On Tue, Dec 06, 2022 at 05:07:01PM -0800, Brett Creeley wrote:
> +struct file *
> +pds_vfio_step_device_state_locked(struct pds_vfio_pci_device *pds_vfio,
> + enum vfio_device_mig_state next)
> +{
> + enum vfio_device_mig_state cur = pds_vfio->state;
> + struct device *dev = &pds_vfio->pdev->dev;
> + unsigned long lm_action_start;
> + int err = 0;
> +
> + dev_dbg(dev, "%s => %s\n",
> + pds_vfio_lm_state(cur), pds_vfio_lm_state(next));
> +
> + lm_action_start = jiffies;
> + if (cur == VFIO_DEVICE_STATE_STOP && next == VFIO_DEVICE_STATE_STOP_COPY) {
> + /* Device is already stopped
> + * create save device data file & get device state from firmware
> + */
> + err = pds_vfio_get_save_file(pds_vfio);
> + if (err)
> + return ERR_PTR(err);
> +
> + /* Get device state */
> + err = pds_vfio_get_lm_state_cmd(pds_vfio);
> + if (err) {
> + pds_vfio_put_save_file(pds_vfio);
> + return ERR_PTR(err);
> + }
> +
> + return pds_vfio->save_file->filep;
> + }
> +
> + if (cur == VFIO_DEVICE_STATE_STOP_COPY && next == VFIO_DEVICE_STATE_STOP) {
> + /* Device is already stopped
> + * delete the save device state file
> + */
> + pds_vfio_put_save_file(pds_vfio);
> + pds_vfio_send_host_vf_lm_status_cmd(pds_vfio,
> + PDS_LM_STA_NONE);
> + return NULL;
> + }
> +
> + if (cur == VFIO_DEVICE_STATE_STOP && next == VFIO_DEVICE_STATE_RESUMING) {
> + /* create resume device data file */
> + err = pds_vfio_get_restore_file(pds_vfio);
> + if (err)
> + return ERR_PTR(err);
> +
> + return pds_vfio->restore_file->filep;
> + }
> +
> + if (cur == VFIO_DEVICE_STATE_RESUMING && next == VFIO_DEVICE_STATE_STOP) {
> + /* Set device state */
> + err = pds_vfio_set_lm_state_cmd(pds_vfio);
> + if (err)
> + return ERR_PTR(err);
> +
> + /* delete resume device data file */
> + pds_vfio_put_restore_file(pds_vfio);
> + return NULL;
> + }
> +
> + if (cur == VFIO_DEVICE_STATE_RUNNING && next == VFIO_DEVICE_STATE_STOP) {
> + /* Device should be stopped
> + * no interrupts, dma or change in internal state
> + */
> + err = pds_vfio_suspend_device_cmd(pds_vfio);
> + if (err)
> + return ERR_PTR(err);
> +
> + return NULL;
> + }
> +
> + if (cur == VFIO_DEVICE_STATE_STOP && next == VFIO_DEVICE_STATE_RUNNING) {
> + /* Device should be functional
> + * interrupts, dma, mmio or changes to internal state is allowed
> + */
> + err = pds_vfio_resume_device_cmd(pds_vfio);
> + if (err)
> + return ERR_PTR(err);
> +
> + pds_vfio_send_host_vf_lm_status_cmd(pds_vfio,
> + PDS_LM_STA_NONE);
> + return NULL;
> + }
Please implement the P2P states in your device. After long discussions
we really want to see all VFIO migrations implementations support
this.
It is still not clear what qemu will do when it sees devices that do
not support P2P, but it will not be nice.
Also, since you are obviously using and testing the related qemu
series, please participate in the review of that in the qemu list, or
at least offer your support with testing.
While HCH is objecting to this driver even existing I won't comment on
specific details.. Though it is intesting this approach doesn't change
NVMe at all so it does seem less objectionable to me than the Intel
RFC.
Jason
