[PATCH 06/10] KVM: arm/arm64: vgic: Allow dynamic mapping of physical/virtual interrupts
Eric Auger
eric.auger at linaro.org
Tue Jun 16 02:10:06 PDT 2015
On 06/16/2015 10:28 AM, Marc Zyngier wrote:
> Hi Eric,
>
> On 15/06/15 16:44, Eric Auger wrote:
>> Hi Marc,
>> On 06/08/2015 07:04 PM, Marc Zyngier wrote:
>>> In order to be able to feed physical interrupts to a guest, we need
>>> to be able to establish the virtual-physical mapping between the two
>>> worlds.
>>>
>>> The mapping is kept in a rbtree, indexed by virtual interrupts.
>>>
>>> Signed-off-by: Marc Zyngier <marc.zyngier at arm.com>
>>> ---
>>> include/kvm/arm_vgic.h | 18 ++++++++
>>> virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++
>>> 2 files changed, 128 insertions(+)
>>>
>>> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
>>> index 4f9fa1d..33d121a 100644
>>> --- a/include/kvm/arm_vgic.h
>>> +++ b/include/kvm/arm_vgic.h
>>> @@ -159,6 +159,14 @@ struct vgic_io_device {
>>> struct kvm_io_device dev;
>>> };
>>>
>>> +struct irq_phys_map {
>>> + struct rb_node node;
>>> + u32 virt_irq;
>>> + u32 phys_irq;
>>> + u32 irq;
>>> + bool active;
>>> +};
>>> +
>>> struct vgic_dist {
>>> spinlock_t lock;
>>> bool in_kernel;
>>> @@ -256,6 +264,10 @@ struct vgic_dist {
>>> struct vgic_vm_ops vm_ops;
>>> struct vgic_io_device dist_iodev;
>>> struct vgic_io_device *redist_iodevs;
>>> +
>>> + /* Virtual irq to hwirq mapping */
>>> + spinlock_t irq_phys_map_lock;
>>> + struct rb_root irq_phys_map;
>>> };
>>>
>>> struct vgic_v2_cpu_if {
>>> @@ -307,6 +319,9 @@ struct vgic_cpu {
>>> struct vgic_v2_cpu_if vgic_v2;
>>> struct vgic_v3_cpu_if vgic_v3;
>>> };
>>> +
>>> + /* Protected by the distributor's irq_phys_map_lock */
>>> + struct rb_root irq_phys_map;
>>> };
>>>
>>> #define LR_EMPTY 0xff
>>> @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
>>> 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
>>>
>>> #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
>>> #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
>>> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
>>> index 59ed7a3..c6604f2 100644
>>> --- a/virt/kvm/arm/vgic.c
>>> +++ b/virt/kvm/arm/vgic.c
>>> @@ -24,6 +24,7 @@
>>> #include <linux/of.h>
>>> #include <linux/of_address.h>
>>> #include <linux/of_irq.h>
>>> +#include <linux/rbtree.h>
>>> #include <linux/uaccess.h>
>>>
>>> #include <linux/irqchip/arm-gic.h>
>>> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
>>> static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
>>> static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
>>> static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
>>> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
>>> + int virt_irq);
>>>
>>> static const struct vgic_ops *vgic_ops;
>>> static const struct vgic_params *vgic;
>>> @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
>>> return IRQ_HANDLED;
>>> }
>>>
>>> +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu,
>>> + int virt_irq)
>>> +{
>>> + if (virt_irq < VGIC_NR_PRIVATE_IRQS)
>>> + return &vcpu->arch.vgic_cpu.irq_phys_map;
>>> + else
>>> + return &vcpu->kvm->arch.vgic.irq_phys_map;
>>> +}
>>> +
>>> +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu,
>>> + int virt_irq, int irq)
>>> +{
>>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
>>> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq);
>>> + struct rb_node **new = &root->rb_node, *parent = NULL;
>>> + struct irq_phys_map *new_map;
>>> + struct irq_desc *desc;
>>> + struct irq_data *data;
>>> + int phys_irq;
>>> +
>>> + desc = irq_to_desc(irq);
>>> + if (!desc) {
>>> + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n");
>>> + return NULL;
>>> + }
>>> +
>>> + data = irq_desc_get_irq_data(desc);
>>> + while (data->parent_data)
>>> + data = data->parent_data;
>>> +
>>> + phys_irq = data->hwirq;
>>> +
>>> + spin_lock(&dist->irq_phys_map_lock);
>>> +
>>> + /* Boilerplate rb_tree code */
>>> + while (*new) {
>>> + struct irq_phys_map *this;
>>> +
>>> + this = container_of(*new, struct irq_phys_map, node);
>>> + parent = *new;
>>> + if (this->virt_irq < virt_irq)
>>> + new = &(*new)->rb_left;
>>> + else if (this->virt_irq > virt_irq)
>>> + new = &(*new)->rb_right;
>>> + else {
>>> + new_map = this;
>> in case the mapping already exists you don't update the mappping or
>> return an error. Is it what you want here?
