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
  ...

net/sctp/input.c

@@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
 void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 			   struct sctp_transport *t, __u32 pmtu)
 {
-	if (!t || (t->pathmtu <= pmtu))
+	if (!t ||
+	    (t->pathmtu <= pmtu &&
+	     t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu))
 		return;
 
 	if (sock_owned_by_user(sk)) {
@@ -554,6 +556,50 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
 	sctp_transport_put(t);
 }
 
+static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb,
+			       __u8 type, __u8 code, __u32 info)
+{
+	struct sctp_association *asoc = t->asoc;
+	struct sock *sk = asoc->base.sk;
+	int err = 0;
+
+	switch (type) {
+	case ICMP_PARAMETERPROB:
+		err = EPROTO;
+		break;
+	case ICMP_DEST_UNREACH:
+		if (code > NR_ICMP_UNREACH)
+			return;
+		if (code == ICMP_FRAG_NEEDED) {
+			sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info));
+			return;
+		}
+		if (code == ICMP_PROT_UNREACH) {
+			sctp_icmp_proto_unreachable(sk, asoc, t);
+			return;
+		}
+		err = icmp_err_convert[code].errno;
+		break;
+	case ICMP_TIME_EXCEEDED:
+		if (code == ICMP_EXC_FRAGTIME)
+			return;
+
+		err = EHOSTUNREACH;
+		break;
+	case ICMP_REDIRECT:
+		sctp_icmp_redirect(sk, t, skb);
+		return;
+	default:
+		return;
+	}
+	if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) {
+		sk->sk_err = err;
+		sk_error_report(sk);
+	} else {  /* Only an error on timeout */
+		sk->sk_err_soft = err;
+	}
+}
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -572,22 +618,19 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
 int sctp_v4_err(struct sk_buff *skb, __u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	const int ihlen = iph->ihl * 4;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
-	struct sock *sk;
-	struct sctp_association *asoc = NULL;
-	struct sctp_transport *transport;
-	struct inet_sock *inet;
-	__u16 saveip, savesctp;
-	int err;
 	struct net *net = dev_net(skb->dev);
+	struct sctp_transport *transport;
+	struct sctp_association *asoc;
+	__u16 saveip, savesctp;
+	struct sock *sk;
 
 	/* Fix up skb to look at the embedded net header. */
 	saveip = skb->network_header;
 	savesctp = skb->transport_header;
 	skb_reset_network_header(skb);
-	skb_set_transport_header(skb, ihlen);
+	skb_set_transport_header(skb, iph->ihl * 4);
 	sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
 	/* Put back, the original values. */
 	skb->network_header = saveip;
@@ -596,61 +639,43 @@ int sctp_v4_err(struct sk_buff *skb, __u32 info)
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return -ENOENT;
 	}
-	/* Warning:  The sock lock is held.  Remember to call
-	 * sctp_err_finish!
-	 */
 
-	switch (type) {
-	case ICMP_PARAMETERPROB:
-		err = EPROTO;
-		break;
-	case ICMP_DEST_UNREACH:
-		if (code > NR_ICMP_UNREACH)
-			goto out_unlock;
-
-		/* PMTU discovery (RFC1191) */
-		if (ICMP_FRAG_NEEDED == code) {
-			sctp_icmp_frag_needed(sk, asoc, transport,
-					      SCTP_TRUNC4(info));
-			goto out_unlock;
-		} else {
-			if (ICMP_PROT_UNREACH == code) {
-				sctp_icmp_proto_unreachable(sk, asoc,
-							    transport);
-				goto out_unlock;
-			}
-		}
-		err = icmp_err_convert[code].errno;
-		break;
-	case ICMP_TIME_EXCEEDED:
-		/* Ignore any time exceeded errors due to fragment reassembly
-		 * timeouts.
-		 */
-		if (ICMP_EXC_FRAGTIME == code)
-			goto out_unlock;
-
-		err = EHOSTUNREACH;
-		break;
-	case ICMP_REDIRECT:
-		sctp_icmp_redirect(sk, transport, skb);
-		goto out_unlock;
-	default:
-		goto out_unlock;
-	}
-
-	inet = inet_sk(sk);
-	if (!sock_owned_by_user(sk) && inet->recverr) {
-		sk->sk_err = err;
-		sk->sk_error_report(sk);
-	} else {  /* Only an error on timeout */
-		sk->sk_err_soft = err;
-	}
-
-out_unlock:
+	sctp_v4_err_handle(transport, skb, type, code, info);
 	sctp_err_finish(sk, transport);
+
 	return 0;
 }
 
+int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	struct sctp_association *asoc;
+	struct sctp_transport *t;
+	struct icmphdr *hdr;
+	__u32 info = 0;
+
+	skb->transport_header += sizeof(struct udphdr);
+	sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t);
+	if (!sk) {
+		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
+		return -ENOENT;
+	}
+
+	skb->transport_header -= sizeof(struct udphdr);
+	hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr));
+	if (hdr->type == ICMP_REDIRECT) {
+		/* can't be handled without outer iphdr known, leave it to udp_err */
+		sctp_err_finish(sk, t);
+		return 0;
+	}
+	if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED)
+		info = ntohs(hdr->un.frag.mtu);
+	sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info);
+
+	sctp_err_finish(sk, t);
+	return 1;
+}
+
 /*
  * RFC 2960, 8.4 - Handle "Out of the blue" Packets.
  *
@@ -1131,7 +1156,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
 		if (!af)
 			continue;
 
-		af->from_addr_param(paddr, params.addr, sh->source, 0);
+		if (!af->from_addr_param(paddr, params.addr, sh->source, 0))
+			continue;
 
 		asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
 		if (asoc)
@@ -1167,6 +1193,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
 	union sctp_addr_param *param;
 	union sctp_addr paddr;
 
+	if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr))
+		return NULL;
+
 	/* Skip over the ADDIP header and find the Address parameter */
 	param = (union sctp_addr_param *)(asconf + 1);
 
@@ -1174,7 +1203,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
 	if (unlikely(!af))
 		return NULL;
 
-	af->from_addr_param(&paddr, param, peer_port, 0);
+	if (af->from_addr_param(&paddr, param, peer_port, 0))
+		return NULL;
 
 	return __sctp_lookup_association(net, laddr, &paddr, transportp);
 }
@@ -1246,7 +1276,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net,
 
 		ch = (struct sctp_chunkhdr *)ch_end;
 		chunk_num++;
-	} while (ch_end < skb_tail_pointer(skb));
+	} while (ch_end + sizeof(*ch) < skb_tail_pointer(skb));
 
 	return asoc;
 }