3 files changed, 94 insertions, 197 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 284b97b6b258..f4fbcb5aa24a 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -433,7 +433,7 @@ struct nvsp_1_message_revoke_send_buffer {
  */
 struct nvsp_1_message_send_rndis_packet {
 	/*
-	 * This field is specified by RNIDS. They assume there's two different
+	 * This field is specified by RNDIS. They assume there's two different
 	 * channels of communication. However, the Network VSP only has one.
 	 * Therefore, the channel travels with the RNDIS packet.
 	 */
@@ -578,7 +578,7 @@ struct nvsp_5_send_indirect_table {
 	/* The number of entries in the send indirection table */
 	u32 count;
 
-	/* The offset of the send indireciton table from top of this struct.
+	/* The offset of the send indirection table from top of this struct.
 	 * The send indirection table tells which channel to put the send
 	 * traffic on. Each entry is a channel number.
 	 */
@@ -649,6 +649,8 @@ struct multi_recv_comp {
 struct netvsc_stats {
 	u64 packets;
 	u64 bytes;
+	u64 broadcast;
+	u64 multicast;
 	struct u64_stats_sync syncp;
 };
 
@@ -695,9 +697,8 @@ struct net_device_context {
 	bool start_remove;
 
 	/* State to manage the associated VF interface. */
-	struct net_device *vf_netdev;
-	bool vf_inject;
-	atomic_t vf_use_cnt;
+	struct net_device __rcu *vf_netdev;
+
 	/* 1: allocated, serial number is valid. 0: not allocated */
 	u32 vf_alloc;
 	/* Serial number of the VF to team with */
@@ -733,7 +734,6 @@ struct netvsc_device {
 	struct nvsp_message channel_init_pkt;
 
 	struct nvsp_message revoke_packet;
-	/* unsigned char HwMacAddr[HW_MACADDR_LEN]; */
 
 	struct vmbus_channel *chn_table[VRSS_CHANNEL_MAX];
 	u32 send_table[VRSS_SEND_TAB_SIZE];
@@ -1238,7 +1238,7 @@ struct rndis_message {
 	u32 ndis_msg_type;
 
 	/* Total length of this message, from the beginning */
-	/* of the sruct rndis_message, in bytes. */
+	/* of the struct rndis_message, in bytes. */
 	u32 msg_len;
 
 	/* Actual message */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 2a9ccc4d9e3c..720b5fa9e625 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -34,89 +34,6 @@
 #include "hyperv_net.h"
 
 /*
- * An API to support in-place processing of incoming VMBUS packets.
- */
-#define VMBUS_PKT_TRAILER	8
-
-static struct vmpacket_descriptor *
-get_next_pkt_raw(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 read_loc = ring_info->priv_read_index;
-	void *ring_buffer = hv_get_ring_buffer(ring_info);
-	struct vmpacket_descriptor *cur_desc;
-	u32 packetlen;
-	u32 dsize = ring_info->ring_datasize;
-	u32 delta = read_loc - ring_info->ring_buffer->read_index;
-	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
-
-	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
-		return NULL;
-
-	if ((read_loc + sizeof(*cur_desc)) > dsize)
-		return NULL;
-
-	cur_desc = ring_buffer + read_loc;
-	packetlen = cur_desc->len8 << 3;
-
-	/*
-	 * If the packet under consideration is wrapping around,
-	 * return failure.
-	 */
-	if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1))
-		return NULL;
-
-	return cur_desc;
-}
-
-/*
- * A helper function to step through packets "in-place"
- * This API is to be called after each successful call
- * get_next_pkt_raw().
- */
-static void put_pkt_raw(struct vmbus_channel *channel,
-			struct vmpacket_descriptor *desc)
-{
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 read_loc = ring_info->priv_read_index;
-	u32 packetlen = desc->len8 << 3;
-	u32 dsize = ring_info->ring_datasize;
-
-	BUG_ON((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize);
-
-	/*
-	 * Include the packet trailer.
-	 */
-	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
-}
-
-/*
- * This call commits the read index and potentially signals the host.
- * Here is the pattern for using the "in-place" consumption APIs:
- *
- * while (get_next_pkt_raw() {
- *	process the packet "in-place";
- *	put_pkt_raw();
- * }
- * if (packets processed in place)
- *	commit_rd_index();
- */
-static void commit_rd_index(struct vmbus_channel *channel)
-{
-	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	/*
-	 * Make sure all reads are done before we update the read index since
-	 * the writer may start writing to the read area once the read index
-	 * is updated.
-	 */
-	virt_rmb();
-	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
-
-	if (hv_need_to_signal_on_read(ring_info))
-		vmbus_set_event(channel);
-}
-
-/*
  * Switch the data path from the synthetic interface to the VF
  * interface.
  */
@@ -718,7 +635,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 		q_idx = nvsc_packet->q_idx;
 		channel = incoming_channel;
 
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 	}
 
 	num_outstanding_sends =
@@ -840,7 +757,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 	return msg_size;
 }
 
-static int netvsc_send_pkt(
+static inline int netvsc_send_pkt(
 	struct hv_device *device,
 	struct hv_netvsc_packet *packet,
 	struct netvsc_device *net_device,
@@ -1027,7 +944,7 @@ int netvsc_send(struct hv_device *device,
 		}
 
 		if (msdp->skb)
-			dev_kfree_skb_any(msdp->skb);
+			dev_consume_skb_any(msdp->skb);
 
 		if (xmit_more && !packet->cp_partial) {
 			msdp->skb = skb;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 2360e704e271..52eeb2f67276 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -667,51 +667,23 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 {
 	struct net_device *net = hv_get_drvdata(device_obj);
 	struct net_device_context *net_device_ctx = netdev_priv(net);
+	struct net_device *vf_netdev;
 	struct sk_buff *skb;
-	struct sk_buff *vf_skb;
 	struct netvsc_stats *rx_stats;
-	u32 bytes_recvd = packet->total_data_buflen;
-	int ret = 0;
 
-	if (!net || net->reg_state != NETREG_REGISTERED)
+	if (net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
 
-	if (READ_ONCE(net_device_ctx->vf_inject)) {
-		atomic_inc(&net_device_ctx->vf_use_cnt);
-		if (!READ_ONCE(net_device_ctx->vf_inject)) {
-			/*
-			 * We raced; just move on.
-			 */
-			atomic_dec(&net_device_ctx->vf_use_cnt);
-			goto vf_injection_done;
-		}
-
-		/*
-		 * Inject this packet into the VF inerface.
-		 * On Hyper-V, multicast and brodcast packets
-		 * are only delivered on the synthetic interface
-		 * (after subjecting these to policy filters on
-		 * the host). Deliver these via the VF interface
-		 * in the guest.
-		 */
-		vf_skb = netvsc_alloc_recv_skb(net_device_ctx->vf_netdev,
-					       packet, csum_info, *data,
-					       vlan_tci);
-		if (vf_skb != NULL) {
-			++net_device_ctx->vf_netdev->stats.rx_packets;
-			net_device_ctx->vf_netdev->stats.rx_bytes +=
-				bytes_recvd;
-			netif_receive_skb(vf_skb);
-		} else {
-			++net->stats.rx_dropped;
-			ret = NVSP_STAT_FAIL;
-		}
-		atomic_dec(&net_device_ctx->vf_use_cnt);
-		return ret;
-	}
-
-vf_injection_done:
-	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
+	/*
+	 * If necessary, inject this packet into the VF interface.
+	 * On Hyper-V, multicast and brodcast packets are only delivered
+	 * to the synthetic interface (after subjecting these to
+	 * policy filters on the host). Deliver these via the VF
+	 * interface in the guest.
+	 */
+	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
+	if (vf_netdev && (vf_netdev->flags & IFF_UP))
+		net = vf_netdev;
 
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci);
@@ -719,12 +691,25 @@ vf_injection_done:
 		++net->stats.rx_dropped;
 		return NVSP_STAT_FAIL;
 	}
-	skb_record_rx_queue(skb, channel->
-			    offermsg.offer.sub_channel_index);
 
