Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Remove socket skb caches

   - Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
     avoid memory accounting overhead on each message sent

   - Introduce managed neighbor entries - added by control plane and
     resolved by the kernel for use in acceleration paths (BPF / XDP
     right now, HW offload users will benefit as well)

   - Make neighbor eviction on link down controllable by userspace to
     work around WiFi networks with bad roaming implementations

   - vrf: Rework interaction with netfilter/conntrack

   - fq_codel: implement L4S style ce_threshold_ect1 marking

   - sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()

  BPF:

   - Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
     as implemented in LLVM14

   - Introduce bpf_get_branch_snapshot() to capture Last Branch Records

   - Implement variadic trace_printk helper

   - Add a new Bloomfilter map type

   - Track <8-byte scalar spill and refill

   - Access hw timestamp through BPF's __sk_buff

   - Disallow unprivileged BPF by default

   - Document BPF licensing

  Netfilter:

   - Introduce egress hook for looking at raw outgoing packets

   - Allow matching on and modifying inner headers / payload data

   - Add NFT_META_IFTYPE to match on the interface type either from
     ingress or egress

  Protocols:

   - Multi-Path TCP:
      - increase default max additional subflows to 2
      - rework forward memory allocation
      - add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS

   - MCTP flow support allowing lower layer drivers to configure msg
     muxing as needed

   - Automatic Multicast Tunneling (AMT) driver based on RFC7450

   - HSR support the redbox supervision frames (IEC-62439-3:2018)

   - Support for the ip6ip6 encapsulation of IOAM

   - Netlink interface for CAN-FD's Transmitter Delay Compensation

   - Support SMC-Rv2 eliminating the current same-subnet restriction, by
     exploiting the UDP encapsulation feature of RoCE adapters

   - TLS: add SM4 GCM/CCM crypto support

   - Bluetooth: initial support for link quality and audio/codec offload

  Driver APIs:

   - Add a batched interface for RX buffer allocation in AF_XDP buffer
     pool

   - ethtool: Add ability to control transceiver modules' power mode

   - phy: Introduce supported interfaces bitmap to express MAC
     capabilities and simplify PHY code

   - Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks

  New drivers:

   - WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)

   - Ethernet driver for ASIX AX88796C SPI device (x88796c)

  Drivers:

   - Broadcom PHYs
      - support 72165, 7712 16nm PHYs
      - support IDDQ-SR for additional power savings

   - PHY support for QCA8081, QCA9561 PHYs

   - NXP DPAA2: support for IRQ coalescing

   - NXP Ethernet (enetc): support for software TCP segmentation

   - Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
     Gigabit-capable IP found on RZ/G2L SoC

   - Intel 100G Ethernet
      - support for eswitch offload of TC/OvS flow API, including
        offload of GRE, VxLAN, Geneve tunneling
      - support application device queues - ability to assign Rx and Tx
        queues to application threads
      - PTP and PPS (pulse-per-second) extensions

   - Broadcom Ethernet (bnxt)
      - devlink health reporting and device reload extensions

   - Mellanox Ethernet (mlx5)
      - offload macvlan interfaces
      - support HW offload of TC rules involving OVS internal ports
      - support HW-GRO and header/data split
      - support application device queues

   - Marvell OcteonTx2:
      - add XDP support for PF
      - add PTP support for VF

   - Qualcomm Ethernet switch (qca8k): support for QCA8328

   - Realtek Ethernet DSA switch (rtl8366rb)
      - support bridge offload
      - support STP, fast aging, disabling address learning
      - support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch

   - Mellanox Ethernet/IB switch (mlxsw)
      - multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
      - offload root TBF qdisc as port shaper
      - support multiple routing interface MAC address prefixes
      - support for IP-in-IP with IPv6 underlay

   - MediaTek WiFi (mt76)
      - mt7921 - ASPM, 6GHz, SDIO and testmode support
      - mt7915 - LED and TWT support

   - Qualcomm WiFi (ath11k)
      - include channel rx and tx time in survey dump statistics
      - support for 80P80 and 160 MHz bandwidths
      - support channel 2 in 6 GHz band
      - spectral scan support for QCN9074
      - support for rx decapsulation offload (data frames in 802.3
        format)

   - Qualcomm phone SoC WiFi (wcn36xx)
      - enable Idle Mode Power Save (IMPS) to reduce power consumption
        during idle

   - Bluetooth driver support for MediaTek MT7922 and MT7921

   - Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
     Realtek 8822C/8852A

   - Microsoft vNIC driver (mana)
      - support hibernation and kexec

   - Google vNIC driver (gve)
      - support for jumbo frames
      - implement Rx page reuse

  Refactor:

   - Make all writes to netdev->dev_addr go thru helpers, so that we can
     add this address to the address rbtree and handle the updates

   - Various TCP cleanups and optimizations including improvements to
     CPU cache use

   - Simplify the gnet_stats, Qdisc stats' handling and remove
     qdisc->running sequence counter

   - Driver changes and API updates to address devlink locking
     deficiencies"

* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
  Revert "net: avoid double accounting for pure zerocopy skbs"
  selftests: net: add arp_ndisc_evict_nocarrier
  net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
  net: arp: introduce arp_evict_nocarrier sysctl parameter
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
  net: avoid double accounting for pure zerocopy skbs
  tcp: rename sk_wmem_free_skb
  netdevsim: fix uninit value in nsim_drv_configure_vfs()
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  ...

