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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 77 insertions, 13 deletions

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 2040bff945d4..53f464d7cddc 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -36,25 +36,19 @@ struct inet_peer {
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
 	unsigned long		rate_last;
-	unsigned long		pmtu_expires;
-	u32			pmtu_orig;
-	u32			pmtu_learned;
-	struct inetpeer_addr_base redirect_learned;
 	union {
 		struct list_head	gc_list;
 		struct rcu_head     gc_rcu;
 	};
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp
+	 * are not available: rid, ip_id_count
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
 			atomic_t			ip_id_count;	/* IP ID for the next packet */
-			__u32				tcp_ts;
-			__u32				tcp_ts_stamp;
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
@@ -65,6 +59,69 @@ struct inet_peer {
 	atomic_t		refcnt;
 };
 
+struct inet_peer_base {
+	struct inet_peer __rcu	*root;
+	seqlock_t		lock;
+	u32			flush_seq;
+	int			total;
+};
+
+#define INETPEER_BASE_BIT	0x1UL
+
+static inline struct inet_peer *inetpeer_ptr(unsigned long val)
+{
+	BUG_ON(val & INETPEER_BASE_BIT);
+	return (struct inet_peer *) val;
+}
+
+static inline struct inet_peer_base *inetpeer_base_ptr(unsigned long val)
+{
+	if (!(val & INETPEER_BASE_BIT))
+		return NULL;
+	val &= ~INETPEER_BASE_BIT;
+	return (struct inet_peer_base *) val;
+}
+
+static inline bool inetpeer_ptr_is_peer(unsigned long val)
+{
+	return !(val & INETPEER_BASE_BIT);
+}
+
+static inline void __inetpeer_ptr_set_peer(unsigned long *val, struct inet_peer *peer)
+{
+	/* This implicitly clears INETPEER_BASE_BIT */
+	*val = (unsigned long) peer;
+}
+
+static inline bool inetpeer_ptr_set_peer(unsigned long *ptr, struct inet_peer *peer)
+{
+	unsigned long val = (unsigned long) peer;
+	unsigned long orig = *ptr;
+
+	if (!(orig & INETPEER_BASE_BIT) ||
+	    cmpxchg(ptr, orig, val) != orig)
+		return false;
+	return true;
+}
+
+static inline void inetpeer_init_ptr(unsigned long *ptr, struct inet_peer_base *base)
+{
+	*ptr = (unsigned long) base | INETPEER_BASE_BIT;
+}
+
+static inline void inetpeer_transfer_peer(unsigned long *to, unsigned long *from)
+{
+	unsigned long val = *from;
+
+	*to = val;
+	if (inetpeer_ptr_is_peer(val)) {
+		struct inet_peer *peer = inetpeer_ptr(val);
+		atomic_inc(&peer->refcnt);
+	}
+}
+
+extern void inet_peer_base_init(struct inet_peer_base *);
+
 void			inet_initpeers(void) __init;
 
 #define INETPEER_METRICS_NEW	(~(u32) 0)
@@ -75,31 +132,38 @@ static inline bool inet_metrics_new(const struct inet_peer *p)
 }
 
 /* can be called with or without local BH being disabled */
-struct inet_peer	*inet_getpeer(const struct inetpeer_addr *daddr, int create);
+struct inet_peer *inet_getpeer(struct inet_peer_base *base,
+			       const struct inetpeer_addr *daddr,
+			       int create);
 
-static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create)
+static inline struct inet_peer *inet_getpeer_v4(struct inet_peer_base *base,
+						__be32 v4daddr,
+						int create)
 {
 	struct inetpeer_addr daddr;
 
 	daddr.addr.a4 = v4daddr;
 	daddr.family = AF_INET;
-	return inet_getpeer(&daddr, create);
+	return inet_getpeer(base, &daddr, create);
 }
 
-static inline struct inet_peer *inet_getpeer_v6(const struct in6_addr *v6daddr, int create)
+static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
+						const struct in6_addr *v6daddr,
+						int create)
 {
 	struct inetpeer_addr daddr;
 
 	*(struct in6_addr *)daddr.addr.a6 = *v6daddr;
 	daddr.family = AF_INET6;
-	return inet_getpeer(&daddr, create);
+	return inet_getpeer(base, &daddr, create);
 }
 
 /* can be called from BH context or outside */
 extern void inet_putpeer(struct inet_peer *p);
 extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 
-extern void inetpeer_invalidate_tree(int family);
+extern void inetpeer_invalidate_tree(struct inet_peer_base *);
+extern void inetpeer_invalidate_family(int family);
 
 /*
  * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,