3 files changed, 91 insertions, 35 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 59ac04a610ad..442c520ab8f3 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -269,7 +269,7 @@ int rndis_filter_receive(struct net_device *ndev,
 int rndis_filter_set_device_mac(struct netvsc_device *ndev,
 				const char *mac);
 
-void netvsc_switch_datapath(struct net_device *nv_dev, bool vf);
+int netvsc_switch_datapath(struct net_device *nv_dev, bool vf);
 
 #define NVSP_INVALID_PROTOCOL_VERSION	((u32)0xFFFFFFFF)
 
@@ -1718,4 +1718,8 @@ struct rndis_message {
 #define TRANSPORT_INFO_IPV6_TCP 0x10
 #define TRANSPORT_INFO_IPV6_UDP 0x20
 
+#define RETRY_US_LO	5000
+#define RETRY_US_HI	10000
+#define RETRY_MAX	2000	/* >10 sec */
+
 #endif /* _HYPERV_NET_H */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index c64cc7639c39..9d07c9ce4be2 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -31,12 +31,13 @@
  * Switch the data path from the synthetic interface to the VF
  * interface.
  */
-void netvsc_switch_datapath(struct net_device *ndev, bool vf)
+int netvsc_switch_datapath(struct net_device *ndev, bool vf)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct hv_device *dev = net_device_ctx->device_ctx;
 	struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev);
 	struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt;
+	int ret, retry = 0;
 
 	/* Block sending traffic to VF if it's about to be gone */
 	if (!vf)
@@ -51,15 +52,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 		init_pkt->msg.v4_msg.active_dp.active_datapath =
 			NVSP_DATAPATH_SYNTHETIC;
 
+again:
 	trace_nvsp_send(ndev, init_pkt);
 
-	vmbus_sendpacket(dev->channel, init_pkt,
+	ret = vmbus_sendpacket(dev->channel, init_pkt,
 			       sizeof(struct nvsp_message),
-			       (unsigned long)init_pkt,
-			       VM_PKT_DATA_INBAND,
+			       (unsigned long)init_pkt, VM_PKT_DATA_INBAND,
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+
+	/* If failed to switch to/from VF, let data_path_is_vf stay false,
+	 * so we use synthetic path to send data.
+	 */
+	if (ret) {
+		if (ret != -EAGAIN) {
+			netdev_err(ndev,
+				   "Unable to send sw datapath msg, err: %d\n",
+				   ret);
+			return ret;
+		}
+
+		if (retry++ < RETRY_MAX) {
+			usleep_range(RETRY_US_LO, RETRY_US_HI);
+			goto again;
+		} else {
+			netdev_err(
+				ndev,
+				"Retry failed to send sw datapath msg, err: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
 	wait_for_completion(&nv_dev->channel_init_wait);
 	net_device_ctx->data_path_is_vf = vf;
+
+	return 0;
 }
 
 /* Worker to setup sub channels on initial setup
@@ -1017,6 +1044,26 @@ static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
 }
 
 /* RCU already held by caller */
+/* Batching/bouncing logic is designed to attempt to optimize
+ * performance.
+ *
+ * For small, non-LSO packets we copy the packet to a send buffer
+ * which is pre-registered with the Hyper-V side. This enables the
+ * hypervisor to avoid remapping the aperture to access the packet
+ * descriptor and data.
+ *
+ * If we already started using a buffer and the netdev is transmitting
+ * a burst of packets, keep on copying into the buffer until it is
+ * full or we are done collecting a burst. If there is an existing
+ * buffer with space for the RNDIS descriptor but not the packet, copy
+ * the RNDIS descriptor to the buffer, keeping the packet in place.
+ *
+ * If we do batching and send more than one packet using a single
+ * NetVSC message, free the SKBs of the packets copied, except for the
+ * last packet. This is done to streamline the handling of the case
+ * where the last packet only had the RNDIS descriptor copied to the
+ * send buffer, with the data pointers included in the NetVSC message.
+ */
 int netvsc_send(struct net_device *ndev,
 		struct hv_netvsc_packet *packet,
 		struct rndis_message *rndis_msg,
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 15f262b70489..f682a5572d84 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -38,9 +38,6 @@
 #include "hyperv_net.h"
 
