Re: [PATCH v5 1/4] kvm: Extend irqfd to support level interrupts

From: Michael S. Tsirkin
Date: Wed Jul 18 2012 - 06:40:53 EST


On Mon, Jul 16, 2012 at 02:33:47PM -0600, Alex Williamson wrote:
> In order to inject a level interrupt from an external source using an
> irqfd, we need to allocate a new irq_source_id. This allows us to
> assert and (later) de-assert an interrupt line independently from
> users of KVM_IRQ_LINE and avoid lost interrupts.
>
> We also add what may appear like a bit of excessive infrastructure
> around an object for storing this irq_source_id. However, notice
> that we only provide a way to assert the interrupt here. A follow-on
> interface will make use of the same irq_source_id to allow de-assert.
>
> Signed-off-by: Alex Williamson <alex.williamson@xxxxxxxxxx>
> ---
>
> Documentation/virtual/kvm/api.txt | 6 ++
> arch/x86/kvm/x86.c | 1
> include/linux/kvm.h | 3 +
> virt/kvm/eventfd.c | 114 ++++++++++++++++++++++++++++++++++++-
> 4 files changed, 120 insertions(+), 4 deletions(-)
>
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index 100acde..c7267d5 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -1981,6 +1981,12 @@ the guest using the specified gsi pin. The irqfd is removed using
> the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
> and kvm_irqfd.gsi.
>
> +The KVM_IRQFD_FLAG_LEVEL flag indicates the gsi input is for a level
> +triggered interrupt. In this case a new irqchip input is allocated
> +which is logically OR'd with other inputs allowing multiple sources
> +to independently assert level interrupts. The KVM_IRQFD_FLAG_LEVEL
> +is only necessary on setup, teardown is identical to that above.
> +KVM_IRQFD_FLAG_LEVEL support is indicated by KVM_CAP_IRQFD_LEVEL.
>
> 5. The kvm_run structure
> ------------------------
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index a01a424..80bed07 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -2148,6 +2148,7 @@ int kvm_dev_ioctl_check_extension(long ext)
> case KVM_CAP_GET_TSC_KHZ:
> case KVM_CAP_PCI_2_3:
> case KVM_CAP_KVMCLOCK_CTRL:
> + case KVM_CAP_IRQFD_LEVEL:
> r = 1;
> break;
> case KVM_CAP_COALESCED_MMIO:
> diff --git a/include/linux/kvm.h b/include/linux/kvm.h
> index 2ce09aa..b2e6e4f 100644
> --- a/include/linux/kvm.h
> +++ b/include/linux/kvm.h
> @@ -618,6 +618,7 @@ struct kvm_ppc_smmu_info {
> #define KVM_CAP_PPC_GET_SMMU_INFO 78
> #define KVM_CAP_S390_COW 79
> #define KVM_CAP_PPC_ALLOC_HTAB 80
> +#define KVM_CAP_IRQFD_LEVEL 81
>
> #ifdef KVM_CAP_IRQ_ROUTING
>
> @@ -683,6 +684,8 @@ struct kvm_xen_hvm_config {
> #endif
>
> #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
> +/* Available with KVM_CAP_IRQFD_LEVEL */
> +#define KVM_IRQFD_FLAG_LEVEL (1 << 1)
>
> struct kvm_irqfd {
> __u32 fd;
> diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
> index 7d7e2aa..ecdbfea 100644
> --- a/virt/kvm/eventfd.c
> +++ b/virt/kvm/eventfd.c
> @@ -36,6 +36,68 @@
> #include "iodev.h"
>
> /*
> + * An irq_source_id can be created from KVM_IRQFD for level interrupt
> + * injections and shared with other interfaces for EOI or de-assert.
> + * Create an object with reference counting to make it easy to use.
> + */
> +struct _irq_source {
> + int id; /* the IRQ source ID */
> + bool level_asserted; /* Track assertion state and protect with lock */
> + spinlock_t lock; /* to avoid unnecessary re-assert/spurious eoi. */
> + struct kvm *kvm;
> + struct kref kref;
> +};
> +
> +static void _irq_source_release(struct kref *kref)
> +{
> + struct _irq_source *source;
> +
> + source = container_of(kref, struct _irq_source, kref);
> +
> + /* This also de-asserts */
> + kvm_free_irq_source_id(source->kvm, source->id);
> + kfree(source);
> +}
> +
> +static void _irq_source_put(struct _irq_source *source)
> +{
> + if (source)
> + kref_put(&source->kref, _irq_source_release);
> +}
> +
> +static struct _irq_source *__attribute__ ((used)) /* white lie for now */
> +_irq_source_get(struct _irq_source *source)
> +{
> + if (source)
> + kref_get(&source->kref);
> +
> + return source;
> +}
> +
> +static struct _irq_source *_irq_source_alloc(struct kvm *kvm)
> +{
> + struct _irq_source *source;
> + int id;
> +
> + source = kzalloc(sizeof(*source), GFP_KERNEL);
> + if (!source)
> + return ERR_PTR(-ENOMEM);
> +
> + id = kvm_request_irq_source_id(kvm);
> + if (id < 0) {
> + kfree(source);
> + return ERR_PTR(id);
> + }
> +
> + kref_init(&source->kref);
> + spin_lock_init(&source->lock);
> + source->kvm = kvm;
> + source->id = id;
> +
> + return source;
> +}
> +
> +/*
> * --------------------------------------------------------------------
> * irqfd: Allows an fd to be used to inject an interrupt to the guest
> *
> @@ -52,6 +114,8 @@ struct _irqfd {
> /* Used for level IRQ fast-path */
> int gsi;
> struct work_struct inject;
> + /* IRQ source ID for level triggered irqfds */
> + struct _irq_source *source;
> /* Used for setup/shutdown */
> struct eventfd_ctx *eventfd;
> struct list_head list;
> @@ -62,7 +126,7 @@ struct _irqfd {
> static struct workqueue_struct *irqfd_cleanup_wq;
>
> static void
> -irqfd_inject(struct work_struct *work)
> +irqfd_inject_edge(struct work_struct *work)
> {
> struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
> struct kvm *kvm = irqfd->kvm;
> @@ -71,6 +135,29 @@ irqfd_inject(struct work_struct *work)
> kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
> }
>
> +static void
> +irqfd_inject_level(struct work_struct *work)
> +{
> + struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
> +
> + /*
> + * Inject an interrupt only if not already asserted.
> + *
> + * We can safely ignore the kvm_set_irq return value here. If
> + * masked, the irr bit is still set and will eventually be serviced.
> + * This interface does not guarantee immediate injection. If
> + * coalesced, an eoi will be coming where we can de-assert and
> + * re-inject if necessary. NB, if you need to know if an interrupt
> + * was coalesced, this interface is not for you.
> + */
> + spin_lock(&irqfd->source->lock);
> + if (!irqfd->source->level_asserted) {
> + kvm_set_irq(irqfd->kvm, irqfd->source->id, irqfd->gsi, 1);
> + irqfd->source->level_asserted = true;
> + }
> + spin_unlock(&irqfd->source->lock);
> +}
> +

