*
-	 * Trust non-zero tsc_khz as authorative,
+	 * Trust non-zero tsc_khz as authoritative,
 	 * and use it to sanity check cpu_khz,
 	 * which will be off if system timer is off.
 	 */
@@ -1383,52 +1398,78 @@ void __init tsc_init(void)
 	else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz)
 		cpu_khz = tsc_khz;
 
-	if (!tsc_khz) {
-		mark_tsc_unstable("could not calculate TSC khz");
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
-	}
+	if (tsc_khz == 0)
+		return false;
 
 	pr_info("Detected %lu.%03lu MHz processor\n",
-		(unsigned long)cpu_khz / 1000,
-		(unsigned long)cpu_khz % 1000);
+		(unsigned long)cpu_khz / KHZ,
+		(unsigned long)cpu_khz % KHZ);
 
 	if (cpu_khz != tsc_khz) {
 		pr_info("Detected %lu.%03lu MHz TSC",
-			(unsigned long)tsc_khz / 1000,
-			(unsigned long)tsc_khz % 1000);
+			(unsigned long)tsc_khz / KHZ,
+			(unsigned long)tsc_khz % KHZ);
 	}
+	return true;
+}
+
+static unsigned long __init get_loops_per_jiffy(void)
+{
+	unsigned long lpj = tsc_khz * KHZ;
 
+	do_div(lpj, HZ);
+	return lpj;
+}
+
+static void __init tsc_enable_sched_clock(void)
+{
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
+	cyc2ns_init_boot_cpu();
+	static_branch_enable(&__use_tsc);
+}
+
+void __init tsc_early_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_TSC))
+		return;
+	if (!determine_cpu_tsc_frequencies(true))
+		return;
+	loops_per_jiffy = get_loops_per_jiffy();
 
+	tsc_enable_sched_clock();
+}
+
+void __init tsc_init(void)
+{
 	/*
-	 * Secondary CPUs do not run through tsc_init(), so set up
-	 * all the scale factors for all CPUs, assuming the same
-	 * speed as the bootup CPU. (cpufreq notifiers will fix this
-	 * up if their speed diverges)
+	 * native_calibrate_cpu_early can only calibrate using methods that are
+	 * available early in boot.
 	 */
-	cyc = rdtsc();
-	for_each_possible_cpu(cpu) {
-		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu, cyc);
-	}
+	if (x86_platform.calibrate_cpu == native_calibrate_cpu_early)
+		x86_platform.calibrate_cpu = native_calibrate_cpu;
 
-	if (tsc_disabled > 0)
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
-	/* now allow native_sched_clock() to use rdtsc */
+	if (!tsc_khz) {
+		/* We failed to determine frequencies earlier, try again */
+		if (!determine_cpu_tsc_frequencies(false)) {
+			mark_tsc_unstable("could not calculate TSC khz");
+			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+			return;
+		}
+		tsc_enable_sched_clock();
+	}
 
-	tsc_disabled = 0;
-	static_branch_enable(&__use_tsc);
+	cyc2ns_init_secondary_cpus();
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
 
-	lpj = ((u64)tsc_khz * 1000);
-	do_div(lpj, HZ);
-	lpj_fine = lpj;
-
+	lpj_fine = get_loops_per_jiffy();
 	use_tsc_delay();
 
 	check_system_tsc_reliable();
@@ -1455,7 +1496,7 @@ unsigned long calibrate_delay_is_known(void)
 	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
 	const struct cpumask *mask = topology_core_cpumask(cpu);
 
-	if (tsc_disabled || !constant_tsc || !mask)
+	if (!constant_tsc || !mask)
 		return 0;
 
 	sibling = cpumask_any_but(mask, cpu);