Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (448 commits)
  [IPV4] nl_fib_lookup: Initialise res.r before fib_res_put(&res)
  [IPV6]: Fix thinko in ipv6_rthdr_rcv() changes.
  [IPV4]: Add multipath cached to feature-removal-schedule.txt
  [WIRELESS] cfg80211: Clarify locking comment.
  [WIRELESS] cfg80211: Fix locking in wiphy_new.
  [WEXT] net_device: Don't include wext bits if not required.
  [WEXT]: Misc code cleanups.
  [WEXT]: Reduce inline abuse.
  [WEXT]: Move EXPORT_SYMBOL statements where they belong.
  [WEXT]: Cleanup early ioctl call path.
  [WEXT]: Remove options.
  [WEXT]: Remove dead debug code.
  [WEXT]: Clean up how wext is called.
  [WEXT]: Move to net/wireless
  [AFS]: Eliminate cmpxchg() usage in vlocation code.
  [RXRPC]: Fix pointers passed to bitops.
  [RXRPC]: Remove bogus atomic_* overrides.
  [AFS]: Fix u64 printing in debug logging.
  [AFS]: Add "directory write" support.
  [AFS]: Implement the CB.InitCallBackState3 operation.
  ...

1 files changed, 143 insertions, 47 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5c472f255b7..a385797f160 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -220,6 +220,7 @@ extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
 extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
+extern int sysctl_tcp_frto_response;
 extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_dma_copybreak;
 extern int sysctl_tcp_nometrics_save;
@@ -230,6 +231,7 @@ 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_max_ssthresh;
 
 extern atomic_t tcp_memory_allocated;
 extern atomic_t tcp_sockets_allocated;
@@ -341,6 +343,7 @@ extern struct sock *		tcp_check_req(struct sock *sk,struct sk_buff *skb,
 extern int			tcp_child_process(struct sock *parent,
 						  struct sock *child,
 						  struct sk_buff *skb);
+extern int			tcp_use_frto(struct sock *sk);
 extern void			tcp_enter_frto(struct sock *sk);
 extern void			tcp_enter_loss(struct sock *sk, int how);
 extern void			tcp_clear_retrans(struct tcp_sock *tp);
@@ -417,9 +420,9 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
 
 /* tcp_output.c */
 
-extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
-				      unsigned int cur_mss, int nonagle);
-extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp);
+extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
+				      int nonagle);
+extern int tcp_may_send_now(struct sock *sk);
 extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
 extern void tcp_xmit_retransmit_queue(struct sock *);
 extern void tcp_simple_retransmit(struct sock *);
@@ -476,8 +479,10 @@ static inline void tcp_fast_path_on(struct tcp_sock *tp)
 	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
 }
 
-static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_fast_path_check(struct sock *sk)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	if (skb_queue_empty(&tp->out_of_order_queue) &&
 	    tp->rcv_wnd &&
 	    atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
@@ -588,10 +593,10 @@ static inline void tcp_dec_pcount_approx(__u32 *count,
 	}
 }
 
-static inline void tcp_packets_out_inc(struct sock *sk, 
-				       struct tcp_sock *tp,
+static inline void tcp_packets_out_inc(struct sock *sk,
 				       const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	int orig = tp->packets_out;
 
 	tp->packets_out += tcp_skb_pcount(skb);
@@ -624,9 +629,12 @@ enum tcp_ca_event {
 #define TCP_CA_MAX	128
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
+#define TCP_CONG_NON_RESTRICTED 0x1
+#define TCP_CONG_RTT_STAMP	0x2
+
 struct tcp_congestion_ops {
 	struct list_head	list;
-	int	non_restricted;
+	unsigned long flags;
 
 	/* initialize private data (optional) */
 	void (*init)(struct sock *sk);
@@ -640,8 +648,6 @@ struct tcp_congestion_ops {
 	/* do new cwnd calculation (required) */
 	void (*cong_avoid)(struct sock *sk, u32 ack,
 			   u32 rtt, u32 in_flight, int good_ack);
-	/* round trip time sample per acked packet (optional) */
-	void (*rtt_sample)(struct sock *sk, u32 usrtt);
 	/* call before changing ca_state (optional) */
 	void (*set_state)(struct sock *sk, u8 new_state);
 	/* call when cwnd event occurs (optional) */
@@ -649,7 +655,7 @@ struct tcp_congestion_ops {
 	/* new value of cwnd after loss (optional) */
 	u32  (*undo_cwnd)(struct sock *sk);
 	/* hook for packet ack accounting (optional) */
-	void (*pkts_acked)(struct sock *sk, u32 num_acked);
+	void (*pkts_acked)(struct sock *sk, u32 num_acked, ktime_t last);
 	/* get info for inet_diag (optional) */
 	void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
 
@@ -736,7 +742,7 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp)
 	tp->left_out = tp->sacked_out + tp->lost_out;
 }
 
-extern void tcp_enter_cwr(struct sock *sk);
+extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
 extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
 
 /* Slow start with delack produces 3 packets of burst, so that
@@ -775,18 +781,21 @@ static inline void tcp_minshall_update(struct tcp_sock *tp, int mss,
 		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
 }
 
-static inline void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_check_probe_timer(struct sock *sk)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
+
 	if (!tp->packets_out && !icsk->icsk_pending)
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
 					  icsk->icsk_rto, TCP_RTO_MAX);
 }
 
