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
  ...

5 files changed, 156 insertions, 8 deletions

diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
index 775a46d0b0f0..6bf43176f14c 100644
--- a/include/trace/events/mptcp.h
+++ b/include/trace/events/mptcp.h
@@ -73,6 +73,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__field(u64, data_seq)
 		__field(u32, subflow_seq)
 		__field(u16, data_len)
+		__field(u16, csum)
 		__field(u8, use_map)
 		__field(u8, dsn64)
 		__field(u8, data_fin)
@@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__field(u8, frozen)
 		__field(u8, reset_transient)
 		__field(u8, reset_reason)
+		__field(u8, csum_reqd)
 	),
 
 	TP_fast_assign(
@@ -89,6 +91,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__entry->data_seq = mpext->data_seq;
 		__entry->subflow_seq = mpext->subflow_seq;
 		__entry->data_len = mpext->data_len;
+		__entry->csum = (__force u16)mpext->csum;
 		__entry->use_map = mpext->use_map;
 		__entry->dsn64 = mpext->dsn64;
 		__entry->data_fin = mpext->data_fin;
@@ -98,16 +101,18 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
 		__entry->frozen = mpext->frozen;
 		__entry->reset_transient = mpext->reset_transient;
 		__entry->reset_reason = mpext->reset_reason;
+		__entry->csum_reqd = mpext->csum_reqd;
 	),
 
-	TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u",
+	TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u",
 		  __entry->data_ack, __entry->data_seq,
 		  __entry->subflow_seq, __entry->data_len,
-		  __entry->use_map, __entry->dsn64,
-		  __entry->data_fin, __entry->use_ack,
-		  __entry->ack64, __entry->mpc_map,
-		  __entry->frozen, __entry->reset_transient,
-		  __entry->reset_reason)
+		  __entry->csum, __entry->use_map,
+		  __entry->dsn64, __entry->data_fin,
+		  __entry->use_ack, __entry->ack64,
+		  __entry->mpc_map, __entry->frozen,
+		  __entry->reset_transient, __entry->reset_reason,
+		  __entry->csum_reqd)
 );
 
 DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status,
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index a966d4b5ab37..12c315782766 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -201,6 +201,66 @@ TRACE_EVENT(inet_sock_set_state,
 			show_tcp_state_name(__entry->newstate))
 );
 
+TRACE_EVENT(inet_sk_error_report,
+
+	TP_PROTO(const struct sock *sk),
+
+	TP_ARGS(sk),
+
+	TP_STRUCT__entry(
+		__field(int, error)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__field(__u16, family)
+		__field(__u16, protocol)
+		__array(__u8, saddr, 4)
+		__array(__u8, daddr, 4)
+		__array(__u8, saddr_v6, 16)
+		__array(__u8, daddr_v6, 16)
+	),
+
+	TP_fast_assign(
+		struct inet_sock *inet = inet_sk(sk);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->error = sk->sk_err;
+		__entry->family = sk->sk_family;
+		__entry->protocol = sk->sk_protocol;
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+
+		p32 = (__be32 *) __entry->saddr;
+		*p32 = inet->inet_saddr;
+
+		p32 = (__be32 *) __entry->daddr;
+		*p32 =  inet->inet_daddr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (sk->sk_family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			*pin6 = sk->sk_v6_rcv_saddr;
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			*pin6 = sk->sk_v6_daddr;
+		} else
+#endif
+		{
+			pin6 = (struct in6_addr *)__entry->saddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
+			pin6 = (struct in6_addr *)__entry->daddr_v6;
+			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
+		}
+	),
+
+	TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d",
+		  show_family_name(__entry->family),
+		  show_inet_protocol_name(__entry->protocol),
+		  __entry->sport, __entry->dport,
+		  __entry->saddr, __entry->daddr,
+		  __entry->saddr_v6, __entry->daddr_v6,
+		  __entry->error)
+);
+
 #endif /* _TRACE_SOCK_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index ba94857eea11..521059d8dc0a 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -295,6 +295,82 @@ TRACE_EVENT(tcp_probe,
 		  __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie)
 );
 
+#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)			\
+	do {								\
+		const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+		struct sockaddr_in *v4 = (void *)__entry->saddr;	\
+									\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->source;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->saddr;		\
+		v4 = (void *)__entry->daddr;				\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = th->dest;				\
+		v4->sin_addr.s_addr = ip_hdr(skb)->daddr;		\
+	} while (0)
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)				\
+	do {								\
+		const struct iphdr *iph = ip_hdr(skb);			\
+									\
+		if (iph->version == 6) {				\
+			const struct tcphdr *th = (const struct tcphdr *)skb->data; \
+			struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+									\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->source;			\
+			v6->sin6_addr = ipv6_hdr(skb)->saddr;		\
+			v6 = (void *)__entry->daddr;			\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = th->dest;			\
+			v6->sin6_addr = ipv6_hdr(skb)->daddr;		\
+		} else							\
+			TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb);	\
+	} while (0)
+
+#else
+
+#define TP_STORE_ADDR_PORTS_SKB(__entry, skb)		\
+	TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb)
+
+#endif
+
+/*
+ * tcp event with only skb
+ */
+DECLARE_EVENT_CLASS(tcp_event_skb,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(const void *, skbaddr)
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+		TP_STORE_ADDR_PORTS_SKB(__entry, skb);
+	),
+
+	TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr)
+);
+
+DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
 #endif /* _TRACE_TCP_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h
index 6782213778be..d0b3f0ea9ba1 100644
--- a/include/trace/events/vsock_virtio_transport_common.h
+++ b/include/trace/events/vsock_virtio_transport_common.h
@@ -9,9 +9,12 @@
 #include <linux/tracepoint.h>
 
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM);
+TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_SEQPACKET);
 
 #define show_type(val) \
-	__print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" })
+	__print_symbolic(val, \
+			 { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }, \
+			 { VIRTIO_VSOCK_TYPE_SEQPACKET, "SEQPACKET" })
 
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID);
 TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST);
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index fcad3645a70b..c40fc97f9417 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 		u32 ifindex = 0, map_index = index;
 
 		if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-			ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+			/* Just leave to_ifindex to 0 if do broadcast redirect,
+			 * as tgt will be NULL.
+			 */
+			if (tgt)
+				ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
 		} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
 			ifindex = index;
 			map_index = 0;