kvm: exclude ioeventfd from counting kvm_io_range limit

We can easily reach the 1000 limit by start VM with a couple
hundred I/O devices (multifunction=on). The hardcode limit
already been adjusted 3 times (6 ~ 200 ~ 300 ~ 1000).

In userspace, we already have maximum file descriptor to
limit ioeventfd count. But kvm_io_bus devices also are used
for pit, pic, ioapic, coalesced_mmio. They couldn't be limited
by maximum file descriptor.

Currently only ioeventfds take too much kvm_io_bus devices,
so just exclude it from counting kvm_io_range limit.

Also fixed one indent issue in kvm_host.h

Signed-off-by: Amos Kong <[email protected]>
Reviewed-by: Stefan Hajnoczi <[email protected]>
Signed-off-by: Gleb Natapov <[email protected]>

Author: amoskong

include/linux/kvm_host.h

@@ -145,7 +145,8 @@ struct kvm_io_range {
 #define NR_IOBUS_DEVS 1000
 
 struct kvm_io_bus {
-	int                   dev_count;
+	int dev_count;
+	int ioeventfd_count;
 	struct kvm_io_range range[];
 };
 

virt/kvm/eventfd.c

@@ -753,6 +753,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (ret < 0)
 		goto unlock_fail;
 
+	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
 	mutex_unlock(&kvm->slots_lock);
@@ -798,6 +799,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
+		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;

virt/kvm/kvm_main.c

@@ -2926,7 +2926,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	if (bus->dev_count > NR_IOBUS_DEVS - 1)
+	/* exclude ioeventfd which is limited by maximum fd */
+	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
 
 	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) *