Re: [PATCH v1] KVM: x86: Rate-limit global clock updates on vCPU load

[Sean Christopherson <seanjc@google.com>]

On Tue, Apr 07, 2026, Lei Chen wrote:
> commit 446fcce2a52b ("Revert "x86: kvm: rate-limit global clock updates"")
> dropped the rate limiting for KVM_REQ_GLOBAL_CLOCK_UPDATE.
> 
> As a result, kvm_arch_vcpu_load() can queue global clock update requests
> every time a vCPU is scheduled when the master clock is disabled or when
> the vCPU is loaded for the first time.
> 
> Restore the throttling with a per-VM ratelimit state and gate
> KVM_REQ_GLOBAL_CLOCK_UPDATE through __ratelimit(), so frequent vCPU
> scheduling does not generate a steady stream of redundant clock update
> requests.
> 
> Fixes: 446fcce2a52b ("Revert "x86: kvm: rate-limit global clock updates"")
> Signed-off-by: Lei Chen <lei.chen@smartx.com>
> Reported-by: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
> Closes: https://lore.kernel.org/all/CAK8fFZ5gY8_Mw2A=iZVFNVKQNrXQzVsn-HTd+Me9K6ZfmdgA+Q@mail.gmail.com/
> ---
>  arch/x86/include/asm/kvm_host.h | 2 ++
>  arch/x86/kvm/x86.c              | 5 ++++-
>  2 files changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 5a3bfa293e8b..6d3d3f19af01 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1453,6 +1453,8 @@ struct kvm_arch {
>  	bool use_master_clock;
>  	u64 master_kernel_ns;
>  	u64 master_cycle_now;
> +	/* how often to make KVM_REQ_GLOBAL_CLOCK_UPDATE on vcpu sched*/

Eh, I would just omit this comment.  If we want to document the ratelimit,
the function comment above kvm_gen_kvmclock_update() is the best place for it.

> +	struct ratelimit_state kvmclock_update_rs;
>  
>  #ifdef CONFIG_KVM_HYPERV
>  	struct kvm_hv hyperv;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 63afdb6bb078..4a37027cc0b8 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5211,7 +5211,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>  		 * kvmclock on vcpu->cpu migration
>  		 */
>  		if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
> -			kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
> +			if (__ratelimit(&vcpu->kvm->arch.kvmclock_update_rs))
> +				kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);

To maintain pre-revert compatibility, where KVM did this:

	kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
			      KVMCLOCK_UPDATE_DELAY);


the ratelimit should be on blasting KVM_REQ_CLOCK_UPDATE to *all* vCPUs, but KVM
should still trigger KVM_REQ_CLOCK_UPDATE on the initiating vCPU so that the
immediate update goes through.

That will also apply the ratelimiting to kvm_write_system_time(), though if a
guest is changing system time that fast, it probably has other issues :-)

Completely untested, but this?

---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/x86.c              | 13 +++++--------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c470e40a00aa..f14009f25a3b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1504,6 +1504,7 @@ struct kvm_arch {
 	bool use_master_clock;
 	u64 master_kernel_ns;
 	u64 master_cycle_now;
+	struct ratelimit_state kvmclock_update_rs;
 
 #ifdef CONFIG_KVM_HYPERV
 	struct kvm_hv hyperv;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0a1b63c63d1a..5dc33f207a83 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3522,16 +3522,12 @@ uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm)
  * The worst case for a remote vcpu to update its kvmclock
  * is then bounded by maximum nohz sleep latency.
  */
-static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *vcpu)
 {
-	unsigned long i;
-	struct kvm_vcpu *vcpu;
-	struct kvm *kvm = v->kvm;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
+	if (__ratelimit(&vcpu->kvm->arch.kvmclock_update_rs))
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
-		kvm_vcpu_kick(vcpu);
-	}
+	else
+		kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_CLOCK_UPDATE);
 }
 
 /* These helpers are safe iff @msr is known to be an MCx bank MSR. */
@@ -13366,6 +13362,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
 	seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
+	ratelimit_state_init(&kvm->arch.kvmclock_update_rs, HZ, 10);
 	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);

base-commit: b89df297a47e641581ee67793592e5c6ae0428f4
--