On option could be to simply chunk it:

+struct kvm_vcpus {
+       struct kvm_vcpu vcpus[32];
+};
+
 /*
  * Note:
  * memslots are not sorted by id anymore, please use id_to_memslot()

@@ -391,7 +395,7 @@ struct kvm {
        struct mutex slots_lock;
        struct mm_struct *mm; /* userspace tied to this vm */
        struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
-       struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+       struct kvm_vcpus vcpus[(KVM_MAX_VCPUS + 31) / 32];

        /*
         * created_vcpus is protected by kvm->lock, and is incremented

@@ -483,12 +487,14 @@ static inline struct kvm_io_bus

*kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)


1. make nobody access kvm->vcpus directly (factor out)
2. allocate next chunk if necessary when creating a VCPU and store
pointer using WRITE_ONCE
3. use READ_ONCE to test for availability of the current chunk

kvm_for_each_vcpu just has to use READ_ONCE to access/test for the right
chunk. Pointers never get invalid. No RCU needed. Sleeping in the loop
is possible.

-- 

Thanks,

David