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, 102 insertions, 32 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d448a4804aea..54fe91183a8e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
  * the end of the header data, ie. at skb->end.
  */
 struct skb_shared_info {
-	unsigned short	_unused;
-	unsigned char	nr_frags;
+	__u8		__unused;
+	__u8		meta_len;
+	__u8		nr_frags;
 	__u8		tx_flags;
 	unsigned short	gso_size;
 	/* Warning: this field is not always filled in (UFO)! */
@@ -499,7 +500,6 @@ struct skb_shared_info {
 	struct skb_shared_hwtstamps hwtstamps;
 	unsigned int	gso_type;
 	u32		tskey;
-	__be32          ip6_frag_id;
 
 	/*
 	 * Warning : all fields before dataref are cleared in __alloc_skb()
@@ -616,6 +616,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@nf_trace: netfilter packet trace flag
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
+ *	@tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
  *	@_nfct: Associated connection, if any (with nfctinfo bits)
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
@@ -661,8 +662,12 @@ struct sk_buff {
 			struct sk_buff		*prev;
 
 			union {
-				ktime_t		tstamp;
-				u64		skb_mstamp;
+				struct net_device	*dev;
+				/* Some protocols might use this space to store information,
+				 * while device pointer would be NULL.
+				 * UDP receive path is one user.
+				 */
+				unsigned long		dev_scratch;
 			};
 		};
 		struct rb_node	rbnode; /* used in netem & tcp stack */
@@ -670,12 +675,8 @@ struct sk_buff {
 	struct sock		*sk;
 
 	union {
-		struct net_device	*dev;
-		/* Some protocols might use this space to store information,
-		 * while device pointer would be NULL.
-		 * UDP receive path is one user.
-		 */
-		unsigned long		dev_scratch;
+		ktime_t		tstamp;
+		u64		skb_mstamp;
 	};
 	/*
 	 * This is the control buffer. It is free to use for every
@@ -685,8 +686,14 @@ struct sk_buff {
 	 */
 	char			cb[48] __aligned(8);
 
-	unsigned long		_skb_refdst;
-	void			(*destructor)(struct sk_buff *skb);
+	union {
+		struct {
+			unsigned long	_skb_refdst;
+			void		(*destructor)(struct sk_buff *skb);
+		};
+		struct list_head	tcp_tsorted_anchor;
+	};
+
 #ifdef CONFIG_XFRM
 	struct	sec_path	*sp;
 #endif
@@ -771,6 +778,7 @@ struct sk_buff {
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
 	__u8			offload_fwd_mark:1;
+	__u8			offload_mr_fwd_mark:1;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
 	__u8			tc_skip_classify:1;
@@ -1457,27 +1465,8 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
 }
 
 /**
- *	skb_header_release - release reference to header
- *	@skb: buffer to operate on
- *
- *	Drop a reference to the header part of the buffer.  This is done
- *	by acquiring a payload reference.  You must not read from the header
- *	part of skb->data after this.
- *	Note : Check if you can use __skb_header_release() instead.
- */
-static inline void skb_header_release(struct sk_buff *skb)
-{
-	BUG_ON(skb->nohdr);
-	skb->nohdr = 1;
-	atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
-}
-
-/**
  *	__skb_header_release - release reference to header
  *	@skb: buffer to operate on
- *
- *	Variant of skb_header_release() assuming skb is private to caller.
- *	We can avoid one atomic operation.
  */
 static inline void __skb_header_release(struct sk_buff *skb)
 {
@@ -3168,6 +3157,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 	return __skb_grow(skb, len);
 }
 
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+#define skb_rb_first(root) rb_to_skb(rb_first(root))
+#define skb_rb_last(root)  rb_to_skb(rb_last(root))
+#define skb_rb_next(skb)   rb_to_skb(rb_next(&(skb)->rbnode))
+#define skb_rb_prev(skb)   rb_to_skb(rb_prev(&(skb)->rbnode))
+
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     skb != (struct sk_buff *)(queue);				\
@@ -3182,6 +3177,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 		for (; skb != (struct sk_buff *)(queue);			\
 		     skb = skb->next)
 
+#define skb_rbtree_walk(skb, root)						\
+		for (skb = skb_rb_first(root); skb != NULL;			\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from(skb)						\
+		for (; skb != NULL;						\
+		     skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from_safe(skb, tmp)					\
+		for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL);	\
+		     skb = tmp)
+
 #define skb_queue_walk_from_safe(queue, skb, tmp)				\
 		for (tmp = skb->next;						\
 		     skb != (struct sk_buff *)(queue);				\
@@ -3419,6 +3426,69 @@ static inline ktime_t net_invalid_timestamp(void)
 	return 0;
 }
 
+static inline u8 skb_metadata_len(const struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->meta_len;
+}
+
+static inline void *skb_metadata_end(const struct sk_buff *skb)
+{
+	return skb_mac_header(skb);
+}
+
+static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
+					  const struct sk_buff *skb_b,
+					  u8 meta_len)
+{
+	const void *a = skb_metadata_end(skb_a);
+	const void *b = skb_metadata_end(skb_b);
+	/* Using more efficient varaiant than plain call to memcmp(). */
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	u64 diffs = 0;
+
+	switch (meta_len) {
+#define __it(x, op) (x -= sizeof(u##op))
+#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
+	case 32: diffs |= __it_diff(a, b, 64);
+	case 24: diffs |= __it_diff(a, b, 64);
+	case 16: diffs |= __it_diff(a, b, 64);
+	case  8: diffs |= __it_diff(a, b, 64);
+		break;
+	case 28: diffs |= __it_diff(a, b, 64);
+	case 20: diffs |= __it_diff(a, b, 64);
+	case 12: diffs |= __it_diff(a, b, 64);
+	case  4: diffs |= __it_diff(a, b, 32);
+		break;
+	}
+	return diffs;
+#else
+	return memcmp(a - meta_len, b - meta_len, meta_len);
+#endif
+}
+
+static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
+					const struct sk_buff *skb_b)
+{
+	u8 len_a = skb_metadata_len(skb_a);
+	u8 len_b = skb_metadata_len(skb_b);
+
+	if (!(len_a | len_b))
+		return false;
+
+	return len_a != len_b ?
+	       true : __skb_metadata_differs(skb_a, skb_b, len_a);
+}
+
+static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len)
+{
+	skb_shinfo(skb)->meta_len = meta_len;
+}
+
+static inline void skb_metadata_clear(struct sk_buff *skb)
+{
+	skb_metadata_set(skb, 0);
+}
+
 struct sk_buff *skb_clone_sk(struct sk_buff *skb);
 
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING