Re: [PATCH v10 9/9] KVM: Enable and expose KVM_MEM_PRIVATE

[Sean Christopherson]

On Fri, Dec 02, 2022, Chao Peng wrote:
> @@ -10357,6 +10364,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>  
>               if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
>                       static_call(kvm_x86_update_cpu_dirty_logging)(vcpu);
> +
> +             if (kvm_check_request(KVM_REQ_MEMORY_MCE, vcpu)) {
> +                     vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;

Synthesizing triple fault shutdown is not the right approach.  Even with TDX's
MCE "architecture" (heavy sarcasm), it's possible that host userspace and the
guest have a paravirt interface for handling memory errors without killing the
host.

> +                     r = 0;
> +                     goto out;
> +             }
>       }


> @@ -1982,6 +2112,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
>            !access_ok((void __user *)(unsigned long)mem->userspace_addr,
>                       mem->memory_size))
>               return -EINVAL;
> +     if (mem->flags & KVM_MEM_PRIVATE &&
> +             (mem->restricted_offset & (PAGE_SIZE - 1) ||

Align indentation.

> +              mem->restricted_offset > U64_MAX - mem->memory_size))

Strongly prefer to use similar logic to existing code that detects wraps:

                mem->restricted_offset + mem->memory_size < 
mem->restricted_offset

This is also where I'd like to add the "gfn is aligned to offset" check, though
my brain is too fried to figure that out right now.

> +             return -EINVAL;
>       if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
>               return -EINVAL;
>       if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
> @@ -2020,6 +2154,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
>               if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
>                       return -EINVAL;
>       } else { /* Modify an existing slot. */
> +             /* Private memslots are immutable, they can only be deleted. */

I'm 99% certain I suggested this, but if we're going to make these memslots
immutable, then we should straight up disallow dirty logging, otherwise we'll
end up with a bizarre uAPI.

> +             if (mem->flags & KVM_MEM_PRIVATE)
> +                     return -EINVAL;
>               if ((mem->userspace_addr != old->userspace_addr) ||
>                   (npages != old->npages) ||
>                   ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
> @@ -2048,10 +2185,28 @@ int __kvm_set_memory_region(struct kvm *kvm,
>       new->npages = npages;
>       new->flags = mem->flags;
>       new->userspace_addr = mem->userspace_addr;
> +     if (mem->flags & KVM_MEM_PRIVATE) {
> +             new->restricted_file = fget(mem->restricted_fd);
> +             if (!new->restricted_file ||
> +                 !file_is_restrictedmem(new->restricted_file)) {
> +                     r = -EINVAL;
> +                     goto out;
> +             }
> +             new->restricted_offset = mem->restricted_offset;
> +     }
> +
> +     new->kvm = kvm;

Set this above, just so that the code flows better.