Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 72 insertions, 86 deletions

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 53af72824c9c..34a97ea36cc8 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -73,9 +73,6 @@ struct sockaddr_pair {
 /**
  * struct tipc_sock - TIPC socket structure
  * @sk: socket - interacts with 'port' and with user via the socket API
- * @conn_type: TIPC type used when connection was established
- * @conn_instance: TIPC instance used when connection was established
- * @published: non-zero if port has one or more associated names
  * @max_pkt: maximum packet size "hint" used when building messages sent by port
  * @maxnagle: maximum size of msg which can be subject to nagle
  * @portid: unique port identity in TIPC socket hash table
@@ -106,11 +103,11 @@ struct sockaddr_pair {
  * @expect_ack: whether this TIPC socket is expecting an ack
  * @nodelay: setsockopt() TIPC_NODELAY setting
  * @group_is_open: TIPC socket group is fully open (FIXME)
+ * @published: true if port has one or more associated names
+ * @conn_addrtype: address type used when establishing connection
  */
 struct tipc_sock {
 	struct sock sk;
-	u32 conn_type;
-	u32 conn_instance;
 	u32 max_pkt;
 	u32 maxnagle;
 	u32 portid;
@@ -141,6 +138,7 @@ struct tipc_sock {
 	bool nodelay;
 	bool group_is_open;
 	bool published;
+	u8 conn_addrtype;
 };
 
 static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
@@ -664,7 +662,7 @@ static int tipc_release(struct socket *sock)
  * @skaddr: socket address describing name(s) and desired operation
  * @alen: size of socket address data structure
  *
- * Name and name sequence binding is indicated using a positive scope value;
+ * Name and name sequence binding are indicated using a positive scope value;
  * a negative scope value unbinds the specified name.  Specifying no name
  * (i.e. a socket address length of 0) unbinds all names from the socket.
  *
@@ -1202,12 +1200,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 	struct tipc_msg *hdr;
 	struct tipc_uaddr ua;
 	int user, mtyp, hlen;
-	bool exact;
 
 	__skb_queue_head_init(&tmpq);
 	INIT_LIST_HEAD(&dports);
 	ua.addrtype = TIPC_SERVICE_RANGE;
 
+	/* tipc_skb_peek() increments the head skb's reference counter */
 	skb = tipc_skb_peek(arrvq, &inputq->lock);
 	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
 		hdr = buf_msg(skb);
@@ -1216,6 +1214,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 		hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
 		onode = msg_orignode(hdr);
 		ua.sr.type = msg_nametype(hdr);
+		ua.sr.lower = msg_namelower(hdr);
+		ua.sr.upper = msg_nameupper(hdr);
+		if (onode == self)
+			ua.scope = TIPC_ANY_SCOPE;
+		else
+			ua.scope = TIPC_CLUSTER_SCOPE;
 
 		if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
 			spin_lock_bh(&inputq->lock);
@@ -1233,20 +1237,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 			ua.sr.lower = 0;
 			ua.sr.upper = ~0;
 			ua.scope = msg_lookup_scope(hdr);
-			exact = true;
-		} else {
-			/* TIPC_NODE_SCOPE means "any scope" in this context */
-			if (onode == self)
-				ua.scope = TIPC_NODE_SCOPE;
-			else
-				ua.scope = TIPC_CLUSTER_SCOPE;
-			exact = false;
-			ua.sr.lower = msg_namelower(hdr);
-			ua.sr.upper = msg_nameupper(hdr);
 		}
 
 		/* Create destination port list: */
-		tipc_nametbl_lookup_mcast_sockets(net, &ua, exact, &dports);
+		tipc_nametbl_lookup_mcast_sockets(net, &ua, &dports);
 
 		/* Clone message per destination */
 		while (tipc_dest_pop(&dports, NULL, &portid)) {
@@ -1258,13 +1252,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 			}
 			pr_warn("Failed to clone mcast rcv buffer\n");
 		}
-		/* Append to inputq if not already done by other thread */
+		/* Append clones to inputq only if skb is still head of arrvq */
 		spin_lock_bh(&inputq->lock);
 		if (skb_peek(arrvq) == skb) {
 			skb_queue_splice_tail_init(&tmpq, inputq);
-			/* Decrease the skb's refcnt as increasing in the
-			 * function tipc_skb_peek
-			 */
+			/* Decrement the skb's refcnt */
 			kfree_skb(__skb_dequeue(arrvq));
 		}
 		spin_unlock_bh(&inputq->lock);
@@ -1463,10 +1455,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 			return -EISCONN;
 		if (tsk->published)
 			return -EOPNOTSUPP;
-		if (atype == TIPC_SERVICE_ADDR) {
-			tsk->conn_type = ua->sa.type;
-			tsk->conn_instance = ua->sa.instance;
-		}
+		if (atype == TIPC_SERVICE_ADDR)
+			tsk->conn_addrtype = atype;
 		msg_set_syn(hdr, 1);
 	}
 
@@ -1737,67 +1727,58 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
-	struct tipc_msg *msg;
-	u32 anc_data[3];
-	u32 err;
-	u32 dest_type;
-	int has_name;
-	int res;
+	struct tipc_msg *hdr;
+	u32 data[3] = {0,};
+	bool has_addr;
+	int dlen, rc;
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
-	msg = buf_msg(skb);
 
