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

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (867 commits)
  [SKY2]: status polling loop (post merge)
  [NET]: Fix NAPI completion handling in some drivers.
  [TCP]: Limit processing lost_retrans loop to work-to-do cases
  [TCP]: Fix lost_retrans loop vs fastpath problems
  [TCP]: No need to re-count fackets_out/sacked_out at RTO
  [TCP]: Extract tcp_match_queue_to_sack from sacktag code
  [TCP]: Kill almost unused variable pcount from sacktag
  [TCP]: Fix mark_head_lost to ignore R-bit when trying to mark L
  [TCP]: Add bytes_acked (ABC) clearing to FRTO too
  [IPv6]: Update setsockopt(IPV6_MULTICAST_IF) to support RFC 3493, try2
  [NETFILTER]: x_tables: add missing ip6t_modulename aliases
  [NETFILTER]: nf_conntrack_tcp: fix connection reopening
  [QETH]: fix qeth_main.c
  [NETLINK]: fib_frontend build fixes
  [IPv6]: Export userland ND options through netlink (RDNSS support)
  [9P]: build fix with !CONFIG_SYSCTL
  [NET]: Fix dev_put() and dev_hold() comments
  [NET]: make netlink user -> kernel interface synchronious
  [NET]: unify netlink kernel socket recognition
  [NET]: cleanup 3rd argument in netlink_sendskb
  ...

Fix up conflicts manually in Documentation/feature-removal-schedule.txt
and my new least favourite crap, the "mod_devicetable" support in the
files include/linux/mod_devicetable.h and scripts/mod/file2alias.c.

(The latter files seem to be explicitly _designed_ to get conflicts when
different subsystems work with them - that have an absolutely horrid
lack of subsystem separation!)

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 57 insertions, 63 deletions

diff --git a/net/dccp/input.c b/net/dccp/input.c
index da6ec185ed5b..19d7e1dbd87e 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -68,7 +68,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh = dccp_hdr(skb);
 	struct dccp_sock *dp = dccp_sk(sk);
-	u64 lswl, lawl;
+	u64 lswl, lawl, seqno = DCCP_SKB_CB(skb)->dccpd_seq,
+			ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
 
 	/*
 	 *   Step 5: Prepare sequence numbers for Sync
@@ -84,11 +85,9 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (dh->dccph_type == DCCP_PKT_SYNC ||
 	    dh->dccph_type == DCCP_PKT_SYNCACK) {
-		if (between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
-			      dp->dccps_awl, dp->dccps_awh) &&
-		    dccp_delta_seqno(dp->dccps_swl,
-				     DCCP_SKB_CB(skb)->dccpd_seq) >= 0)
-			dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
+		if (between48(ackno, dp->dccps_awl, dp->dccps_awh) &&
+		    dccp_delta_seqno(dp->dccps_swl, seqno) >= 0)
+			dccp_update_gsr(sk, seqno);
 		else
 			return -1;
 	}
@@ -103,9 +102,6 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
 	 *	  Update S.GSR, S.SWL, S.SWH
 	 *	  If P.type != Sync,
 	 *	     Update S.GAR
-	 *      Otherwise,
-	 *	  Send Sync packet acknowledging P.seqno
-	 *	  Drop packet and return
 	 */
 	lswl = dp->dccps_swl;
 	lawl = dp->dccps_awl;
@@ -113,35 +109,52 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
 	if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
 	    dh->dccph_type == DCCP_PKT_CLOSE ||
 	    dh->dccph_type == DCCP_PKT_RESET) {
-		lswl = dp->dccps_gsr;
-		dccp_inc_seqno(&lswl);
+		lswl = ADD48(dp->dccps_gsr, 1);
 		lawl = dp->dccps_gar;
 	}
 
-	if (between48(DCCP_SKB_CB(skb)->dccpd_seq, lswl, dp->dccps_swh) &&
-	    (DCCP_SKB_CB(skb)->dccpd_ack_seq == DCCP_PKT_WITHOUT_ACK_SEQ ||
-	     between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
-		       lawl, dp->dccps_awh))) {
-		dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
+	if (between48(seqno, lswl, dp->dccps_swh) &&
+	    (ackno == DCCP_PKT_WITHOUT_ACK_SEQ ||
+	     between48(ackno, lawl, dp->dccps_awh))) {
+		dccp_update_gsr(sk, seqno);
 
