Re: [PATCH/RFC] KVM: track pid for VCPU only on KVM_RUN ioctl

[Christian Borntraeger <borntraeger@de.ibm.com>]

On 18/08/14 07:02, Wanpeng Li wrote:
> Hi Christian,
> On Tue, Aug 05, 2014 at 04:44:14PM +0200, Christian Borntraeger wrote:
>> We currently track the pid of the task that runs the VCPU in
>> vcpu_load. Since we call vcpu_load for all kind of ioctls on a
>> CPU, this causes hickups due to synchronize_rcu if one CPU is
>> modified by another CPU or the main thread (e.g. initialization,
>> reset). We track the pid only for the purpose of yielding, so
>> let's update the pid only in the KVM_RUN ioctl.
>>
>> In addition, don't do a synchronize_rcu on startup (pid == 0).
>>
>> This speeds up guest boot time on s390 noticably for some configs, e.g.
>> HZ=100, no full state tracking, 64 guest cpus 32 host cpus.
>>
>> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
>> CC: Rik van Riel <riel@redhat.com>
>> CC: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
>> CC: Michael Mueller <mimu@linux.vnet.ibm.com>
>> ---
>> virt/kvm/kvm_main.c | 17 +++++++++--------
>> 1 file changed, 9 insertions(+), 8 deletions(-)
>>
>> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
>> index 9ae9135..ebc8f54 100644
>> --- a/virt/kvm/kvm_main.c
>> +++ b/virt/kvm/kvm_main.c
>> @@ -124,14 +124,6 @@ int vcpu_load(struct kvm_vcpu *vcpu)
>>
>> 	if (mutex_lock_killable(&vcpu->mutex))
>> 		return -EINTR;
> 
> One question: 
> 
>> -	if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
> 
> When vcpu->pid and current->pids[PIDTYPE_PID].pid will be different?

If two different thread call an ioctl on a vcpu fd. (It must be an ioctl that has done vcpu_load - almost all except for some interrupt injections)