[PATCH v5 49/51] x86/kvmclock: Plumb in AP-online and BSP-resume to kvmlock, for documentation
From: Sean Christopherson <seanjc@google.com>
Date: 2026-07-01 19:33:26
Also in:
kvm, linux-coco, linux-hyperv, lkml, virtualization, xen-devel
Subsystem:
kernel virtual machine for x86 (kvm/x86), kvm paravirt (kvm/paravirt), the rest, x86 architecture (32-bit and 64-bit) · Maintainers:
Sean Christopherson, Paolo Bonzini, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen
Invoke kvmclock_cpu_action() with AP_ONLINE and BSP_RESUME, even though kvmclock doesn't need to do anything in either case, so that the asymmetry of kvmclock is a detail buried in kvmclock, and to explicitly document that doing nothing during those phases is intentional and correct. For all intents and purposes, no functional change intended. Reviewed-by: David Woodhouse <redacted> Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/x86/include/asm/kvm_para.h | 2 ++ arch/x86/kernel/kvm.c | 22 +++++++++++++------- arch/x86/kernel/kvmclock.c | 37 ++++++++++++++++++++++++++------- 3 files changed, 45 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 08686ff19caa..763ed017738a 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h@@ -120,6 +120,8 @@ static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1, #ifdef CONFIG_KVM_GUEST enum kvm_guest_cpu_action { KVM_GUEST_BSP_SUSPEND, + KVM_GUEST_BSP_RESUME, + KVM_GUEST_AP_ONLINE, KVM_GUEST_AP_OFFLINE, KVM_GUEST_SHUTDOWN, };
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 604b52f233aa..f9a6346077b0 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c@@ -474,18 +474,24 @@ static void kvm_guest_cpu_offline(enum kvm_guest_cpu_action action) kvmclock_cpu_action(action); } +static void __kvm_cpu_online(unsigned int cpu, enum kvm_guest_cpu_action action) +{ + unsigned long flags; + + local_irq_save(flags); + kvmclock_cpu_action(action); + kvm_guest_cpu_init(); + local_irq_restore(flags); +} + +#ifdef CONFIG_SMP + static int kvm_cpu_online(unsigned int cpu) { - unsigned long flags; - - local_irq_save(flags); - kvm_guest_cpu_init(); - local_irq_restore(flags); + __kvm_cpu_online(cpu, KVM_GUEST_AP_ONLINE); return 0; } -#ifdef CONFIG_SMP - static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); static bool pv_tlb_flush_supported(void)
@@ -750,7 +756,7 @@ static int kvm_suspend(void *data) static void kvm_resume(void *data) { - kvm_cpu_online(raw_smp_processor_id()); + __kvm_cpu_online(raw_smp_processor_id(), KVM_GUEST_BSP_RESUME); #ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bc98ebb8587d..842f38c5f6ca 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c@@ -150,7 +150,7 @@ static void kvm_save_sched_clock_state(void) #ifdef CONFIG_SMP static void kvm_setup_secondary_clock(void) { - kvm_register_clock("secondary cpu clock"); + kvm_register_clock("secondary cpu, startup"); } #endif
@@ -174,13 +174,34 @@ static void kvmclock_resume(struct clocksource *cs) void kvmclock_cpu_action(enum kvm_guest_cpu_action action) { - /* - * Don't disable kvmclock on the BSP during suspend. If kvmclock is - * being used for sched_clock, then it needs to be kept alive until the - * last minute, and restored as quickly as possible after resume. - */ - if (action != KVM_GUEST_BSP_SUSPEND) + switch (action) { + /* + * The BSP's clock is managed via clocksource suspend/resume, + * to ensure it's enabled/disabled when timekeeping needs it + * to be, e.g. before reading wallclock (which uses kvmclock). + */ + case KVM_GUEST_BSP_SUSPEND: + case KVM_GUEST_BSP_RESUME: + break; + case KVM_GUEST_AP_ONLINE: + /* + * Secondary CPUs use a dedicated hook to enable kvmclock early + * during bringup, there's nothing to be done during CPU online + * (which runs at CPUHP_AP_ONLINE_DYN). When kvmclock is being + * used as sched_clock, kvmclock must be enabled *very* early, + * and even when kvmclock is "only" being used for the main + * clocksource, it still needs to be enabled long before the + * dynamic CPUHP calls are made. + */ + break; + case KVM_GUEST_AP_OFFLINE: + case KVM_GUEST_SHUTDOWN: kvmclock_disable(); + break; + default: + WARN_ON_ONCE(1); + break; + } } /*
@@ -382,7 +403,7 @@ void __init kvmclock_init(bool prefer_tsc) msr_kvm_system_time, msr_kvm_wall_clock); this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]); - kvm_register_clock("primary cpu clock"); + kvm_register_clock("primary cpu, online"); pvclock_set_pvti_cpu0_va(hv_clock_boot); if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) {
--
2.55.0.rc0.799.gd6f94ed593-goog