1 files changed, 151 insertions, 62 deletions

diff --git a/kernel/include/net/tcp.h b/kernel/include/net/tcp.h
index 6d204f3f9..414d822bc 100644
--- a/kernel/include/net/tcp.h
+++ b/kernel/include/net/tcp.h
@@ -279,13 +279,24 @@ extern int sysctl_tcp_limit_output_bytes;
 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_min_rtt_wlen;
 extern int sysctl_tcp_autocorking;
 extern int sysctl_tcp_invalid_ratelimit;
+extern int sysctl_tcp_pacing_ss_ratio;
+extern int sysctl_tcp_pacing_ca_ratio;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
 extern int tcp_memory_pressure;
 
+/* optimized version of sk_under_memory_pressure() for TCP sockets */
+static inline bool tcp_under_memory_pressure(const struct sock *sk)
+{
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return !!sk->sk_cgrp->memory_pressure;
+
+	return tcp_memory_pressure;
+}
 /*
  * The next routines deal with comparing 32 bit unsigned ints
  * and worry about wraparound (automatic with unsigned arithmetic).
@@ -311,6 +322,8 @@ static inline bool tcp_out_of_memory(struct sock *sk)
 	return false;
 }
 
+void sk_forced_mem_schedule(struct sock *sk, int size);
+
 static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 {
 	struct percpu_counter *ocp = sk->sk_prot->orphan_count;
@@ -326,18 +339,6 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 
 bool tcp_check_oom(struct sock *sk, int shift);
 
-/* syncookies: remember time of last synqueue overflow */
-static inline void tcp_synq_overflow(struct sock *sk)
-{
-	tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
-}
-
-/* syncookies: no recent synqueue overflow on this listening socket? */
-static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
-{
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK);
-}
 
 extern struct proto tcp_prot;
 
@@ -365,8 +366,7 @@ void tcp_wfree(struct sk_buff *skb);
 void tcp_write_timer_handler(struct sock *sk);
 void tcp_delack_timer_handler(struct sock *sk);
 int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
-int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
-			  const struct tcphdr *th, unsigned int len);
+int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			 const struct tcphdr *th, unsigned int len);
 void tcp_rcv_space_adjust(struct sock *sk);
@@ -449,21 +449,24 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
-void tcp_req_err(struct sock *sk, u32 seq);
+void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
-struct sock *tcp_create_openreq_child(struct sock *sk,
+struct sock *tcp_create_openreq_child(const 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 sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
-				  struct dst_entry *dst);
+				  struct dst_entry *dst,
+				  struct request_sock *req_unhash,
+				  bool *own_req);
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
-struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
-				struct tcp_fastopen_cookie *foc);
+				struct tcp_fastopen_cookie *foc,
+				bool attach_req);
 int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -471,6 +474,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size);
 void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 
 /* From syncookies.c */
+struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
+				 struct request_sock *req,
+				 struct dst_entry *dst);
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 		      u32 cookie);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
@@ -483,20 +489,42 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
  * the counter advances immediately after a cookie is generated).
  */
-#define MAX_SYNCOOKIE_AGE 2
+#define MAX_SYNCOOKIE_AGE	2
+#define TCP_SYNCOOKIE_PERIOD	(60 * HZ)
+#define TCP_SYNCOOKIE_VALID	(MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD)
+
+/* syncookies: remember time of last synqueue overflow
+ * But do not dirty this field too often (once per second is enough)
+ * It is racy as we do not hold a lock, but race is very minor.
+ */
+static inline void tcp_synq_overflow(const struct sock *sk)
+{
+	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned long now = jiffies;
+
+	if (time_after(now, last_overflow + HZ))
+		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+}
+
+/* syncookies: no recent synqueue overflow on this listening socket? */
+static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
+{
+	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+
+	return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+}
 
 static inline u32 tcp_cookie_time(void)
 {
 	u64 val = get_jiffies_64();
 
-	do_div(val, 60 * HZ);
+	do_div(val, TCP_SYNCOOKIE_PERIOD);
 	return val;
 }
 
 u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 			      u16 *mssp);
-__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb,
-			      __u16 *mss);
+__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
 __u32 cookie_init_timestamp(struct request_sock *req);
 bool cookie_timestamp_decode(struct tcp_options_received *opt);
 bool cookie_ecn_ok(const struct tcp_options_received *opt,
@@ -509,8 +537,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
 
 u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
 			      const struct tcphdr *th, u16 *mssp);
-__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb,
-			      __u16 *mss);
+__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
 #endif
 /* tcp_output.c */
 
