1 files changed, 88 insertions, 21 deletions

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ad2b925a808e..fb4302738410 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -25,6 +25,7 @@
 #include <asm/geode.h>
 #include <asm/apic.h>
 #include <asm/intel-family.h>
+#include <asm/i8259.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -112,7 +113,7 @@ static void cyc2ns_data_init(struct cyc2ns_data *data)
 	data->cyc2ns_offset = 0;
 }
 
-static void cyc2ns_init(int cpu)
+static void __init cyc2ns_init(int cpu)
 {
 	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
 
@@ -363,6 +364,20 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 	unsigned long tscmin, tscmax;
 	int pitcnt;
 
+	if (!has_legacy_pic()) {
+		/*
+		 * Relies on tsc_early_delay_calibrate() to have given us semi
+		 * usable udelay(), wait for the same 50ms we would have with
+		 * the PIT loop below.
+		 */
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		udelay(10 * USEC_PER_MSEC);
+		return ULONG_MAX;
+	}
+
 	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
@@ -487,6 +502,9 @@ static unsigned long quick_pit_calibrate(void)
 	u64 tsc, delta;
 	unsigned long d1, d2;
 
+	if (!has_legacy_pic())
+		return 0;
+
 	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
@@ -602,7 +620,6 @@ unsigned long native_calibrate_tsc(void)
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_SKYLAKE_X:
 		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
@@ -612,6 +629,8 @@ unsigned long native_calibrate_tsc(void)
 		}
 	}
 
+	if (crystal_khz == 0)
+		return 0;
 	/*
 	 * TSC frequency determined by CPUID is a "hardware reported"
 	 * frequency and is the most accurate one so far we have. This
@@ -812,13 +831,13 @@ unsigned long native_calibrate_cpu(void)
 	return tsc_pit_min;
 }
 
-int recalibrate_cpu_khz(void)
+void recalibrate_cpu_khz(void)
 {
 #ifndef CONFIG_SMP
 	unsigned long cpu_khz_old = cpu_khz;
 
 	if (!boot_cpu_has(X86_FEATURE_TSC))
-		return -ENODEV;
+		return;
 
 	cpu_khz = x86_platform.calibrate_cpu();
 	tsc_khz = x86_platform.calibrate_tsc();
@@ -828,10 +847,6 @@ int recalibrate_cpu_khz(void)
 		cpu_khz = tsc_khz;
 	cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy,
 						    cpu_khz_old, cpu_khz);
-
-	return 0;
-#else
-	return -ENODEV;
 #endif
 }
 
@@ -959,17 +974,21 @@ core_initcall(cpufreq_register_tsc_scaling);
 /*
  * If ART is present detect the numerator:denominator to convert to TSC
  */
-static void detect_art(void)
+static void __init detect_art(void)
 {
 	unsigned int unused[2];
 
 	if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
 		return;
 
-	/* Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required */
+	/*
+	 * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required,
+	 * and the TSC counter resets must not occur asynchronously.
+	 */
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR) ||
 	    !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
-	    !boot_cpu_has(X86_FEATURE_TSC_ADJUST))
+	    !boot_cpu_has(X86_FEATURE_TSC_ADJUST) ||
+	    tsc_async_resets)
 		return;
 
 	cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
@@ -987,8 +1006,6 @@ static void detect_art(void)
 
 /* clocksource code */
 
-static struct clocksource clocksource_tsc;
-
 static void tsc_resume(struct clocksource *cs)
 {
 	tsc_verify_tsc_adjust(true);
@@ -1039,12 +1056,31 @@ static void tsc_cs_tick_stable(struct clocksource *cs)
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
+static struct clocksource clocksource_tsc_early = {
+	.name                   = "tsc-early",
+	.rating                 = 299,
+	.read                   = read_tsc,
+	.mask                   = CLOCKSOURCE_MASK(64),
+	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_MUST_VERIFY,
+	.archdata               = { .vclock_mode = VCLOCK_TSC },
+	.resume			= tsc_resume,
+	.mark_unstable		= tsc_cs_mark_unstable,
+	.tick_stable		= tsc_cs_tick_stable,
+};
+
+/*
+ * Must mark VALID_FOR_HRES early such that when we unregister tsc_early
+ * this one will immediately take over. We will only register if TSC has
+ * been found good.
+ */
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_VALID_FOR_HRES |
 				  CLOCK_SOURCE_MUST_VERIFY,
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
@@ -1168,8 +1204,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	int cpu;
 
 	/* Don't bother refining TSC on unstable systems */
-	if (check_tsc_unstable())
-		goto out;
+	if (tsc_unstable)
+		return;
 
 	/*
 	 * Since the work is started early in boot, we may be
@@ -1221,9 +1257,13 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
 
 out:
+	if (tsc_unstable)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+	clocksource_unregister(&clocksource_tsc_early);
 }
 
 
@@ -1232,13 +1272,11 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
+	if (check_tsc_unstable())
+		return 0;
+
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-	/* lower the rating if we already know its unstable: */
-	if (check_tsc_unstable()) {
-		clocksource_tsc.rating = 0;
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
-	}
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1251,6 +1289,7 @@ static int __init init_tsc_clocksource(void)
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+		clocksource_unregister(&clocksource_tsc_early);
 		return 0;
 	}
 
@@ -1263,6 +1302,25 @@ static int __init init_tsc_clocksource(void)
  */
 device_initcall(init_tsc_clocksource);
 
+void __init tsc_early_delay_calibrate(void)
+{
+	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;
@@ -1296,6 +1354,12 @@ void __init tsc_init(void)
 		(unsigned long)cpu_khz / 1000,
 		(unsigned long)cpu_khz % 1000);
 
+	if (cpu_khz != tsc_khz) {
+		pr_info("Detected %lu.%03lu MHz TSC",
+			(unsigned long)tsc_khz / 1000,
+			(unsigned long)tsc_khz % 1000);
+	}
+
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
 
@@ -1330,9 +1394,12 @@ void __init tsc_init(void)
 
 	check_system_tsc_reliable();
 
-	if (unsynchronized_tsc())
+	if (unsynchronized_tsc()) {
 		mark_tsc_unstable("TSCs unsynchronized");
+		return;
+	}
 
+	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }