From: Pavel Tikhomirov <[email protected]>
This ioctl is needed for QEMU's CPR (checkpoint-restore) migration of
the guest with vhost-vsock device. For this to work, we need to reset
the device ownership on the source side by calling RESET_OWNER, and then
claim it on the dest side by calling SET_OWNER. We expect not to lose any
AF_VSOCK connection while this happens.
To that end, unlike the release path, RESET_OWNER keeps the guest CID
hashed: established connections survive, and host sends issued while
the device is between owners simply stay on send_pkt_queue until the
next device start drains them.
Since the device stays reachable through the CID hash, the lockless
send/cancel paths can race with the worker teardown in
vhost_workers_free(). The previous commit ("vhost: synchronize with
RCU readers when freeing workers") makes that safe.
Signed-off-by: Pavel Tikhomirov <[email protected]>
Signed-off-by: Andrey Drobyshev <[email protected]>
---
drivers/vhost/vsock.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index d5022d21120b..86f25ff80722 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -903,6 +903,29 @@ static int vhost_vsock_set_features(struct vhost_vsock
*vsock, u64 features)
return -EFAULT;
}
+static long vhost_vsock_reset_owner(struct vhost_vsock *vsock)
+{
+ struct vhost_iotlb *umem;
+ long err;
+
+ mutex_lock(&vsock->dev.mutex);
+ err = vhost_dev_check_owner(&vsock->dev);
+ if (err)
+ goto done;
+ umem = vhost_dev_reset_owner_prepare();
+ if (!umem) {
+ err = -ENOMEM;
+ goto done;
+ }
+ vhost_vsock_drop_backends(vsock);
+ vhost_vsock_flush(vsock);
+ vhost_dev_stop(&vsock->dev);
+ vhost_dev_reset_owner(&vsock->dev, umem);
+done:
+ mutex_unlock(&vsock->dev.mutex);
+ return err;
+}
+
static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
unsigned long arg)
{
@@ -946,6 +969,8 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned
int ioctl,
return -EOPNOTSUPP;
vhost_set_backend_features(&vsock->dev, features);
return 0;
+ case VHOST_RESET_OWNER:
+ return vhost_vsock_reset_owner(vsock);
default:
mutex_lock(&vsock->dev.mutex);
r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
--
2.47.1