@@ -527,7 +554,7 @@ int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
 
 void tcp_send_probe0(struct sock *);
 void tcp_send_partial(struct sock *);
-int tcp_write_wakeup(struct sock *);
+int tcp_write_wakeup(struct sock *, int mib);
 void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
@@ -540,7 +567,9 @@ bool tcp_schedule_loss_probe(struct sock *sk);
 /* tcp_input.c */
 void tcp_resume_early_retransmit(struct sock *sk);
 void tcp_rearm_rto(struct sock *sk);
+void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
 void tcp_reset(struct sock *sk);
+void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
 
 /* tcp_timer.c */
 void tcp_init_xmit_timers(struct sock *);
@@ -646,6 +675,12 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
 	return dst_metric_locked(dst, RTAX_CC_ALGO);
 }
 
+/* Minimum RTT in usec. ~0 means not available. */
+static inline u32 tcp_min_rtt(const struct tcp_sock *tp)
+{
+	return tp->rtt_min[0].rtt;
+}
+
 /* 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.
@@ -692,6 +727,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
 #define TCPHDR_ECE 0x40
 #define TCPHDR_CWR 0x80
 
+#define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
+
 /* This is what the send packet queuing engine uses to pass
  * TCP per-packet control information to the transmission code.
  * We also store the host-order sequence numbers in here too.
@@ -705,11 +742,14 @@ struct tcp_skb_cb {
 		/* 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()
+		 * 	  tcp_gso_segs/size are used in write queue only,
+		 *	  cf tcp_skb_pcount()/tcp_skb_mss()
 		 */
 		__u32		tcp_tw_isn;
-		__u32		tcp_gso_segs;
+		struct {
+			u16	tcp_gso_segs;
+			u16	tcp_gso_size;
+		};
 	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
@@ -765,10 +805,10 @@ static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs)
 	TCP_SKB_CB(skb)->tcp_gso_segs += segs;
 }
 
-/* This is valid iff tcp_skb_pcount() > 1. */
+/* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */
 static inline int tcp_skb_mss(const struct sk_buff *skb)
 {
-	return skb_shinfo(skb)->gso_size;
+	return TCP_SKB_CB(skb)->tcp_gso_size;
 }
 
 /* Events passed to congestion control interface */
@@ -858,7 +898,7 @@ 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);
+u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);
 #ifdef CONFIG_INET
 char *tcp_ca_get_name_by_key(u32 key, char *buffer);
 #else
@@ -961,6 +1001,11 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
 
 #define TCP_INFINITE_SSTHRESH	0x7fffffff
 
+static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+	return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
 static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
 {
 	return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
@@ -1037,20 +1082,37 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
+	if (tcp_in_slow_start(tp))
 		return tp->snd_cwnd < 2 * tp->max_packets_out;
 
 	return tp->is_cwnd_limited;
 }
 
-static inline void tcp_check_probe_timer(struct sock *sk)
+/* Something is really bad, we could not queue an additional packet,
+ * because qdisc is full or receiver sent a 0 window.
+ * We do not want to add fuel to the fire, or abort too early,
+ * so make sure the timer we arm now is at least 200ms in the future,
+ * regardless of current icsk_rto value (as it could be ~2ms)
+ */
+static inline unsigned long tcp_probe0_base(const struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN);
+}
+
+/* Variant of inet_csk_rto_backoff() used for zero window probes */
+static inline unsigned long tcp_probe0_when(const struct sock *sk,
+					    unsigned long max_when)
+{
+	u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff;
+
+	return (unsigned long)min_t(u64, when, max_when);
+}
 
-	if (!tp->packets_out && !icsk->icsk_pending)
+static inline void tcp_check_probe_timer(struct sock *sk)
+{
+	if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  icsk->icsk_rto, TCP_RTO_MAX);
+					  tcp_probe0_base(sk), TCP_RTO_MAX);
 }
 
 static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
@@ -1115,6 +1177,19 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 }
 
 u32 tcp_default_init_rwnd(u32 mss);
+void tcp_cwnd_restart(struct sock *sk, s32 delta);
+
+static inline void tcp_slow_start_after_idle_check(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	s32 delta;
+
+	if (!sysctl_tcp_slow_start_after_idle || tp->packets_out)
+		return;
+	delta = tcp_time_stamp - tp->lsndtime;
+	if (delta > inet_csk(sk)->icsk_rto)
+		tcp_cwnd_restart(sk, delta);
+}
 
 /* Determine a window scaling and initial window to offer. */
 void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
@@ -1141,7 +1216,8 @@ static inline int tcp_full_space(const struct sock *sk)
 }
 
 extern void tcp_openreq_init_rwin(struct request_sock *req,
-				  struct sock *sk, struct dst_entry *dst);
+				  const struct sock *sk_listener,
+				  const struct dst_entry *dst);
 
 void tcp_enter_memory_pressure(struct sock *sk);
 
