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

9 files changed, 58 insertions, 181 deletions

diff --git a/include/linux/if_shaper.h b/include/linux/if_shaper.h
index 004e6f09a6e..68c896a36a3 100644
--- a/include/linux/if_shaper.h
+++ b/include/linux/if_shaper.h
@@ -23,7 +23,7 @@ struct shaper
 	__u32 shapeclock;
 	unsigned long recovery;	/* Time we can next clock a packet out on
 				   an empty queue */
-	struct semaphore sem;
+	spinlock_t lock;
         struct net_device_stats stats;
 	struct net_device *dev;
 	int  (*hard_start_xmit) (struct sk_buff *skb,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 416a2e4024b..14b95041349 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -183,7 +183,6 @@ struct skb_shared_info {
  *	@priority: Packet queueing priority
  *	@users: User count - see {datagram,tcp}.c
  *	@protocol: Packet protocol from driver
- *	@security: Security level of packet
  *	@truesize: Buffer size 
  *	@head: Head of buffer
  *	@data: Data head pointer
@@ -249,18 +248,18 @@ struct sk_buff {
 				data_len,
 				mac_len,
 				csum;
-	unsigned char		local_df,
-				cloned:1,
-				nohdr:1,
-				pkt_type,
-				ip_summed;
 	__u32			priority;
-	unsigned short		protocol,
-				security;
+	__u8			local_df:1,
+				cloned:1,
+				ip_summed:2,
+				nohdr:1;
+				/* 3 bits spare */
+	__u8			pkt_type;
+	__u16			protocol;
 
 	void			(*destructor)(struct sk_buff *skb);
 #ifdef CONFIG_NETFILTER
-        unsigned long		nfmark;
+	unsigned long		nfmark;
 	__u32			nfcache;
 	__u32			nfctinfo;
 	struct nf_conntrack	*nfct;
@@ -1211,7 +1210,7 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 {
 	int hlen = skb_headlen(skb);
 
-	if (offset + len <= hlen)
+	if (hlen - offset >= len)
 		return skb->data + offset;
 
 	if (skb_copy_bits(skb, offset, buffer, len) < 0)
diff --git a/include/linux/tc_ematch/tc_em_meta.h b/include/linux/tc_ematch/tc_em_meta.h
index a6b2cc530af..bcb762d9312 100644
--- a/include/linux/tc_ematch/tc_em_meta.h
+++ b/include/linux/tc_ematch/tc_em_meta.h
@@ -45,7 +45,7 @@ enum
 	TCF_META_ID_REALDEV,
 	TCF_META_ID_PRIORITY,
 	TCF_META_ID_PROTOCOL,
-	TCF_META_ID_SECURITY,
+	TCF_META_ID_SECURITY, /* obsolete */
 	TCF_META_ID_PKTTYPE,
 	TCF_META_ID_PKTLEN,
 	TCF_META_ID_DATALEN,
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index dfd93d03f5d..e4fd82e4210 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -286,7 +286,7 @@ struct tcp_sock {
 	__u32	max_window;	/* Maximal window ever seen from peer	*/
 	__u32	pmtu_cookie;	/* Last pmtu seen by socket		*/
 	__u32	mss_cache;	/* Cached effective mss, not including SACKS */
-	__u16	mss_cache_std;	/* Like mss_cache, but without TSO */
+	__u16	xmit_size_goal;	/* Goal for segmenting output packets	*/
 	__u16	ext_header_len;	/* Network protocol overhead (IP/IPv6 options) */
 	__u8	ca_state;	/* State of fast-retransmit machine 	*/
 	__u8	retransmits;	/* Number of unrecovered RTO timeouts.	*/
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index fcb05a387db..6492e7363d8 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -13,13 +13,12 @@ struct qdisc_walker
 
 extern rwlock_t qdisc_tree_lock;
 
-#define	QDISC_ALIGN		32
-#define	QDISC_ALIGN_CONST	(QDISC_ALIGN - 1)
+#define QDISC_ALIGNTO		32
+#define QDISC_ALIGN(len)	(((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1))
 
 static inline void *qdisc_priv(struct Qdisc *q)
 {
-	return (char *)q + ((sizeof(struct Qdisc) + QDISC_ALIGN_CONST)
-			      & ~QDISC_ALIGN_CONST);
+	return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc));
 }
 
