On Tue, Aug 12, 2025 at 07:48:45PM +0000, Wei Liu wrote:
> The HV_ACCESS_TSC_INVARIANT bit is always zero when Linux runs as the
> root partition. The root partition will see directly what the hardware
> provides.
>
> The old logic in ms_hyperv_init_platform caused the native TSC clock
> source to be incorrectly marked as unstable on x86. Fix it.
>
> Skip the unnecessary checks in code for the root partition. Add one
> extra comment in code to clarify the behavior.
>
> Signed-off-by: Wei Liu <wei....@kernel.org>
> ---
> v2: update the commit message and comments
> ---
> arch/x86/kernel/cpu/mshyperv.c | 11 ++++++++++-
> drivers/clocksource/hyperv_timer.c | 10 +++++++++-
> 2 files changed, 19 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index c78f860419d6..25773af116bc 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -565,6 +565,11 @@ static void __init ms_hyperv_init_platform(void)
> machine_ops.crash_shutdown = hv_machine_crash_shutdown;
> #endif
> #endif
> + /*
> + * HV_ACCESS_TSC_INVARIANT is always zero for the root partition. Root
> + * partition doesn't need to write to synthetic MSR to enable invariant
> + * TSC feature. It sees what the hardware provides.
> + */
> if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
> /*
> * Writing to synthetic MSR 0x40000118 updates/changes the
> @@ -636,8 +641,12 @@ static void __init ms_hyperv_init_platform(void)
> * TSC should be marked as unstable only after Hyper-V
> * clocksource has been initialized. This ensures that the
> * stability of the sched_clock is not altered.
> + *
> + * HV_ACCESS_TSC_INVARIANT is always zero for the root partition. No
> + * need to check for it.
> */
> - if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
> + if (!hv_root_partition() &&
> + !(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
> mark_tsc_unstable("running on Hyper-V");
>
> hardlockup_detector_disable();
> diff --git a/drivers/clocksource/hyperv_timer.c
> b/drivers/clocksource/hyperv_timer.c
> index 2edc13ca184e..ca39044a4a60 100644
> --- a/drivers/clocksource/hyperv_timer.c
> +++ b/drivers/clocksource/hyperv_timer.c
> @@ -549,14 +549,22 @@ static void __init hv_init_tsc_clocksource(void)
> union hv_reference_tsc_msr tsc_msr;
>
> /*
> + * When running as a guest partition:
> + *
> * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
> * handles frequency and offset changes due to live migration,
> * pause/resume, and other VM management operations. So lower the
> * 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.
> + *
> + * When running as the root partition:
> + *
> + * There is no HV_ACCESS_TSC_INVARIANT feature. Skip the unnecessary
> + * check.
This comment needs to be changed.
* There is no HV_ACCESS_TSC_INVARIANT feature. Always lower the
* rating of the Hyper-V Reference TSC.
> */
> - if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
> + if ((ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) ||
> + hv_root_partition()) {
> hyperv_cs_tsc.rating = 250;
> hyperv_cs_msr.rating = 245;
> }
> --
> 2.43.0
>