 #define RING_SIZE_MIN	64
-#define RETRY_US_LO	5000
-#define RETRY_US_HI	10000
-#define RETRY_MAX	2000	/* >10 sec */
 
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
@@ -1612,34 +1609,23 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++) {
-			memcpy(p, netvsc_stats[i].name, ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
+		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
+			ethtool_sprintf(&p, netvsc_stats[i].name);
 
-		for (i = 0; i < ARRAY_SIZE(vf_stats); i++) {
-			memcpy(p, vf_stats[i].name, ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
+		for (i = 0; i < ARRAY_SIZE(vf_stats); i++)
+			ethtool_sprintf(&p, vf_stats[i].name);
 
 		for (i = 0; i < nvdev->num_chn; i++) {
-			sprintf(p, "tx_queue_%u_packets", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "tx_queue_%u_bytes", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_packets", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_bytes", i);
-			p += ETH_GSTRING_LEN;
-			sprintf(p, "rx_queue_%u_xdp_drop", i);
-			p += ETH_GSTRING_LEN;
+			ethtool_sprintf(&p, "tx_queue_%u_packets", i);
+			ethtool_sprintf(&p, "tx_queue_%u_bytes", i);
+			ethtool_sprintf(&p, "rx_queue_%u_packets", i);
+			ethtool_sprintf(&p, "rx_queue_%u_bytes", i);
+			ethtool_sprintf(&p, "rx_queue_%u_xdp_drop", i);
 		}
 
 		for_each_present_cpu(cpu) {
-			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) {
-				sprintf(p, pcpu_stats[i].name, cpu);
-				p += ETH_GSTRING_LEN;
-			}
+			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++)
+				ethtool_sprintf(&p, pcpu_stats[i].name, cpu);
 		}
 
 		break;
@@ -2311,6 +2297,7 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 {
 	struct device *parent = vf_netdev->dev.parent;
 	struct net_device_context *ndev_ctx;
+	struct net_device *ndev;
 	struct pci_dev *pdev;
 	u32 serial;
 
@@ -2333,8 +2320,17 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 		if (!ndev_ctx->vf_alloc)
 			continue;
 
-		if (ndev_ctx->vf_serial == serial)
-			return hv_get_drvdata(ndev_ctx->device_ctx);
+		if (ndev_ctx->vf_serial != serial)
+			continue;
+
+		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
+		if (ndev->addr_len != vf_netdev->addr_len ||
+		    memcmp(ndev->perm_addr, vf_netdev->perm_addr,
+			   ndev->addr_len) != 0)
+			continue;
+
+		return ndev;
+
 	}
 
 	netdev_notice(vf_netdev,
@@ -2413,6 +2409,7 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
 	struct netvsc_device *netvsc_dev;
 	struct net_device *ndev;
 	bool vf_is_up = false;
+	int ret;
 
 	if (event != NETDEV_GOING_DOWN)
 		vf_is_up = netif_running(vf_netdev);
@@ -2429,9 +2426,17 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
 	if (net_device_ctx->data_path_is_vf == vf_is_up)
 		return NOTIFY_OK;
 
-	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);
+	ret = netvsc_switch_datapath(ndev, vf_is_up);
+
+	if (ret) {
+		netdev_err(ndev,
+			   "Data path failed to switch %s VF: %s, err: %d\n",
+			   vf_is_up ? "to" : "from", vf_netdev->name, ret);
+		return NOTIFY_DONE;
+	} else {
+		netdev_info(ndev, "Data path switched %s VF: %s\n",
+			    vf_is_up ? "to" : "from", vf_netdev->name);
+	}
 
 	return NOTIFY_OK;
 }