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

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [NET]: rt_check_expire() can take a long time, add a cond_resched()
  [ISDN] sc: Really, really fix warning
  [ISDN] sc: Fix sndpkt to have the correct number of arguments
  [TCP] FRTO: Clear frto_highmark only after process_frto that uses it
  [NET]: Remove notifier block from chain when register_netdevice_notifier fails
  [FS_ENET]: Fix module build.
  [TCP]: Make sure write_queue_from does not begin with NULL ptr
  [TCP]: Fix size calculation in sk_stream_alloc_pskb
  [S2IO]: Fixed memory leak when MSI-X vector allocation fails
  [BONDING]: Fix resource use after free
  [SYSCTL]: Fix warning for token-ring from sysctl checker
  [NET] random : secure_tcp_sequence_number should not assume CONFIG_KTIME_SCALAR
  [IWLWIFI]: Not correctly dealing with hotunplug.
  [TCP] FRTO: Plug potential LOST-bit leak
  [TCP] FRTO: Limit snd_cwnd if TCP was application limited
  [E1000]: Fix schedule while atomic when called from mii-tool.
  [NETX]: Fix build failure added by 2.6.24 statistics cleanup.
  [EP93xx_ETH]: Build fix after 2.6.24 NAPI changes.
  [PKT_SCHED]: Check subqueue status before calling hard_start_xmit

4 files changed, 21 insertions, 5 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index dd40b35bb006..86d62611f2fc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1171,6 +1171,8 @@ rollback:
 			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
 		}
 	}
+
+	raw_notifier_chain_unregister(&netdev_chain, nb);
 	goto unlock;
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 45651834e1e2..1bff9ed349ff 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -578,6 +578,9 @@ static void rt_check_expire(struct work_struct *work)
 		i = (i + 1) & rt_hash_mask;
 		rthp = &rt_hash_table[i].chain;
 
+		if (need_resched())
+			cond_resched();
+
 		if (*rthp == NULL)
 			continue;
 		spin_lock_bh(rt_hash_lock_addr(i));
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 20c9440ab85e..0f0c1c9829a1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1269,6 +1269,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 	if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
 		return 0;
 
+	if (!tp->packets_out)
+		goto out;
+
 	/* SACK fastpath:
 	 * if the only SACK change is the increase of the end_seq of
 	 * the first block then only apply that SACK block
@@ -1515,6 +1518,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 	    (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
 		tcp_update_reordering(sk, tp->fackets_out - reord, 0);
 
+out:
+
 #if FASTRETRANS_DEBUG > 0
 	BUG_TRAP((int)tp->sacked_out >= 0);
 	BUG_TRAP((int)tp->lost_out >= 0);
@@ -1669,6 +1674,9 @@ void tcp_enter_frto(struct sock *sk)
 	}
 	tcp_verify_left_out(tp);
 
+	/* Too bad if TCP was application limited */
+	tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1);
+
 	/* Earlier loss recovery underway (see RFC4138; Appendix B).
 	 * The last condition is necessary at least in tp->frto_counter case.
 	 */
@@ -1701,6 +1709,8 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
 	tcp_for_write_queue(skb, sk) {
 		if (skb == tcp_send_head(sk))
 			break;
+
+		TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
 		/*
 		 * Count the retransmission made on RTO correctly (only when
 		 * waiting for the first ACK and did not get it)...
@@ -1714,7 +1724,7 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
 		} else {
 			if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
 				tp->undo_marker = 0;
-			TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
 		}
 
 		/* Don't lost mark skbs that were fwd transmitted after RTO */
@@ -3103,11 +3113,11 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
 	/* See if we can take anything off of the retransmit queue. */
 	flag |= tcp_clean_rtx_queue(sk, &seq_rtt, prior_fackets);
 
+	if (tp->frto_counter)
+		frto_cwnd = tcp_process_frto(sk, flag);
 	/* Guarantee sacktag reordering detection against wrap-arounds */
 	if (before(tp->frto_highmark, tp->snd_una))
 		tp->frto_highmark = 0;
-	if (tp->frto_counter)
-		frto_cwnd = tcp_process_frto(sk, flag);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		/* Advance CWND, if state allows this. */
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index fa1a6f45dc41..e595e6570ce0 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -134,7 +134,7 @@ static inline int qdisc_restart(struct net_device *dev)
 {
 	struct Qdisc *q = dev->qdisc;
 	struct sk_buff *skb;
-	int ret;
+	int ret = NETDEV_TX_BUSY;
 
 	/* Dequeue packet */
 	if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL))
@@ -145,7 +145,8 @@ static inline int qdisc_restart(struct net_device *dev)
 	spin_unlock(&dev->queue_lock);
 
 	HARD_TX_LOCK(dev, smp_processor_id());
-	ret = dev_hard_start_xmit(skb, dev);
+	if (!netif_subqueue_stopped(dev, skb))
+		ret = dev_hard_start_xmit(skb, dev);
 	HARD_TX_UNLOCK(dev);
 
 	spin_lock(&dev->queue_lock);