4 files changed, 203 insertions, 96 deletions

diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig
index 23a2d145813a..0765d5f61714 100644
--- a/drivers/net/hyperv/Kconfig
+++ b/drivers/net/hyperv/Kconfig
@@ -2,6 +2,5 @@ config HYPERV_NET
 	tristate "Microsoft Hyper-V virtual network driver"
 	depends on HYPERV
 	select UCS2_STRING
-	select FAILOVER
 	help
 	  Select this option to enable the Hyper-V virtual network driver.
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 99d8e7398a5b..1a924b867b07 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -189,7 +189,6 @@ struct netvsc_device;
 struct net_device_context;
 
 extern u32 netvsc_ring_bytes;
-extern struct reciprocal_value netvsc_ring_reciprocal;
 
 struct netvsc_device *netvsc_device_add(struct hv_device *device,
 					const struct netvsc_device_info *info);
@@ -902,6 +901,8 @@ struct net_device_context {
 	struct hv_device *device_ctx;
 	/* netvsc_device */
 	struct netvsc_device __rcu *nvdev;
+	/* list of netvsc net_devices */
+	struct list_head list;
 	/* reconfigure work */
 	struct delayed_work dwork;
 	/* last reconfig time */
@@ -932,8 +933,6 @@ struct net_device_context {
 	u32 vf_alloc;
 	/* Serial number of the VF to team with */
 	u32 vf_serial;
-
-	struct failover *failover;
 };
 
 /* Per channel data */
@@ -1278,17 +1277,17 @@ struct ndis_lsov2_offload {
 
 struct ndis_ipsecv2_offload {
 	u32	encap;
-	u16	ip6;
-	u16	ip4opt;
-	u16	ip6ext;
-	u16	ah;
-	u16	esp;
-	u16	ah_esp;
-	u16	xport;
-	u16	tun;
-	u16	xport_tun;
-	u16	lso;
-	u16	extseq;
+	u8	ip6;
+	u8	ip4opt;
+	u8	ip6ext;
+	u8	ah;
+	u8	esp;
+	u8	ah_esp;
+	u8	xport;
+	u8	tun;
+	u8	xport_tun;
+	u8	lso;
+	u8	extseq;
 	u32	udp_esp;
 	u32	auth;
 	u32	crypto;
@@ -1296,8 +1295,8 @@ struct ndis_ipsecv2_offload {
 };
 
 struct ndis_rsc_offload {
-	u16	ip4;
-	u16	ip6;
+	u8	ip4;
+	u8	ip6;
 };
 
 struct ndis_encap_offload {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d2ee66c259a7..5d5bd513847f 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -31,7 +31,6 @@
 #include <linux/vmalloc.h>
 #include <linux/rtnetlink.h>
 #include <linux/prefetch.h>
-#include <linux/reciprocal_div.h>
 
 #include <asm/sync_bitops.h>
 
@@ -635,17 +634,6 @@ void netvsc_device_remove(struct hv_device *device)
 #define RING_AVAIL_PERCENT_HIWATER 20
 #define RING_AVAIL_PERCENT_LOWATER 10
 
-/*
- * Get the percentage of available bytes to write in the ring.
- * The return value is in range from 0 to 100.
- */
-static u32 hv_ringbuf_avail_percent(const struct hv_ring_buffer_info *ring_info)
-{
-	u32 avail_write = hv_get_bytes_to_write(ring_info);
-
-	return reciprocal_divide(avail_write  * 100, netvsc_ring_reciprocal);
-}
-
 static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
 					 u32 index)
 {
@@ -694,8 +682,8 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
 
 		if (netif_tx_queue_stopped(txq) &&
-		    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
-		     queue_sends < 1)) {
+		    (hv_get_avail_to_write_percent(&channel->outbound) >
+		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
 			netif_tx_wake_queue(txq);
 			ndev_ctx->eth_stats.wake_queue++;
 		}
@@ -802,7 +790,7 @@ static inline int netvsc_send_pkt(
 	struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
 	u64 req_id;
 	int ret;
-	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
+	u32 ring_avail = hv_get_avail_to_write_percent(&out_channel->outbound);
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
 	if (skb)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index bef4d55a108c..fe2256bf1d13 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -35,7 +35,6 @@
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
 #include <linux/netpoll.h>
-#include <linux/reciprocal_div.h>
 
