Re: [PATCH v2 4/4] vhost-user-scsi: support reconnect to backend

[Raphael Norwitz <raphael.norwitz@nutanix.com>]

I don’t think we should be changing any vhost-scsi-common code here. I’d rather implement wrappers around vhost_user_scsi_start/stop() around vhost_user_scsi_common_start/stop() and check started_vu there.

Otherwise I think this is looking good. 

Glad to see you caught the vhost_user_scsi_handle_ouptut and implemented it like vhost-user-blk. Can it go in a separate change?

> On Jul 25, 2023, at 6:42 AM, Li Feng <fengli@smartx.com> wrote:
> 
> If the backend crashes and restarts, the device is broken.
> This patch adds reconnect for vhost-user-scsi.
> 
> Tested with spdk backend.
> 
> Signed-off-by: Li Feng <fengli@smartx.com>
> ---
> hw/scsi/vhost-scsi-common.c           |   6 +
> hw/scsi/vhost-user-scsi.c             | 220 +++++++++++++++++++++++---
> include/hw/virtio/vhost-scsi-common.h |   3 +
> include/hw/virtio/vhost-user-scsi.h   |   3 +
> 4 files changed, 211 insertions(+), 21 deletions(-)
> 
> diff --git a/hw/scsi/vhost-scsi-common.c b/hw/scsi/vhost-scsi-common.c
> index 664adb15b4..3fde477eee 100644
> --- a/hw/scsi/vhost-scsi-common.c
> +++ b/hw/scsi/vhost-scsi-common.c
> @@ -81,6 +81,7 @@ int vhost_scsi_common_start(VHostSCSICommon *vsc)
>         error_report("Error start vhost dev");
>         goto err_guest_notifiers;
>     }
> +    vsc->started_vu = true;
> 
>     /* guest_notifier_mask/pending not used yet, so just unmask
>      * everything here.  virtio-pci will do the right thing by
> @@ -106,6 +107,11 @@ void vhost_scsi_common_stop(VHostSCSICommon *vsc)
>     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
>     int ret = 0;
> 
> +    if (!vsc->started_vu) {
> +        return;
> +    }
> +    vsc->started_vu = false;
> +
>     vhost_dev_stop(&vsc->dev, vdev, true);
> 
>     if (k->set_guest_notifiers) {
> diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c
> index ee99b19e7a..bd32dcf999 100644
> --- a/hw/scsi/vhost-user-scsi.c
> +++ b/hw/scsi/vhost-user-scsi.c
> @@ -46,20 +46,25 @@ enum VhostUserProtocolFeature {
> static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
> {
>     VHostUserSCSI *s = (VHostUserSCSI *)vdev;
> +    DeviceState *dev = &s->parent_obj.parent_obj.parent_obj.parent_obj;
>     VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> -    bool start = (status & VIRTIO_CONFIG_S_DRIVER_OK) && vdev->vm_running;
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +    bool should_start = virtio_device_should_start(vdev, status);
> +    int ret;
> 
> -    if (vhost_dev_is_started(&vsc->dev) == start) {
> +    if (!s->connected) {
>         return;
>     }
> 
> -    if (start) {
> -        int ret;
> +    if (vhost_dev_is_started(&vsc->dev) == should_start) {
> +        return;
> +    }
> 
> +    if (should_start) {
>         ret = vhost_scsi_common_start(vsc);
>         if (ret < 0) {
>             error_report("unable to start vhost-user-scsi: %s", strerror(-ret));
> -            exit(1);
> +            qemu_chr_fe_disconnect(&vs->conf.chardev);
>         }
>     } else {
>         vhost_scsi_common_stop(vsc);
> @@ -85,8 +90,160 @@ static void vhost_user_scsi_reset(VirtIODevice *vdev)
>     }
> }
> 
> -static void vhost_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
> +static void vhost_user_scsi_handle_output(VirtIODevice *vdev, VirtQueue *vq)
> {
> +    VHostUserSCSI *s = (VHostUserSCSI *)vdev;
> +    DeviceState *dev = &s->parent_obj.parent_obj.parent_obj.parent_obj;
> +    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +
> +    Error *local_err = NULL;
> +    int i, ret;
> +
> +    if (!vdev->start_on_kick) {
> +        return;
> +    }
> +
> +    if (!s->connected) {
> +        return;
> +    }
> +
> +    if (vhost_dev_is_started(&vsc->dev)) {
> +        return;
> +    }
> +
> +    /*
> +     * Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
> +     * vhost here instead of waiting for .set_status().
> +     */
> +    ret = vhost_scsi_common_start(vsc);
> +    if (ret < 0) {
> +        error_reportf_err(local_err, "vhost-user-blk: vhost start failed: ");
> +        qemu_chr_fe_disconnect(&vs->conf.chardev);
> +        return;
> +    }
> +