-static inline void tcp_push_pending_frames(struct sock *sk,
-					   struct tcp_sock *tp)
+static inline void tcp_push_pending_frames(struct sock *sk)
 {
-	__tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk, 1), tp->nonagle);
 }
 
 static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
@@ -815,7 +824,7 @@ static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
 
 static inline int tcp_checksum_complete(struct sk_buff *skb)
 {
-	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+	return !skb_csum_unnecessary(skb) &&
 		__tcp_checksum_complete(skb);
 }
 
@@ -918,21 +927,7 @@ static inline void tcp_set_state(struct sock *sk, int state)
 #endif	
 }
 
-static inline void tcp_done(struct sock *sk)
-{
-	if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
-		TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
-
-	tcp_set_state(sk, TCP_CLOSE);
-	tcp_clear_xmit_timers(sk);
-
-	sk->sk_shutdown = SHUTDOWN_MASK;
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_state_change(sk);
-	else
-		inet_csk_destroy_sock(sk);
-}
+extern void tcp_done(struct sock *sk);
 
 static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 {
@@ -981,7 +976,7 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->wscale_ok = rx_opt->wscale_ok;
 	ireq->acked = 0;
 	ireq->ecn_ok = 0;
-	ireq->rmt_port = skb->h.th->source;
+	ireq->rmt_port = tcp_hdr(skb)->source;
 }
 
 extern void tcp_enter_memory_pressure(void);
@@ -1011,7 +1006,7 @@ static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int
 {
 	if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
 		return 0;
-	if (xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
+	if (get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
 		return 0;
 
 	/* RST segments are not recommended to carry timestamp,
@@ -1026,26 +1021,13 @@ static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int
 
 	   However, we can relax time bounds for RST segments to MSL.
 	 */
-	if (rst && xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
+	if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
 		return 0;
 	return 1;
 }
 
 #define TCP_CHECK_TIMER(sk) do { } while (0)
 
-static inline int tcp_use_frto(const struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	
-	/* F-RTO must be activated in sysctl and there must be some
-	 * unsent new data, and the advertised window should allow
-	 * sending it.
-	 */
-	return (sysctl_tcp_frto && sk->sk_send_head &&
-		!after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
-		       tp->snd_una + tp->snd_wnd));
-}
-
 static inline void tcp_mib_init(void)
 {
 	/* See RFC 2012 */
@@ -1172,6 +1154,120 @@ static inline void		tcp_put_md5sig_pool(void)
 	put_cpu();
 }
 
+/* write queue abstraction */
+static inline void tcp_write_queue_purge(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
+		sk_stream_free_skb(sk, skb);
+	sk_stream_mem_reclaim(sk);
+}
+
+static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
+{
+	struct sk_buff *skb = sk->sk_write_queue.next;
+	if (skb == (struct sk_buff *) &sk->sk_write_queue)
+		return NULL;
+	return skb;
+}
+
+static inline struct sk_buff *tcp_write_queue_tail(struct sock *sk)
+{
+	struct sk_buff *skb = sk->sk_write_queue.prev;
+	if (skb == (struct sk_buff *) &sk->sk_write_queue)
+		return NULL;
+	return skb;
+}
+
+static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_buff *skb)
+{
+	return skb->next;
+}
+
+#define tcp_for_write_queue(skb, sk)					\
+		for (skb = (sk)->sk_write_queue.next;			\
+		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
+		     skb = skb->next)
+
+#define tcp_for_write_queue_from(skb, sk)				\
+		for (; (skb != (struct sk_buff *)&(sk)->sk_write_queue);\
+		     skb = skb->next)
+
+static inline struct sk_buff *tcp_send_head(struct sock *sk)
+{
+	return sk->sk_send_head;
+}
+
+static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
+{
+	sk->sk_send_head = skb->next;
+	if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
+		sk->sk_send_head = NULL;
+}
+
+static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
+{
+	if (sk->sk_send_head == skb_unlinked)
+		sk->sk_send_head = NULL;
+}
+
+static inline void tcp_init_send_head(struct sock *sk)
+{
+	sk->sk_send_head = NULL;
+}
+
+static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
+{
+	__skb_queue_tail(&sk->sk_write_queue, skb);
+}
+
+static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
+{
+	__tcp_add_write_queue_tail(sk, skb);
+
+	/* Queue it, remembering where we must start sending. */
+	if (sk->sk_send_head == NULL)
+		sk->sk_send_head = skb;
+}
+
+static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
+{
+	__skb_queue_head(&sk->sk_write_queue, skb);
+}
+
+/* Insert buff after skb on the write queue of sk.  */
+static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
+						struct sk_buff *buff,
+						struct sock *sk)
+{
+	__skb_append(skb, buff, &sk->sk_write_queue);
+}
+
+/* Insert skb between prev and next on the write queue of sk.  */
+static inline void tcp_insert_write_queue_before(struct sk_buff *new,
+						  struct sk_buff *skb,
+						  struct sock *sk)
+{
+	__skb_insert(new, skb->prev, skb, &sk->sk_write_queue);
+}
+
+static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
+{
+	__skb_unlink(skb, &sk->sk_write_queue);
+}
+
+static inline int tcp_skb_is_last(const struct sock *sk,
+				  const struct sk_buff *skb)
+{
+	return skb->next == (struct sk_buff *)&sk->sk_write_queue;
+}
+
+static inline int tcp_write_queue_empty(struct sock *sk)
+{
+	return skb_queue_empty(&sk->sk_write_queue);
+}
+
 /* /proc */
 enum tcp_seq_states {
 	TCP_SEQ_STATE_LISTENING,