 #include <net/arp.h>
 #include <net/route.h>
@@ -43,7 +42,6 @@
 #include <net/pkt_sched.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
-#include <net/failover.h>
 
 #include "hyperv_net.h"
 
@@ -59,7 +57,6 @@ static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
 unsigned int netvsc_ring_bytes __ro_after_init;
-struct reciprocal_value netvsc_ring_reciprocal __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				NETIF_MSG_LINK | NETIF_MSG_IFUP |
@@ -70,6 +67,8 @@ static int debug = -1;
 module_param(debug, int, 0444);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
+static LIST_HEAD(netvsc_dev_list);
+
 static void netvsc_change_rx_flags(struct net_device *net, int change)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
@@ -127,8 +126,10 @@ static int netvsc_open(struct net_device *net)
 	}
 
 	rdev = nvdev->extension;
-	if (!rdev->link_state)
+	if (!rdev->link_state) {
 		netif_carrier_on(net);
+		netif_tx_wake_all_queues(net);
+	}
 
 	if (vf_netdev) {
 		/* Setting synthetic device up transparently sets
@@ -1780,6 +1781,36 @@ out_unlock:
 	rtnl_unlock();
 }
 
+static struct net_device *get_netvsc_bymac(const u8 *mac)
+{
+	struct net_device_context *ndev_ctx;
+
+	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
+		struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx);
+
+		if (ether_addr_equal(mac, dev->perm_addr))
+			return dev;
+	}
+
+	return NULL;
+}
+
+static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
+{
+	struct net_device_context *net_device_ctx;
+	struct net_device *dev;
+
+	dev = netdev_master_upper_dev_get(vf_netdev);
+	if (!dev || dev->netdev_ops != &device_ops)
+		return NULL;	/* not a netvsc device */
+
+	net_device_ctx = netdev_priv(dev);
+	if (!rtnl_dereference(net_device_ctx->nvdev))
+		return NULL;	/* device is removed */
+
+	return dev;
+}
+
 /* Called when VF is injecting data into network stack.
  * Change the associated network device from VF to netvsc.
  * note: already called with rcu_read_lock
@@ -1802,6 +1833,46 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
 	return RX_HANDLER_ANOTHER;
 }
 
+static int netvsc_vf_join(struct net_device *vf_netdev,
+			  struct net_device *ndev)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	int ret;
+
+	ret = netdev_rx_handler_register(vf_netdev,
+					 netvsc_vf_handle_frame, ndev);
+	if (ret != 0) {
+		netdev_err(vf_netdev,
+			   "can not register netvsc VF receive handler (err = %d)\n",
+			   ret);
+		goto rx_handler_failed;
+	}
+
+	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+					   NULL, NULL, NULL);
+	if (ret != 0) {
+		netdev_err(vf_netdev,
+			   "can not set master device %s (err = %d)\n",
+			   ndev->name, ret);
+		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);
+
+	netdev_info(vf_netdev, "joined to %s\n", ndev->name);
+	return 0;
+
+upper_link_failed:
+	netdev_rx_handler_unregister(vf_netdev);
+rx_handler_failed:
+	return ret;
+}
+
 static void __netvsc_vf_setup(struct net_device *ndev,
 			      struct net_device *vf_netdev)
 {
@@ -1852,95 +1923,104 @@ static void netvsc_vf_setup(struct work_struct *w)
 	rtnl_unlock();
 }
 
