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, 91 insertions, 13 deletions

diff --git a/net/mctp/device.c b/net/mctp/device.c
index b9f38e765f61..8799ee77e7b7 100644
--- a/net/mctp/device.c
+++ b/net/mctp/device.c
@@ -35,14 +35,6 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev)
 	return rtnl_dereference(dev->mctp_ptr);
 }
 
-static void mctp_dev_destroy(struct mctp_dev *mdev)
-{
-	struct net_device *dev = mdev->dev;
-
-	dev_put(dev);
-	kfree_rcu(mdev, rcu);
-}
-
 static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb,
 			      struct mctp_dev *mdev, mctp_eid_t eid)
 {
@@ -255,6 +247,37 @@ static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 }
 
+void mctp_dev_hold(struct mctp_dev *mdev)
+{
+	refcount_inc(&mdev->refs);
+}
+
+void mctp_dev_put(struct mctp_dev *mdev)
+{
+	if (refcount_dec_and_test(&mdev->refs)) {
+		dev_put(mdev->dev);
+		kfree_rcu(mdev, rcu);
+	}
+}
+
+void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	if (!dev)
+		return;
+	if (dev->ops && dev->ops->release_flow)
+		dev->ops->release_flow(dev, key);
+	key->dev = NULL;
+	mctp_dev_put(dev);
+}
+
+void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	mctp_dev_hold(dev);
+	key->dev = dev;
+}
+
 static struct mctp_dev *mctp_add_dev(struct net_device *dev)
 {
 	struct mctp_dev *mdev;
@@ -270,7 +293,9 @@ static struct mctp_dev *mctp_add_dev(struct net_device *dev)
 	mdev->net = mctp_default_net(dev_net(dev));
 
 	/* associate to net_device */
+	refcount_set(&mdev->refs, 1);
 	rcu_assign_pointer(dev->mctp_ptr, mdev);
+
 	dev_hold(dev);
 	mdev->dev = dev;
 
@@ -330,12 +355,26 @@ static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr,
 	return 0;
 }
 
+/* Matches netdev types that should have MCTP handling */
+static bool mctp_known(struct net_device *dev)
+{
+	/* only register specific types (inc. NONE for TUN devices) */
+	return dev->type == ARPHRD_MCTP ||
+		   dev->type == ARPHRD_LOOPBACK ||
+		   dev->type == ARPHRD_NONE;
+}
+
 static void mctp_unregister(struct net_device *dev)
 {
 	struct mctp_dev *mdev;
 
 	mdev = mctp_dev_get_rtnl(dev);
-
+	if (mctp_known(dev) != (bool)mdev) {
+		// Sanity check, should match what was set in mctp_register
+		netdev_warn(dev, "%s: mdev pointer %d but type (%d) match is %d",
+			    __func__, (bool)mdev, mctp_known(dev), dev->type);
+		return;
+	}
 	if (!mdev)
 		return;
 
@@ -345,7 +384,7 @@ static void mctp_unregister(struct net_device *dev)
 	mctp_neigh_remove_dev(mdev);
 	kfree(mdev->addrs);
 
-	mctp_dev_destroy(mdev);
+	mctp_dev_put(mdev);
 }
 
 static int mctp_register(struct net_device *dev)
@@ -353,11 +392,17 @@ static int mctp_register(struct net_device *dev)
 	struct mctp_dev *mdev;
 
 	/* Already registered? */
-	if (rtnl_dereference(dev->mctp_ptr))
+	mdev = rtnl_dereference(dev->mctp_ptr);
+
+	if (mdev) {
+		if (!mctp_known(dev))
+			netdev_warn(dev, "%s: mctp_dev set for unknown type %d",
+				    __func__, dev->type);
 		return 0;
+	}
 
-	/* only register specific types; MCTP-specific and loopback for now */
-	if (dev->type != ARPHRD_MCTP && dev->type != ARPHRD_LOOPBACK)
+	/* only register specific types */
+	if (!mctp_known(dev))
 		return 0;
 
 	mdev = mctp_add_dev(dev);
@@ -387,6 +432,39 @@ static int mctp_dev_notify(struct notifier_block *this, unsigned long event,
 	return NOTIFY_OK;
 }
 
+static int mctp_register_netdevice(struct net_device *dev,
+				   const struct mctp_netdev_ops *ops)
+{
+	struct mctp_dev *mdev;
+
+	mdev = mctp_add_dev(dev);
+	if (IS_ERR(mdev))
+		return PTR_ERR(mdev);
+
+	mdev->ops = ops;
+
+	return register_netdevice(dev);
+}
+
+int mctp_register_netdev(struct net_device *dev,
+			 const struct mctp_netdev_ops *ops)
+{
+	int rc;
+
+	rtnl_lock();
+	rc = mctp_register_netdevice(dev, ops);
+	rtnl_unlock();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(mctp_register_netdev);
+
+void mctp_unregister_netdev(struct net_device *dev)
+{
+	unregister_netdev(dev);
+}
+EXPORT_SYMBOL_GPL(mctp_unregister_netdev);
+
 static struct rtnl_af_ops mctp_af_ops = {
 	.family = AF_MCTP,
 	.fill_link_af = mctp_fill_link_af,