vhost-user-scsi: support reconnect to backend

If the backend crashes and restarts, the device is broken.
This patch adds reconnect for vhost-user-scsi.

This patch also improves the error messages, and reports some silent errors.

Tested with spdk backend.

Signed-off-by: Li Feng <fengli@smartx.com>
Message-Id: <20231009044735.941655-4-fengli@smartx.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>

1 files changed, 181 insertions, 20 deletions

diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c
index b7c6100f3e..24c250d3f8 100644
--- a/hw/scsi/vhost-user-scsi.c
+++ b/hw/scsi/vhost-user-scsi.c
@@ -39,26 +39,56 @@ static const int user_feature_bits[] = {
     VHOST_INVALID_FEATURE_BIT
 };
 
+static int vhost_user_scsi_start(VHostUserSCSI *s, Error **errp)
+{
+    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
+    int ret;
+
+    ret = vhost_scsi_common_start(vsc, errp);
+    s->started_vu = !(ret < 0);
+
+    return ret;
+}
+
+static void vhost_user_scsi_stop(VHostUserSCSI *s)
+{
+    VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
+
+    if (!s->started_vu) {
+        return;
+    }
+    s->started_vu = false;
+
+    vhost_scsi_common_stop(vsc);
+}
+
 static void vhost_user_scsi_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserSCSI *s = (VHostUserSCSI *)vdev;
+    DeviceState *dev = DEVICE(vdev);
     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);
+    Error *local_err = NULL;
+    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;
+    }
 
-        ret = vhost_scsi_common_start(vsc);
+    if (should_start) {
+        ret = vhost_user_scsi_start(s, &local_err);
         if (ret < 0) {
-            error_report("unable to start vhost-user-scsi: %s", strerror(-ret));
-            exit(1);
+            error_reportf_err(local_err, "unable to start vhost-user-scsi: %s",
+                              strerror(-ret));
+            qemu_chr_fe_disconnect(&vs->conf.chardev);
         }
     } else {
-        vhost_scsi_common_stop(vsc);
+        vhost_user_scsi_stop(s);
     }
 }
 
@@ -66,14 +96,124 @@ static void vhost_dummy_handle_output(VirtIODevice *vdev, VirtQueue *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_user_scsi_start(s, errp);
+    }
+
+    return ret;
+}
+
+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_user_scsi_stop(s);
+
+    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 = DEVICE(s);
+    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)
 {
+    ERRP_GUARD();
     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");
@@ -92,18 +232,28 @@ 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;
@@ -112,8 +262,12 @@ 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);
 }
@@ -123,16 +277,23 @@ 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[] = {