On Sun, Mar 22, 2020 at 09:33:17AM -0700, Davidlohr Bueso wrote:
> On Fri, 20 Mar 2020, Peter Zijlstra wrote:
>
> > On Fri, Mar 20, 2020 at 01:55:26AM -0700, Davidlohr Bueso wrote:
> > > - swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
> > > -(
On Fri, 20 Mar 2020, Peter Zijlstra wrote:
On Fri, Mar 20, 2020 at 01:55:26AM -0700, Davidlohr Bueso wrote:
- swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
- (!vcpu->arch.pause)));
+ rcuwait_wait_event(*wait,
+
On Fri, Mar 20, 2020 at 01:55:26AM -0700, Davidlohr Bueso wrote:
> - swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
> -(!vcpu->arch.pause)));
> + rcuwait_wait_event(*wait,
> +(!vcpu->arch.power_off) && (!vcpu-
On 20/03/20 09:55, Davidlohr Bueso wrote:
> Only compiled and tested on x86.
It shows :) as the __KVM_HAVE_ARCH_WQP case is broken. But no problem,
Paul and I can pick this up and fix it.
This is missing:
diff --git a/arch/powerpc/include/asm/kvm_book3s.h
b/arch/powerpc/include/asm/kvm_book3s
The use of any sort of waitqueue (simple or regular) for
wait/waking vcpus has always been an overkill and semantically
wrong. Because this is per-vcpu (which is blocked) there is
only ever a single waiting vcpu, thus no need for any sort of
queue.
As such, make use of the rcuwait primitive, with
