1 files changed, 104 insertions, 35 deletions

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ebcfbae05690..261e6e55a907 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -367,38 +367,35 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	}
 	rcu_read_unlock();
 
-	while (unlikely(txq >= ndev->real_num_tx_queues))
+	while (txq >= ndev->real_num_tx_queues)
 		txq -= ndev->real_num_tx_queues;
 
 	return txq;
 }
 
-static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
+static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
 		       struct hv_page_buffer *pb)
 {
 	int j = 0;
 
-	/* Deal with compound pages by ignoring unused part
-	 * of the page.
-	 */
-	page += (offset >> PAGE_SHIFT);
-	offset &= ~PAGE_MASK;
+	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
+	offset = offset & ~HV_HYP_PAGE_MASK;
 
 	while (len > 0) {
 		unsigned long bytes;
 
-		bytes = PAGE_SIZE - offset;
+		bytes = HV_HYP_PAGE_SIZE - offset;
 		if (bytes > len)
 			bytes = len;
-		pb[j].pfn = page_to_pfn(page);
+		pb[j].pfn = hvpfn;
 		pb[j].offset = offset;
 		pb[j].len = bytes;
 
 		offset += bytes;
 		len -= bytes;
 
-		if (offset == PAGE_SIZE && len) {
-			page++;
+		if (offset == HV_HYP_PAGE_SIZE && len) {
+			hvpfn++;
 			offset = 0;
 			j++;
 		}
@@ -421,23 +418,26 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_page(hdr),
-				  offset_in_page(hdr),
-				  len, &pb[slots_used]);
+	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
+				  offset_in_hvpage(hdr),
+				  len,
+				  &pb[slots_used]);
 
 	packet->rmsg_size = len;
 	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_page(data),
-				offset_in_page(data),
-				skb_headlen(skb), &pb[slots_used]);
+	slots_used += fill_pg_buf(virt_to_hvpfn(data),
+				  offset_in_hvpage(data),
+				  skb_headlen(skb),
+				  &pb[slots_used]);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
 
-		slots_used += fill_pg_buf(skb_frag_page(frag),
-					skb_frag_off(frag),
-					skb_frag_size(frag), &pb[slots_used]);
+		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
+					  skb_frag_off(frag),
+					  skb_frag_size(frag),
+					  &pb[slots_used]);
 	}
 	return slots_used;
 }
@@ -453,8 +453,8 @@ static int count_skb_frag_slots(struct sk_buff *skb)
 		unsigned long offset = skb_frag_off(frag);
 
 		/* Skip unused frames from start of page */
-		offset &= ~PAGE_MASK;
-		pages += PFN_UP(offset + size);
+		offset &= ~HV_HYP_PAGE_MASK;
+		pages += HVPFN_UP(offset + size);
 	}
 	return pages;
 }
@@ -462,12 +462,12 @@ static int count_skb_frag_slots(struct sk_buff *skb)
 static int netvsc_get_slots(struct sk_buff *skb)
 {
 	char *data = skb->data;
-	unsigned int offset = offset_in_page(data);
+	unsigned int offset = offset_in_hvpage(data);
 	unsigned int len = skb_headlen(skb);
 	int slots;
 	int frag_slots;
 
-	slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+	slots = DIV_ROUND_UP(offset + len, HV_HYP_PAGE_SIZE);
 	frag_slots = count_skb_frag_slots(skb);
 	return slots + frag_slots;
 }
@@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
 	int rc;
 
 	skb->dev = vf_netdev;
-	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+	skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping);
 
 	rc = dev_queue_xmit(skb);
 	if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
@@ -532,12 +532,13 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
-	/* if VF is present and up then redirect packets
-	 * already called with rcu_read_lock_bh
+	/* If VF is present and up then redirect packets to it.
+	 * Skip the VF if it is marked down or has no carrier.
+	 * If netpoll is in uses, then VF can not be used either.
 	 */
 	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
 	if (vf_netdev && netif_running(vf_netdev) &&
-	    !netpoll_tx_running(net))
+	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net))
 		return netvsc_vf_xmit(net, vf_netdev, skb);
 
 	/* We will atmost need two pages to describe the rndis
@@ -605,6 +606,29 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 		*hash_info = hash;
 	}
 
+	/* When using AF_PACKET we need to drop VLAN header from
+	 * the frame and update the SKB to allow the HOST OS
+	 * to transmit the 802.1Q packet
+	 */
+	if (skb->protocol == htons(ETH_P_8021Q)) {
+		u16 vlan_tci;
+
+		skb_reset_mac_header(skb);
+		if (eth_type_vlan(eth_hdr(skb)->h_proto)) {
+			if (unlikely(__skb_vlan_pop(skb, &vlan_tci) != 0)) {
+				++net_device_ctx->eth_stats.vlan_error;
+				goto drop;
+			}
+
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+			/* Update the NDIS header pkt lengths */
+			packet->total_data_buflen -= VLAN_HLEN;
+			packet->total_bytes -= VLAN_HLEN;
+			rndis_msg->msg_len = packet->total_data_buflen;
+			rndis_msg->msg.pkt.data_len = packet->total_data_buflen;
+		}
+	}
+
 	if (skb_vlan_tag_present(skb)) {
 		struct ndis_pkt_8021q_info *vlan;
 
