x86/tsc: Always Running Timer (ART) correlated clocksource

On modern Intel systems TSC is derived from the new Always Running Timer
(ART). ART can be captured simultaneous to the capture of
audio and network device clocks, allowing a correlation between timebases
to be constructed. Upon capture, the driver converts the captured ART
value to the appropriate system clock using the correlated clocksource
mechanism.

On systems that support ART a new CPUID leaf (0x15) returns parameters
“m” and “n” such that:

TSC_value = (ART_value * m) / n + k [n >= 1]

[k is an offset that can adjusted by a privileged agent. The
IA32_TSC_ADJUST MSR is an example of an interface to adjust k.
See 17.14.4 of the Intel SDM for more details]

Cc: Prarit Bhargava <[e-mail]>
Cc: Richard Cochran <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Reviewed-by: Thomas Gleixner <[e-mail]>
Signed-off-by: Christopher S. Hall <[e-mail]>
[jstultz: Tweaked to fix build issue, also reworked math for
64bit division on 32bit systems, as well as !CONFIG_CPU_FREQ build
fixes]
Signed-off-by: John Stultz <[e-mail]>

arch/x86/include/asm/cpufeature.h

···
 #define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
 #define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ART		(3*32+10) /* Platform has always running timer (ART) */
 #define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
 #define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */

arch/x86/include/asm/tsc.h

···
 	return rdtsc();
 }
 
+extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);

arch/x86/kernel/tsc.c

···
 
 int tsc_clocksource_reliable;
 
+static u32 art_to_tsc_numerator;
+static u32 art_to_tsc_denominator;
+static u64 art_to_tsc_offset;
+struct clocksource *art_related_clocksource;
+
 /*
  * Use a ring-buffer like data structure, where a writer advances the head by
  * writing a new data entry and a reader advances the tail when it observes a
···
 
 #endif /* CONFIG_CPU_FREQ */
 
+#define ART_CPUID_LEAF (0x15)
+#define ART_MIN_DENOMINATOR (1)
+
+
+/*
+ * If ART is present detect the numerator:denominator to convert to TSC
+ */
+static void detect_art(void)
+{
+	unsigned int unused[2];
+
+	if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
+		return;
+
+	cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
+	      &art_to_tsc_numerator, unused, unused+1);
+
+	/* Don't enable ART in a VM, non-stop TSC required */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
+	    art_to_tsc_denominator < ART_MIN_DENOMINATOR)
+		return;
+
+	if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset))
+		return;
+
+	/* Make this sticky over multiple CPU init calls */
+	setup_force_cpu_cap(X86_FEATURE_ART);
+}
+
+
 /* clocksource code */
 
 static struct clocksource clocksource_tsc;
···
 	return 0;
 }
 
+/*
+ * Convert ART to TSC given numerator/denominator found in detect_art()
+ */
+struct system_counterval_t convert_art_to_tsc(cycle_t art)
+{
+	u64 tmp, res, rem;
+
+	rem = do_div(art, art_to_tsc_denominator);
+
+	res = art * art_to_tsc_numerator;
+	tmp = rem * art_to_tsc_numerator;
+
+	do_div(tmp, art_to_tsc_denominator);
+	res += tmp + art_to_tsc_offset;
+
+	return (struct system_counterval_t) {.cs = art_related_clocksource,
+			.cycles = res};
+}
+EXPORT_SYMBOL(convert_art_to_tsc);
 
 static void tsc_refine_calibration_work(struct work_struct *work);
 static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
···
 		(unsigned long)tsc_khz % 1000);
 
 out:
+	if (boot_cpu_has(X86_FEATURE_ART))
+		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
···
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
+
+	detect_art();
 }
 
 #ifdef CONFIG_SMP