 /* 
@@ -207,8 +206,6 @@ psched_tod_diff(int delta_sec, int bound)
 
 #endif /* !CONFIG_NET_SCH_CLK_GETTIMEOFDAY */
 
-extern struct Qdisc noop_qdisc;
-extern struct Qdisc_ops noop_qdisc_ops;
 extern struct Qdisc_ops pfifo_qdisc_ops;
 extern struct Qdisc_ops bfifo_qdisc_ops;
 
@@ -216,14 +213,6 @@ extern int register_qdisc(struct Qdisc_ops *qops);
 extern int unregister_qdisc(struct Qdisc_ops *qops);
 extern struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
 extern struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle);
-extern void dev_init_scheduler(struct net_device *dev);
-extern void dev_shutdown(struct net_device *dev);
-extern void dev_activate(struct net_device *dev);
-extern void dev_deactivate(struct net_device *dev);
-extern void qdisc_reset(struct Qdisc *qdisc);
-extern void qdisc_destroy(struct Qdisc *qdisc);
-extern struct Qdisc * qdisc_create_dflt(struct net_device *dev,
-	struct Qdisc_ops *ops);
 extern struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
 		struct rtattr *tab);
 extern void qdisc_put_rtab(struct qdisc_rate_table *tab);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7b97405e2db..7b6ec998671 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -164,6 +164,19 @@ extern void qdisc_unlock_tree(struct net_device *dev);
 #define tcf_tree_lock(tp)	qdisc_lock_tree((tp)->q->dev)
 #define tcf_tree_unlock(tp)	qdisc_unlock_tree((tp)->q->dev)
 
+extern struct Qdisc noop_qdisc;
+extern struct Qdisc_ops noop_qdisc_ops;
+
+extern void dev_init_scheduler(struct net_device *dev);
+extern void dev_shutdown(struct net_device *dev);
+extern void dev_activate(struct net_device *dev);
+extern void dev_deactivate(struct net_device *dev);
+extern void qdisc_reset(struct Qdisc *qdisc);
+extern void qdisc_destroy(struct Qdisc *qdisc);
+extern struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops);
+extern struct Qdisc *qdisc_create_dflt(struct net_device *dev,
+				       struct Qdisc_ops *ops);
+
 static inline void
 tcf_destroy(struct tcf_proto *tp)
 {
diff --git a/include/net/slhc_vj.h b/include/net/slhc_vj.h
index 0b2c2784f33..8716d5942b6 100644
--- a/include/net/slhc_vj.h
+++ b/include/net/slhc_vj.h
@@ -170,19 +170,14 @@ struct slcompress {
 };
 #define NULLSLCOMPR	(struct slcompress *)0
 
-#define __ARGS(x) x
-
 /* In slhc.c: */
-struct slcompress *slhc_init __ARGS((int rslots, int tslots));
-void slhc_free __ARGS((struct slcompress *comp));
-
-int slhc_compress __ARGS((struct slcompress *comp, unsigned char *icp,
-			  int isize, unsigned char *ocp, unsigned char **cpp,
-			  int compress_cid));
-int slhc_uncompress __ARGS((struct slcompress *comp, unsigned char *icp,
-			    int isize));
-int slhc_remember __ARGS((struct slcompress *comp, unsigned char *icp,
-			  int isize));
-int slhc_toss __ARGS((struct slcompress *comp));
+struct slcompress *slhc_init(int rslots, int tslots);
+void slhc_free(struct slcompress *comp);
+
+int slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
+		  unsigned char *ocp, unsigned char **cpp, int compress_cid);
+int slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize);
+int slhc_remember(struct slcompress *comp, unsigned char *icp, int isize);
+int slhc_toss(struct slcompress *comp);
 
 #endif	/* _SLHC_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e593af5b1ec..7b76f891ae2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1134,13 +1134,16 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
 						   int size, int mem, int gfp)
 {
-	struct sk_buff *skb = alloc_skb(size + sk->sk_prot->max_header, gfp);
+	struct sk_buff *skb;
+	int hdr_len;
 
