[PATCH v5 25/51] clocksource: hyper-v: Register sched_clock save/restore iff it's necessary
From: Sean Christopherson <seanjc@google.com>
Date: 2026-07-01 19:32:57
Also in:
kvm, linux-coco, linux-doc, linux-hyperv, lkml, xen-devel
Subsystem:
clocksource, clockevent drivers, hyper-v/azure core and drivers, the rest, x86 architecture (32-bit and 64-bit) · Maintainers:
Daniel Lezcano, Thomas Gleixner, "K. Y. Srinivasan", Haiyang Zhang, Wei Liu, Dexuan Cui, Long Li, Linus Torvalds, Ingo Molnar, Borislav Petkov, Dave Hansen
Register the Hyper-V reference counter (refcounter) callbacks for saving and restoring its PV sched_clock, if and only if the refcounter is actually being used for sched_clock. Currently, Hyper-V overrides the save/restore hooks if the reference TSC available, whereas the Hyper-V refcounter code only overrides sched_clock if the reference TSC is available *and* it's not invariant. The flaw is effectively papered over by invoking the "old" save/restore callbacks as part of save/restore, but that's unnecessary and fragile. To avoid introducing more complexity, and to allow for additional cleanups of the PV sched_clock code, move the save/restore hooks and logic into hyperv_timer.c and simply wire up the hooks when overriding sched_clock itself. Note, while the Hyper-V refcounter code is intended to be architecture neutral, CONFIG_PARAVIRT is firmly x86-only, i.e. adding a small amount of x86 specific code (which will be reduced in future cleanups) doesn't meaningfully pollute generic code. Reviewed-by: Michael Kelley <redacted> Tested-by: Michael Kelley <redacted> Acked-by: Wei Liu <wei.liu@kernel.org> Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/x86/kernel/cpu/mshyperv.c | 58 ------------------------------ drivers/clocksource/hyperv_timer.c | 50 ++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 58 deletions(-)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e03c69a4db33..c4da8e35319a 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c@@ -275,63 +275,6 @@ static void hv_guest_crash_shutdown(struct pt_regs *regs) } #endif /* CONFIG_CRASH_DUMP */ -static u64 hv_ref_counter_at_suspend; -static void (*old_save_sched_clock_state)(void); -static void (*old_restore_sched_clock_state)(void); - -/* - * Hyper-V clock counter resets during hibernation. Save and restore clock - * offset during suspend/resume, while also considering the time passed - * before suspend. This is to make sure that sched_clock using hv tsc page - * based clocksource, proceeds from where it left off during suspend and - * it shows correct time for the timestamps of kernel messages after resume. - */ -static void save_hv_clock_tsc_state(void) -{ - hv_ref_counter_at_suspend = hv_read_reference_counter(); -} - -static void restore_hv_clock_tsc_state(void) -{ - /* - * Adjust the offsets used by hv tsc clocksource to - * account for the time spent before hibernation. - * adjusted value = reference counter (time) at suspend - * - reference counter (time) now. - */ - hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); -} - -/* - * Functions to override save_sched_clock_state and restore_sched_clock_state - * functions of x86_platform. The Hyper-V clock counter is reset during - * suspend-resume and the offset used to measure time needs to be - * corrected, post resume. - */ -static void hv_save_sched_clock_state(void) -{ - old_save_sched_clock_state(); - save_hv_clock_tsc_state(); -} - -static void hv_restore_sched_clock_state(void) -{ - restore_hv_clock_tsc_state(); - old_restore_sched_clock_state(); -} - -static void __init x86_setup_ops_for_tsc_pg_clock(void) -{ - if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) - return; - - old_save_sched_clock_state = x86_platform.save_sched_clock_state; - x86_platform.save_sched_clock_state = hv_save_sched_clock_state; - - old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; - x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; -} - #ifdef CONFIG_X86_64 DEFINE_STATIC_CALL(hv_hypercall, hv_std_hypercall); EXPORT_STATIC_CALL_TRAMP_GPL(hv_hypercall);
@@ -736,7 +679,6 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); - x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /*
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index df567795d175..4293173c3a27 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c@@ -554,10 +554,60 @@ static __always_inline void hv_setup_sched_clock(void *sched_clock) #elif defined CONFIG_PARAVIRT #include <asm/timer.h> +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + static __always_inline void hv_setup_sched_clock(void *sched_clock) { /* We're on x86/x64 *and* using PV ops */ paravirt_set_sched_clock(sched_clock); + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; } #else /* !CONFIG_GENERIC_SCHED_CLOCK && !CONFIG_PARAVIRT */ static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
--
2.55.0.rc0.799.gd6f94ed593-goog