Re: [PATCH 6/6] KVM: perform a wake_up in kvm_make_all_cpus_request

[Paolo Bonzini]

On 07/04/2017 04:20, Radim KrÄmÃÅ wrote:
> I think that most requests do not need the wake up, so we would flip the
> bit then.

True.  I may need a bit more convincing, but let's see the patches:

- point against: on the other hand no wakeup is a bug, possibly hard to
find, while an extra wakeup is just annoying.

- point in favor: the same argument (multiplied by 9000) would apply to
a wait flag in the request number, but it would be obviously stupid to
add a no_wait flag to all requests except the couple that need it.

Thanks,

Paolo