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, 134 insertions, 18 deletions

diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index a9526ac29dff..d344b02a1cde 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -16,6 +16,9 @@
 #include <net/mctpdevice.h>
 #include <net/sock.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/mctp.h>
+
 /* socket implementation */
 
 static int mctp_release(struct socket *sock)
@@ -74,6 +77,7 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
 	int rc, addrlen = msg->msg_namelen;
 	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct mctp_skb_cb *cb;
 	struct mctp_route *rt;
 	struct sk_buff *skb;
@@ -97,11 +101,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (addr->smctp_network == MCTP_NET_ANY)
 		addr->smctp_network = mctp_default_net(sock_net(sk));
 
-	rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
-			       addr->smctp_addr.s_addr);
-	if (!rt)
-		return -EHOSTUNREACH;
-
 	skb = sock_alloc_send_skb(sk, hlen + 1 + len,
 				  msg->msg_flags & MSG_DONTWAIT, &rc);
 	if (!skb)
@@ -113,19 +112,45 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	*(u8 *)skb_put(skb, 1) = addr->smctp_type;
 
 	rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len);
-	if (rc < 0) {
-		kfree_skb(skb);
-		return rc;
-	}
+	if (rc < 0)
+		goto err_free;
 
 	/* set up cb */
 	cb = __mctp_cb(skb);
 	cb->net = addr->smctp_network;
 
+	/* direct addressing */
+	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+
+		if (extaddr->smctp_halen > sizeof(cb->haddr)) {
+			rc = -EINVAL;
+			goto err_free;
+		}
+
+		cb->ifindex = extaddr->smctp_ifindex;
+		cb->halen = extaddr->smctp_halen;
+		memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
+
+		rt = NULL;
+	} else {
+		rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+				       addr->smctp_addr.s_addr);
+		if (!rt) {
+			rc = -EHOSTUNREACH;
+			goto err_free;
+		}
+	}
+
 	rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
 			       addr->smctp_tag);
 
 	return rc ? : len;
+
+err_free:
+	kfree_skb(skb);
+	return rc;
 }
 
 static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
@@ -133,6 +158,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 {
 	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
 	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct sk_buff *skb;
 	size_t msglen;
 	u8 type;
@@ -178,6 +204,16 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		addr->smctp_tag = hdr->flags_seq_tag &
 					(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
 		msg->msg_namelen = sizeof(*addr);
+
+		if (msk->addr_ext) {
+			DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae,
+					 msg->msg_name);
+			msg->msg_namelen = sizeof(*ae);
+			ae->smctp_ifindex = cb->ifindex;
+			ae->smctp_halen = cb->halen;
+			memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr));
+			memcpy(ae->smctp_haddr, cb->haddr, cb->halen);
+		}
 	}
 
 	rc = len;
@@ -193,12 +229,45 @@ out_free:
 static int mctp_setsockopt(struct socket *sock, int level, int optname,
 			   sockptr_t optval, unsigned int optlen)
 {
-	return -EINVAL;
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		if (copy_from_sockptr(&val, optval, sizeof(int)))
+			return -EFAULT;
+		msk->addr_ext = val;
+		return 0;
+	}
+
+	return -ENOPROTOOPT;
 }
 
 static int mctp_getsockopt(struct socket *sock, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int len, val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (len != sizeof(int))
+			return -EINVAL;
+		val = !!msk->addr_ext;
+		if (copy_to_user(optval, &val, len))
+			return -EFAULT;
+		return 0;
+	}
+
 	return -EINVAL;
 }
 
@@ -223,16 +292,61 @@ static const struct proto_ops mctp_dgram_ops = {
 	.sendpage	= sock_no_sendpage,
 };
 
+static void mctp_sk_expire_keys(struct timer_list *timer)
+{
+	struct mctp_sock *msk = container_of(timer, struct mctp_sock,
+					     key_expiry);
+	struct net *net = sock_net(&msk->sk);
+	unsigned long next_expiry, flags;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	bool next_expiry_valid = false;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		spin_lock(&key->lock);
+
+		if (!time_after_eq(key->expiry, jiffies)) {
+			trace_mctp_key_release(key, MCTP_TRACE_KEY_TIMEOUT);
+			key->valid = false;
+			hlist_del_rcu(&key->hlist);
+			hlist_del_rcu(&key->sklist);
+			spin_unlock(&key->lock);
+			mctp_key_unref(key);
+			continue;
+		}
+
+		if (next_expiry_valid) {
+			if (time_before(key->expiry, next_expiry))
+				next_expiry = key->expiry;
+		} else {
+			next_expiry = key->expiry;
+			next_expiry_valid = true;
+		}
+		spin_unlock(&key->lock);
+	}
+
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	if (next_expiry_valid)
+		mod_timer(timer, next_expiry);
+}
+
 static int mctp_sk_init(struct sock *sk)
 {
 	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 
 	INIT_HLIST_HEAD(&msk->keys);
+	timer_setup(&msk->key_expiry, mctp_sk_expire_keys, 0);
 	return 0;
 }
 
 static void mctp_sk_close(struct sock *sk, long timeout)
 {
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+
+	del_timer_sync(&msk->key_expiry);
 	sk_common_release(sk);
 }
 
@@ -263,21 +377,23 @@ static void mctp_sk_unhash(struct sock *sk)
 	/* remove tag allocations */
 	spin_lock_irqsave(&net->mctp.keys_lock, flags);
 	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
-		hlist_del_rcu(&key->sklist);
-		hlist_del_rcu(&key->hlist);
+		hlist_del(&key->sklist);
+		hlist_del(&key->hlist);
 
-		spin_lock(&key->reasm_lock);
+		trace_mctp_key_release(key, MCTP_TRACE_KEY_CLOSED);
+
+		spin_lock(&key->lock);
 		if (key->reasm_head)
 			kfree_skb(key->reasm_head);
 		key->reasm_head = NULL;
 		key->reasm_dead = true;
-		spin_unlock(&key->reasm_lock);
+		key->valid = false;
+		spin_unlock(&key->lock);
 
-		kfree_rcu(key, rcu);
+		/* key is no longer on the lookup lists, unref */
+		mctp_key_unref(key);
 	}
 	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
-
-	synchronize_rcu();
 }
 
 static struct proto mctp_proto = {
@@ -385,7 +501,7 @@ static __exit void mctp_exit(void)
 	sock_unregister(PF_MCTP);
 }
 
-module_init(mctp_init);
+subsys_initcall(mctp_init);
 module_exit(mctp_exit);
 
 MODULE_DESCRIPTION("MCTP core");