[PATCH net 4/4] hv_netvsc: avoid deadlocks between rtnl lock and netvsc_inject_disable()

[Vitaly Kuznetsov]

Here is a deadlock scenario:
- netvsc_vf_up() schedules netvsc_notify_peers() work and quits.
- netvsc_vf_down() runs before netvsc_notify_peers() gets executed. As it
  is being executed from netdev notifier chain we hold rtnl lock when we
  get here.
- we enter netvsc_inject_disable() and loop and wait till
  netvsc_notify_peers() drops vf_use_cnt.
- netvsc_notify_peers() starts on some other CPU but netdev_notify_peers()
  will hang on rtnl_lock().
- deadlock!

Similar deadlocks are possible between netvsc_vf_{up,down}() and
netvsc_unregister_vf() as it also waits till vf_use_cnt drops to zero.
Instead of introducing additional synchronization I suggest we drop
gwrk.dwrk completely and call NETDEV_NOTIFY_PEERS directly. As we're
acting under rtnl lock this is legitimate.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 drivers/net/hyperv/hyperv_net.h |  7 -------
 drivers/net/hyperv/netvsc_drv.c | 33 +++++----------------------------
 2 files changed, 5 insertions(+), 35 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 3b3ecf2..591af71 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -644,12 +644,6 @@ struct netvsc_reconfig {
 	u32 event;
 };
 
-struct garp_wrk {
-	struct work_struct dwrk;
-	struct net_device *netdev;
-	struct net_device_context *net_device_ctx;
-};
-
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -667,7 +661,6 @@ struct net_device_context {
 
 	struct work_struct work;
 	u32 msg_enable; /* debug level */
-	struct garp_wrk gwrk;
 
 	struct netvsc_stats __percpu *tx_stats;
 	struct netvsc_stats __percpu *rx_stats;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 874829a..62a4e6e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1151,17 +1151,6 @@ static void netvsc_free_netdev(struct net_device *netdev)
 	free_netdev(netdev);
 }
 
-static void netvsc_notify_peers(struct work_struct *wrk)
-{
-	struct garp_wrk *gwrk;
-
-	gwrk = container_of(wrk, struct garp_wrk, dwrk);
-
-	netdev_notify_peers(gwrk->netdev);
-
-	atomic_dec(&gwrk->net_device_ctx->vf_use_cnt);
-}
-
 static struct net_device *get_netvsc_net_device(char *mac)
 {
 	struct net_device *dev, *found = NULL;
@@ -1266,15 +1255,8 @@ static int netvsc_vf_up(struct net_device *vf_netdev)
 
 	netif_carrier_off(ndev);
 
-	/*
-	 * Now notify peers. We are scheduling work to
-	 * notify peers; take a reference to prevent
-	 * the VF interface from vanishing.
-	 */
-	atomic_inc(&net_device_ctx->vf_use_cnt);
-	net_device_ctx->gwrk.netdev = vf_netdev;
-	net_device_ctx->gwrk.net_device_ctx = net_device_ctx;
-	schedule_work(&net_device_ctx->gwrk.dwrk);
+	/* Now notify peers through VF device. */
+	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev);
 
 	return NOTIFY_OK;
 }
@@ -1306,13 +1288,9 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
 	netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
 	rndis_filter_close(netvsc_dev);
 	netif_carrier_on(ndev);
-	/*
-	 * Notify peers.
-	 */
-	atomic_inc(&net_device_ctx->vf_use_cnt);
-	net_device_ctx->gwrk.netdev = ndev;
-	net_device_ctx->gwrk.net_device_ctx = net_device_ctx;
-	schedule_work(&net_device_ctx->gwrk.dwrk);
+
+	/* Now notify peers through netvsc device. */
+	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev);
 
 	return NOTIFY_OK;
 }
@@ -1384,7 +1362,6 @@ static int netvsc_probe(struct hv_device *dev,
 
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
-	INIT_WORK(&net_device_ctx->gwrk.dwrk, netvsc_notify_peers);
 
 	spin_lock_init(&net_device_ctx->lock);
 	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
-- 
2.7.4