int kvm_handle_guest_abort()

in kvm/mmu.c [1310:1421]

• 69 lines of code
• 16 McCabe index (conditional complexity)

int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
{
	unsigned long fault_status;
	phys_addr_t fault_ipa;
	struct kvm_memory_slot *memslot;
	unsigned long hva;
	bool is_iabt, write_fault, writable;
	gfn_t gfn;
	int ret, idx;

	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);

	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);

	/* Synchronous External Abort? */
	if (kvm_vcpu_abt_issea(vcpu)) {
		/*
		 * For RAS the host kernel may handle this abort.
		 * There is no need to pass the error into the guest.
		 */
		if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu)))
			kvm_inject_vabt(vcpu);

		return 1;
	}

	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
			      kvm_vcpu_get_hfar(vcpu), fault_ipa);

	/* Check the stage-2 fault is trans. fault or write fault */
	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
	    fault_status != FSC_ACCESS) {
		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
			kvm_vcpu_trap_get_class(vcpu),
			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
			(unsigned long)kvm_vcpu_get_esr(vcpu));
		return -EFAULT;
	}

	idx = srcu_read_lock(&vcpu->kvm->srcu);

	gfn = fault_ipa >> PAGE_SHIFT;
	memslot = gfn_to_memslot(vcpu->kvm, gfn);
	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
	write_fault = kvm_is_write_fault(vcpu);
	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
		/*
		 * The guest has put either its instructions or its page-tables
		 * somewhere it shouldn't have. Userspace won't be able to do
		 * anything about this (there's no syndrome for a start), so
		 * re-inject the abort back into the guest.
		 */
		if (is_iabt) {
			ret = -ENOEXEC;
			goto out;
		}

		if (kvm_vcpu_abt_iss1tw(vcpu)) {
			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
			ret = 1;
			goto out_unlock;
		}

		/*
		 * Check for a cache maintenance operation. Since we
		 * ended-up here, we know it is outside of any memory
		 * slot. But we can't find out if that is for a device,
		 * or if the guest is just being stupid. The only thing
		 * we know for sure is that this range cannot be cached.
		 *
		 * So let's assume that the guest is just being
		 * cautious, and skip the instruction.
		 */
		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
			kvm_incr_pc(vcpu);
			ret = 1;
			goto out_unlock;
		}

		/*
		 * The IPA is reported as [MAX:12], so we need to
		 * complement it with the bottom 12 bits from the
		 * faulting VA. This is always 12 bits, irrespective
		 * of the page size.
		 */
		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
		ret = io_mem_abort(vcpu, fault_ipa);
		goto out_unlock;
	}

	/* Userspace should not be able to register out-of-bounds IPAs */
	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));

	if (fault_status == FSC_ACCESS) {
		handle_access_fault(vcpu, fault_ipa);
		ret = 1;
		goto out_unlock;
	}

	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
	if (ret == 0)
		ret = 1;
out:
	if (ret == -ENOEXEC) {
		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
		ret = 1;
	}
out_unlock:
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
	return ret;
}