KVM: Avoid synchronize_srcu() in kvm_io_bus_register_dev()

Device MMIO registration may happen quite frequently during VM boot,
and the SRCU synchronization each time has a measurable effect
on VM startup time. In our experiments it can account for around 25%
of a VM's startup time.

Replace the synchronization with a deferred free of the old kvm_io_bus
structure.

Tested-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Keir Fraser <keirf@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Keir Fraser

include/linux/kvm_host.h

@@ -206,6 +206,7 @@ struct kvm_io_range {
 struct kvm_io_bus {
 	int dev_count;
 	int ioeventfd_count;
+	struct rcu_head rcu;
 	struct kvm_io_range range[];
 };
 

virt/kvm/kvm_main.c

@@ -1320,6 +1320,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
+	srcu_barrier(&kvm->srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 	xa_destroy(&kvm->mem_attr_array);
@@ -5952,6 +5953,13 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 }
 EXPORT_SYMBOL_GPL(kvm_io_bus_read);
 
+static void __free_bus(struct rcu_head *rcu)
+{
+	struct kvm_io_bus *bus = container_of(rcu, struct kvm_io_bus, rcu);
+
+	kfree(bus);
+}
+
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
 {
@@ -5990,8 +5998,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	memcpy(new_bus->range + i + 1, bus->range + i,
 		(bus->dev_count - i) * sizeof(struct kvm_io_range));
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
-	synchronize_srcu_expedited(&kvm->srcu);
-	kfree(bus);
+	call_srcu(&kvm->srcu, &bus->rcu, __free_bus);
 
 	return 0;
 }