x86: merge tsc_init and clocksource code

Unify the clocksource code.
Unify the tsc_init code.

Signed-off-by: Alok N Kataria <akataria@vmware.com>
Signed-off-by: Dan Hecht <dhecht@vmware.com>
Cc: Dan Hecht <dhecht@vmware.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/Makefile

@@ -26,7 +26,7 @@ obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o
-obj-y			+= tsc_$(BITS).o io_delay.o rtc.o tsc.o
+obj-y			+= tsc.o io_delay.o rtc.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o

arch/x86/kernel/time_64.c

@@ -56,7 +56,7 @@ static irqreturn_t timer_event_interrupt(int irq, void *dev_id)
 /* calibrate_cpu is used on systems with fixed rate TSCs to determine
  * processor frequency */
 #define TICK_COUNT 100000000
-static unsigned long __init calibrate_cpu(void)
+unsigned long __init calibrate_cpu(void)
 {
 	int tsc_start, tsc_now;
 	int i, no_ctr_free;
@@ -114,41 +114,13 @@ void __init hpet_time_init(void)
 	setup_irq(0, &irq0);
 }
 
-extern void set_cyc2ns_scale(unsigned long cpu_khz, int cpu);
-
 void __init time_init(void)
 {
-	int cpu;
-
-	cpu_khz = calculate_cpu_khz();
-	tsc_khz = cpu_khz;
-
-	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
-			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
-		cpu_khz = calibrate_cpu();
-
-	lpj_fine = ((unsigned long)tsc_khz * 1000)/HZ;
-
-	if (unsynchronized_tsc())
-		mark_tsc_unstable("TSCs unsynchronized");
-
+	tsc_init();
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
 		vgetcpu_mode = VGETCPU_RDTSCP;
 	else
 		vgetcpu_mode = VGETCPU_LSL;
 
-	printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
-			cpu_khz / 1000, cpu_khz % 1000);
-
-	/*
-	 * 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)
-	 */
-	for_each_possible_cpu(cpu)
-		set_cyc2ns_scale(cpu_khz, cpu);
-
-	init_tsc_clocksource();
 	late_time_init = choose_time_init();
 }

arch/x86/kernel/tsc.c

@@ -5,8 +5,16 @@
 #include <linux/timer.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/cpufreq.h>
+#include <linux/dmi.h>
+#include <linux/delay.h>
+#include <linux/clocksource.h>
+#include <linux/percpu.h>
 
 #include <asm/hpet.h>
+#include <asm/timer.h>
+#include <asm/vgtod.h>
+#include <asm/time.h>
+#include <asm/delay.h>
 
 unsigned int cpu_khz;           /* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -16,12 +24,12 @@ EXPORT_SYMBOL(tsc_khz);
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
-int tsc_unstable;
+static int 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 !cpu_has_tsc processors */
-int tsc_disabled = -1;
+static int tsc_disabled = -1;
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -241,7 +249,7 @@ EXPORT_SYMBOL(recalibrate_cpu_khz);
 
 DEFINE_PER_CPU(unsigned long, cyc2ns);
 
-void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
+static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
 	unsigned long long tsc_now, ns_now;
 	unsigned long flags, *scale;
@@ -329,3 +337,201 @@ static int __init cpufreq_tsc(void)
 core_initcall(cpufreq_tsc);
 
