Merge branch 'hv_netvsc-fix-race-of-netvsc-vf-register-and-slave-bit'

Haiyang Zhang says:

====================
hv_netvsc: fix race of netvsc, VF register, and slave bit

There are some races between netvsc probe, set notifier, VF register,
and slave bit setting.
This patch set fixes them.
====================

Link: https://lore.kernel.org/r/1700411023-14317-1-git-send-email-haiyangz@microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 45 insertions, 21 deletions

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 3ba3c8fb28a5d6..706ea5263e879d 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2206,9 +2206,6 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	/* set slave flag before open to prevent IPv6 addrconf */
-	vf_netdev->flags |= IFF_SLAVE;
-
 	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
@@ -2315,16 +2312,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 
 	}
 
-	/* Fallback path to check synthetic vf with
-	 * help of mac addr
+	/* Fallback path to check synthetic vf with help of mac addr.
+	 * Because this function can be called before vf_netdev is
+	 * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied
+	 * from dev_addr, also try to match to its dev_addr.
+	 * Note: On Hyper-V and Azure, it's not possible to set a MAC address
+	 * on a VF that matches to the MAC of a unrelated NETVSC device.
 	 */
 	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
 		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
-		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) {
-			netdev_notice(vf_netdev,
-				      "falling back to mac addr based matching\n");
+		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) ||
+		    ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr))
 			return ndev;
-		}
 	}
 
 	netdev_notice(vf_netdev,
@@ -2332,6 +2331,19 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 	return NULL;
 }
 
+static int netvsc_prepare_bonding(struct net_device *vf_netdev)
+{
+	struct net_device *ndev;
+
+	ndev = get_netvsc_byslot(vf_netdev);
+	if (!ndev)
+		return NOTIFY_DONE;
+
+	/* set slave flag before open to prevent IPv6 addrconf */
+	vf_netdev->flags |= IFF_SLAVE;
+	return NOTIFY_DONE;
+}
+
 static int netvsc_register_vf(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2531,15 +2543,6 @@ static int netvsc_probe(struct hv_device *dev,
 		goto devinfo_failed;
 	}
 
-	nvdev = rndis_filter_device_add(dev, device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
-		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		goto rndis_failed;
-	}
-
-	eth_hw_addr_set(net, device_info->mac_adr);
-
 	/* We must get rtnl lock before scheduling nvdev->subchan_work,
 	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
 	 * all subchannels to show up, but that may not happen because
@@ -2547,9 +2550,23 @@ static int netvsc_probe(struct hv_device *dev,
 	 * -> ... -> device_add() -> ... -> __device_attach() can't get
 	 * the device lock, so all the subchannels can't be processed --
 	 * finally netvsc_subchan_work() hangs forever.
+	 *
+	 * The rtnl lock also needs to be held before rndis_filter_device_add()
+	 * which advertises nvsp_2_vsc_capability / sriov bit, and triggers
+	 * VF NIC offering and registering. If VF NIC finished register_netdev()
+	 * earlier it may cause name based config failure.
 	 */
 	rtnl_lock();
 
+	nvdev = rndis_filter_device_add(dev, device_info);
+	if (IS_ERR(nvdev)) {
+		ret = PTR_ERR(nvdev);
+		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
+		goto rndis_failed;
+	}
+
+	eth_hw_addr_set(net, device_info->mac_adr);
+
 	if (nvdev->num_chn > 1)
 		schedule_work(&nvdev->subchan_work);
 
@@ -2586,9 +2603,9 @@ static int netvsc_probe(struct hv_device *dev,
 	return 0;
 
 register_failed:
-	rtnl_unlock();
 	rndis_filter_device_remove(dev, nvdev);
 rndis_failed:
+	rtnl_unlock();
 	netvsc_devinfo_put(device_info);
 devinfo_failed:
 	free_percpu(net_device_ctx->vf_stats);
@@ -2753,6 +2770,8 @@ static int netvsc_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	switch (event) {
+	case NETDEV_POST_INIT:
+		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
 		return netvsc_register_vf(event_dev);
 	case NETDEV_UNREGISTER:
@@ -2788,12 +2807,17 @@ static int __init netvsc_drv_init(void)
 	}
 	netvsc_ring_bytes = ring_size * PAGE_SIZE;
 
+	register_netdevice_notifier(&netvsc_netdev_notifier);
+
 	ret = vmbus_driver_register(&netvsc_drv);
 	if (ret)
-		return ret;
+		goto err_vmbus_reg;
 
-	register_netdevice_notifier(&netvsc_netdev_notifier);
 	return 0;
+
+err_vmbus_reg:
+	unregister_netdevice_notifier(&netvsc_netdev_notifier);
+	return ret;
 }
 
 MODULE_LICENSE("GPL");