> +    /* Kick right away to begin processing requests already in vring */
> +    for (i = 0; i < vsc->dev.nvqs; i++) {
> +        VirtQueue *kick_vq = virtio_get_queue(vdev, i);
> +
> +        if (!virtio_queue_get_desc_addr(vdev, i)) {
> +            continue;
> +        }
> +        event_notifier_set(virtio_queue_get_host_notifier(kick_vq));
> +    }
> +}
> +
> +static int vhost_user_scsi_connect(DeviceState *dev, Error **errp)
> +{
> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> +    VHostUserSCSI *s = VHOST_USER_SCSI(vdev);
> +    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +    int ret = 0;
> +
> +    if (s->connected) {
> +        return 0;
> +    }
> +    s->connected = true;
> +
> +    vsc->dev.num_queues = vs->conf.num_queues;
> +    vsc->dev.nvqs = VIRTIO_SCSI_VQ_NUM_FIXED + vs->conf.num_queues;
> +    vsc->dev.vqs = s->vhost_vqs;
> +    vsc->dev.vq_index = 0;
> +    vsc->dev.backend_features = 0;
> +
> +    ret = vhost_dev_init(&vsc->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0,
> +                         errp);
> +    if (ret < 0) {
> +        return ret;
> +    }
> +
> +    /* restore vhost state */
> +    if (virtio_device_started(vdev, vdev->status)) {
> +        ret = vhost_scsi_common_start(vsc);
> +        if (ret < 0) {
> +            return ret;
> +        }
> +    }
> +
> +    return 0;
> +}
> +
> +static void vhost_user_scsi_event(void *opaque, QEMUChrEvent event);
> +
> +static void vhost_user_scsi_disconnect(DeviceState *dev)
> +{
> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> +    VHostUserSCSI *s = VHOST_USER_SCSI(vdev);
> +    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +
> +    if (!s->connected) {
> +        return;
> +    }
> +    s->connected = false;
> +
> +    vhost_scsi_common_stop(vsc);
> +
> +    vhost_dev_cleanup(&vsc->dev);
> +
> +    /* Re-instate the event handler for new connections */
> +    qemu_chr_fe_set_handlers(&vs->conf.chardev, NULL, NULL,
> +                             vhost_user_scsi_event, NULL, dev, NULL, true);
> +}
> +
> +static void vhost_user_scsi_event(void *opaque, QEMUChrEvent event)
> +{
> +    DeviceState *dev = opaque;
> +    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
> +    VHostUserSCSI *s = VHOST_USER_SCSI(vdev);
> +    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +    Error *local_err = NULL;
> +
> +    switch (event) {
> +    case CHR_EVENT_OPENED:
> +        if (vhost_user_scsi_connect(dev, &local_err) < 0) {
> +            error_report_err(local_err);
> +            qemu_chr_fe_disconnect(&vs->conf.chardev);
> +            return;
> +        }
> +        break;
> +    case CHR_EVENT_CLOSED:
> +        /* defer close until later to avoid circular close */
> +        vhost_user_async_close(dev, &vs->conf.chardev, &vsc->dev,
> +                               vhost_user_scsi_disconnect);
> +        break;
> +    case CHR_EVENT_BREAK:
> +    case CHR_EVENT_MUX_IN:
> +    case CHR_EVENT_MUX_OUT:
> +        /* Ignore */
> +        break;
> +    }
> +}
> +
> +static int vhost_user_scsi_realize_connect(VHostUserSCSI *s, Error **errp)
> +{
> +    DeviceState *dev = &s->parent_obj.parent_obj.parent_obj.parent_obj;
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> +    int ret;
> +
> +    s->connected = false;
> +
> +    ret = qemu_chr_fe_wait_connected(&vs->conf.chardev, errp);
> +    if (ret < 0) {
> +        return ret;
> +    }
> +
> +    ret = vhost_user_scsi_connect(dev, errp);
> +    if (ret < 0) {
> +        qemu_chr_fe_disconnect(&vs->conf.chardev);
> +        return ret;
> +    }
> +    assert(s->connected);
> +
> +    return 0;
> }
> 
> static void vhost_user_scsi_realize(DeviceState *dev, Error **errp)
> @@ -94,18 +251,18 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp)
>     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
>     VHostUserSCSI *s = VHOST_USER_SCSI(dev);
>     VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> -    struct vhost_virtqueue *vqs = NULL;
>     Error *err = NULL;
>     int ret;
> +    int retries = VU_REALIZE_CONN_RETRIES;
> 
>     if (!vs->conf.chardev.chr) {
>         error_setg(errp, "vhost-user-scsi: missing chardev");
>         return;
>     }
> 
> -    virtio_scsi_common_realize(dev, vhost_dummy_handle_output,