-	/* Optionally capture errored message object(s) */
-	err = msg ? msg_errcode(msg) : 0;
-	if (unlikely(err)) {
-		anc_data[0] = err;
-		anc_data[1] = msg_data_sz(msg);
-		res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data);
-		if (res)
-			return res;
-		if (anc_data[1]) {
-			if (skb_linearize(skb))
-				return -ENOMEM;
-			msg = buf_msg(skb);
-			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
-				       msg_data(msg));
-			if (res)
-				return res;
-		}
+	hdr = buf_msg(skb);
+	dlen = msg_data_sz(hdr);
+
+	/* Capture errored message object, if any */
+	if (msg_errcode(hdr)) {
+		if (skb_linearize(skb))
+			return -ENOMEM;
+		hdr = buf_msg(skb);
+		data[0] = msg_errcode(hdr);
+		data[1] = dlen;
+		rc = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, data);
+		if (rc || !dlen)
+			return rc;
+		rc = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, dlen, msg_data(hdr));
+		if (rc)
+			return rc;
 	}
 
-	/* Optionally capture message destination object */
-	dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG;
-	switch (dest_type) {
+	/* Capture TIPC_SERVICE_ADDR/RANGE destination address, if any */
+	switch (msg_type(hdr)) {
 	case TIPC_NAMED_MSG:
-		has_name = 1;
-		anc_data[0] = msg_nametype(msg);
-		anc_data[1] = msg_namelower(msg);
-		anc_data[2] = msg_namelower(msg);
+		has_addr = true;
+		data[0] = msg_nametype(hdr);
+		data[1] = msg_namelower(hdr);
+		data[2] = data[1];
 		break;
 	case TIPC_MCAST_MSG:
-		has_name = 1;
-		anc_data[0] = msg_nametype(msg);
-		anc_data[1] = msg_namelower(msg);
-		anc_data[2] = msg_nameupper(msg);
+		has_addr = true;
+		data[0] = msg_nametype(hdr);
+		data[1] = msg_namelower(hdr);
+		data[2] = msg_nameupper(hdr);
 		break;
 	case TIPC_CONN_MSG:
-		has_name = (tsk->conn_type != 0);
-		anc_data[0] = tsk->conn_type;
-		anc_data[1] = tsk->conn_instance;
-		anc_data[2] = tsk->conn_instance;
+		has_addr = !!tsk->conn_addrtype;
+		data[0] = msg_nametype(&tsk->phdr);
+		data[1] = msg_nameinst(&tsk->phdr);
+		data[2] = data[1];
 		break;
 	default:
-		has_name = 0;
+		has_addr = false;
 	}
-	if (has_name) {
-		res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data);
-		if (res)
-			return res;
-	}
-
-	return 0;
+	if (!has_addr)
+		return 0;
+	return put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, data);
 }
 
 static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk)
@@ -2750,8 +2731,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
 
 	tsk_set_importance(new_sk, msg_importance(msg));
 	if (msg_named(msg)) {
-		new_tsock->conn_type = msg_nametype(msg);
-		new_tsock->conn_instance = msg_nameinst(msg);
+		new_tsock->conn_addrtype = TIPC_SERVICE_ADDR;
+		msg_set_nametype(&new_tsock->phdr, msg_nametype(msg));
+		msg_set_nameinst(&new_tsock->phdr, msg_nameinst(msg));
 	}
 
 	/*
@@ -3455,13 +3437,14 @@ void tipc_socket_stop(void)
 /* Caller should hold socket lock for the passed tipc socket. */
 static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 {
-	u32 peer_node;
-	u32 peer_port;
+	u32 peer_node, peer_port;
+	u32 conn_type, conn_instance;
 	struct nlattr *nest;
 
 	peer_node = tsk_peer_node(tsk);
 	peer_port = tsk_peer_port(tsk);
-
+	conn_type = msg_nametype(&tsk->phdr);
+	conn_instance = msg_nameinst(&tsk->phdr);
 	nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON);
 	if (!nest)
 		return -EMSGSIZE;
@@ -3471,12 +3454,12 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 	if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port))
 		goto msg_full;
 
-	if (tsk->conn_type != 0) {
+	if (tsk->conn_addrtype != 0) {
 		if (nla_put_flag(skb, TIPC_NLA_CON_FLAG))
 			goto msg_full;
-		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type))
+		if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, conn_type))
 			goto msg_full;
-		if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance))
+		if (nla_put_u32(skb, TIPC_NLA_CON_INST, conn_instance))
 			goto msg_full;
 	}
 	nla_nest_end(skb, nest);
@@ -3866,9 +3849,9 @@ bool tipc_sk_filtering(struct sock *sk)
 	}
 
 	if (!tipc_sk_type_connectionless(sk)) {
-		type = tsk->conn_type;
-		lower = tsk->conn_instance;
-		upper = tsk->conn_instance;
+		type = msg_nametype(&tsk->phdr);
+		lower = msg_nameinst(&tsk->phdr);
+		upper = lower;
 	}
 
 	if ((_type && _type != type) || (_lower && _lower != lower) ||
@@ -3933,6 +3916,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 {
 	int i = 0;
 	size_t sz = (dqueues) ? SK_LMAX : SK_LMIN;
+	u32 conn_type, conn_instance;
 	struct tipc_sock *tsk;
 	struct publication *p;
 	bool tsk_connected;
@@ -3953,8 +3937,10 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 	if (tsk_connected) {
 		i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk));
 		i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk));
-		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type);
-		i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance);
+		conn_type = msg_nametype(&tsk->phdr);
+		conn_instance = msg_nameinst(&tsk->phdr);
+		i += scnprintf(buf + i, sz - i, " %u", conn_type);
+		i += scnprintf(buf + i, sz - i, " %u", conn_instance);
 	}
 	i += scnprintf(buf + i, sz - i, " | %u", tsk->published);
 	if (tsk->published) {