1 files changed, 23 insertions, 31 deletions

diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index d851970e310c..e56307a81f4d 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -485,15 +485,9 @@ static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
 	return read_hv_clock_msr();
 }
 
-static u64 noinstr read_hv_sched_clock_msr(void)
-{
-	return (read_hv_clock_msr() - hv_sched_clock_offset) *
-		(NSEC_PER_SEC / HV_CLOCK_HZ);
-}
-
 static struct clocksource hyperv_cs_msr = {
 	.name	= "hyperv_clocksource_msr",
-	.rating	= 500,
+	.rating	= 495,
 	.read	= read_hv_clock_msr_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
@@ -523,7 +517,7 @@ static __always_inline void hv_setup_sched_clock(void *sched_clock)
 static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
 #endif /* CONFIG_GENERIC_SCHED_CLOCK */
 
-static bool __init hv_init_tsc_clocksource(void)
+static void __init hv_init_tsc_clocksource(void)
 {
 	union hv_reference_tsc_msr tsc_msr;
 
@@ -534,17 +528,14 @@ static bool __init hv_init_tsc_clocksource(void)
 	 * Hyper-V Reference TSC rating, causing the generic TSC to be used.
 	 * TSC_INVARIANT is not offered on ARM64, so the Hyper-V Reference
 	 * TSC will be preferred over the virtualized ARM64 arch counter.
-	 * While the Hyper-V MSR clocksource won't be used since the
-	 * Reference TSC clocksource is present, change its rating as
-	 * well for consistency.
 	 */
 	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
 		hyperv_cs_tsc.rating = 250;
-		hyperv_cs_msr.rating = 250;
+		hyperv_cs_msr.rating = 245;
 	}
 
 	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
-		return false;
+		return;
 
 	hv_read_reference_counter = read_hv_clock_tsc;
 
@@ -575,33 +566,34 @@ static bool __init hv_init_tsc_clocksource(void)
 
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
-	hv_sched_clock_offset = hv_read_reference_counter();
-	hv_setup_sched_clock(read_hv_sched_clock_tsc);
-
-	return true;
+	/*
+	 * If TSC is invariant, then let it stay as the sched clock since it
+	 * will be faster than reading the TSC page. But if not invariant, use
+	 * the TSC page so that live migrations across hosts with different
+	 * frequencies is handled correctly.
+	 */
+	if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT)) {
+		hv_sched_clock_offset = hv_read_reference_counter();
+		hv_setup_sched_clock(read_hv_sched_clock_tsc);
+	}
 }
 
 void __init hv_init_clocksource(void)
 {
 	/*
-	 * Try to set up the TSC page clocksource. If it succeeds, we're
-	 * done. Otherwise, set up the MSR clocksource.  At least one of
-	 * these will always be available except on very old versions of
-	 * Hyper-V on x86.  In that case we won't have a Hyper-V
+	 * Try to set up the TSC page clocksource, then the MSR clocksource.
+	 * At least one of these will always be available except on very old
+	 * versions of Hyper-V on x86.  In that case we won't have a Hyper-V
 	 * clocksource, but Linux will still run with a clocksource based
 	 * on the emulated PIT or LAPIC timer.
+	 *
+	 * Never use the MSR clocksource as sched clock.  It's too slow.
+	 * Better to use the native sched clock as the fallback.
 	 */
-	if (hv_init_tsc_clocksource())
-		return;
-
-	if (!(ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE))
-		return;
-
-	hv_read_reference_counter = read_hv_clock_msr;
-	clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
+	hv_init_tsc_clocksource();
 
-	hv_sched_clock_offset = hv_read_reference_counter();
-	hv_setup_sched_clock(read_hv_sched_clock_msr);
+	if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)
+		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
 }
 
 void __init hv_remap_tsc_clocksource(void)