diff options
Diffstat (limited to 'drivers/clocksource/hyperv_timer.c')
| -rw-r--r-- | drivers/clocksource/hyperv_timer.c | 47 |
1 files changed, 41 insertions, 6 deletions
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index b2a080647e41..10356d4ec55c 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -22,12 +22,14 @@ #include <linux/irq.h> #include <linux/acpi.h> #include <linux/hyperv.h> +#include <linux/export.h> #include <clocksource/hyperv_timer.h> -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -137,7 +139,21 @@ static int hv_stimer_init(unsigned int cpu) ce->name = "Hyper-V clockevent"; ce->features = CLOCK_EVT_FEAT_ONESHOT; ce->cpumask = cpumask_of(cpu); - ce->rating = 1000; + + /* + * Lower the rating of the Hyper-V timer in a TDX VM without paravisor, + * so the local APIC timer (lapic_clockevent) is the default timer in + * such a VM. The Hyper-V timer is not preferred in such a VM because + * it depends on the slow VM Reference Counter MSR (the Hyper-V TSC + * page is not enbled in such a VM because the VM uses Invariant TSC + * as a better clocksource and it's challenging to mark the Hyper-V + * TSC page shared in very early boot). + */ + if (!ms_hyperv.paravisor_present && hv_isolation_type_tdx()) + ce->rating = 90; + else + ce->rating = 1000; + ce->set_state_shutdown = hv_ce_shutdown; ce->set_state_oneshot = hv_ce_set_oneshot; ce->set_next_event = hv_ce_set_next_event; @@ -456,6 +472,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { @@ -522,14 +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. 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; } @@ -556,7 +591,7 @@ static void __init hv_init_tsc_clocksource(void) * mapped. */ tsc_msr.as_uint64 = hv_get_msr(HV_MSR_REFERENCE_TSC); - if (hv_root_partition) + if (hv_root_partition()) tsc_pfn = tsc_msr.pfn; else tsc_pfn = HVPFN_DOWN(virt_to_phys(tsc_page)); @@ -601,7 +636,7 @@ void __init hv_remap_tsc_clocksource(void) if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) return; - if (!hv_root_partition) { + if (!hv_root_partition()) { WARN(1, "%s: attempt to remap TSC page in guest partition\n", __func__); return; |