@@ -1305,16 +1381,16 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp);
 int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
 		   int family);
-struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
 					 const union tcp_md5_addr *addr,
 					 int family);
 #define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_key)
 #else
-static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
 					 const union tcp_md5_addr *addr,
 					 int family)
 {
@@ -1355,10 +1431,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
 
 extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 int tcp_fastopen_reset_cipher(void *key, unsigned int len);
-bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
-		      struct request_sock *req,
-		      struct tcp_fastopen_cookie *foc,
-		      struct dst_entry *dst);
+struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+			      struct request_sock *req,
+			      struct tcp_fastopen_cookie *foc,
+			      struct dst_entry *dst);
 void tcp_fastopen_init_key_once(bool publish);
 #define TCP_FASTOPEN_KEY_LENGTH 16
 
@@ -1553,7 +1629,6 @@ static inline bool tcp_stream_is_thin(struct tcp_sock *tp)
 /* /proc */
 enum tcp_seq_states {
 	TCP_SEQ_STATE_LISTENING,
-	TCP_SEQ_STATE_OPENREQ,
 	TCP_SEQ_STATE_ESTABLISHED,
 };
 
@@ -1572,7 +1647,6 @@ struct tcp_iter_state {
 	enum tcp_seq_states	state;
 	struct sock		*syn_wait_sk;
 	int			bucket, offset, sbucket, num;
-	kuid_t			uid;
 	loff_t			last_pos;
 };
 
@@ -1609,7 +1683,7 @@ int tcp4_proc_init(void);
 void tcp4_proc_exit(void);
 #endif
 
-int tcp_rtx_synack(struct sock *sk, struct request_sock *req);
+int tcp_rtx_synack(const struct sock *sk, struct request_sock *req);
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb);
@@ -1617,7 +1691,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 /* TCP af-specific functions */
 struct tcp_sock_af_ops {
 #ifdef CONFIG_TCP_MD5SIG
-	struct tcp_md5sig_key	*(*md5_lookup) (struct sock *sk,
+	struct tcp_md5sig_key	*(*md5_lookup) (const struct sock *sk,
 						const struct sock *addr_sk);
 	int		(*calc_md5_hash)(char *location,
 					 const struct tcp_md5sig_key *md5,
@@ -1632,40 +1706,42 @@ struct tcp_sock_af_ops {
 struct tcp_request_sock_ops {
 	u16 mss_clamp;
 #ifdef CONFIG_TCP_MD5SIG
-	struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk,
+	struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk,
 						 const struct sock *addr_sk);
 	int		(*calc_md5_hash) (char *location,
 					  const struct tcp_md5sig_key *md5,
 					  const struct sock *sk,
 					  const struct sk_buff *skb);
 #endif
-	void (*init_req)(struct request_sock *req, struct sock *sk,
+	void (*init_req)(struct request_sock *req,
+			 const struct sock *sk_listener,
 			 struct sk_buff *skb);
 #ifdef CONFIG_SYN_COOKIES
-	__u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb,
+	__u32 (*cookie_init_seq)(const struct sk_buff *skb,
 				 __u16 *mss);
 #endif
-	struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl,
+	struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
 				       const struct request_sock *req,
 				       bool *strict);
 	__u32 (*init_seq)(const struct sk_buff *skb);
-	int (*send_synack)(struct sock *sk, struct dst_entry *dst,
+	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
-			   u16 queue_mapping, struct tcp_fastopen_cookie *foc);
-	void (*queue_hash_add)(struct sock *sk, struct request_sock *req,
-			       const unsigned long timeout);
+			   struct tcp_fastopen_cookie *foc,
+			   bool attach_req);
 };
 
 #ifdef CONFIG_SYN_COOKIES
 static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
-					 struct sock *sk, struct sk_buff *skb,
+					 const struct sock *sk, struct sk_buff *skb,
 					 __u16 *mss)
 {
-	return ops->cookie_init_seq(sk, skb, mss);
+	tcp_synq_overflow(sk);
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT);
+	return ops->cookie_init_seq(skb, mss);
 }
 #else
 static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops,
-					 struct sock *sk, struct sk_buff *skb,
+					 const struct sock *sk, struct sk_buff *skb,
 					 __u16 *mss)
 {
 	return 0;
@@ -1677,6 +1753,19 @@ int tcpv4_offload_init(void);
 void tcp_v4_init(void);
 void tcp_init(void);
 
+/* tcp_recovery.c */
+
+/* Flags to enable various loss recovery features. See below */
+extern int sysctl_tcp_recovery;
+
+/* Use TCP RACK to detect (some) tail and retransmit losses */
+#define TCP_RACK_LOST_RETRANS  0x1
+
+extern int tcp_rack_mark_lost(struct sock *sk);
+
+extern void tcp_rack_advance(struct tcp_sock *tp,
+			     const struct skb_mstamp *xmit_time, u8 sacked);
+
 /*
  * Save and compile IPv4 options, return a pointer to it
  */