-static int netvsc_pre_register_vf(struct net_device *vf_netdev,
-				  struct net_device *ndev)
+static int netvsc_register_vf(struct net_device *vf_netdev)
 {
+	struct net_device *ndev;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
+	int ret;
+
+	if (vf_netdev->addr_len != ETH_ALEN)
+		return NOTIFY_DONE;
+
+	/*
+	 * We will use the MAC address to locate the synthetic interface to
+	 * associate with the VF interface. If we don't find a matching
+	 * synthetic interface, move on.
+	 */
+	ndev = get_netvsc_bymac(vf_netdev->perm_addr);
+	if (!ndev)
+		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
-		return -ENODEV;
-
-	return 0;
-}
+		return NOTIFY_DONE;
 
-static int netvsc_register_vf(struct net_device *vf_netdev,
-			      struct net_device *ndev)
-{
-	struct net_device_context *ndev_ctx = netdev_priv(ndev);
-
-	/* set slave flag before open to prevent IPv6 addrconf */
-	vf_netdev->flags |= IFF_SLAVE;
-
-	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+	/* if syntihetic interface is a different namespace,
+	 * then move the VF to that namespace; join will be
+	 * done again in that context.
+	 */
+	if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
+		ret = dev_change_net_namespace(vf_netdev,
+					       dev_net(ndev), "eth%d");
+		if (ret)
+			netdev_err(vf_netdev,
+				   "could not move to same namespace as %s: %d\n",
+				   ndev->name, ret);
+		else
+			netdev_info(vf_netdev,
+				    "VF moved to namespace with: %s\n",
+				    ndev->name);
+		return NOTIFY_DONE;
+	}
 
-	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
+	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
 
-	netdev_info(vf_netdev, "joined to %s\n", ndev->name);
+	if (netvsc_vf_join(vf_netdev, ndev) != 0)
+		return NOTIFY_DONE;
 
 	dev_hold(vf_netdev);
-	rcu_assign_pointer(ndev_ctx->vf_netdev, vf_netdev);
-
-	return 0;
+	rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
+	return NOTIFY_OK;
 }
 
 /* VF up/down change detected, schedule to change data path */
-static int netvsc_vf_changed(struct net_device *vf_netdev,
-			     struct net_device *ndev)
+static int netvsc_vf_changed(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
+	struct net_device *ndev;
 	bool vf_is_up = netif_running(vf_netdev);
 
+	ndev = get_netvsc_byref(vf_netdev);
+	if (!ndev)
+		return NOTIFY_DONE;
+
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev)
-		return -ENODEV;
+		return NOTIFY_DONE;
 
 	netvsc_switch_datapath(ndev, vf_is_up);
 	netdev_info(ndev, "Data path switched %s VF: %s\n",
 		    vf_is_up ? "to" : "from", vf_netdev->name);
 
-	return 0;
+	return NOTIFY_OK;
 }
 
-static int netvsc_pre_unregister_vf(struct net_device *vf_netdev,
-				    struct net_device *ndev)
+static int netvsc_unregister_vf(struct net_device *vf_netdev)
 {
+	struct net_device *ndev;
 	struct net_device_context *net_device_ctx;
 
-	net_device_ctx = netdev_priv(ndev);
-	cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
-
-	return 0;
-}
-
-static int netvsc_unregister_vf(struct net_device *vf_netdev,
-				struct net_device *ndev)
-{
-	struct net_device_context *net_device_ctx;
+	ndev = get_netvsc_byref(vf_netdev);
+	if (!ndev)
+		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
+	cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
 
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
 
+	netdev_rx_handler_unregister(vf_netdev);
+	netdev_upper_dev_unlink(vf_netdev, ndev);
 	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
 	dev_put(vf_netdev);
 
