Merge branch 'x86-tsc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-tsc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Check tsc available/disabled in the delayed init function
  x86: Improve TSC calibration using a delayed workqueue
  x86: Make tsc=reliable override boot time stability checks

2 files changed, 96 insertions, 9 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d6496fde6180..f3dc951e949f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2461,12 +2461,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			to facilitate early boot debugging.
 			See also Documentation/trace/events.txt
 
-	tsc=		Disable clocksource-must-verify flag for TSC.
+	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
 			[x86] reliable: mark tsc clocksource as reliable, this
-			disables clocksource verification at runtime.
-			Used to enable high-resolution timer mode on older
-			hardware, and in virtualized environment.
+			disables clocksource verification at runtime, as well
+			as the stability checks done at bootup.	Used to enable
+			high-resolution timer mode on older hardware, and in
+			virtualized environment.
 			[x86] noirqtime: Do not use TSC to do irq accounting.
 			Used to run time disable IRQ_TIME_ACCOUNTING on any
 			platforms where RDTSC is slow and this accounting
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0c40d8b72416..356a0d455cf9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void)
 
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		return 0;
+
+	if (tsc_clocksource_reliable)
+		return 0;
 	/*
 	 * Intel systems are normally all synchronized.
 	 * Exceptions must mark TSC as unstable:
@@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void)
 	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 1;
 	}
 
-	return tsc_unstable;
+	return 0;
+}
+
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomolies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
+{
+	static u64 tsc_start = -1, ref_start;
+	static int hpet;
+	u64 tsc_stop, ref_stop, delta;
+	unsigned long freq;
+
+	/* Don't bother refining TSC on unstable systems */
+	if (check_tsc_unstable())
+		goto out;
+
+	/*
+	 * Since the work is started early in boot, we may be
+	 * delayed the first time we expire. So set the workqueue
+	 * again once we know timers are working.
+	 */
+	if (tsc_start == -1) {
+		/*
+		 * Only set hpet once, to avoid mixing hardware
+		 * if the hpet becomes enabled later.
+		 */
+		hpet = is_hpet_enabled();
+		schedule_delayed_work(&tsc_irqwork, HZ);
+		tsc_start = tsc_read_refs(&ref_start, hpet);
+		return;
+	}
+
+	tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+	/* hpet or pmtimer available ? */
+	if (!hpet && !ref_start && !ref_stop)
+		goto out;
+
+	/* Check, whether the sampling was disturbed by an SMI */
+	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+		goto out;
+
+	delta = tsc_stop - tsc_start;
+	delta *= 1000000LL;
+	if (hpet)
+		freq = calc_hpet_ref(delta, ref_start, ref_stop);
+	else
+		freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+	/* Make sure we're within 1% */
+	if (abs(tsc_khz - freq) > tsc_khz/100)
+		goto out;
+
+	tsc_khz = freq;
+	printk(KERN_INFO "Refined TSC clocksource calibration: "
+		"%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+					(unsigned long)tsc_khz % 1000);
+
+out:
+	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-static void __init init_tsc_clocksource(void)
+
+static int __init init_tsc_clocksource(void)
 {
+	if (!cpu_has_tsc || tsc_disabled > 0)
+		return 0;
+
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 	/* lower the rating if we already know its unstable: */
@@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void)
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
-	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+	schedule_delayed_work(&tsc_irqwork, 0);
+	return 0;
 }
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
 
 void __init tsc_init(void)
 {
@@ -949,6 +1036,5 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
-	init_tsc_clocksource();
 }