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, 42 insertions, 23 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 752e392083e6..c695d294a5df 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -993,14 +993,8 @@ static bool icmp_redirect(struct sk_buff *skb)
 
 static bool icmp_echo(struct sk_buff *skb)
 {
-	struct icmp_ext_hdr *ext_hdr, _ext_hdr;
-	struct icmp_ext_echo_iio *iio, _iio;
 	struct icmp_bxm icmp_param;
-	struct net_device *dev;
-	char buff[IFNAMSIZ];
 	struct net *net;
-	u16 ident_len;
-	u8 status;
 
 	net = dev_net(skb_dst(skb)->dev);
 	/* should there be an ICMP stat for ignored echos? */
@@ -1013,20 +1007,46 @@ static bool icmp_echo(struct sk_buff *skb)
 	icmp_param.data_len	   = skb->len;
 	icmp_param.head_len	   = sizeof(struct icmphdr);
 
-	if (icmp_param.data.icmph.type == ICMP_ECHO) {
+	if (icmp_param.data.icmph.type == ICMP_ECHO)
 		icmp_param.data.icmph.type = ICMP_ECHOREPLY;
-		goto send_reply;
-	}
-	if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+	else if (!icmp_build_probe(skb, &icmp_param.data.icmph))
 		return true;
+
+	icmp_reply(&icmp_param, skb);
+	return true;
+}
+
+/*	Helper for icmp_echo and icmpv6_echo_reply.
+ *	Searches for net_device that matches PROBE interface identifier
+ *		and builds PROBE reply message in icmphdr.
+ *
+ *	Returns false if PROBE responses are disabled via sysctl
+ */
+
+bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
+{
+	struct icmp_ext_hdr *ext_hdr, _ext_hdr;
+	struct icmp_ext_echo_iio *iio, _iio;
+	struct net *net = dev_net(skb->dev);
+	struct net_device *dev;
+	char buff[IFNAMSIZ];
+	u16 ident_len;
+	u8 status;
+
+	if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+		return false;
+
 	/* We currently only support probing interfaces on the proxy node
 	 * Check to ensure L-bit is set
 	 */
-	if (!(ntohs(icmp_param.data.icmph.un.echo.sequence) & 1))
-		return true;
+	if (!(ntohs(icmphdr->un.echo.sequence) & 1))
+		return false;
 	/* Clear status bits in reply message */
-	icmp_param.data.icmph.un.echo.sequence &= htons(0xFF00);
-	icmp_param.data.icmph.type = ICMP_EXT_ECHOREPLY;
+	icmphdr->un.echo.sequence &= htons(0xFF00);
+	if (icmphdr->type == ICMP_EXT_ECHO)
+		icmphdr->type = ICMP_EXT_ECHOREPLY;
+	else
+		icmphdr->type = ICMPV6_EXT_ECHO_REPLY;
 	ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr);
 	/* Size of iio is class_type dependent.
 	 * Only check header here and assign length based on ctype in the switch statement
@@ -1066,7 +1086,7 @@ static bool icmp_echo(struct sk_buff *skb)
 			if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) +
 					 sizeof(struct in_addr))
 				goto send_mal_query;
-			dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr.s_addr);
+			dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr);
 			break;
 #if IS_ENABLED(CONFIG_IPV6)
 		case ICMP_AFI_IP6:
@@ -1087,8 +1107,8 @@ static bool icmp_echo(struct sk_buff *skb)
 		goto send_mal_query;
 	}
 	if (!dev) {
-		icmp_param.data.icmph.code = ICMP_EXT_CODE_NO_IF;
-		goto send_reply;
+		icmphdr->code = ICMP_EXT_CODE_NO_IF;
+		return true;
 	}
 	/* Fill bits in reply message */
 	if (dev->flags & IFF_UP)
@@ -1098,14 +1118,13 @@ static bool icmp_echo(struct sk_buff *skb)
 	if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
 		status |= ICMP_EXT_ECHOREPLY_IPV6;
 	dev_put(dev);
-	icmp_param.data.icmph.un.echo.sequence |= htons(status);
-send_reply:
-	icmp_reply(&icmp_param, skb);
-		return true;
+	icmphdr->un.echo.sequence |= htons(status);
+	return true;
 send_mal_query:
-	icmp_param.data.icmph.code = ICMP_EXT_CODE_MAL_QUERY;
-	goto send_reply;
+	icmphdr->code = ICMP_EXT_CODE_MAL_QUERY;
+	return true;
 }
+EXPORT_SYMBOL_GPL(icmp_build_probe);
 
 /*
  *	Handle ICMP Timestamp requests.