 		if (dh->dccph_type != DCCP_PKT_SYNC &&
-		    (DCCP_SKB_CB(skb)->dccpd_ack_seq !=
-		     DCCP_PKT_WITHOUT_ACK_SEQ))
-			dp->dccps_gar = DCCP_SKB_CB(skb)->dccpd_ack_seq;
+		    (ackno != DCCP_PKT_WITHOUT_ACK_SEQ))
+			dp->dccps_gar = ackno;
 	} else {
+		unsigned long now = jiffies;
+		/*
+		 *   Step 6: Check sequence numbers
+		 *      Otherwise,
+		 *         If P.type == Reset,
+		 *            Send Sync packet acknowledging S.GSR
+		 *         Otherwise,
+		 *            Send Sync packet acknowledging P.seqno
+		 *      Drop packet and return
+		 *
+		 *   These Syncs are rate-limited as per RFC 4340, 7.5.4:
+		 *   at most 1 / (dccp_sync_rate_limit * HZ) Syncs per second.
+		 */
+		if (time_before(now, (dp->dccps_rate_last +
+				      sysctl_dccp_sync_ratelimit)))
+			return 0;
+
 		DCCP_WARN("DCCP: Step 6 failed for %s packet, "
 			  "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
 			  "(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
 			  "sending SYNC...\n",  dccp_packet_name(dh->dccph_type),
-			  (unsigned long long) lswl,
-			  (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq,
+			  (unsigned long long) lswl, (unsigned long long) seqno,
 			  (unsigned long long) dp->dccps_swh,
-			  (DCCP_SKB_CB(skb)->dccpd_ack_seq ==
-				DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist" : "exists",
-			  (unsigned long long) lawl,
-			  (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq,
+			  (ackno == DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist"
+							      : "exists",
+			  (unsigned long long) lawl, (unsigned long long) ackno,
 			  (unsigned long long) dp->dccps_awh);
-		dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
+
+		dp->dccps_rate_last = now;
+
+		if (dh->dccph_type == DCCP_PKT_RESET)
+			seqno = dp->dccps_gsr;
+		dccp_send_sync(sk, seqno, DCCP_PKT_SYNC);
 		return -1;
 	}
 
@@ -280,6 +293,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk,
 	if (dh->dccph_type == DCCP_PKT_RESPONSE) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 		struct dccp_sock *dp = dccp_sk(sk);
+		long tstamp = dccp_timestamp();
 
 		/* Stop the REQUEST timer */
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
@@ -300,13 +314,10 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk,
 		if (dccp_parse_options(sk, skb))
 			goto out_invalid_packet;
 
-		/* Obtain RTT sample from SYN exchange (used by CCID 3) */
-		if (dp->dccps_options_received.dccpor_timestamp_echo) {
-			struct timeval now;
-
-			dccp_timestamp(sk, &now);
-			dp->dccps_syn_rtt = dccp_sample_rtt(sk, &now, NULL);
-		}
+		/* Obtain usec RTT sample from SYN exchange (used by CCID 3) */
+		if (likely(dp->dccps_options_received.dccpor_timestamp_echo))
+			dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
+			    dp->dccps_options_received.dccpor_timestamp_echo));
 
 		if (dccp_msk(sk)->dccpms_send_ack_vector &&
 		    dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
@@ -540,11 +551,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		return 0;
 	}
 
-	if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
-		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
-		goto discard;
-	}
-
 	switch (sk->sk_state) {
 	case DCCP_CLOSED:
 		dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
@@ -575,6 +581,9 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			sk_wake_async(sk, 0, POLL_OUT);
 			break;
 		}
+	} else if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
+		dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
+		goto discard;
 	}
 
 	if (!queued) {
@@ -587,37 +596,22 @@ discard:
 EXPORT_SYMBOL_GPL(dccp_rcv_state_process);
 
 /**
- * dccp_sample_rtt  -  Sample RTT from packet exchange
- *
- * @sk:     connected dccp_sock
- * @t_recv: receive timestamp of packet with timestamp echo
- * @t_hist: packet history timestamp or NULL
+ *  dccp_sample_rtt  -  Validate and finalise computation of RTT sample
+ *  @delta:	number of microseconds between packet and acknowledgment
+ *  The routine is kept generic to work in different contexts. It should be
+ *  called immediately when the ACK used for the RTT sample arrives.
  */
-u32 dccp_sample_rtt(struct sock *sk, struct timeval *t_recv,
-				     struct timeval *t_hist)
+u32 dccp_sample_rtt(struct sock *sk, long delta)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct dccp_options_received *or = &dp->dccps_options_received;
-	suseconds_t delta;
-
-	if (t_hist == NULL) {
-		if (!or->dccpor_timestamp_echo) {
-			DCCP_WARN("packet without timestamp echo\n");
-			return DCCP_SANE_RTT_MAX;
-		}
-		timeval_sub_usecs(t_recv, or->dccpor_timestamp_echo * 10);
-		delta = timeval_usecs(t_recv);
-	} else
-		delta = timeval_delta(t_recv, t_hist);
-
-	delta -= or->dccpor_elapsed_time * 10;		/* either set or 0 */
+	/* dccpor_elapsed_time is either zeroed out or set and > 0 */
+	delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10;
 
 	if (unlikely(delta <= 0)) {
-		DCCP_WARN("unusable RTT sample %ld, using min\n", (long)delta);
+		DCCP_WARN("unusable RTT sample %ld, using min\n", delta);
 		return DCCP_SANE_RTT_MIN;
 	}
-	if (unlikely(delta - (suseconds_t)DCCP_SANE_RTT_MAX > 0)) {
-		DCCP_WARN("RTT sample %ld too large, using max\n", (long)delta);
+	if (unlikely(delta > DCCP_SANE_RTT_MAX)) {
+		DCCP_WARN("RTT sample %ld too large, using max\n", delta);
 		return DCCP_SANE_RTT_MAX;
 	}