 #endif /* CONFIG_CPU_FREQ */
+
+/* clocksource code */
+
+static struct clocksource clocksource_tsc;
+
+/*
+ * We compare the TSC to the cycle_last value in the clocksource
+ * structure to avoid a nasty time-warp. This can be observed in a
+ * very small window right after one CPU updated cycle_last under
+ * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
+ * is smaller than the cycle_last reference value due to a TSC which
+ * is slighty behind. This delta is nowhere else observable, but in
+ * that case it results in a forward time jump in the range of hours
+ * due to the unsigned delta calculation of the time keeping core
+ * code, which is necessary to support wrapping clocksources like pm
+ * timer.
+ */
+static cycle_t read_tsc(void)
+{
+	cycle_t ret = (cycle_t)get_cycles();
+
+	return ret >= clocksource_tsc.cycle_last ?
+		ret : clocksource_tsc.cycle_last;
+}
+
+static cycle_t __vsyscall_fn vread_tsc(void)
+{
+	cycle_t ret = (cycle_t)vget_cycles();
+
+	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
+		ret : __vsyscall_gtod_data.clock.cycle_last;
+}
+
+static struct clocksource clocksource_tsc = {
+	.name                   = "tsc",
+	.rating                 = 300,
+	.read                   = read_tsc,
+	.mask                   = CLOCKSOURCE_MASK(64),
+	.shift                  = 22,
+	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_MUST_VERIFY,
+#ifdef CONFIG_X86_64
+	.vread                  = vread_tsc,
+#endif
+};
+
+void mark_tsc_unstable(char *reason)
+{
+	if (!tsc_unstable) {
+		tsc_unstable = 1;
+		printk("Marking TSC unstable due to %s\n", reason);
+		/* Change only the rating, when not registered */
+		if (clocksource_tsc.mult)
+			clocksource_change_rating(&clocksource_tsc, 0);
+		else
+			clocksource_tsc.rating = 0;
+	}
+}
+
+EXPORT_SYMBOL_GPL(mark_tsc_unstable);
+
+static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
+{
+	printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
+			d->ident);
+	tsc_unstable = 1;
+	return 0;
+}
+
+/* List of systems that have known TSC problems */
+static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
+	{
+		.callback = dmi_mark_tsc_unstable,
+		.ident = "IBM Thinkpad 380XD",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
+			DMI_MATCH(DMI_BOARD_NAME, "2635FA0"),
+		},
+	},
+	{}
+};
+
+/*
+ * Geode_LX - the OLPC CPU has a possibly a very reliable TSC
+ */
+#ifdef CONFIG_MGEODE_LX
+/* RTSC counts during suspend */
+#define RTSC_SUSP 0x100
+
+static void __init check_geode_tsc_reliable(void)
+{
+	unsigned long res_low, res_high;
+
+	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+	if (res_low & RTSC_SUSP)
+		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+}
+#else
+static inline void check_geode_tsc_reliable(void) { }
+#endif
+
+/*
+ * Make an educated guess if the TSC is trustworthy and synchronized
+ * over all CPUs.
+ */
+__cpuinit int unsynchronized_tsc(void)
+{
+	if (!cpu_has_tsc || tsc_unstable)
+		return 1;
+
+#ifdef CONFIG_SMP
+	if (apic_is_clustered_box())
+		return 1;
+#endif
+
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return 0;
+	/*
+	 * Intel systems are normally all synchronized.
+	 * Exceptions must mark TSC as unstable:
+	 */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+		/* assume multi socket systems are not synchronized: */
+		if (num_possible_cpus() > 1)
+			tsc_unstable = 1;
+	}
+
+	return tsc_unstable;
+}
+
+static void __init init_tsc_clocksource(void)
+{
+	clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
+			clocksource_tsc.shift);
+	/* lower the rating if we already know its unstable: */
+	if (check_tsc_unstable()) {
+		clocksource_tsc.rating = 0;
+		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
+	}
+	clocksource_register(&clocksource_tsc);
+}
+
+void __init tsc_init(void)
+{
+	u64 lpj;
+	int cpu;
+
+	if (!cpu_has_tsc)
+		return;
+
+	cpu_khz = calculate_cpu_khz();
+	tsc_khz = cpu_khz;
+
+	if (!cpu_khz) {
+		mark_tsc_unstable("could not calculate TSC khz");
+		return;
+	}
+
+#ifdef CONFIG_X86_64
+	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
+			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
+		cpu_khz = calibrate_cpu();
+#endif
+
+	lpj = ((u64)tsc_khz * 1000);
+	do_div(lpj, HZ);
+	lpj_fine = lpj;
+
+	printk("Detected %lu.%03lu MHz processor.\n",
+			(unsigned long)cpu_khz / 1000,
+			(unsigned long)cpu_khz % 1000);
+
+	/*
+	 * 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)
+	 */
+	for_each_possible_cpu(cpu)
+		set_cyc2ns_scale(cpu_khz, cpu);
+
+	if (tsc_disabled > 0)
+		return;
+
+	/* now allow native_sched_clock() to use rdtsc */
+	tsc_disabled = 0;
+
+	use_tsc_delay();
+	/* Check and install the TSC clocksource */
+	dmi_check_system(bad_tsc_dmi_table);
+
+	if (unsynchronized_tsc())
+		mark_tsc_unstable("TSCs unsynchronized");
+
+	check_geode_tsc_reliable();
+	init_tsc_clocksource();
+}
+