Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

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;
 }