On 20/08/14 01:22, Wanpeng Li wrote:
> On Tue, Aug 19, 2014 at 04:04:03PM +0200, Christian Borntraeger wrote:
>> 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@xxxxxxxxxx>
>>>> CC: Rik van Riel <riel@xxxxxxxxxx>
>>>> CC: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>
>>>> CC: Michael Mueller <mimu@xxxxxxxxxxxxxxxxxx>
>>>> ---
>>>> 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)
>
> Thanks for your explanation. When can this happen?
In general, by using clone and do an ioctl in the new thread on a pre-existing fd.
In qemu, e.g. by using an kvm_ioctl on a vcpu from main thread or another cpu.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
