Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

5 files changed, 322 insertions, 18 deletions

diff --git a/include/trace/events/bridge.h b/include/trace/events/bridge.h
index 1bee3e7fdf32..8ea966448b58 100644
--- a/include/trace/events/bridge.h
+++ b/include/trace/events/bridge.h
@@ -82,8 +82,8 @@ TRACE_EVENT(fdb_delete,
 	TP_fast_assign(
 		__assign_str(br_dev, br->dev->name);
 		__assign_str(dev, f->dst ? f->dst->dev->name : "null");
-		memcpy(__entry->addr, f->addr.addr, ETH_ALEN);
-		__entry->vid = f->vlan_id;
+		memcpy(__entry->addr, f->key.addr.addr, ETH_ALEN);
+		__entry->vid = f->key.vlan_id;
 	),
 
 	TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u",
diff --git a/include/trace/events/net_probe_common.h b/include/trace/events/net_probe_common.h
new file mode 100644
index 000000000000..3930119cab08
--- /dev/null
+++ b/include/trace/events/net_probe_common.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#if !defined(_TRACE_NET_PROBE_COMMON_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_PROBE_COMMON_H
+
+#define TP_STORE_ADDR_PORTS_V4(__entry, inet, sk)			\
+	do {								\
+		struct sockaddr_in *v4 = (void *)__entry->saddr;	\
+									\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = inet->inet_sport;			\
+		v4->sin_addr.s_addr = inet->inet_saddr;			\
+		v4 = (void *)__entry->daddr;				\
+		v4->sin_family = AF_INET;				\
+		v4->sin_port = inet->inet_dport;			\
+		v4->sin_addr.s_addr = inet->inet_daddr;			\
+	} while (0)
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+#define TP_STORE_ADDR_PORTS(__entry, inet, sk)				\
+	do {								\
+		if (sk->sk_family == AF_INET6) {			\
+			struct sockaddr_in6 *v6 = (void *)__entry->saddr; \
+									\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = inet->inet_sport;		\
+			v6->sin6_addr = inet6_sk(sk)->saddr;		\
+			v6 = (void *)__entry->daddr;			\
+			v6->sin6_family = AF_INET6;			\
+			v6->sin6_port = inet->inet_dport;		\
+			v6->sin6_addr = sk->sk_v6_daddr;		\
+		} else							\
+			TP_STORE_ADDR_PORTS_V4(__entry, inet, sk);	\
+	} while (0)
+
+#else
+
+#define TP_STORE_ADDR_PORTS(__entry, inet, sk)		\
+	TP_STORE_ADDR_PORTS_V4(__entry, inet, sk);
+
+#endif
+
+#endif
diff --git a/include/trace/events/sctp.h b/include/trace/events/sctp.h
new file mode 100644
index 000000000000..7475c7be165a
--- /dev/null
+++ b/include/trace/events/sctp.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sctp
+
+#if !defined(_TRACE_SCTP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCTP_H
+
+#include <net/sctp/structs.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(sctp_probe_path,
+
+	TP_PROTO(struct sctp_transport *sp,
+		 const struct sctp_association *asoc),
+
+	TP_ARGS(sp, asoc),
+
+	TP_STRUCT__entry(
+		__field(__u64, asoc)
+		__field(__u32, primary)
+		__array(__u8, ipaddr, sizeof(union sctp_addr))
+		__field(__u32, state)
+		__field(__u32, cwnd)
+		__field(__u32, ssthresh)
+		__field(__u32, flight_size)
+		__field(__u32, partial_bytes_acked)
+		__field(__u32, pathmtu)
+	),
+
+	TP_fast_assign(
+		__entry->asoc = (unsigned long)asoc;
+		__entry->primary = (sp == asoc->peer.primary_path);
+		memcpy(__entry->ipaddr, &sp->ipaddr, sizeof(union sctp_addr));
+		__entry->state = sp->state;
+		__entry->cwnd = sp->cwnd;
+		__entry->ssthresh = sp->ssthresh;
+		__entry->flight_size = sp->flight_size;
+		__entry->partial_bytes_acked = sp->partial_bytes_acked;
+		__entry->pathmtu = sp->pathmtu;
+	),
+
+	TP_printk("asoc=%#llx%s ipaddr=%pISpc state=%u cwnd=%u ssthresh=%u "
+		  "flight_size=%u partial_bytes_acked=%u pathmtu=%u",
+		  __entry->asoc, __entry->primary ? "(*)" : "",
+		  __entry->ipaddr, __entry->state, __entry->cwnd,
+		  __entry->ssthresh, __entry->flight_size,
+		  __entry->partial_bytes_acked, __entry->pathmtu)
+);
+
+TRACE_EVENT(sctp_probe,
+
+	TP_PROTO(const struct sctp_endpoint *ep,
+		 const struct sctp_association *asoc,
+		 struct sctp_chunk *chunk),
+
+	TP_ARGS(ep, asoc, chunk),
+
+	TP_STRUCT__entry(
+		__field(__u64, asoc)
+		__field(__u32, mark)
+		__field(__u16, bind_port)
+		__field(__u16, peer_port)
+		__field(__u32, pathmtu)
+		__field(__u32, rwnd)
+		__field(__u16, unack_data)
+	),
+
+	TP_fast_assign(
+		struct sk_buff *skb = chunk->skb;
+
+		__entry->asoc = (unsigned long)asoc;
+		__entry->mark = skb->mark;
+		__entry->bind_port = ep->base.bind_addr.port;
+		__entry->peer_port = asoc->peer.port;
+		__entry->pathmtu = asoc->pathmtu;
+		__entry->rwnd = asoc->peer.rwnd;
+		__entry->unack_data = asoc->unack_data;
+
+		if (trace_sctp_probe_path_enabled()) {
+			struct sctp_transport *sp;
+
+			list_for_each_entry(sp, &asoc->peer.transport_addr_list,
+					    transports) {
+				trace_sctp_probe_path(sp, asoc);
+			}
+		}
+	),
+
+	TP_printk("asoc=%#llx mark=%#x bind_port=%d peer_port=%d pathmtu=%d "
+		  "rwnd=%u unack_data=%d",
+		  __entry->asoc, __entry->mark, __entry->bind_port,
+		  __entry->peer_port, __entry->pathmtu, __entry->rwnd,
+		  __entry->unack_data)
+);
+
+#endif /* _TRACE_SCTP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index ec4dade24466..3176a3931107 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -6,7 +6,58 @@
 #define _TRACE_SOCK_H
 
