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, 76 insertions, 45 deletions

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index bd08807c9e44..e48dd909dee5 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -122,54 +122,28 @@ static struct notifier_block sctp_inet6addr_notifier = {
 	.notifier_call = sctp_inet6addr_event,
 };
 
-/* ICMP error handler. */
-static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-			u8 type, u8 code, int offset, __be32 info)
+static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb,
+			       __u8 type, __u8 code, __u32 info)
 {
-	struct inet6_dev *idev;
-	struct sock *sk;
-	struct sctp_association *asoc;
-	struct sctp_transport *transport;
+	struct sctp_association *asoc = t->asoc;
+	struct sock *sk = asoc->base.sk;
 	struct ipv6_pinfo *np;
-	__u16 saveip, savesctp;
-	int err, ret = 0;
-	struct net *net = dev_net(skb->dev);
-
-	idev = in6_dev_get(skb->dev);
-
-	/* 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, offset);
-	sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
-	/* Put back, the original pointers. */
-	skb->network_header   = saveip;
-	skb->transport_header = savesctp;
-	if (!sk) {
-		__ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS);
-		ret = -ENOENT;
-		goto out;
-	}
-
-	/* Warning:  The sock lock is held.  Remember to call
-	 * sctp_err_finish!
-	 */
+	int err = 0;
 
 	switch (type) {
 	case ICMPV6_PKT_TOOBIG:
 		if (ip6_sk_accept_pmtu(sk))
-			sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
-		goto out_unlock;
+			sctp_icmp_frag_needed(sk, asoc, t, info);
+		return;
 	case ICMPV6_PARAMPROB:
 		if (ICMPV6_UNK_NEXTHDR == code) {
-			sctp_icmp_proto_unreachable(sk, asoc, transport);
-			goto out_unlock;
+			sctp_icmp_proto_unreachable(sk, asoc, t);
+			return;
 		}
 		break;
 	case NDISC_REDIRECT:
-		sctp_icmp_redirect(sk, transport, skb);
-		goto out_unlock;
+		sctp_icmp_redirect(sk, t, skb);
+		return;
 	default:
 		break;
 	}
@@ -178,18 +152,70 @@ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	icmpv6_err_convert(type, code, &err);
 	if (!sock_owned_by_user(sk) && np->recverr) {
 		sk->sk_err = err;
-		sk->sk_error_report(sk);
-	} else {  /* Only an error on timeout */
+		sk_error_report(sk);
+	} else {
 		sk->sk_err_soft = err;
 	}
+}
+
+/* ICMP error handler. */
+static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		       u8 type, u8 code, int offset, __be32 info)
+{
+	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, offset);
+	sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport);
+	/* Put back, the original pointers. */
+	skb->network_header   = saveip;
+	skb->transport_header = savesctp;
+	if (!sk) {
+		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+		return -ENOENT;
+	}
 
-out_unlock:
+	sctp_v6_err_handle(transport, skb, type, code, ntohl(info));
 	sctp_err_finish(sk, transport);
-out:
-	if (likely(idev != NULL))
-		in6_dev_put(idev);
 
-	return ret;
+	return 0;
+}
+
+int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	struct sctp_association *asoc;
+	struct sctp_transport *t;
+	struct icmp6hdr *hdr;
+	__u32 info = 0;
+
+	skb->transport_header += sizeof(struct udphdr);
+	sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t);
+	if (!sk) {
+		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
+		return -ENOENT;
+	}
+
+	skb->transport_header -= sizeof(struct udphdr);
+	hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr));
+	if (hdr->icmp6_type == NDISC_REDIRECT) {
+		/* can't be handled without outer ip6hdr known, leave it to udpv6_err */
+		sctp_err_finish(sk, t);
+		return 0;
+	}
+	if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG)
+		info = ntohl(hdr->icmp6_mtu);
+	sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info);
+
+	sctp_err_finish(sk, t);
+	return 1;
 }
 
 static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
@@ -551,15 +577,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
 }
 
 /* Initialize a sctp_addr from an address parameter. */
-static void sctp_v6_from_addr_param(union sctp_addr *addr,
+static bool sctp_v6_from_addr_param(union sctp_addr *addr,
 				    union sctp_addr_param *param,
 				    __be16 port, int iif)
 {
+	if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param))
+		return false;
+
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = port;
 	addr->v6.sin6_flowinfo = 0; /* BUG */
 	addr->v6.sin6_addr = param->v6.addr;
 	addr->v6.sin6_scope_id = iif;
+
+	return true;
 }
 
 /* Initialize an address parameter from a sctp_addr and return the length