Re: [PATCH] KVM: x86: switch hugepage recovery thread to vhost_task

[Paolo Bonzini <pbonzini@redhat.com>]

On 1/13/25 16:35, Keith Busch wrote:
>> Ok, I found the code and it doesn't exec (e.g.
>> https://github.com/google/crosvm/blob/b339d3d7/src/crosvm/sys/linux/jail_warden.rs#L122),
>> so that's not an option. Well, if I understand correctly from a
>> cursory look at the code, crosvm is creating a jailed child process
>> early, and then spawns further jails through it; so it's just this
>> first process that has to cheat.
>>
>> One possibility on the KVM side is to delay creating the vhost_task
>> until the first KVM_RUN. I don't like it but...
> 
> This option is actually kind of appealing in that we don't need to
> change any application side to filter out kernel tasks, as well as not
> having a new kernel dependency to even report these types of tasks as
> kernel threads.
> 
> I gave it a quick try. I'm not very familiar with the code here, so not
> sure if this is thread safe or not, but it did successfully get crosvm
> booting again.

That looks good to me too.  Would you like to send it with a commit 
message and SoB?

Thanks,

Paolo

> ---
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 2401606db2604..422b6b06de4fe 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -7415,6 +7415,8 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
>   {
>   	if (nx_hugepage_mitigation_hard_disabled)
>   		return 0;
> +	if (kvm->arch.nx_huge_page_recovery_thread)
> +		return 0;
>   
>   	kvm->arch.nx_huge_page_last = get_jiffies_64();
>   	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index c79a8cc57ba42..263363c46626b 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -11463,6 +11463,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
>   	struct kvm_run *kvm_run = vcpu->run;
>   	int r;
>   
> +	r = kvm_mmu_post_init_vm(vcpu->kvm);
> +	if (r)
> +		return r;
> +
>   	vcpu_load(vcpu);
>   	kvm_sigset_activate(vcpu);
>   	kvm_run->flags = 0;
> @@ -12740,11 +12744,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
>   	return ret;
>   }
>   
> -int kvm_arch_post_init_vm(struct kvm *kvm)
> -{
> -	return kvm_mmu_post_init_vm(kvm);
> -}
> -
>   static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
>   {
>   	vcpu_load(vcpu);
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 401439bb21e3e..a219bd2d8aec8 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1596,7 +1596,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
>   bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
>   bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
>   bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
> -int kvm_arch_post_init_vm(struct kvm *kvm);
>   void kvm_arch_pre_destroy_vm(struct kvm *kvm);
>   void kvm_arch_create_vm_debugfs(struct kvm *kvm);
>   
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index de2c11dae2316..adacc6eaa7d9d 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -1065,15 +1065,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
>   	return ret;
>   }
>   
> -/*
> - * Called after the VM is otherwise initialized, but just before adding it to
> - * the vm_list.
> - */
> -int __weak kvm_arch_post_init_vm(struct kvm *kvm)
> -{
> -	return 0;
> -}
> -
>   /*
>    * Called just after removing the VM from the vm_list, but before doing any
>    * other destruction.
> @@ -1194,10 +1185,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
>   	if (r)
>   		goto out_err_no_debugfs;
>   
> -	r = kvm_arch_post_init_vm(kvm);
> -	if (r)
> -		goto out_err;
> -
>   	mutex_lock(&kvm_lock);
>   	list_add(&kvm->vm_list, &vm_list);
>   	mutex_unlock(&kvm_lock);
> @@ -1207,8 +1194,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
>   
>   	return kvm;
>   
> -out_err:
> -	kvm_destroy_vm_debugfs(kvm);
>   out_err_no_debugfs:
>   	kvm_coalesced_mmio_free(kvm);
>   out_no_coalesced_mmio:
> --
>