+	if (net != vf_netdev)
+		skb_record_rx_queue(skb,
+				    channel->offermsg.offer.sub_channel_index);
+
+	/*
+	 * Even if injecting the packet, record the statistics
+	 * on the synthetic device because modifying the VF device
+	 * statistics will not work correctly.
+	 */
+	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->packets++;
 	rx_stats->bytes += packet->total_data_buflen;
+
+	if (skb->pkt_type == PACKET_BROADCAST)
+		++rx_stats->broadcast;
+	else if (skb->pkt_type == PACKET_MULTICAST)
+		++rx_stats->multicast;
 	u64_stats_update_end(&rx_stats->syncp);
 
 	/*
@@ -967,7 +952,7 @@ static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
 							    cpu);
 		struct netvsc_stats *rx_stats = per_cpu_ptr(ndev_ctx->rx_stats,
 							    cpu);
-		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
+		u64 tx_packets, tx_bytes, rx_packets, rx_bytes, rx_multicast;
 		unsigned int start;
 
 		do {
@@ -980,12 +965,14 @@ static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
 			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
 			rx_packets = rx_stats->packets;
 			rx_bytes = rx_stats->bytes;
+			rx_multicast = rx_stats->multicast + rx_stats->broadcast;
 		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
 
 		t->tx_bytes	+= tx_bytes;
 		t->tx_packets	+= tx_packets;
 		t->rx_bytes	+= rx_bytes;
 		t->rx_packets	+= rx_packets;
+		t->multicast	+= rx_multicast;
 	}
 
 	t->tx_dropped	= net->stats.tx_dropped;
@@ -1215,22 +1202,44 @@ static void netvsc_free_netdev(struct net_device *netdev)
 	free_netdev(netdev);
 }
 
-static struct net_device *get_netvsc_net_device(char *mac)
+static struct net_device *get_netvsc_bymac(const u8 *mac)
 {
-	struct net_device *dev, *found = NULL;
+	struct net_device *dev;
 
 	ASSERT_RTNL();
 
 	for_each_netdev(&init_net, dev) {
-		if (memcmp(dev->dev_addr, mac, ETH_ALEN) == 0) {
-			if (dev->netdev_ops != &device_ops)
-				continue;
-			found = dev;
-			break;
-		}
+		if (dev->netdev_ops != &device_ops)
+			continue;	/* not a netvsc device */
+
+		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 *dev;
+
+	ASSERT_RTNL();
+
+	for_each_netdev(&init_net, dev) {
+		struct net_device_context *net_device_ctx;
+
+		if (dev->netdev_ops != &device_ops)
+			continue;	/* not a netvsc device */
+
+		net_device_ctx = netdev_priv(dev);
+		if (net_device_ctx->nvdev == NULL)
+			continue;	/* device is removed */
+
+		if (rtnl_dereference(net_device_ctx->vf_netdev) == vf_netdev)
+			return dev;	/* a match */
 	}
 
-	return found;
+	return NULL;
 }
 
 static int netvsc_register_vf(struct net_device *vf_netdev)
@@ -1238,9 +1247,8 @@ 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;
-	const struct ethtool_ops *eth_ops = vf_netdev->ethtool_ops;
 
-	if (eth_ops == NULL || eth_ops == &ethtool_ops)
+	if (vf_netdev->addr_len != ETH_ALEN)
 		return NOTIFY_DONE;
 
 	/*
@@ -1248,13 +1256,13 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	 * associate with the VF interface. If we don't find a matching
 	 * synthetic interface, move on.
 	 */
-	ndev = get_netvsc_net_device(vf_netdev->dev_addr);
+	ndev = get_netvsc_bymac(vf_netdev->perm_addr);
 	if (!ndev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = net_device_ctx->nvdev;
-	if (!netvsc_dev || net_device_ctx->vf_netdev)
+	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
 		return NOTIFY_DONE;
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
@@ -1262,46 +1270,26 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	 * Take a reference on the module.
 	 */
 	try_module_get(THIS_MODULE);
-	net_device_ctx->vf_netdev = vf_netdev;
-	return NOTIFY_OK;
-}
 
