linux-kernel - Re: [PATCH v2 5/9] KVM: perform a wake_up in kvm_make_all_cpus

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <246ae7e1-f381-6672-3573-278620a48547@redhat.com>
Date:   Thu, 27 Apr 2017 14:15:57 +0200
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Cornelia Huck <cornelia.huck@...ibm.com>,
        Radim Krčmář <rkrcmar@...hat.com>
Cc:     linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        Christoffer Dall <cdall@...aro.org>,
        Andrew Jones <drjones@...hat.com>,
        Marc Zyngier <marc.zyngier@....com>,
        Christian Borntraeger <borntraeger@...ibm.com>,
        James Hogan <james.hogan@...tec.com>,
        Paul Mackerras <paulus@...abs.org>
Subject: Re: [PATCH v2 5/9] KVM: perform a wake_up in
 kvm_make_all_cpus_request



On 27/04/2017 14:06, Cornelia Huck wrote:
> On Wed, 26 Apr 2017 22:32:23 +0200
> Radim Krčmář <rkrcmar@...hat.com> wrote:
> 
>> We want to have kvm_make_all_cpus_request() to be an optmized version of
>>
>>   kvm_for_each_vcpu(i, vcpu, kvm) {
>>     kvm_make_request(vcpu, request);
>>     kvm_vcpu_kick(vcpu);
>>   }
>>
>> and kvm_vcpu_kick() wakes up the target vcpu.  We know which requests do
>> not need the wake up and use it to optimize the loop.
>>
>> Thanks to that, this patch doesn't change the behavior of current users
>> (the all don't need the wake up) and only prepares for future where the
> 
> s/the all/they all/
> 
>> wake up is going to be needed.
>>
>> I think that most requests do not need the wake up, so we would flip the
>> bit then.
>>
>> kvm_vcpu_kick() will get this condition after it is merged with
>> kvm_make_request() because we currently don't know which request is being
>> kicked.
> 
> I find this sentence confusing: not all kicks are directly related to
> requests.

I agree, it is backwards.  Changing to "Later on, kvm_make_request()
will take care of kicking too, using this bit to make the decision
whether to kick or not".

Paolo
>>
>> Signed-off-by: Radim Krčmář <rkrcmar@...hat.com>
>> ---
>>  virt/kvm/kvm_main.c | 3 +++
>>  1 file changed, 3 insertions(+)
>>
>> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
>> index e5d52b46b531..3772f7dcc72d 100644
>> --- a/virt/kvm/kvm_main.c
>> +++ b/virt/kvm/kvm_main.c
>> @@ -186,6 +186,9 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
>>  		/* Set ->requests bit before we read ->mode. */
>>  		smp_mb__after_atomic();
>>
>> +		if (!(req & KVM_REQUEST_NO_WAKEUP))
>> +			kvm_vcpu_wake_up(vcpu);
>> +
>>  		if (cpus != NULL && cpu != -1 && cpu != me &&
>>  		      kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)
>>  			cpumask_set_cpu(cpu, cpus);
> 
> The code change looks good to me.
>