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

Pull networking updates from David Miller:
 "Highlights:

   1) Support SPI based w5100 devices, from Akinobu Mita.

   2) Partial Segmentation Offload, from Alexander Duyck.

   3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE.

   4) Allow cls_flower stats offload, from Amir Vadai.

   5) Implement bpf blinding, from Daniel Borkmann.

   6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is
      actually using FASYNC these atomics are superfluous.  From Eric
      Dumazet.

   7) Run TCP more preemptibly, also from Eric Dumazet.

   8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e
      driver, from Gal Pressman.

   9) Allow creating ppp devices via rtnetlink, from Guillaume Nault.

  10) Improve BPF usage documentation, from Jesper Dangaard Brouer.

  11) Support tunneling offloads in qed, from Manish Chopra.

  12) aRFS offloading in mlx5e, from Maor Gottlieb.

  13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo
      Leitner.

  14) Add MSG_EOR support to TCP, this allows controlling packet
      coalescing on application record boundaries for more accurate
      socket timestamp sampling.  From Martin KaFai Lau.

  15) Fix alignment of 64-bit netlink attributes across the board, from
      Nicolas Dichtel.

  16) Per-vlan stats in bridging, from Nikolay Aleksandrov.

  17) Several conversions of drivers to ethtool ksettings, from Philippe
      Reynes.

  18) Checksum neutral ILA in ipv6, from Tom Herbert.

  19) Factorize all of the various marvell dsa drivers into one, from
      Vivien Didelot

  20) Add VF support to qed driver, from Yuval Mintz"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits)
  Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m"
  Revert "phy dp83867: Make rgmii parameters optional"
  r8169: default to 64-bit DMA on recent PCIe chips
  phy dp83867: Make rgmii parameters optional
  phy dp83867: Fix compilation with CONFIG_OF_MDIO=m
  bpf: arm64: remove callee-save registers use for tmp registers
  asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions
  switchdev: pass pointer to fib_info instead of copy
  net_sched: close another race condition in tcf_mirred_release()
  tipc: fix nametable publication field in nl compat
  drivers: net: Don't print unpopulated net_device name
  qed: add support for dcbx.
  ravb: Add missing free_irq() calls to ravb_close()
  qed: Remove a stray tab
  net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fec-mpc52xx: use phydev from struct net_device
  bpf, doc: fix typo on bpf_asm descriptions
  stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set
  net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fs-enet: use phydev from struct net_device
  ...

1 files changed, 53 insertions, 28 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6db10228113f..0bcc70f4e1fb 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -332,9 +332,8 @@ bool tcp_check_oom(struct sock *sk, int shift);
 extern struct proto tcp_prot;
 
 #define TCP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.tcp_statistics, field)
-#define TCP_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field)
+#define __TCP_INC_STATS(net, field)	__SNMP_INC_STATS((net)->mib.tcp_statistics, field)
 #define TCP_DEC_STATS(net, field)	SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
-#define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
 #define TCP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
 
 void tcp_tasklet_init(void);
@@ -452,10 +451,15 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
+enum tcp_synack_type {
+	TCP_SYNACK_NORMAL,
+	TCP_SYNACK_FASTOPEN,
+	TCP_SYNACK_COOKIE,
+};
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				bool attach_req);
+				enum tcp_synack_type synack_type);
 int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -533,8 +537,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 			       int nonagle);
 bool tcp_may_send_now(struct sock *sk);
-int __tcp_retransmit_skb(struct sock *, struct sk_buff *);
-int tcp_retransmit_skb(struct sock *, struct sk_buff *);
+int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
+int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
 void tcp_retransmit_timer(struct sock *sk);
 void tcp_xmit_retransmit_queue(struct sock *);
 void tcp_simple_retransmit(struct sock *);
@@ -756,14 +760,21 @@ struct tcp_skb_cb {
 				TCPCB_REPAIRED)
 
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
-	/* 1 byte hole */
+	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+			eor:1,		/* Is skb MSG_EOR marked? */
+			unused:6;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
-		struct inet_skb_parm	h4;
+		struct {
+			/* There is space for up to 20 bytes */
+		} tx;   /* only used for outgoing skbs */
+		union {
+			struct inet_skb_parm	h4;
 #if IS_ENABLED(CONFIG_IPV6)
-		struct inet6_skb_parm	h6;
+			struct inet6_skb_parm	h6;
 #endif
-	} header;	/* For incoming frames		*/
+		} header;	/* For incoming skbs */
+	};
 };
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
@@ -775,7 +786,9 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
-	return TCP_SKB_CB(skb)->header.h6.iif;
+	bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+
+	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
 #endif
 
@@ -803,6 +816,11 @@ static inline int tcp_skb_mss(const struct sk_buff *skb)
 	return TCP_SKB_CB(skb)->tcp_gso_size;
 }
 
+static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
+{
+	return likely(!TCP_SKB_CB(skb)->eor);
+}
+
 /* Events passed to congestion control interface */
 enum tcp_ca_event {
 	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
@@ -838,6 +856,11 @@ enum tcp_ca_ack_event_flags {
 
 union tcp_cc_info;
 
+struct ack_sample {
+	u32 pkts_acked;
+	s32 rtt_us;
+};
+
 struct tcp_congestion_ops {
 	struct list_head	list;
 	u32 key;
@@ -861,7 +884,7 @@ struct tcp_congestion_ops {
 	/* new value of cwnd after loss (optional) */
 	u32  (*undo_cwnd)(struct sock *sk);
 	/* hook for packet ack accounting (optional) */
-	void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
+	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
 	/* get info for inet_diag (optional) */
 	size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
 			   union tcp_cc_info *info);
@@ -1041,17 +1064,6 @@ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp)
 	return 3;
 }
 
-/* Slow start with delack produces 3 packets of burst, so that
- * it is safe "de facto".  This will be the default - same as
- * the default reordering threshold - but if reordering increases,
- * we must be able to allow cwnd to burst at least this much in order
- * to not pull it back when holes are filled.
- */
-static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
-{
-	return tp->reordering;
-}
-
 /* Returns end sequence number of the receiver's advertised window */
 static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
 {
@@ -1303,10 +1315,10 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 static inline void tcp_mib_init(struct net *net)
 {
 	/* See RFC 2012 */
-	TCP_ADD_STATS_USER(net, TCP_MIB_RTOALGORITHM, 1);
-	TCP_ADD_STATS_USER(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
-	TCP_ADD_STATS_USER(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
-	TCP_ADD_STATS_USER(net, TCP_MIB_MAXCONN, -1);
+	TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1);
+	TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
+	TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
+	TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1);
 }
 
 /* from STCP */
@@ -1740,7 +1752,7 @@ struct tcp_request_sock_ops {
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
-			   bool attach_req);
+			   enum tcp_synack_type synack_type);
 };
 
 #ifdef CONFIG_SYN_COOKIES
@@ -1749,7 +1761,7 @@ static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
 					 __u16 *mss)
 {
 	tcp_synq_overflow(sk);
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
 	return ops->cookie_init_seq(skb, mss);
 }
 #else
@@ -1848,4 +1860,17 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
 		tp->data_segs_in += segs_in;
 }
 
+/*
+ * TCP listen path runs lockless.
+ * We forced "struct sock" to be const qualified to make sure
+ * we don't modify one of its field by mistake.
+ * Here, we increment sk_drops which is an atomic_t, so we can safely
+ * make sock writable again.
+ */
+static inline void tcp_listendrop(const struct sock *sk)
+{
+	atomic_inc(&((struct sock *)sk)->sk_drops);
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
+}
+
 #endif	/* _TCP_H */