Re: [PATCH v3 4/4] KVM: Avoid synchronize_srcu() in kvm_io_bus_register_dev()

[Sean Christopherson <seanjc@xxxxxxxxxx>]

On Tue, Aug 19, 2025, Keir Fraser wrote:
> Device MMIO registration may happen quite frequently during VM boot,
> and the SRCU synchronization each time has a measurable effect
> on VM startup time. In our experiments it can account for around 25%
> of a VM's startup time.
> 
> Replace the synchronization with a deferred free of the old kvm_io_bus
> structure.
> 
> Signed-off-by: Keir Fraser <keirf@xxxxxxxxxx>
> ---
>  include/linux/kvm_host.h |  1 +
>  virt/kvm/kvm_main.c      | 10 ++++++++--
>  2 files changed, 9 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index e7d6111cf254..103be35caf0d 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -206,6 +206,7 @@ struct kvm_io_range {
>  struct kvm_io_bus {
>  	int dev_count;
>  	int ioeventfd_count;
> +	struct rcu_head rcu;
>  	struct kvm_io_range range[];
>  };
>  
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 4f35ae23ee5a..9144a0b4a268 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -5953,6 +5953,13 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
>  }
>  EXPORT_SYMBOL_GPL(kvm_io_bus_read);
>  
> +static void __free_bus(struct rcu_head *rcu)
> +{
> +	struct kvm_io_bus *bus = container_of(rcu, struct kvm_io_bus, rcu);
> +
> +	kfree(bus);
> +}
> +
>  int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
>  			    int len, struct kvm_io_device *dev)
>  {
> @@ -5991,8 +5998,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
>  	memcpy(new_bus->range + i + 1, bus->range + i,
>  		(bus->dev_count - i) * sizeof(struct kvm_io_range));
>  	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
> -	synchronize_srcu_expedited(&kvm->srcu);
> -	kfree(bus);
> +	call_srcu(&kvm->srcu, &bus->rcu, __free_bus);

To address the syzkaller splat, KVM needs to call srcu_barrier() prior to freeing
the structure.

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9144a0b4a268..62693f18ecf4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1321,6 +1321,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
                kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
        }
        cleanup_srcu_struct(&kvm->irq_srcu);
+       srcu_barrier(&kvm->srcu);
        cleanup_srcu_struct(&kvm->srcu);
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
        xa_destroy(&kvm->mem_attr_array);