 #include <net/sock.h>
+#include <net/ipv6.h>
 #include <linux/tracepoint.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#define family_names			\
+		EM(AF_INET)				\
+		EMe(AF_INET6)
+
+/* The protocol traced by inet_sock_set_state */
+#define inet_protocol_names		\
+		EM(IPPROTO_TCP)			\
+		EM(IPPROTO_DCCP)		\
+		EMe(IPPROTO_SCTP)
+
+#define tcp_state_names			\
+		EM(TCP_ESTABLISHED)		\
+		EM(TCP_SYN_SENT)		\
+		EM(TCP_SYN_RECV)		\
+		EM(TCP_FIN_WAIT1)		\
+		EM(TCP_FIN_WAIT2)		\
+		EM(TCP_TIME_WAIT)		\
+		EM(TCP_CLOSE)			\
+		EM(TCP_CLOSE_WAIT)		\
+		EM(TCP_LAST_ACK)		\
+		EM(TCP_LISTEN)			\
+		EM(TCP_CLOSING)			\
+		EMe(TCP_NEW_SYN_RECV)
+
+/* enums need to be exported to user space */
+#undef EM
+#undef EMe
+#define EM(a)       TRACE_DEFINE_ENUM(a);
+#define EMe(a)      TRACE_DEFINE_ENUM(a);
+
+family_names
+inet_protocol_names
+tcp_state_names
+
+#undef EM
+#undef EMe
+#define EM(a)       { a, #a },
+#define EMe(a)      { a, #a }
+
+#define show_family_name(val)			\
+	__print_symbolic(val, family_names)
+
+#define show_inet_protocol_name(val)    \
+	__print_symbolic(val, inet_protocol_names)
+
+#define show_tcp_state_name(val)        \
+	__print_symbolic(val, tcp_state_names)
 
 TRACE_EVENT(sock_rcvqueue_full,
 
@@ -63,6 +114,72 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__entry->rmem_alloc)
 );
 
+TRACE_EVENT(inet_sock_set_state,
+
+	TP_PROTO(const struct sock *sk, const int oldstate, const int newstate),
+
+	TP_ARGS(sk, oldstate, newstate),
+
+	TP_STRUCT__entry(
+		__field(const void *, skaddr)
+		__field(int, oldstate)
+		__field(int, newstate)
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__field(__u16, family)
+		__field(__u8, 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->skaddr = sk;
+		__entry->oldstate = oldstate;
+		__entry->newstate = newstate;
+
+		__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 oldstate=%s newstate=%s",
+			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,
+			show_tcp_state_name(__entry->oldstate),
+			show_tcp_state_name(__entry->newstate))
+);
+
 #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 ab34c561f26b..878b2be7ce77 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM tcp
 
@@ -8,22 +9,7 @@
 #include <linux/tcp.h>
 #include <linux/tracepoint.h>
 #include <net/ipv6.h>
-
-#define tcp_state_name(state)	{ state, #state }
-#define show_tcp_state_name(val)			\
-	__print_symbolic(val,				\
-		tcp_state_name(TCP_ESTABLISHED),	\
-		tcp_state_name(TCP_SYN_SENT),		\
-		tcp_state_name(TCP_SYN_RECV),		\
-		tcp_state_name(TCP_FIN_WAIT1),		\
-		tcp_state_name(TCP_FIN_WAIT2),		\
-		tcp_state_name(TCP_TIME_WAIT),		\
-		tcp_state_name(TCP_CLOSE),		\
-		tcp_state_name(TCP_CLOSE_WAIT),		\
-		tcp_state_name(TCP_LAST_ACK),		\
-		tcp_state_name(TCP_LISTEN),		\
-		tcp_state_name(TCP_CLOSING),		\
-		tcp_state_name(TCP_NEW_SYN_RECV))
+#include <net/tcp.h>
 
 #define TP_STORE_V4MAPPED(__entry, saddr, daddr)		\
 	do {							\
@@ -270,6 +256,64 @@ TRACE_EVENT(tcp_retransmit_synack,
 		  __entry->saddr_v6, __entry->daddr_v6)
 );
 
+#include <trace/events/net_probe_common.h>
+
+TRACE_EVENT(tcp_probe,
+
+	TP_PROTO(struct sock *sk, struct sk_buff *skb),
+
+	TP_ARGS(sk, skb),
+
+	TP_STRUCT__entry(
+		/* sockaddr_in6 is always bigger than sockaddr_in */
+		__array(__u8, saddr, sizeof(struct sockaddr_in6))
+		__array(__u8, daddr, sizeof(struct sockaddr_in6))
+		__field(__u16, sport)
+		__field(__u16, dport)
+		__field(__u32, mark)
+		__field(__u16, length)
+		__field(__u32, snd_nxt)
+		__field(__u32, snd_una)
+		__field(__u32, snd_cwnd)
+		__field(__u32, ssthresh)
+		__field(__u32, snd_wnd)
+		__field(__u32, srtt)
+		__field(__u32, rcv_wnd)
+	),
+
+	TP_fast_assign(
+		const struct tcp_sock *tp = tcp_sk(sk);
+		const struct inet_sock *inet = inet_sk(sk);
+
+		memset(__entry->saddr, 0, sizeof(struct sockaddr_in6));
+		memset(__entry->daddr, 0, sizeof(struct sockaddr_in6));
+
+		TP_STORE_ADDR_PORTS(__entry, inet, sk);
+
+		/* For filtering use */
+		__entry->sport = ntohs(inet->inet_sport);
+		__entry->dport = ntohs(inet->inet_dport);
+		__entry->mark = skb->mark;
+
+		__entry->length = skb->len;
+		__entry->snd_nxt = tp->snd_nxt;
+		__entry->snd_una = tp->snd_una;
+		__entry->snd_cwnd = tp->snd_cwnd;
+		__entry->snd_wnd = tp->snd_wnd;
+		__entry->rcv_wnd = tp->rcv_wnd;
+		__entry->ssthresh = tcp_current_ssthresh(sk);
+		__entry->srtt = tp->srtt_us >> 3;
+	),
+
+	TP_printk("src=%pISpc dest=%pISpc mark=%#x length=%d snd_nxt=%#x "
+		  "snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u "
+		  "rcv_wnd=%u",
+		  __entry->saddr, __entry->daddr, __entry->mark,
+		  __entry->length, __entry->snd_nxt, __entry->snd_una,
+		  __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd,
+		  __entry->srtt, __entry->rcv_wnd)
+);
+
 #endif /* _TRACE_TCP_H */
 
 /* This part must be outside protection */