-static void netvsc_inject_enable(struct net_device_context *net_device_ctx)
-{
-	net_device_ctx->vf_inject = true;
-}
-
-static void netvsc_inject_disable(struct net_device_context *net_device_ctx)
-{
-	net_device_ctx->vf_inject = false;
-
-	/* Wait for currently active users to drain out. */
-	while (atomic_read(&net_device_ctx->vf_use_cnt) != 0)
-		udelay(50);
+	dev_hold(vf_netdev);
+	rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
+	return NOTIFY_OK;
 }
 
 static int netvsc_vf_up(struct net_device *vf_netdev)
 {
 	struct net_device *ndev;
 	struct netvsc_device *netvsc_dev;
-	const struct ethtool_ops *eth_ops = vf_netdev->ethtool_ops;
 	struct net_device_context *net_device_ctx;
 
-	if (eth_ops == &ethtool_ops)
-		return NOTIFY_DONE;
-
-	ndev = get_netvsc_net_device(vf_netdev->dev_addr);
+	ndev = get_netvsc_byref(vf_netdev);
 	if (!ndev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = net_device_ctx->nvdev;
 
-	if (!netvsc_dev || !net_device_ctx->vf_netdev)
-		return NOTIFY_DONE;
-
 	netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
-	netvsc_inject_enable(net_device_ctx);
 
 	/*
 	 * Open the device before switching data path.
@@ -1327,23 +1315,15 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
 	struct net_device *ndev;
 	struct netvsc_device *netvsc_dev;
 	struct net_device_context *net_device_ctx;
-	const struct ethtool_ops *eth_ops = vf_netdev->ethtool_ops;
-
-	if (eth_ops == &ethtool_ops)
-		return NOTIFY_DONE;
 
-	ndev = get_netvsc_net_device(vf_netdev->dev_addr);
+	ndev = get_netvsc_byref(vf_netdev);
 	if (!ndev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = net_device_ctx->nvdev;
 
-	if (!netvsc_dev || !net_device_ctx->vf_netdev)
-		return NOTIFY_DONE;
-
 	netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
-	netvsc_inject_disable(net_device_ctx);
 	netvsc_switch_datapath(ndev, false);
 	netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
 	rndis_filter_close(netvsc_dev);
@@ -1359,23 +1339,19 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 {
 	struct net_device *ndev;
 	struct netvsc_device *netvsc_dev;
-	const struct ethtool_ops *eth_ops = vf_netdev->ethtool_ops;
 	struct net_device_context *net_device_ctx;
 
-	if (eth_ops == &ethtool_ops)
-		return NOTIFY_DONE;
-
-	ndev = get_netvsc_net_device(vf_netdev->dev_addr);
+	ndev = get_netvsc_byref(vf_netdev);
 	if (!ndev)
 		return NOTIFY_DONE;
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = net_device_ctx->nvdev;
-	if (!netvsc_dev || !net_device_ctx->vf_netdev)
-		return NOTIFY_DONE;
+
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
-	netvsc_inject_disable(net_device_ctx);
-	net_device_ctx->vf_netdev = NULL;
+
+	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
+	dev_put(vf_netdev);
 	module_put(THIS_MODULE);
 	return NOTIFY_OK;
 }
@@ -1427,10 +1403,6 @@ static int netvsc_probe(struct hv_device *dev,
 	spin_lock_init(&net_device_ctx->lock);
 	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
 
-	atomic_set(&net_device_ctx->vf_use_cnt, 0);
-	net_device_ctx->vf_netdev = NULL;
-	net_device_ctx->vf_inject = false;
-
 	net->netdev_ops = &device_ops;
 
 	net->hw_features = NETVSC_HW_FEATURES;
@@ -1539,13 +1511,21 @@ static int netvsc_netdev_event(struct notifier_block *this,
 {
 	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 (event_dev->priv_flags & IFF_802_1Q_VLAN)
 		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)
+	if ((event_dev->priv_flags & IFF_BONDING) &&
+	    (event_dev->flags & IFF_MASTER))
 		return NOTIFY_DONE;
 
 	switch (event) {