Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

4 files changed, 91 insertions, 12 deletions

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index dc107ffad48..34a1a09e5ae 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -120,6 +120,7 @@ typedef union {
 	int error;
 	sctp_state_t state;
 	sctp_event_timeout_t to;
+	unsigned long zero;
 	void *ptr;
 	struct sctp_chunk *chunk;
 	struct sctp_association *asoc;
@@ -148,17 +149,17 @@ static inline sctp_arg_t SCTP_NULL(void)
 }
 static inline sctp_arg_t SCTP_NOFORCE(void)
 {
-	sctp_arg_t retval; retval.i32 = 0; return retval;
+	sctp_arg_t retval = {.zero = 0UL}; retval.i32 = 0; return retval;
 }
 static inline sctp_arg_t SCTP_FORCE(void)
 {
-	sctp_arg_t retval; retval.i32 = 1; return retval;
+	sctp_arg_t retval = {.zero = 0UL}; retval.i32 = 1; return retval;
 }
 
 #define SCTP_ARG_CONSTRUCTOR(name, type, elt) \
 static inline sctp_arg_t	\
 SCTP_## name (type arg)		\
-{ sctp_arg_t retval; retval.elt = arg; return retval; }
+{ sctp_arg_t retval = {.zero = 0UL}; retval.elt = arg; return retval; }
 
 SCTP_ARG_CONSTRUCTOR(I32,	__s32, i32)
 SCTP_ARG_CONSTRUCTOR(U32,	__u32, u32)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 9c385b6417c..8e7794ee27f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -161,6 +161,13 @@ extern struct sctp_globals {
 	 */
 	int sndbuf_policy;
 
+	/*
+	 * Policy for preforming sctp/socket accounting
+	 * 0   - do socket level accounting, all assocs share sk_rcvbuf
+	 * 1   - do sctp accounting, each asoc may use sk_rcvbuf bytes
+	 */
+	int rcvbuf_policy;
+
 	/* Delayed SACK timeout  200ms default*/
 	int sack_timeout;
 
@@ -218,6 +225,7 @@ extern struct sctp_globals {
 #define sctp_cookie_preserve_enable	(sctp_globals.cookie_preserve_enable)
 #define sctp_max_retrans_association	(sctp_globals.max_retrans_association)
 #define sctp_sndbuf_policy	 	(sctp_globals.sndbuf_policy)
+#define sctp_rcvbuf_policy	 	(sctp_globals.rcvbuf_policy)
 #define sctp_max_retrans_path		(sctp_globals.max_retrans_path)
 #define sctp_max_retrans_init		(sctp_globals.max_retrans_init)
 #define sctp_sack_timeout		(sctp_globals.sack_timeout)
@@ -1222,11 +1230,11 @@ struct sctp_endpoint {
 	int last_key;
 	int key_changed_at;
 
-	/* Default timeouts.  */
-	int timeouts[SCTP_NUM_TIMEOUT_TYPES];
-
 	/* sendbuf acct. policy.	*/
 	__u32 sndbuf_policy;
+
+	/* rcvbuf acct. policy.	*/
+	__u32 rcvbuf_policy;
 };
 
 /* Recover the outter endpoint structure. */
@@ -1553,6 +1561,11 @@ struct sctp_association {
 	 */
 	int sndbuf_used;
 
+	/* This is the amount of memory that this association has allocated
+	 * in the receive path at any given time.
+	 */
+	atomic_t rmem_alloc;
+
 	/* This is the wait queue head for send requests waiting on
 	 * the association sndbuf space.
 	 */
diff --git a/include/net/sock.h b/include/net/sock.h
index ff13c4cc287..982b4ecd187 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1247,6 +1247,12 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk)
 		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
 		     skb = skb->next)
 
+/*from STCP for fast SACK Process*/
+#define sk_stream_for_retrans_queue_from(skb, sk)			\
+		for (; (skb != (sk)->sk_send_head) &&                   \
+		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
+		     skb = skb->next)
+
 /*
  *	Default write policy as shown to user space via poll/select/SIGIO
  */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 96cc3b434e4..0f984801197 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -89,10 +89,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 				 */
 
 #define TCP_SYN_RETRIES	 5	/* number of times to retry active opening a
-				 * connection: ~180sec is RFC minumum	*/
+				 * connection: ~180sec is RFC minimum	*/
 
