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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 31 insertions, 4 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index a6b9a8d1a6df..f8715c5af37d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -60,7 +60,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/cgroup-defs.h>
-
+#include <linux/rbtree.h>
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
 #include <linux/poll.h>
@@ -267,6 +267,7 @@ struct sock_common {
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
   *	@sk_gso_max_size: Maximum GSO segment size to build
   *	@sk_gso_max_segs: Maximum number of GSO segments
+  *	@sk_pacing_shift: scaling factor for TCP Small Queues
   *	@sk_lingertime: %SO_LINGER l_linger setting
   *	@sk_backlog: always used with the per-socket spinlock held
   *	@sk_callback_lock: used with the callbacks in the end of this struct
@@ -397,7 +398,10 @@ struct sock {
 	int			sk_wmem_queued;
 	refcount_t		sk_wmem_alloc;
 	unsigned long		sk_tsq_flags;
-	struct sk_buff		*sk_send_head;
+	union {
+		struct sk_buff	*sk_send_head;
+		struct rb_root	tcp_rtx_queue;
+	};
 	struct sk_buff_head	sk_write_queue;
 	__s32			sk_peek_off;
 	int			sk_write_pending;
@@ -448,6 +452,7 @@ struct sock {
 	kmemcheck_bitfield_end(flags);
 
 	u16			sk_gso_max_segs;
+	u8			sk_pacing_shift;
 	unsigned long	        sk_lingertime;
 	struct proto		*sk_prot_creator;
 	rwlock_t		sk_callback_lock;
@@ -734,10 +739,10 @@ static inline void sk_add_bind_node(struct sock *sk,
  *
  */
 #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset)		       \
-	for (pos = rcu_dereference((head)->first);			       \
+	for (pos = rcu_dereference(hlist_first_rcu(head));		       \
 	     pos != NULL &&						       \
 		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
-	     pos = rcu_dereference(pos->next))
+	     pos = rcu_dereference(hlist_next_rcu(pos)))
 
 static inline struct user_namespace *sk_user_ns(struct sock *sk)
 {
@@ -1098,8 +1103,12 @@ struct proto {
 	 */
 	unsigned long		*memory_pressure;
 	long			*sysctl_mem;
+
 	int			*sysctl_wmem;
 	int			*sysctl_rmem;
+	u32			sysctl_wmem_offset;
+	u32			sysctl_rmem_offset;
+
 	int			max_header;
 	bool			no_autobind;
 
@@ -2387,4 +2396,22 @@ extern int sysctl_optmem_max;
 extern __u32 sysctl_wmem_default;
 extern __u32 sysctl_rmem_default;
 
+static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
+{
+	/* Does this proto have per netns sysctl_wmem ? */
+	if (proto->sysctl_wmem_offset)
+		return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+
+	return *proto->sysctl_wmem;
+}
+
+static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
+{
+	/* Does this proto have per netns sysctl_rmem ? */
+	if (proto->sysctl_rmem_offset)
+		return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+
+	return *proto->sysctl_rmem;
+}
+
 #endif	/* _SOCK_H */