Re: [PATCH v4 02/15] KVM: async_pf: Add helper function to check completion queue

[Gavin Shan <gshan@redhat.com>]

Hi Vitaly,

On 8/17/21 2:53 AM, Vitaly Kuznetsov wrote:
> Gavin Shan <gshan@redhat.com> writes:
> 
>> This adds inline helper kvm_check_async_pf_completion_queue() to
>> check if there are pending completion in the queue. The empty stub
>> is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't
>> consider if CONFIG_KVM_ASYNC_PF is enabled.
>>
>> All checks on the completion queue is done by the newly added inline
>> function since list_empty() and list_empty_careful() are interchangeable.
>>
>> Signed-off-by: Gavin Shan <gshan@redhat.com>
>> ---
>>   arch/x86/kvm/x86.c       |  2 +-
>>   include/linux/kvm_host.h | 10 ++++++++++
>>   virt/kvm/async_pf.c      | 10 +++++-----
>>   virt/kvm/kvm_main.c      |  4 +---
>>   4 files changed, 17 insertions(+), 9 deletions(-)
>>
>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>> index e5d5c5ed7dd4..7f35d9324b99 100644
>> --- a/arch/x86/kvm/x86.c
>> +++ b/arch/x86/kvm/x86.c
>> @@ -11591,7 +11591,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
>>   
>>   static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
>>   {
>> -	if (!list_empty_careful(&vcpu->async_pf.done))
>> +	if (kvm_check_async_pf_completion_queue(vcpu))
>>   		return true;
>>   
>>   	if (kvm_apic_has_events(vcpu))
>> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
>> index 85b61a456f1c..a5f990f6dc35 100644
>> --- a/include/linux/kvm_host.h
>> +++ b/include/linux/kvm_host.h
>> @@ -339,12 +339,22 @@ struct kvm_async_pf {
>>   	bool				notpresent_injected;
>>   };
>>   
>> +static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
> 
> Nitpicking: When not reading the implementation, I'm not exactly sure
> what this function returns as 'check' is too ambiguous ('true' when the
> queue is full? when it's empty? when it's not empty? when it was
> properly set up?). I'd suggest we go with a more specific:
> 
> kvm_async_pf_completion_queue_empty() or something like that instead
> (we'll have to invert the logic everywhere then).
> 
> Side note: x86 seems to already use a shortened 'apf' instead of
> 'async_pf' in a number of places (e.g. 'apf_put_user_ready()'), we may
> want to either fight this practice or support the rebelion by renaming
> all functions from below instead :-)
> 

Yeah, I was wandering if the name is ambiguous when I had it. The
reason why I had the name is to be consistent with the existing
one, which is kvm_check_async_pf_completion().

Yes, kvm_async_pf_completion_queue_empty() is much better and I
will include this in next revision.

It's correct that x86 functions include 'apf', but the generic
functions, shared by multiple architectures, use 'async_pf' if
my understanding is correct. So I wouldn't bother to change
the generic function names in this series :)

>> +{
>> +	return !list_empty_careful(&vcpu->async_pf.done);
>> +}
>> +
>>   void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
>>   void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
>>   bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>>   			unsigned long hva, struct kvm_arch_async_pf *arch);
>>   int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
>>   #else
>> +static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
>> +{
>> +	return false;
>> +}
>> +
>>   static inline void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) { }
>>   #endif
>>   
>> diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
>> index dd777688d14a..d145a61a046a 100644
>> --- a/virt/kvm/async_pf.c
>> +++ b/virt/kvm/async_pf.c
>> @@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)
>>   		kvm_arch_async_page_present(vcpu, apf);
>>   
>>   	spin_lock(&vcpu->async_pf.lock);
>> -	first = list_empty(&vcpu->async_pf.done);
>> +	first = !kvm_check_async_pf_completion_queue(vcpu);
>>   	list_add_tail(&apf->link, &vcpu->async_pf.done);
>>   	apf->vcpu = NULL;
>>   	spin_unlock(&vcpu->async_pf.lock);
>> @@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
>>   		spin_lock(&vcpu->async_pf.lock);
>>   	}
>>   
>> -	while (!list_empty(&vcpu->async_pf.done)) {
>> +	while (kvm_check_async_pf_completion_queue(vcpu)) {
>>   		struct kvm_async_pf *work =
>>   			list_first_entry(&vcpu->async_pf.done,
>>   					 typeof(*work), link);
>> @@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
>>   {
>>   	struct kvm_async_pf *work;
>>   
>> -	while (!list_empty_careful(&vcpu->async_pf.done) &&
>> +	while (kvm_check_async_pf_completion_queue(vcpu) &&
>>   	      kvm_arch_can_dequeue_async_page_present(vcpu)) {
>>   		spin_lock(&vcpu->async_pf.lock);
>>   		work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
>> @@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
>>   	struct kvm_async_pf *work;
>>   	bool first;
>>   
>> -	if (!list_empty_careful(&vcpu->async_pf.done))
>> +	if (kvm_check_async_pf_completion_queue(vcpu))
>>   		return 0;
>>   
>>   	work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
>> @@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
>>   	INIT_LIST_HEAD(&work->queue); /* for list_del to work */
>>   
>>   	spin_lock(&vcpu->async_pf.lock);
>> -	first = list_empty(&vcpu->async_pf.done);
>> +	first = !kvm_check_async_pf_completion_queue(vcpu);
>>   	list_add_tail(&work->link, &vcpu->async_pf.done);
>>   	spin_unlock(&vcpu->async_pf.lock);
>>   
>> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
>> index b50dbe269f4b..8795503651b1 100644
>> --- a/virt/kvm/kvm_main.c
>> +++ b/virt/kvm/kvm_main.c
>> @@ -3282,10 +3282,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
>>   	if (kvm_arch_dy_runnable(vcpu))
>>   		return true;
>>   
>> -#ifdef CONFIG_KVM_ASYNC_PF
>> -	if (!list_empty_careful(&vcpu->async_pf.done))
>> +	if (kvm_check_async_pf_completion_queue(vcpu))
>>   		return true;
>> -#endif
>>   
>>   	return false;
>>   }
> 

Thanks,
Gavin