int kvm_arch_vcpu_ioctl_run()

in kvm/vcpu.c [702:849]

• 74 lines of code
• 11 McCabe index (conditional complexity)

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
	int ret;
	struct kvm_cpu_trap trap;
	struct kvm_run *run = vcpu->run;

	/* Mark this VCPU ran at least once */
	vcpu->arch.ran_atleast_once = true;

	vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

	/* Process MMIO value returned from user-space */
	if (run->exit_reason == KVM_EXIT_MMIO) {
		ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run);
		if (ret) {
			srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
			return ret;
		}
	}

	/* Process SBI value returned from user-space */
	if (run->exit_reason == KVM_EXIT_RISCV_SBI) {
		ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run);
		if (ret) {
			srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
			return ret;
		}
	}

	if (run->immediate_exit) {
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
		return -EINTR;
	}

	vcpu_load(vcpu);

	kvm_sigset_activate(vcpu);

	ret = 1;
	run->exit_reason = KVM_EXIT_UNKNOWN;
	while (ret > 0) {
		/* Check conditions before entering the guest */
		cond_resched();

		kvm_riscv_stage2_vmid_update(vcpu);

		kvm_riscv_check_vcpu_requests(vcpu);

		preempt_disable();

		local_irq_disable();

		/*
		 * Exit if we have a signal pending so that we can deliver
		 * the signal to user space.
		 */
		if (signal_pending(current)) {
			ret = -EINTR;
			run->exit_reason = KVM_EXIT_INTR;
		}

		/*
		 * Ensure we set mode to IN_GUEST_MODE after we disable
		 * interrupts and before the final VCPU requests check.
		 * See the comment in kvm_vcpu_exiting_guest_mode() and
		 * Documentation/virt/kvm/vcpu-requests.rst
		 */
		vcpu->mode = IN_GUEST_MODE;

		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
		smp_mb__after_srcu_read_unlock();

		/*
		 * We might have got VCPU interrupts updated asynchronously
		 * so update it in HW.
		 */
		kvm_riscv_vcpu_flush_interrupts(vcpu);

		/* Update HVIP CSR for current CPU */
		kvm_riscv_update_hvip(vcpu);

		if (ret <= 0 ||
		    kvm_riscv_stage2_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
		    kvm_request_pending(vcpu)) {
			vcpu->mode = OUTSIDE_GUEST_MODE;
			local_irq_enable();
			preempt_enable();
			vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
			continue;
		}

		guest_enter_irqoff();

		__kvm_riscv_switch_to(&vcpu->arch);

		vcpu->mode = OUTSIDE_GUEST_MODE;
		vcpu->stat.exits++;

		/*
		 * Save SCAUSE, STVAL, HTVAL, and HTINST because we might
		 * get an interrupt between __kvm_riscv_switch_to() and
		 * local_irq_enable() which can potentially change CSRs.
		 */
		trap.sepc = vcpu->arch.guest_context.sepc;
		trap.scause = csr_read(CSR_SCAUSE);
		trap.stval = csr_read(CSR_STVAL);
		trap.htval = csr_read(CSR_HTVAL);
		trap.htinst = csr_read(CSR_HTINST);

		/* Syncup interrupts state with HW */
		kvm_riscv_vcpu_sync_interrupts(vcpu);

		/*
		 * We may have taken a host interrupt in VS/VU-mode (i.e.
		 * while executing the guest). This interrupt is still
		 * pending, as we haven't serviced it yet!
		 *
		 * We're now back in HS-mode with interrupts disabled
		 * so enabling the interrupts now will have the effect
		 * of taking the interrupt again, in HS-mode this time.
		 */
		local_irq_enable();

		/*
		 * We do local_irq_enable() before calling guest_exit() so
		 * that if a timer interrupt hits while running the guest
		 * we account that tick as being spent in the guest. We
		 * enable preemption after calling guest_exit() so that if
		 * we get preempted we make sure ticks after that is not
		 * counted as guest time.
		 */
		guest_exit();

		preempt_enable();

		vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

		ret = kvm_riscv_vcpu_exit(vcpu, run, &trap);
	}

	kvm_sigset_deactivate(vcpu);

	vcpu_put(vcpu);

	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);

	return ret;
}