+	hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
+	skb = alloc_skb(size + hdr_len, gfp);
 	if (skb) {
 		skb->truesize += mem;
 		if (sk->sk_forward_alloc >= (int)skb->truesize ||
 		    sk_stream_mem_schedule(sk, skb->truesize, 0)) {
-			skb_reserve(skb, sk->sk_prot->max_header);
+			skb_reserve(skb, hdr_len);
 			return skb;
 		}
 		__kfree_skb(skb);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ec9e20c2717..a166918ca56 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -721,11 +721,16 @@ static inline int tcp_ack_scheduled(struct tcp_sock *tp)
 	return tp->ack.pending&TCP_ACK_SCHED;
 }
 
-static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp)
+static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp, unsigned int pkts)
 {
-	if (tp->ack.quick && --tp->ack.quick == 0) {
-		/* Leaving quickack mode we deflate ATO. */
-		tp->ack.ato = TCP_ATO_MIN;
+	if (tp->ack.quick) {
+		if (pkts >= tp->ack.quick) {
+			tp->ack.quick = 0;
+
+			/* Leaving quickack mode we deflate ATO. */
+			tp->ack.ato = TCP_ATO_MIN;
+		} else
+			tp->ack.quick -= pkts;
 	}
 }
 
@@ -843,7 +848,9 @@ extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
 
 /* tcp_output.c */
 
-extern int tcp_write_xmit(struct sock *, int nonagle);
+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 int tcp_retransmit_skb(struct sock *, struct sk_buff *);
 extern void tcp_xmit_retransmit_queue(struct sock *);
 extern void tcp_simple_retransmit(struct sock *);
@@ -855,10 +862,13 @@ extern int  tcp_write_wakeup(struct sock *);
 extern void tcp_send_fin(struct sock *sk);
 extern void tcp_send_active_reset(struct sock *sk, int priority);
 extern int  tcp_send_synack(struct sock *);
-extern void tcp_push_one(struct sock *, unsigned mss_now);
+extern void tcp_push_one(struct sock *, unsigned int mss_now);
 extern void tcp_send_ack(struct sock *sk);
 extern void tcp_send_delayed_ack(struct sock *sk);
 
+/* tcp_input.c */
+extern void tcp_cwnd_application_limited(struct sock *sk);
+
 /* tcp_timer.c */
 extern void tcp_init_xmit_timers(struct sock *);
 extern void tcp_clear_xmit_timers(struct sock *);
@@ -958,7 +968,7 @@ static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long
 static inline void tcp_initialize_rcv_mss(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned int hint = min(tp->advmss, tp->mss_cache_std);
+	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
 
 	hint = min(hint, tp->rcv_wnd/2);
 	hint = min(hint, TCP_MIN_RCVMSS);
@@ -1225,28 +1235,6 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp)
 	tp->left_out = tp->sacked_out + tp->lost_out;
 }
 
-extern void tcp_cwnd_application_limited(struct sock *sk);
-
-/* Congestion window validation. (RFC2861) */
-
-static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
-{
-	__u32 packets_out = tp->packets_out;
-
-	if (packets_out >= tp->snd_cwnd) {
-		/* Network is feed fully. */
-		tp->snd_cwnd_used = 0;
-		tp->snd_cwnd_stamp = tcp_time_stamp;
-	} else {
-		/* Network starves. */
-		if (tp->packets_out > tp->snd_cwnd_used)
-			tp->snd_cwnd_used = tp->packets_out;
-
-		if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto)
-			tcp_cwnd_application_limited(sk);
-	}
-}
-
 /* Set slow start threshould and cwnd not falling to slow start */
 static inline void __tcp_enter_cwr(struct tcp_sock *tp)
 {
@@ -1279,12 +1267,6 @@ static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
 	return 3;
 }
 
-static __inline__ int tcp_minshall_check(const struct tcp_sock *tp)
-{
-	return after(tp->snd_sml,tp->snd_una) &&
-		!after(tp->snd_sml, tp->snd_nxt);
-}
-
 static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, 
 					   const struct sk_buff *skb)
 {
@@ -1292,122 +1274,18 @@ static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss,
 		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
 }
 
