vhost-user: Interface for migration state transfer

Add the interface for transferring the back-end's state during migration
as defined previously in vhost-user.rst.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-Id: <20231016134243.68248-6-hreitz@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

2 files changed, 183 insertions, 0 deletions

diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 7b42ae8aae..f214df804b 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -103,6 +103,8 @@ typedef enum VhostUserRequest {
     VHOST_USER_SET_STATUS = 39,
     VHOST_USER_GET_STATUS = 40,
     VHOST_USER_GET_SHARED_OBJECT = 41,
+    VHOST_USER_SET_DEVICE_STATE_FD = 42,
+    VHOST_USER_CHECK_DEVICE_STATE = 43,
     VHOST_USER_MAX
 } VhostUserRequest;
 
@@ -201,6 +203,12 @@ typedef struct {
     uint32_t size; /* the following payload size */
 } QEMU_PACKED VhostUserHeader;
 
+/* Request payload of VHOST_USER_SET_DEVICE_STATE_FD */
+typedef struct VhostUserTransferDeviceState {
+    uint32_t direction;
+    uint32_t phase;
+} VhostUserTransferDeviceState;
+
 typedef union {
 #define VHOST_USER_VRING_IDX_MASK   (0xff)
 #define VHOST_USER_VRING_NOFD_MASK  (0x1 << 8)
@@ -216,6 +224,7 @@ typedef union {
         VhostUserVringArea area;
         VhostUserInflight inflight;
         VhostUserShared object;
+        VhostUserTransferDeviceState transfer_state;
 } VhostUserPayload;
 
 typedef struct VhostUserMsg {
@@ -2855,6 +2864,140 @@ static void vhost_user_reset_status(struct vhost_dev *dev)
     }
 }
 