So as was discussed kvm_set_irq under spinlock is bad for scalability
with multiple VCPUs. Why do we need a spinlock simply to protect
level_asserted? Let's use an atomic test and set/test and clear and the
problem goes away.

> /*
> * Race-free decouple logic (ordering is critical)
> */
> @@ -96,6 +183,9 @@ irqfd_shutdown(struct work_struct *work)
> * It is now safe to release the object's resources
> */
> eventfd_ctx_put(irqfd->eventfd);
> +
> + _irq_source_put(irqfd->source);
> +
> kfree(irqfd);
> }
>
> @@ -202,6 +292,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
> {
> struct kvm_irq_routing_table *irq_rt;
> struct _irqfd *irqfd, *tmp;
> + struct _irq_source *source = NULL;
> struct file *file = NULL;
> struct eventfd_ctx *eventfd = NULL;
> int ret;
> @@ -214,7 +305,19 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
> irqfd->kvm = kvm;
> irqfd->gsi = args->gsi;
> INIT_LIST_HEAD(&irqfd->list);
> - INIT_WORK(&irqfd->inject, irqfd_inject);
> +
> + if (args->flags & KVM_IRQFD_FLAG_LEVEL) {
> + source = _irq_source_alloc(kvm);
> + if (IS_ERR(source)) {
> + ret = PTR_ERR(source);
> + goto fail;
> + }
> +
> + irqfd->source = source;
> + INIT_WORK(&irqfd->inject, irqfd_inject_level);
> + } else
> + INIT_WORK(&irqfd->inject, irqfd_inject_edge);
> +
> INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
>
> file = eventfd_fget(args->fd);
> @@ -276,10 +379,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
> return 0;
>
> fail:
> + if (source && !IS_ERR(source))
> + _irq_source_put(source);
> +
> if (eventfd && !IS_ERR(eventfd))
> eventfd_ctx_put(eventfd);
>
> - if (!IS_ERR(file))
> + if (file && !IS_ERR(file))
> fput(file);
>
> kfree(irqfd);
> @@ -340,7 +446,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
> int
> kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
> {
> - if (args->flags & ~KVM_IRQFD_FLAG_DEASSIGN)
> + if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_LEVEL))
> return -EINVAL;
>
> if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/