Re: [RFC 9/9] KVM: KVM_VFIO: ARM: implement irq forwarding control

[Alex Williamson <alex.williamson@redhat.com>]

On Mon, 2014-08-25 at 15:27 +0200, Eric Auger wrote:
> Implements ARM specific KVM-VFIO device group commands:
> - KVM_DEV_VFIO_DEVICE_ASSIGN_IRQ
> - KVM_DEV_VFIO_DEVICE_DEASSIGN_IRQ
> capability can be queried using KVM_HAS_DEVICE_ATTR.
> 
> The new commands enable to set IRQ forwarding on/off for a given
> IRQ index of a VFIO platform device.
> 
> as soon as a forwarded irq is set, a reference to the VFIO device
> is taken by the kvm-vfio device.
> 
> The kvm-vfio device stores in the kvm_vfio_arch_data the list
> of "assigned" devices (kvm_vfio_device). Each kvm_vfio_device
> stores the list of assigned IRQs (potentially allowed a subset of
> IRQ to be forwarded)
> 
> The kvm-vfio device programs both the GIC and vGIC. Also it
> clears the active bit on destruction, in case the guest did not
> do it itself.
> 
> Changing the forwarded state is not allowed in the critical
> section starting from VFIO IRQ handler to LR programming. It is
> up to the client to take care of this.
> 
> Signed-off-by: Eric Auger <eric.auger@linaro.org>
> ---
>  arch/arm/include/asm/kvm_host.h |   2 +
>  arch/arm/kvm/Makefile           |   2 +-
>  arch/arm/kvm/kvm_vfio_arm.c     | 599 ++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 602 insertions(+), 1 deletion(-)
>  create mode 100644 arch/arm/kvm/kvm_vfio_arm.c

I'm really happy that it seems like the kvm-vfio device is going to work
for you, but I think too much stuff is being pushed out to arch code
here.  Exporting the interfaces in patches 7 & 8 are setting the stage
for duplicate code for anyone wanting to implement device attributes.
Instead, I think the core code should support the list of
kvm_vfio_devices with proper cleanup, and we should attempt to access
the kvm_vfio_ callbacks as little as possible from arch code.  Thanks,

Alex