+static bool vhost_user_supports_device_state(struct vhost_dev *dev)
+{
+    return virtio_has_feature(dev->protocol_features,
+                              VHOST_USER_PROTOCOL_F_DEVICE_STATE);
+}
+
+static int vhost_user_set_device_state_fd(struct vhost_dev *dev,
+                                          VhostDeviceStateDirection direction,
+                                          VhostDeviceStatePhase phase,
+                                          int fd,
+                                          int *reply_fd,
+                                          Error **errp)
+{
+    int ret;
+    struct vhost_user *vu = dev->opaque;
+    VhostUserMsg msg = {
+        .hdr = {
+            .request = VHOST_USER_SET_DEVICE_STATE_FD,
+            .flags = VHOST_USER_VERSION,
+            .size = sizeof(msg.payload.transfer_state),
+        },
+        .payload.transfer_state = {
+            .direction = direction,
+            .phase = phase,
+        },
+    };
+
+    *reply_fd = -1;
+
+    if (!vhost_user_supports_device_state(dev)) {
+        close(fd);
+        error_setg(errp, "Back-end does not support migration state transfer");
+        return -ENOTSUP;
+    }
+
+    ret = vhost_user_write(dev, &msg, &fd, 1);
+    close(fd);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret,
+                         "Failed to send SET_DEVICE_STATE_FD message");
+        return ret;
+    }
+
+    ret = vhost_user_read(dev, &msg);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret,
+                         "Failed to receive SET_DEVICE_STATE_FD reply");
+        return ret;
+    }
+
+    if (msg.hdr.request != VHOST_USER_SET_DEVICE_STATE_FD) {
+        error_setg(errp,
+                   "Received unexpected message type, expected %d, received %d",
+                   VHOST_USER_SET_DEVICE_STATE_FD, msg.hdr.request);
+        return -EPROTO;
+    }
+
+    if (msg.hdr.size != sizeof(msg.payload.u64)) {
+        error_setg(errp,
+                   "Received bad message size, expected %zu, received %" PRIu32,
+                   sizeof(msg.payload.u64), msg.hdr.size);
+        return -EPROTO;
+    }
+
+    if ((msg.payload.u64 & 0xff) != 0) {
+        error_setg(errp, "Back-end did not accept migration state transfer");
+        return -EIO;
+    }
+
+    if (!(msg.payload.u64 & VHOST_USER_VRING_NOFD_MASK)) {
+        *reply_fd = qemu_chr_fe_get_msgfd(vu->user->chr);
+        if (*reply_fd < 0) {
+            error_setg(errp,
+                       "Failed to get back-end-provided transfer pipe FD");
+            *reply_fd = -1;
+            return -EIO;
+        }
+    }
+
+    return 0;
+}
+
+static int vhost_user_check_device_state(struct vhost_dev *dev, Error **errp)
+{
+    int ret;
+    VhostUserMsg msg = {
+        .hdr = {
+            .request = VHOST_USER_CHECK_DEVICE_STATE,
+            .flags = VHOST_USER_VERSION,
+            .size = 0,
+        },
+    };
+
+    if (!vhost_user_supports_device_state(dev)) {
+        error_setg(errp, "Back-end does not support migration state transfer");
+        return -ENOTSUP;
+    }
+
+    ret = vhost_user_write(dev, &msg, NULL, 0);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret,
+                         "Failed to send CHECK_DEVICE_STATE message");
+        return ret;
+    }
+
+    ret = vhost_user_read(dev, &msg);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret,
+                         "Failed to receive CHECK_DEVICE_STATE reply");
+        return ret;
+    }
+
+    if (msg.hdr.request != VHOST_USER_CHECK_DEVICE_STATE) {
+        error_setg(errp,
+                   "Received unexpected message type, expected %d, received %d",
+                   VHOST_USER_CHECK_DEVICE_STATE, msg.hdr.request);
+        return -EPROTO;
+    }
+
+    if (msg.hdr.size != sizeof(msg.payload.u64)) {
+        error_setg(errp,
+                   "Received bad message size, expected %zu, received %" PRIu32,
+                   sizeof(msg.payload.u64), msg.hdr.size);
+        return -EPROTO;
+    }
+
+    if (msg.payload.u64 != 0) {
+        error_setg(errp, "Back-end failed to process its internal state");
+        return -EIO;
+    }
+
+    return 0;
+}
+
 const VhostOps user_ops = {
         .backend_type = VHOST_BACKEND_TYPE_USER,
         .vhost_backend_init = vhost_user_backend_init,
@@ -2890,4 +3033,7 @@ const VhostOps user_ops = {
         .vhost_set_inflight_fd = vhost_user_set_inflight_fd,
         .vhost_dev_start = vhost_user_dev_start,
         .vhost_reset_status = vhost_user_reset_status,
+        .vhost_supports_device_state = vhost_user_supports_device_state,
+        .vhost_set_device_state_fd = vhost_user_set_device_state_fd,
+        .vhost_check_device_state = vhost_user_check_device_state,
 };
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 9c9ae7109e..4db9dbfd64 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -2159,3 +2159,40 @@ int vhost_reset_device(struct vhost_dev *hdev)
 
     return -ENOSYS;
 }
+
+bool vhost_supports_device_state(struct vhost_dev *dev)
+{
+    if (dev->vhost_ops->vhost_supports_device_state) {
+        return dev->vhost_ops->vhost_supports_device_state(dev);
+    }
+
+    return false;
+}
+
+int vhost_set_device_state_fd(struct vhost_dev *dev,
+                              VhostDeviceStateDirection direction,
+                              VhostDeviceStatePhase phase,
+                              int fd,
+                              int *reply_fd,
+                              Error **errp)
+{
+    if (dev->vhost_ops->vhost_set_device_state_fd) {
+        return dev->vhost_ops->vhost_set_device_state_fd(dev, direction, phase,
+                                                         fd, reply_fd, errp);
+    }
+
+    error_setg(errp,
+               "vhost transport does not support migration state transfer");
+    return -ENOSYS;
+}
+
+int vhost_check_device_state(struct vhost_dev *dev, Error **errp)
+{
+    if (dev->vhost_ops->vhost_check_device_state) {
+        return dev->vhost_ops->vhost_check_device_state(dev, errp);
+    }
+
+    error_setg(errp,
+               "vhost transport does not support migration state transfer");
+    return -ENOSYS;
+}