-/* Return 0, if packet can be sent now without violation Nagle's rules:
-   1. It is full sized.
-   2. Or it contains FIN.
-   3. Or TCP_NODELAY was set.
-   4. Or TCP_CORK is not set, and all sent packets are ACKed.
-      With Minshall's modification: all sent small packets are ACKed.
- */
-
-static __inline__ int
-tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, 
-		unsigned mss_now, int nonagle)
-{
-	return (skb->len < mss_now &&
-		!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
-		((nonagle&TCP_NAGLE_CORK) ||
-		 (!nonagle &&
-		  tp->packets_out &&
-		  tcp_minshall_check(tp))));
-}
-
-extern void tcp_set_skb_tso_segs(struct sock *, struct sk_buff *);
-
-/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
- * should be put on the wire right now.
- */
-static __inline__ int tcp_snd_test(struct sock *sk,
-				   struct sk_buff *skb,
-				   unsigned cur_mss, int nonagle)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int pkts = tcp_skb_pcount(skb);
-
-	if (!pkts) {
-		tcp_set_skb_tso_segs(sk, skb);
-		pkts = tcp_skb_pcount(skb);
-	}
-
-	/*	RFC 1122 - section 4.2.3.4
-	 *
-	 *	We must queue if
-	 *
-	 *	a) The right edge of this frame exceeds the window
-	 *	b) There are packets in flight and we have a small segment
-	 *	   [SWS avoidance and Nagle algorithm]
-	 *	   (part of SWS is done on packetization)
-	 *	   Minshall version sounds: there are no _small_
-	 *	   segments in flight. (tcp_nagle_check)
-	 *	c) We have too many packets 'in flight'
-	 *
-	 * 	Don't use the nagle rule for urgent data (or
-	 *	for the final FIN -DaveM).
-	 *
-	 *	Also, Nagle rule does not apply to frames, which
-	 *	sit in the middle of queue (they have no chances
-	 *	to get new data) and if room at tail of skb is
-	 *	not enough to save something seriously (<32 for now).
-	 */
-
-	/* Don't be strict about the congestion window for the
-	 * final FIN frame.  -DaveM
-	 */
-	return (((nonagle&TCP_NAGLE_PUSH) || tp->urg_mode
-		 || !tcp_nagle_check(tp, skb, cur_mss, nonagle)) &&
-		(((tcp_packets_in_flight(tp) + (pkts-1)) < tp->snd_cwnd) ||
-		 (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) &&
-		!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una + tp->snd_wnd));
-}
-
 static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
 {
 	if (!tp->packets_out && !tp->pending)
 		tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0, tp->rto);
 }
 
-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;
-}
-
-/* Push out any pending frames which were held back due to
- * TCP_CORK or attempt at coalescing tiny packets.
- * The socket must be locked by the caller.
- */
-static __inline__ void __tcp_push_pending_frames(struct sock *sk,
-						 struct tcp_sock *tp,
-						 unsigned cur_mss,
-						 int nonagle)
-{
-	struct sk_buff *skb = sk->sk_send_head;
-
-	if (skb) {
-		if (!tcp_skb_is_last(sk, skb))
-			nonagle = TCP_NAGLE_PUSH;
-		if (!tcp_snd_test(sk, skb, cur_mss, nonagle) ||
-		    tcp_write_xmit(sk, nonagle))
-			tcp_check_probe_timer(sk, tp);
-	}
-	tcp_cwnd_validate(sk, tp);
-}
-
 static __inline__ void tcp_push_pending_frames(struct sock *sk,
 					       struct tcp_sock *tp)
 {
 	__tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
 }
 
-static __inline__ int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
-{
-	struct sk_buff *skb = sk->sk_send_head;
-
-	return (skb &&
-		tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
-			     tcp_skb_is_last(sk, skb) ? TCP_NAGLE_PUSH : tp->nonagle));
-}
-
 static __inline__ void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
 {
 	tp->snd_wl1 = seq;