 #define TCP_SYNACK_RETRIES 5	/* number of times to retry passive opening a
-				 * connection: ~180sec is RFC minumum	*/
+				 * connection: ~180sec is RFC minimum	*/
 
 
 #define TCP_ORPHAN_RETRIES 7	/* number of times to retry on an orphaned
@@ -180,7 +180,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Flags in tp->nonagle */
 #define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
 #define TCP_NAGLE_CORK		2	/* Socket is corked	    */
-#define TCP_NAGLE_PUSH		4	/* Cork is overriden for already queued data */
+#define TCP_NAGLE_PUSH		4	/* Cork is overridden for already queued data */
 
 extern struct inet_timewait_death_row tcp_death_row;
 
@@ -218,6 +218,7 @@ 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_abc;
 
 extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
@@ -551,13 +552,13 @@ extern u32	__tcp_select_window(struct sock *sk);
 
 /* TCP timestamps are only 32-bits, this causes a slight
  * complication on 64-bit systems since we store a snapshot
- * of jiffies in the buffer control blocks below.  We decidely
+ * of jiffies in the buffer control blocks below.  We decidedly
  * only use of the low 32-bits of jiffies and hide the ugly
  * casts with the following macro.
  */
 #define tcp_time_stamp		((__u32)(jiffies))
 
-/* This is what the send packet queueing engine uses to pass
+/* 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.  This is 36 bytes on 32-bit architectures,
@@ -597,7 +598,7 @@ struct tcp_skb_cb {
 #define TCPCB_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
 #define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
 
-#define TCPCB_URG		0x20	/* Urgent pointer advenced here	*/
+#define TCPCB_URG		0x20	/* Urgent pointer advanced here	*/
 
 #define TCPCB_AT_TAIL		(TCPCB_URG)
 
@@ -765,6 +766,33 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 			    (tp->snd_cwnd >> 2)));
 }
 
+/*
+ * Linear increase during slow start
+ */
+static inline void tcp_slow_start(struct tcp_sock *tp)
+{
+	if (sysctl_tcp_abc) {
+		/* RFC3465: Slow Start
+		 * TCP sender SHOULD increase cwnd by the number of
+		 * previously unacknowledged bytes ACKed by each incoming
+		 * acknowledgment, provided the increase is not more than L
+		 */
+		if (tp->bytes_acked < tp->mss_cache)
+			return;
+
+		/* We MAY increase by 2 if discovered delayed ack */
+		if (sysctl_tcp_abc > 1 && tp->bytes_acked > 2*tp->mss_cache) {
+			if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+				tp->snd_cwnd++;
+		}
+	}
+	tp->bytes_acked = 0;
+
+	if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+		tp->snd_cwnd++;
+}
+
+
 static inline void tcp_sync_left_out(struct tcp_sock *tp)
 {
 	if (tp->rx_opt.sack_ok &&
@@ -794,6 +822,7 @@ static inline void tcp_enter_cwr(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->prior_ssthresh = 0;
+	tp->bytes_acked = 0;
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		__tcp_enter_cwr(sk);
 		tcp_set_ca_state(sk, TCP_CA_CWR);
@@ -810,6 +839,27 @@ static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
 	return 3;
 }
 
+/* RFC2861 Check whether we are limited by application or congestion window
+ * This is the inverse of cwnd check in tcp_tso_should_defer
+ */
+static inline int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	u32 left;
+
+	if (in_flight >= tp->snd_cwnd)
+		return 1;
+
+	if (!(sk->sk_route_caps & NETIF_F_TSO))
+		return 0;
+
+	left = tp->snd_cwnd - in_flight;
+	if (sysctl_tcp_tso_win_divisor)
+		return left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd;
+	else
+		return left <= tcp_max_burst(tp);
+}
+
 static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, 
 					   const struct sk_buff *skb)
 {
@@ -1157,6 +1207,15 @@ static inline void tcp_mib_init(void)
 	TCP_ADD_STATS_USER(TCP_MIB_MAXCONN, -1);
 }
 
+/*from STCP */
+static inline void clear_all_retrans_hints(struct tcp_sock *tp){
+	tp->lost_skb_hint = NULL;
+	tp->scoreboard_skb_hint = NULL;
+	tp->retransmit_skb_hint = NULL;
+	tp->forward_skb_hint = NULL;
+	tp->fastpath_skb_hint = NULL;
+}
+
 /* /proc */
 enum tcp_seq_states {
 	TCP_SEQ_STATE_LISTENING,