1 files changed, 44 insertions, 6 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4ad25a8b0870..cc79343cd220 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -80,6 +80,7 @@ struct virtnet_sq_stats {
 	u64 xdp_tx;
 	u64 xdp_tx_drops;
 	u64 kicks;
+	u64 tx_timeouts;
 };
 
 struct virtnet_rq_stats {
@@ -103,6 +104,7 @@ static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
 	{ "xdp_tx",		VIRTNET_SQ_STAT(xdp_tx) },
 	{ "xdp_tx_drops",	VIRTNET_SQ_STAT(xdp_tx_drops) },
 	{ "kicks",		VIRTNET_SQ_STAT(kicks) },
+	{ "tx_timeouts",	VIRTNET_SQ_STAT(tx_timeouts) },
 };
 
 static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
@@ -732,6 +734,12 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		dev->stats.rx_length_errors++;
 		goto err_len;
 	}
+
+	if (likely(!vi->xdp_enabled)) {
+		xdp_prog = NULL;
+		goto skip_xdp;
+	}
+
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -814,6 +822,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
+skip_xdp:
 	skb = build_skb(buf, buflen);
 	if (!skb) {
 		put_page(page);
@@ -895,6 +904,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		dev->stats.rx_length_errors++;
 		goto err_skb;
 	}
+
+	if (likely(!vi->xdp_enabled)) {
+		xdp_prog = NULL;
+		goto skip_xdp;
+	}
+
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -1022,6 +1037,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
+skip_xdp:
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
 			       metasize, headroom);
 	curr_skb = head_skb;
@@ -1860,7 +1876,7 @@ static void virtnet_stats(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		u64 tpackets, tbytes, rpackets, rbytes, rdrops;
+		u64 tpackets, tbytes, terrors, rpackets, rbytes, rdrops;
 		struct receive_queue *rq = &vi->rq[i];
 		struct send_queue *sq = &vi->sq[i];
 
@@ -1868,6 +1884,7 @@ static void virtnet_stats(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&sq->stats.syncp);
 			tpackets = sq->stats.packets;
 			tbytes   = sq->stats.bytes;
+			terrors  = sq->stats.tx_timeouts;
 		} while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start));
 
 		do {
@@ -1882,6 +1899,7 @@ static void virtnet_stats(struct net_device *dev,
 		tot->rx_bytes   += rbytes;
 		tot->tx_bytes   += tbytes;
 		tot->rx_dropped += rdrops;
+		tot->tx_errors  += terrors;
 	}
 
 	tot->tx_dropped = dev->stats.tx_dropped;
@@ -2534,8 +2552,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	/* XDP requires extra queues for XDP_TX */
 	if (curr_qp + xdp_qp > vi->max_queue_pairs) {
-		netdev_warn(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n",
-			    curr_qp + xdp_qp, vi->max_queue_pairs);
+		netdev_warn_once(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n",
+				 curr_qp + xdp_qp, vi->max_queue_pairs);
 		xdp_qp = 0;
 	}
 
@@ -2663,6 +2681,21 @@ static int virtnet_set_features(struct net_device *dev,
 	return 0;
 }
 
+static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct virtnet_info *priv = netdev_priv(dev);
+	struct send_queue *sq = &priv->sq[txqueue];
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue);
+
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.tx_timeouts++;
+	u64_stats_update_end(&sq->stats.syncp);
+
+	netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n",
+		   txqueue, sq->name, sq->vq->index, sq->vq->name,
+		   jiffies_to_usecs(jiffies - txq->trans_start));
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -2678,6 +2711,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_phys_port_name	= virtnet_get_phys_port_name,
 	.ndo_set_features	= virtnet_set_features,
+	.ndo_tx_timeout		= virtnet_tx_timeout,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
@@ -3143,12 +3177,16 @@ static int virtnet_probe(struct virtio_device *vdev)
 	dev->max_mtu = MAX_MTU;
 
 	/* Configuration may specify what MAC to use.  Otherwise random. */
-	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC))
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
+		u8 addr[ETH_ALEN];
+
 		virtio_cread_bytes(vdev,
 				   offsetof(struct virtio_net_config, mac),
-				   dev->dev_addr, dev->addr_len);
-	else
+				   addr, ETH_ALEN);
+		eth_hw_addr_set(dev, addr);
+	} else {
 		eth_hw_addr_random(dev);
+	}
 
 	/* Set up our device-specific information */
 	vi = netdev_priv(dev);