>
> Calling the map function several times is not necessarily a bad idea, as
> long as they result in the same mapping. Think of a reset function for a
> device that would perform the mapping (just like the timer does). It
> should be possible to perform that reset several times without seeing
> anything failing.
>
> Now, the code doesn't handle the case where you'd end up with a
> different mapping for the same IRQ, which would be an error (you'd need
> to go through an unmap first).
>
> I'll update the code to take care of this case.
>
>>> + goto out;
>>> + }
>>> + }
>>> +
>>> + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL);
>>> + if (!new_map)
>>> + goto out;
>>> +
>>> + new_map->virt_irq = virt_irq;
>>> + new_map->phys_irq = phys_irq;
>>> + new_map->irq = irq;
>>> +
>>> + rb_link_node(&new_map->node, parent, new);
>>> + rb_insert_color(&new_map->node, root);
>>> +
>>> +out:
>>> + spin_unlock(&dist->irq_phys_map_lock);
>>> + return new_map;
>>> +}
>>> +
>>> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
>>> + int virt_irq)
>>> +{
>>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
>>> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq);
>>> + struct rb_node *node = root->rb_node;
>>> + struct irq_phys_map *this = NULL;
>>> +
>>> + spin_lock(&dist->irq_phys_map_lock);
>>> +
>>> + while (node) {
>>> + this = container_of(node, struct irq_phys_map, node);
>>> +
>>> + if (this->virt_irq < virt_irq)
>>> + node = node->rb_left;
>>> + else if (this->virt_irq > virt_irq)
>>> + node = node->rb_right;
>>> + else
>>> + break;
>>> + }
>>> +
>>> + spin_unlock(&dist->irq_phys_map_lock);
>>> + return this;
>>> +}
>>> +
>>> +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map)
>>> +{
>>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
>>> +
>>> + if (!map)
>>> + return -EINVAL;
>>> +
>>> + spin_lock(&dist->irq_phys_map_lock);
>>> + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq));
>>> + spin_unlock(&dist->irq_phys_map_lock);
>>> +
>>> + kfree(map);
>>> + return 0;
>>> +}
>>> +
>>> void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
>>> {
>>> struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
>>> @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
>>> goto out_unlock;
>>>
>>> spin_lock_init(&kvm->arch.vgic.lock);
>> Don't you deallocate the rbtree nodes here?
>
> Erm... Yes, indeed. Silly me.
>
>> Also in the future with EOI mode == 1 we will need to complete the
>> physical IRQ in place of the guest.
>
> That's one of the things I needed your input on. I can perform the
> deactivate here (clearing the active state is easy). But what will
> guarantee that the interrupt won't be screaming? Will the device be
> quiesced at that time?
In my VFIO use case what does happen is that the guest might be killed
without being able to handle and deactivate the vIRQ/pIRQ properly. In
such a case when you restart a new guest using the same forwarded
physical IRQ, the physical IRQ still is active and you cannot restart
properly. This is why it is mandated to take care of the deactivation,
at some point, in case the guest failed to do it.
When killing the guest the device is not necessarily quiescent, ie IRQ
might still be issued. This depends on the availability of a vfio reset
module whose job consists in stopping DMA accesses and IRQ
(https://lkml.org/lkml/2015/6/15/123).
In //lkml.org/lkml/2014/11/23/120 I cleared the unforwarded state before
doing the deactivate so if a new IRQ hits, it is completed by the host
and not injected.
Hope it helps
Eric
>
> Thanks,
>
> M.
>
More information about the linux-arm-kernel
mailing list