On Wed, Jul 08, 2015 at 06:56:42PM +0100, Marc Zyngier wrote:
> So far, the only use of the HW interrupt facility is the timer,
> implying that the active state is context-switched for each vcpu,
> as the device is is shared across all vcpus.
>
> This does not work for a device that has been assigned to a VM,
> as the guest is entierely in control of that device (the HW is
> not shared). In that case, it makes sense to bypass the whole
> active state switchint, and only track the deactivation of the
switching
> interrupt.
>
> Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
> ---
> include/kvm/arm_vgic.h | 5 ++--
> virt/kvm/arm/arch_timer.c | 2 +-
> virt/kvm/arm/vgic.c | 62 ++++++++++++++++++++++++++++++++++++-----------
> 3 files changed, 52 insertions(+), 17 deletions(-)
>
> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
> index 9fd4023..31c987a 100644
> --- a/include/kvm/arm_vgic.h
> +++ b/include/kvm/arm_vgic.h
> @@ -163,7 +163,8 @@ struct irq_phys_map {
> u32 virt_irq;
> u32 phys_irq;
> u32 irq;
> - bool active;
> + bool shared;
> + bool active; /* Only valid if shared */
> };
>
> struct irq_phys_map_entry {
> @@ -354,7 +355,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
> int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
> int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu);
> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu,
> - int virt_irq, int irq);
> + int virt_irq, int irq, bool shared);
> int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
> bool vgic_get_phys_irq_active(struct irq_phys_map *map);
> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active);
> diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
> index b9fff78..9544d79 100644
> --- a/virt/kvm/arm/arch_timer.c
> +++ b/virt/kvm/arm/arch_timer.c
> @@ -202,7 +202,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
> * Tell the VGIC that the virtual interrupt is tied to a
> * physical interrupt. We do that once per VCPU.
> */
> - timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq);
> + timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq, true);
> WARN_ON(!timer->map);
> }
>
> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
> index 39f9479..3585bb0 100644
> --- a/virt/kvm/arm/vgic.c
> +++ b/virt/kvm/arm/vgic.c
> @@ -1123,18 +1123,21 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq,
> map = vgic_irq_map_search(vcpu, irq);
>
> if (map) {
> - int ret;
> -
> - BUG_ON(!map->active);
> vlr.hwirq = map->phys_irq;
> vlr.state |= LR_HW;
> vlr.state &= ~LR_EOI_INT;
>
> - ret = irq_set_irqchip_state(map->irq,
> - IRQCHIP_STATE_ACTIVE,
> - true);
> vgic_irq_set_queued(vcpu, irq);
> - WARN_ON(ret);
> +
> + if (map->shared) {
> + int ret;
> +
> + BUG_ON(!map->active);
> + ret = irq_set_irqchip_state(map->irq,
> + IRQCHIP_STATE_ACTIVE,
> + true);
> + WARN_ON(ret);
do we have any other example of a shared device or is this really simply
because the timer hardware is fscking strangely tied to the gic and is a
total one-off?
In the latter case, would it be cleaner to drop this notion of a shared
device entirely and put all this logic in the arch timer code instead?
> + }
> }
> }
>
> @@ -1366,21 +1369,37 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
> static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr)
> {
> struct irq_phys_map *map;
> + bool active;
> int ret;
>
> if (!(vlr.state & LR_HW))
> return 0;
>
> map = vgic_irq_map_search(vcpu, vlr.irq);
> - BUG_ON(!map || !map->active);
> + BUG_ON(!map);
> + BUG_ON(map->shared && !map->active);
>
> ret = irq_get_irqchip_state(map->irq,
> IRQCHIP_STATE_ACTIVE,
> - &map->active);
> + &active);
>
> WARN_ON(ret);
>
> - if (map->active) {
> + /*
> + * For a non-shared interrupt, we have to catter for two
s/catter/cater/ ?
> + * possible deactivation conditions
conditions:
> + *
> + * - the interrupt is now inactive
> + * - the interrupt is still active, but is flagged as not
> + * queued, indicating another interrupt has fired before we
> + * could observe the deactivate.
are these physical or virtual interrupts we are talking about? I assume
virtual, but it would be good to be specific. It's not like we're going
to remember any of this in a little bit.
> + */
> + if (!map->shared)
> + return !active || !vgic_irq_is_queued(vcpu, vlr.irq);
if the second part of the disjunction returns true, doesn't this mean
we can potentially write the active+pending state in the LR for a HW
interrupt, which is not allowed?
> +
> + map->active = active;
> +
> + if (active) {
should you be doing this for a non-shared interrupt?
> ret = irq_set_irqchip_state(map->irq,
> IRQCHIP_STATE_ACTIVE,
> false);
> @@ -1523,6 +1542,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
> int edge_triggered, level_triggered;
> int enabled;
> bool ret = true, can_inject = true;
> + struct irq_phys_map *map;
>
> spin_lock(&dist->lock);
>
> @@ -1569,6 +1589,18 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
> goto out;
> }
>
> + map = vgic_irq_map_search(vcpu, irq_num);
> + if (map && !map->shared) {
> + /*
> + * We are told to inject a HW irq, so we have to trust
> + * the caller that the previous one has been EOIed,
> + * and that a new one is now active. Clearing the
> + * queued state will have the effect of making it
> + * sample-able again.
> + */
> + vgic_irq_clear_queued(vcpu, irq_num);
see my question above about active+pending
> + }
> +
> if (!vgic_can_sample_irq(vcpu, irq_num)) {
> /*
> * Level interrupt in progress, will be picked up
> @@ -1662,7 +1694,7 @@ static struct list_head *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu,
> }
>
> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu,
> - int virt_irq, int irq)
> + int virt_irq, int irq, bool shared)
> {
> struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
> struct list_head *root = vgic_get_irq_phys_map(vcpu, virt_irq);
> @@ -1691,7 +1723,8 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu,
> if (map) {
> /* Make sure this mapping matches */
> if (map->phys_irq != phys_irq ||
> - map->irq != irq)
> + map->irq != irq ||
> + map->shared != shared)
this really feels like a BUG() - if we have an existing mapping for the
same virtual IRQ, but it's shared in one case and not shared in the
other? Shouldn we even allow the caller to get this far?
> map = NULL;
>
> goto out;
> @@ -1706,6 +1739,7 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu,
> map->virt_irq = virt_irq;
> map->phys_irq = phys_irq;
> map->irq = irq;
> + map->shared = shared;
>
> list_add_tail_rcu(&entry->entry, root);
>
> @@ -1746,13 +1780,13 @@ static void vgic_free_phys_irq_map_rcu(struct rcu_head *rcu)
>
> bool vgic_get_phys_irq_active(struct irq_phys_map *map)
> {
> - BUG_ON(!map);
> + BUG_ON(!map || !map->shared);
> return map->active;
> }
>
> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active)
> {
> - BUG_ON(!map);
> + BUG_ON(!map || !map->shared);
> map->active = active;
> }
>
> --
> 2.1.4
>
Do we really need this patch right now as part of this series or should
this rather go with Eric's forwarding series and we can focus on getting
rid of the timer hack for now?
Thanks,
-Christoffer
--
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
