From: David Woodhouse <dwmw2@xxxxxxxxxxxxx> Sent: Friday, August 2, 2024 6:56 AM
>
> Leaving the PIT interrupt running can cause noticeable steal time for
> virtual guests. The VMM generally has a timer which toggles the IRQ input
> to the PIC and I/O APIC, which takes CPU time away from the guest. Even
> on real hardware, running the counter may use power needlessly (albeit
> not much).
>
> Make sure it's turned off if it isn't going to be used.
>
> Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
> ---
> arch/x86/kernel/i8253.c | 11 +++++++++--
> drivers/clocksource/i8253.c | 13 +++++++++----
> include/linux/i8253.h | 1 +
> 3 files changed, 19 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
> index 2b7999a1a50a..80e262bb627f 100644
> --- a/arch/x86/kernel/i8253.c
> +++ b/arch/x86/kernel/i8253.c
> @@ -8,6 +8,7 @@
> #include <linux/timex.h>
> #include <linux/i8253.h>
>
> +#include <asm/hypervisor.h>
> #include <asm/apic.h>
> #include <asm/hpet.h>
> #include <asm/time.h>
> @@ -39,9 +40,15 @@ static bool __init use_pit(void)
>
> bool __init pit_timer_init(void)
> {
> - if (!use_pit())
> + if (!use_pit()) {
> + /*
> + * Don't just ignore the PIT. Ensure it's stopped, because
> + * VMMs otherwise steal CPU time just to pointlessly waggle
> + * the (masked) IRQ.
> + */
> + clockevent_i8253_disable();
> return false;
> -
> + }
> clockevent_i8253_init(true);
> global_clock_event = &i8253_clockevent;
> return true;
> diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
> index d4350bb10b83..cb215e6f2e83 100644
> --- a/drivers/clocksource/i8253.c
> +++ b/drivers/clocksource/i8253.c
> @@ -108,11 +108,8 @@ int __init clocksource_i8253_init(void)
> #endif
>
> #ifdef CONFIG_CLKEVT_I8253
> -static int pit_shutdown(struct clock_event_device *evt)
> +void clockevent_i8253_disable(void)
> {
> - if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
> - return 0;
> -
> raw_spin_lock(&i8253_lock);
>
> outb_p(0x30, PIT_MODE);
> @@ -123,6 +120,14 @@ static int pit_shutdown(struct clock_event_device *evt)
> }
>
> raw_spin_unlock(&i8253_lock);
> +}
> +
> +static int pit_shutdown(struct clock_event_device *evt)
> +{
> + if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
> + return 0;
> +
> + clockevent_i8253_disable();
> return 0;
> }
>
> diff --git a/include/linux/i8253.h b/include/linux/i8253.h
> index 8336b2f6f834..bf169cfef7f1 100644
> --- a/include/linux/i8253.h
> +++ b/include/linux/i8253.h
> @@ -24,6 +24,7 @@ extern raw_spinlock_t i8253_lock;
> extern bool i8253_clear_counter_on_shutdown;
> extern struct clock_event_device i8253_clockevent;
> extern void clockevent_i8253_init(bool oneshot);
> +extern void clockevent_i8253_disable(void);
>
> extern void setup_pit_timer(void);
>
> --
> 2.44.0
Did a basic smoke test of this two-patch series on a Hyper-V Gen 1
VM and on a Gen 2 VM. All looks good and behaves as expected.
On the Gen 1 VM, the PIT is used briefly at boot (takes ~35 interrupts)
before the Hyper-V synthetic timer takes over and the PIT is shutdown.
As expected, no further interrupts are received from the PIT.
On a Gen 2 VM, apic_needs_pit() returns true because
X86_FEATURE_ARAT isn't present. The PIT doesn't exist in a
Gen 2 VM, but the code paths handle this situation with no
problems, just as before the patch series.
For the two-patch series on Hyper-V,
Tested-by: Michael Kelley <mhkelley@xxxxxxxxxxx>
