[KVM PATCH v8 2/3] KVM: add irqfd DEASSIGN feature

[Gregory Haskins <ghaskins@novell.com>]

DEASSIGN allows us to optionally disassociate an IRQFD from its underlying
eventfd without destroying the eventfd in the process.  This is useful
for conditions like live-migration which may have an eventfd associated
with a device and an IRQFD.  We need to be able to decouple the guest
from the event source while not perturbing the event source itself.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
CC: Michael S. Tsirkin <mst@redhat.com>
---

 include/linux/kvm.h |    2 ++
 virt/kvm/eventfd.c  |   46 ++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 69d3d73..76c6408 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -461,6 +461,8 @@ struct kvm_x86_mce {
 };
 #endif
 
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+
 struct kvm_irqfd {
 	__u32 fd;
 	__u32 gsi;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 05ce447..0fd200c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -161,8 +161,8 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 	add_wait_queue(wqh, &irqfd->wait);
 }
 
-int
-kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+static int
+kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi)
 {
 	struct _irqfd *irqfd;
 	struct file *file = NULL;
@@ -241,6 +241,48 @@ kvm_irqfd_init(struct kvm *kvm)
 }
 
 /*
+ * shutdown any irqfd's that match fd+gsi
+ */
+static int
+kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi)
+{
+	struct _irqfd *irqfd, *tmp;
+	struct eventfd_ctx *eventfd;
+
+	eventfd = eventfd_ctx_fdget(fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+
+	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
+		if (irqfd->eventfd == eventfd && irqfd->gsi == gsi)
+			irqfd_deactivate(irqfd);
+	}
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+	eventfd_ctx_put(eventfd);
+
+	/*
+	 * Block until we know all outstanding shutdown jobs have completed
+	 * so that we guarantee there will not be any more interrupts on this
+	 * gsi once this deassign function returns.
+	 */
+	flush_workqueue(irqfd_cleanup_wq);
+
+	return 0;
+}
+
+int
+kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+{
+	if (flags & KVM_IRQFD_FLAG_DEASSIGN)
+		return kvm_irqfd_deassign(kvm, fd, gsi);
+
+	return kvm_irqfd_assign(kvm, fd, gsi);
+}
+
+/*
  * This function is called as the kvm VM fd is being released. Shutdown all
  * irqfds that still remain open
  */