@@ -724,6 +748,13 @@ void netvsc_linkstatus_callback(struct net_device *net,
 	struct netvsc_reconfig *event;
 	unsigned long flags;
 
+	/* Ensure the packet is big enough to access its fields */
+	if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) {
+		netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n",
+			   resp->msg_len);
+		return;
+	}
+
 	/* Update the physical link speed when changing to another vSwitch */
 	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
 		u32 speed;
@@ -795,7 +826,7 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	if (xbuf) {
 		unsigned int hdroom = xdp->data - xdp->data_hard_start;
 		unsigned int xlen = xdp->data_end - xdp->data;
-		unsigned int frag_size = netvsc_xdp_fraglen(hdroom + xlen);
+		unsigned int frag_size = xdp->frame_sz;
 
 		skb = build_skb(xbuf, frag_size);
 
@@ -1427,6 +1458,7 @@ static const struct {
 	{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
 	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
 	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
+	{ "vlan_error", offsetof(struct netvsc_ethtool_stats, vlan_error) },
 }, pcpu_stats[] = {
 	{ "cpu%u_rx_packets",
 		offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
@@ -1934,6 +1966,23 @@ syncvf:
 	return ret;
 }
 
+static int netvsc_get_regs_len(struct net_device *netdev)
+{
+	return VRSS_SEND_TAB_SIZE * sizeof(u32);
+}
+
+static void netvsc_get_regs(struct net_device *netdev,
+			    struct ethtool_regs *regs, void *p)
+{
+	struct net_device_context *ndc = netdev_priv(netdev);
+	u32 *regs_buff = p;
+
+	/* increase the version, if buffer format is changed. */
+	regs->version = 1;
+
+	memcpy(regs_buff, ndc->tx_table, VRSS_SEND_TAB_SIZE * sizeof(u32));
+}
+
 static u32 netvsc_get_msglevel(struct net_device *ndev)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
@@ -1950,6 +1999,8 @@ static void netvsc_set_msglevel(struct net_device *ndev, u32 val)
 
 static const struct ethtool_ops ethtool_ops = {
 	.get_drvinfo	= netvsc_get_drvinfo,
+	.get_regs_len	= netvsc_get_regs_len,
+	.get_regs	= netvsc_get_regs,
 	.get_msglevel	= netvsc_get_msglevel,
 	.set_msglevel	= netvsc_set_msglevel,
 	.get_link	= ethtool_op_get_link,
@@ -2322,7 +2373,16 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
-/* VF up/down change detected, schedule to change data path */
+/* Change the data path when VF UP/DOWN/CHANGE are detected.
+ *
+ * Typically a UP or DOWN event is followed by a CHANGE event, so
+ * net_device_ctx->data_path_is_vf is used to cache the current data path
+ * to avoid the duplicate call of netvsc_switch_datapath() and the duplicate
+ * message.
+ *
+ * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network
+ * interface, there is only the CHANGE event and no UP or DOWN event.
+ */
 static int netvsc_vf_changed(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2339,6 +2399,10 @@ static int netvsc_vf_changed(struct net_device *vf_netdev)
 	if (!netvsc_dev)
 		return NOTIFY_DONE;
 
+	if (net_device_ctx->data_path_is_vf == vf_is_up)
+		return NOTIFY_OK;
+	net_device_ctx->data_path_is_vf = vf_is_up;
+
 	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);
@@ -2457,6 +2521,8 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
+	netdev_lockdep_set_classes(net);
+
 	/* MTU range: 68 - 1500 or 65521 */
 	net->min_mtu = NETVSC_MTU_MIN;
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
@@ -2541,8 +2607,8 @@ static int netvsc_remove(struct hv_device *dev)
 static int netvsc_suspend(struct hv_device *dev)
 {
 	struct net_device_context *ndev_ctx;
-	struct net_device *vf_netdev, *net;
 	struct netvsc_device *nvdev;
+	struct net_device *net;
 	int ret;
 
 	net = hv_get_drvdata(dev);
@@ -2558,10 +2624,6 @@ static int netvsc_suspend(struct hv_device *dev)
 		goto out;
 	}
 
-	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
-	if (vf_netdev)
-		netvsc_unregister_vf(vf_netdev);
-
 	/* Save the current config info */
 	ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);
 
@@ -2582,6 +2644,12 @@ static int netvsc_resume(struct hv_device *dev)
 	rtnl_lock();
 
 	net_device_ctx = netdev_priv(net);
+
+	/* Reset the data path to the netvsc NIC before re-opening the vmbus
+	 * channel. Later netvsc_netdev_event() will switch the data path to
+	 * the VF upon the UP or CHANGE event.
+	 */
+	net_device_ctx->data_path_is_vf = false;
 	device_info = net_device_ctx->saved_netvsc_dev_info;
 
 	ret = netvsc_attach(net, device_info);
@@ -2649,6 +2717,7 @@ static int netvsc_netdev_event(struct notifier_block *this,
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
 	case NETDEV_DOWN:
+	case NETDEV_CHANGE:
 		return netvsc_vf_changed(event_dev);
 	default:
 		return NOTIFY_DONE;