-	return 0;
+	return NOTIFY_OK;
 }
 
-static struct failover_ops netvsc_failover_ops = {
-	.slave_pre_register	= netvsc_pre_register_vf,
-	.slave_register		= netvsc_register_vf,
-	.slave_pre_unregister	= netvsc_pre_unregister_vf,
-	.slave_unregister	= netvsc_unregister_vf,
-	.slave_link_change	= netvsc_vf_changed,
-	.slave_handle_frame	= netvsc_vf_handle_frame,
-};
-
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
@@ -2024,23 +2104,19 @@ static int netvsc_probe(struct hv_device *dev,
 	else
 		net->max_mtu = ETH_DATA_LEN;
 
-	ret = register_netdev(net);
+	rtnl_lock();
+	ret = register_netdevice(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
 		goto register_failed;
 	}
 
-	net_device_ctx->failover = failover_register(net, &netvsc_failover_ops);
-	if (IS_ERR(net_device_ctx->failover)) {
-		ret = PTR_ERR(net_device_ctx->failover);
-		goto err_failover;
-	}
-
-	return ret;
+	list_add(&net_device_ctx->list, &netvsc_dev_list);
+	rtnl_unlock();
+	return 0;
 
-err_failover:
-	unregister_netdev(net);
 register_failed:
+	rtnl_unlock();
 	rndis_filter_device_remove(dev, nvdev);
 rndis_failed:
 	free_percpu(net_device_ctx->vf_stats);
@@ -2080,14 +2156,13 @@ static int netvsc_remove(struct hv_device *dev)
 	rtnl_lock();
 	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
 	if (vf_netdev)
-		failover_slave_unregister(vf_netdev);
+		netvsc_unregister_vf(vf_netdev);
 
 	if (nvdev)
 		rndis_filter_device_remove(dev, nvdev);
 
 	unregister_netdevice(net);
-
-	failover_unregister(ndev_ctx->failover);
+	list_del(&ndev_ctx->list);
 
 	rtnl_unlock();
 	rcu_read_unlock();
@@ -2115,8 +2190,54 @@ static struct  hv_driver netvsc_drv = {
 	.remove = netvsc_remove,
 };
 
+/*
+ * On Hyper-V, every VF interface is matched with a corresponding
+ * synthetic interface. The synthetic interface is presented first
+ * to the guest. When the corresponding VF instance is registered,
+ * we will take care of switching the data path.
+ */
+static int netvsc_netdev_event(struct notifier_block *this,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+
+	/* Skip our own events */
+	if (event_dev->netdev_ops == &device_ops)
+		return NOTIFY_DONE;
+
+	/* Avoid non-Ethernet type devices */
+	if (event_dev->type != ARPHRD_ETHER)
+		return NOTIFY_DONE;
+
+	/* Avoid Vlan dev with same MAC registering as VF */
+	if (is_vlan_dev(event_dev))
+		return NOTIFY_DONE;
+
+	/* Avoid Bonding master dev with same MAC registering as VF */
+	if ((event_dev->priv_flags & IFF_BONDING) &&
+	    (event_dev->flags & IFF_MASTER))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		return netvsc_register_vf(event_dev);
+	case NETDEV_UNREGISTER:
+		return netvsc_unregister_vf(event_dev);
+	case NETDEV_UP:
+	case NETDEV_DOWN:
+		return netvsc_vf_changed(event_dev);
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block netvsc_netdev_notifier = {
+	.notifier_call = netvsc_netdev_event,
+};
+
 static void __exit netvsc_drv_exit(void)
 {
+	unregister_netdevice_notifier(&netvsc_netdev_notifier);
 	vmbus_driver_unregister(&netvsc_drv);
 }
 
@@ -2130,12 +2251,12 @@ static int __init netvsc_drv_init(void)
 			ring_size);
 	}
 	netvsc_ring_bytes = ring_size * PAGE_SIZE;
-	netvsc_ring_reciprocal = reciprocal_value(netvsc_ring_bytes);
 
 	ret = vmbus_driver_register(&netvsc_drv);
 	if (ret)
 		return ret;
 
+	register_netdevice_notifier(&netvsc_netdev_notifier);
 	return 0;
 }