[PATCH v4] x86/tsc: Add option to force frequency recalibration with HW timer

[Feng Tang]

The kernel assumes that the TSC frequency which is provided by the
hardware / firmware via MSRs or CPUID(0x15) is correct after applying
a few basic consistency checks. This disables the TSC recalibration
against HPET or PM timer.

As a result there is no mechanism to validate that frequency in cases
where a firmware or hardware defect is suspected. And there was case
that some user used atomic clock to measure the TSC frequency and
reported an inaccuracy issue, which was later fixed in firmware.

Add an option 'recalibrate' for 'tsc' kernel parameter to force the
tsc freq recalibration with HPET or PM timer, and warn if the deviation
from previous value is more than about 500 PPM, which provides a way 
to verify the data from hardware / firmware.

There is no functional change to existing work flow.

[Thanks tglx for helping improving the commit log] 

Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>
---
Changelog:

  since v3:
    * add some real world case into commit log
    * rebase against v6.0-rc1

  since v2:
    * revise the option description in kernel-parameters.txt
    * rebase against v5.19-rc2

  since v1:
    * refine commit log to state clearly the problem and intention
      of the patch by copying Thomas' words.

 .../admin-guide/kernel-parameters.txt         |  4 +++
 arch/x86/kernel/tsc.c                         | 34 ++++++++++++++++---
 2 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d7f30902fda0..4924256592d9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6302,6 +6302,10 @@
 			in situations with strict latency requirements (where
 			interruptions from clocksource watchdog are not
 			acceptable).
+			[x86] recalibrate: force to do frequency recalibration
+			with a HW timer (HPET or PM timer) for systems whose
+			TSC frequency comes from HW or FW through MSR or CPUID(0x15),
+			and warn if the difference is more than 500 ppm.
 
 	tsc_early_khz=  [X86] Skip early TSC calibration and use the given
 			value instead. Useful when the early TSC frequency discovery
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cafacb2e58cc..5cf62a58754a 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -48,6 +48,8 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
+static int __read_mostly tsc_force_recalibrate;
+
 static u32 art_to_tsc_numerator;
 static u32 art_to_tsc_denominator;
 static u64 art_to_tsc_offset;
@@ -303,6 +305,8 @@ static int __init tsc_setup(char *str)
 		mark_tsc_unstable("boot parameter");
 	if (!strcmp(str, "nowatchdog"))
 		no_tsc_watchdog = 1;
+	if (!strcmp(str, "recalibrate"))
+		tsc_force_recalibrate = 1;
 	return 1;
 }
 
@@ -1374,6 +1378,25 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	else
 		freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
 
+	/* Will hit this only if tsc_force_recalibrate has been set */
+	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+
+		/* Warn if the deviation exceeds 500 ppm */
+		if (abs(tsc_khz - freq) > (tsc_khz >> 11)) {
+			pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n");
+			pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n",
+				(unsigned long)tsc_khz / 1000,
+				(unsigned long)tsc_khz % 1000);
+		}
+
+		pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n",
+			hpet ? "HPET" : "PM_TIMER",
+			(unsigned long)freq / 1000,
+			(unsigned long)freq % 1000);
+
+		return;
+	}
+
 	/* Make sure we're within 1% */
 	if (abs(tsc_khz - freq) > tsc_khz/100)
 		goto out;
@@ -1407,8 +1430,10 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
-	if (tsc_unstable)
-		goto unreg;
+	if (tsc_unstable) {
+		clocksource_unregister(&clocksource_tsc_early);
+		return 0;
+	}
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1421,9 +1446,10 @@ 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);
-unreg:
 		clocksource_unregister(&clocksource_tsc_early);
-		return 0;
+
+		if (!tsc_force_recalibrate)
+			return 0;
 	}
 
 	schedule_delayed_work(&tsc_irqwork, 0);
-- 
2.27.0