> -                               vhost_dummy_handle_output,
> -                               vhost_dummy_handle_output, &err);
> +    virtio_scsi_common_realize(dev, vhost_user_scsi_handle_output,
> +                               vhost_user_scsi_handle_output,
> +                               vhost_user_scsi_handle_output, &err);
>     if (err != NULL) {
>         error_propagate(errp, err);
>         return;
> @@ -115,18 +272,28 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp)
>         goto free_virtio;
>     }
> 
> -    vsc->dev.nvqs = VIRTIO_SCSI_VQ_NUM_FIXED + vs->conf.num_queues;
> -    vsc->dev.vqs = g_new0(struct vhost_virtqueue, vsc->dev.nvqs);
> -    vsc->dev.vq_index = 0;
> -    vsc->dev.backend_features = 0;
> -    vqs = vsc->dev.vqs;
> +    vsc->inflight = g_new0(struct vhost_inflight, 1);
> +    s->vhost_vqs = g_new0(struct vhost_virtqueue,
> +                          VIRTIO_SCSI_VQ_NUM_FIXED + vs->conf.num_queues);
> +
> +    assert(!*errp);
> +    do {
> +        if (*errp) {
> +            error_prepend(errp, "Reconnecting after error: ");
> +            error_report_err(*errp);
> +            *errp = NULL;
> +        }
> +        ret = vhost_user_scsi_realize_connect(s, errp);
> +    } while (ret < 0 && retries--);
> 
> -    ret = vhost_dev_init(&vsc->dev, &s->vhost_user,
> -                         VHOST_BACKEND_TYPE_USER, 0, errp);
>     if (ret < 0) {
>         goto free_vhost;
>     }
> 
> +    /* we're fully initialized, now we can operate, so add the handler */
> +    qemu_chr_fe_set_handlers(&vs->conf.chardev,  NULL, NULL,
> +                             vhost_user_scsi_event, NULL, (void *)dev,
> +                             NULL, true);
>     /* Channel and lun both are 0 for bootable vhost-user-scsi disk */
>     vsc->channel = 0;
>     vsc->lun = 0;
> @@ -135,8 +302,12 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp)
>     return;
> 
> free_vhost:
> +    g_free(s->vhost_vqs);
> +    s->vhost_vqs = NULL;
> +    g_free(vsc->inflight);
> +    vsc->inflight = NULL;
>     vhost_user_cleanup(&s->vhost_user);
> -    g_free(vqs);
> +
> free_virtio:
>     virtio_scsi_common_unrealize(dev);
> }
> @@ -146,16 +317,23 @@ static void vhost_user_scsi_unrealize(DeviceState *dev)
>     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
>     VHostUserSCSI *s = VHOST_USER_SCSI(dev);
>     VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
> -    struct vhost_virtqueue *vqs = vsc->dev.vqs;
> +    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
> 
>     /* This will stop the vhost backend. */
>     vhost_user_scsi_set_status(vdev, 0);
> +    qemu_chr_fe_set_handlers(&vs->conf.chardev, NULL, NULL, NULL, NULL, NULL,
> +                             NULL, false);
> 
>     vhost_dev_cleanup(&vsc->dev);
> -    g_free(vqs);
> +    g_free(s->vhost_vqs);
> +    s->vhost_vqs = NULL;
> +
> +    vhost_dev_free_inflight(vsc->inflight);
> +    g_free(vsc->inflight);
> +    vsc->inflight = NULL;
> 
> -    virtio_scsi_common_unrealize(dev);
>     vhost_user_cleanup(&s->vhost_user);
> +    virtio_scsi_common_unrealize(dev);
> }
> 
> static Property vhost_user_scsi_properties[] = {
> diff --git a/include/hw/virtio/vhost-scsi-common.h b/include/hw/virtio/vhost-scsi-common.h
> index 18f115527c..daa183018c 100644
> --- a/include/hw/virtio/vhost-scsi-common.h
> +++ b/include/hw/virtio/vhost-scsi-common.h
> @@ -37,6 +37,9 @@ struct VHostSCSICommon {
>     bool migratable;
> 
>     struct vhost_inflight *inflight;
> +
> +    /* vhost_scsi_common_start/vhost_scsi_common_stop */
> +    bool started_vu;

Move to include/hw/virtio/vhost-user-scsi.h

> };
> 
> int vhost_scsi_common_start(VHostSCSICommon *vsc);
> diff --git a/include/hw/virtio/vhost-user-scsi.h b/include/hw/virtio/vhost-user-scsi.h
> index 521b08e559..c66acc68b7 100644
> --- a/include/hw/virtio/vhost-user-scsi.h
> +++ b/include/hw/virtio/vhost-user-scsi.h
> @@ -29,6 +29,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(VHostUserSCSI, VHOST_USER_SCSI)
> struct VHostUserSCSI {
>     VHostSCSICommon parent_obj;
>     VhostUserState vhost_user;
> +    bool connected;
> +
> +    struct vhost_virtqueue *vhost_vqs;
> };
> 
> #endif /* VHOST_USER_SCSI_H */
> -- 
> 2.41.0
>