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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 69 insertions, 3 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9d9111ef43ae..8d6b983d5099 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -262,8 +262,6 @@ extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
-extern int sysctl_tcp_mtu_probing;
-extern int sysctl_tcp_base_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_thin_linear_timeouts;
@@ -274,6 +272,7 @@ extern int sysctl_tcp_challenge_ack_limit;
 extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
 extern int sysctl_tcp_autocorking;
+extern int sysctl_tcp_invalid_ratelimit;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -448,6 +447,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(struct sock *sk,
 				      struct request_sock *req,
 				      struct sk_buff *skb);
+void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst);
 struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst);
@@ -636,6 +636,11 @@ static inline u32 tcp_rto_min_us(struct sock *sk)
 	return jiffies_to_usecs(tcp_rto_min(sk));
 }
 
+static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
+{
+	return dst_metric_locked(dst, RTAX_CC_ALGO);
+}
+
 /* Compute the actual receive window we are currently advertising.
  * Rcv_nxt can be after the window if our peer push more data
  * than the offered window.
@@ -787,6 +792,8 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CA_MAX	128
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
+#define TCP_CA_UNSPEC	0
+
 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
 #define TCP_CONG_NON_RESTRICTED 0x1
 /* Requires ECN/ECT set on all packets */
@@ -794,7 +801,8 @@ enum tcp_ca_ack_event_flags {
 
 struct tcp_congestion_ops {
 	struct list_head	list;
-	unsigned long flags;
+	u32 key;
+	u32 flags;
 
 	/* initialize private data (optional) */
 	void (*init)(struct sock *sk);
@@ -841,6 +849,17 @@ 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;
 
+struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
+u32 tcp_ca_get_key_by_name(const char *name);
+#ifdef CONFIG_INET
+char *tcp_ca_get_name_by_key(u32 key, char *buffer);
+#else
+static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer)
+{
+	return NULL;
+}
+#endif
+
 static inline bool tcp_ca_needs_ecn(const struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1124,6 +1143,7 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
 	tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
+	tcp_rsk(req)->last_oow_ack_time = 0;
 	req->mss = rx_opt->mss_clamp;
 	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
 	ireq->tstamp_ok = rx_opt->tstamp_ok;
@@ -1216,6 +1236,37 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
 	return true;
 }
 
+/* Return true if we're currently rate-limiting out-of-window ACKs and
+ * thus shouldn't send a dupack right now. We rate-limit dupacks in
+ * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
+ * attacks that send repeated SYNs or ACKs for the same connection. To
+ * do this, we do not send a duplicate SYNACK or ACK if the remote
+ * endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
+ */
+static inline bool tcp_oow_rate_limited(struct net *net,
+					const struct sk_buff *skb,
+					int mib_idx, u32 *last_oow_ack_time)
+{
+	/* Data packets without SYNs are not likely part of an ACK loop. */
+	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
+	    !tcp_hdr(skb)->syn)
+		goto not_rate_limited;
+
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+not_rate_limited:
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 static inline void tcp_mib_init(struct net *net)
 {
 	/* See RFC 2012 */
@@ -1693,4 +1744,19 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 	return dopt;
 }
 
+/* locally generated TCP pure ACKs have skb->truesize == 2
+ * (check tcp_send_ack() in net/ipv4/tcp_output.c )
+ * This is much faster than dissecting the packet to find out.
+ * (Think of GRE encapsulations, IPv4, IPv6, ...)
+ */
+static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb)
+{
+	return skb->truesize == 2;
+}
+
+static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
+{
+	skb->truesize = 2;
+}
+
 #endif	/* _TCP_H */