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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 57 insertions, 28 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7523c325673e..74efeda994b3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -669,6 +669,12 @@ void tcp_send_window_probe(struct sock *sk);
  */
 #define tcp_time_stamp		((__u32)(jiffies))
 
+static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
+{
+	return skb->skb_mstamp.stamp_jiffies;
+}
+
+
 #define tcp_flag_byte(th) (((u_int8_t *)th)[13])
 
 #define TCPHDR_FIN 0x01
@@ -687,15 +693,18 @@ void tcp_send_window_probe(struct sock *sk);
  * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.
  */
 struct tcp_skb_cb {
-	union {
-		struct inet_skb_parm	h4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct inet6_skb_parm	h6;
-#endif
-	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	__u32		when;		/* used to compute rtt's	*/
+	union {
+		/* Note : tcp_tw_isn is used in input path only
+		 *	  (isn chosen by tcp_timewait_state_process())
+		 *
+		 * 	  tcp_gso_segs is used in write queue only,
+		 *	  cf tcp_skb_pcount()
+		 */
+		__u32		tcp_tw_isn;
+		__u32		tcp_gso_segs;
+	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/
@@ -711,33 +720,32 @@ struct tcp_skb_cb {
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	/* 1 byte hole */
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
+	union {
+		struct inet_skb_parm	h4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct inet6_skb_parm	h6;
+#endif
+	} header;	/* For incoming frames		*/
 };
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
-/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
- *
- * If we receive a SYN packet with these bits set, it means a network is
- * playing bad games with TOS bits. In order to avoid possible false congestion
- * notifications, we disable TCP ECN negociation.
+/* Due to TSO, an SKB can be composed of multiple actual
+ * packets.  To keep these tracked properly, we use this.
  */
-static inline void
-TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
-		struct net *net)
+static inline int tcp_skb_pcount(const struct sk_buff *skb)
 {
-	const struct tcphdr *th = tcp_hdr(skb);
+	return TCP_SKB_CB(skb)->tcp_gso_segs;
+}
 
-	if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
-	    INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
-		inet_rsk(req)->ecn_ok = 1;
+static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs)
+{
+	TCP_SKB_CB(skb)->tcp_gso_segs = segs;
 }
 
-/* Due to TSO, an SKB can be composed of multiple actual
- * packets.  To keep these tracked properly, we use this.
- */
-static inline int tcp_skb_pcount(const struct sk_buff *skb)
+static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs)
 {
-	return skb_shinfo(skb)->gso_segs;
+	TCP_SKB_CB(skb)->tcp_gso_segs += segs;
 }
 
 /* This is valid iff tcp_skb_pcount() > 1. */
@@ -752,8 +760,17 @@ enum tcp_ca_event {
 	CA_EVENT_CWND_RESTART,	/* congestion window restart */
 	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
 	CA_EVENT_LOSS,		/* loss timeout */
-	CA_EVENT_FAST_ACK,	/* in sequence ack */
-	CA_EVENT_SLOW_ACK,	/* other ack */
+	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
+	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
+	CA_EVENT_DELAYED_ACK,	/* Delayed ack is sent */
+	CA_EVENT_NON_DELAYED_ACK,
+};
+
+/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
+enum tcp_ca_ack_event_flags {
+	CA_ACK_SLOWPATH		= (1 << 0),	/* In slow path processing */
+	CA_ACK_WIN_UPDATE	= (1 << 1),	/* ACK updated window */
+	CA_ACK_ECE		= (1 << 2),	/* ECE bit is set on ack */
 };
 
 /*
@@ -763,7 +780,10 @@ enum tcp_ca_event {
 #define TCP_CA_MAX	128
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
+/* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
 #define TCP_CONG_NON_RESTRICTED 0x1
+/* Requires ECN/ECT set on all packets */
+#define TCP_CONG_NEEDS_ECN	0x2
 
 struct tcp_congestion_ops {
 	struct list_head	list;
@@ -782,6 +802,8 @@ struct tcp_congestion_ops {
 	void (*set_state)(struct sock *sk, u8 new_state);
 	/* call when cwnd event occurs (optional) */
 	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+	/* call when ack arrives (optional) */
+	void (*in_ack_event)(struct sock *sk, u32 flags);
 	/* new value of cwnd after loss (optional) */
 	u32  (*undo_cwnd)(struct sock *sk);
 	/* hook for packet ack accounting (optional) */
@@ -796,6 +818,7 @@ struct tcp_congestion_ops {
 int tcp_register_congestion_control(struct tcp_congestion_ops *type);
 void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
 
+void tcp_assign_congestion_control(struct sock *sk);
 void tcp_init_congestion_control(struct sock *sk);
 void tcp_cleanup_congestion_control(struct sock *sk);
 int tcp_set_default_congestion_control(const char *name);
@@ -804,14 +827,20 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-int tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
-extern struct tcp_congestion_ops tcp_init_congestion_ops;
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
 extern struct tcp_congestion_ops tcp_reno;
 
+static inline bool tcp_ca_needs_ecn(const struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
+}
+
 static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);