net: hv_netvsc: fix loss of early receive events from host during channel open.

[ Upstream commit 9448ccd853368582efa9db05db344f8bb9dffe0f ]

The hv_netvsc driver currently enables NAPI after opening the primary and
subchannels. This ordering creates a race: if the Hyper-V host places data
in the host -> guest ring buffer and signals the channel before
napi_enable() has been called, the channel callback will run but
napi_schedule_prep() will return false. As a result, the NAPI poller never
gets scheduled, the data in the ring buffer is not consumed, and the
receive queue may remain permanently stuck until another interrupt happens
to arrive.

Fix this by enabling NAPI and registering it with the RX/TX queues before
vmbus channel is opened. This guarantees that any early host signal after
open will correctly trigger NAPI scheduling and the ring buffer will be
drained.

Fixes: 76bb5db5c749d ("netvsc: fix use after free on module removal")
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Link: https://patch.msgid.link/20250825115627.GA32189@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

2 files changed, 24 insertions, 16 deletions

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 720104661d7f..60a4629fe6ba 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1812,6 +1812,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 	/* Enable NAPI handler before init callbacks */
 	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);
+	napi_enable(&net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
+			     &net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
+			     &net_device->chan_table[0].napi);
 
 	/* Open the channel */
 	device->channel->next_request_id_callback = vmbus_next_request_id;
@@ -1831,12 +1836,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	/* Channel is opened */
 	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
 
-	napi_enable(&net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
-			     &net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
-			     &net_device->chan_table[0].napi);
-
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device, net_device, device_info);
 	if (ret != 0) {
@@ -1854,14 +1853,14 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 close:
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
-	napi_disable(&net_device->chan_table[0].napi);
 
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(&net_device->chan_table[0].napi);
 	netif_napi_del(&net_device->chan_table[0].napi);
 
 cleanup2:
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9e73959e61ee..c35f9685b6bf 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1252,17 +1252,26 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	new_sc->max_pkt_size = NETVSC_MAX_PKT_SIZE;
 
+	/* Enable napi before opening the vmbus channel to avoid races
+	 * as the host placing data on the host->guest ring may be left
+	 * out if napi was not enabled.
+	 */
+	napi_enable(&nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+			     &nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+			     &nvchan->napi);
+
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);
-	if (ret == 0) {
-		napi_enable(&nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
-				     &nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
-				     &nvchan->napi);
-	} else {
+	if (ret != 0) {
 		netdev_notice(ndev, "sub channel open failed: %d\n", ret);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+				     NULL);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+				     NULL);
+		napi_disable(&nvchan->napi);
 	}
 
 	if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)