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

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (21 commits)
  niu: VLAN_ETH_HLEN should be used to make sure that the whole MAC header was copied to the head buffer in the Vlan packets case
  KS8851: Fix ks8851_set_rx_mode() for IFF_MULTICAST
  KS8851: Fix MAC address write order
  KS8851: Add soft reset at probe time
  net: fix section mismatch in fec.c
  net: Fix struct inet_timewait_sock bitfield annotation
  tcp: Try to catch MSG_PEEK bug
  net: Fix IP_MULTICAST_IF
  bluetooth: static lock key fix
  bluetooth: scheduling while atomic bug fix
  tcp: fix TCP_DEFER_ACCEPT retrans calculation
  tcp: reduce SYN-ACK retrans for TCP_DEFER_ACCEPT
  tcp: accept socket after TCP_DEFER_ACCEPT period
  Revert "tcp: fix tcp_defer_accept to consider the timeout"
  AF_UNIX: Fix deadlock on connecting to shutdown socket
  ethoc: clear only pending irqs
  ethoc: inline regs access
  vmxnet3: use dev_dbg, fix build for CONFIG_BLOCK=n
  virtio_net: use dev_kfree_skb_any() in free_old_xmit_skbs()
  be2net: fix support for PCI hot plug
  ...

8 files changed, 97 insertions, 29 deletions

diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 7f939ce..2bc6f6a 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -92,6 +92,8 @@ static void add_conn(struct work_struct *work)
 
 	dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
 
+	dev_set_drvdata(&conn->dev, conn);
+
 	if (device_add(&conn->dev) < 0) {
 		BT_ERR("Failed to register connection device");
 		return;
@@ -144,8 +146,6 @@ void hci_conn_init_sysfs(struct hci_conn *conn)
 	conn->dev.class = bt_class;
 	conn->dev.parent = &hdev->dev;
 
-	dev_set_drvdata(&conn->dev, conn);
-
 	device_initialize(&conn->dev);
 
 	INIT_WORK(&conn->work_add, add_conn);
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 555d9da..77e9fb1 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -555,12 +555,12 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
 
 	conn->feat_mask = 0;
 
-	setup_timer(&conn->info_timer, l2cap_info_timeout,
-						(unsigned long) conn);
-
 	spin_lock_init(&conn->lock);
 	rwlock_init(&conn->chan_list.lock);
 
+	setup_timer(&conn->info_timer, l2cap_info_timeout,
+						(unsigned long) conn);
+
 	conn->disc_reason = 0x13;
 
 	return conn;
@@ -783,6 +783,9 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 	/* Default config options */
 	pi->conf_len = 0;
 	pi->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+	skb_queue_head_init(TX_QUEUE(sk));
+	skb_queue_head_init(SREJ_QUEUE(sk));
+	INIT_LIST_HEAD(SREJ_LIST(sk));
 }
 
 static struct proto l2cap_proto = {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4351ca2..537731b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -446,6 +446,28 @@ extern int sysctl_tcp_synack_retries;
 
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
+/* Decide when to expire the request and when to resend SYN-ACK */
+static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
+				  const int max_retries,
+				  const u8 rskq_defer_accept,
+				  int *expire, int *resend)
+{
+	if (!rskq_defer_accept) {
+		*expire = req->retrans >= thresh;
+		*resend = 1;
+		return;
+	}
+	*expire = req->retrans >= thresh &&
+		  (!inet_rsk(req)->acked || req->retrans >= max_retries);
+	/*
+	 * Do not resend while waiting for data after ACK,
+	 * start to resend on end of deferring period to give
+	 * last chance for data or ACK to create established socket.
+	 */
+	*resend = !inet_rsk(req)->acked ||
+		  req->retrans >= rskq_defer_accept - 1;
+}
+
 void inet_csk_reqsk_queue_prune(struct sock *parent,
 				const unsigned long interval,
 				const unsigned long timeout,
@@ -501,9 +523,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if ((req->retrans < thresh ||
-				     (inet_rsk(req)->acked && req->retrans < max_retries))
-				    && !req->rsk_ops->rtx_syn_ack(parent, req)) {
+				int expire = 0, resend = 0;
+
+				syn_ack_recalc(req, thresh, max_retries,
+					       queue->rskq_defer_accept,
+					       &expire, &resend);
+				if (!expire &&
+				    (!resend ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req) ||
+				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 0c0b6e3..e982b5c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -634,17 +634,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 				break;
 			}
 			dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
-			if (dev) {
+			if (dev)
 				mreq.imr_ifindex = dev->ifindex;
-				dev_put(dev);
-			}
 		} else
-			dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
+			dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
 
 
 		err = -EADDRNOTAVAIL;
 		if (!dev)
 			break;
+		dev_put(dev);
 
 		err = -EINVAL;
 		if (sk->sk_bound_dev_if &&
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 64d0af6..90b2e06 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk)
 
 EXPORT_SYMBOL(tcp_enter_memory_pressure);
 
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+	u8 res = 0;
+
+	if (seconds > 0) {
+		int period = timeout;
+
+		res = 1;
+		while (seconds > period && res < 255) {
+			res++;
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+	int period = 0;
+
+	if (retrans > 0) {
+		period = timeout;
+		while (--retrans) {
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return period;
+}
+
 /*
  *	Wait for a TCP event.
  *
@@ -1405,7 +1442,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				goto found_ok_skb;
 			if (tcp_hdr(skb)->fin)
 				goto found_fin_ok;
-			WARN_ON(!(flags & MSG_PEEK));
+			if (WARN_ON(!(flags & MSG_PEEK)))
+				printk(KERN_INFO "recvmsg bug 2: copied %X "
+				       "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
 		}
 
 		/* Well, if we have backlog, try to process it now yet. */
@@ -2163,16 +2202,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_DEFER_ACCEPT:
-		icsk->icsk_accept_queue.rskq_defer_accept = 0;
-		if (val > 0) {
-			/* Translate value in seconds to number of
-			 * retransmits */
-			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
-			       val > ((TCP_TIMEOUT_INIT / HZ) <<
-				       icsk->icsk_accept_queue.rskq_defer_accept))
-				icsk->icsk_accept_queue.rskq_defer_accept++;
-			icsk->icsk_accept_queue.rskq_defer_accept++;
-		}
+		/* Translate value in seconds to number of retransmits */
+		icsk->icsk_accept_queue.rskq_defer_accept =
+			secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+					TCP_RTO_MAX / HZ);
 		break;
 
 	case TCP_WINDOW_CLAMP:
@@ -2353,8 +2386,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
-		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
-			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
+		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+				      TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e320afe..4c03598 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -641,10 +641,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!(flg & TCP_FLAG_ACK))
 		return NULL;
 
-	/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
-	if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
+	if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
 	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-		inet_csk(sk)->icsk_accept_queue.rskq_defer_accept--;
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 14f54eb..4f7aaf6 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -496,13 +496,17 @@ done:
 			goto e_inval;
 
 		if (val) {
+			struct net_device *dev;
+
 			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
 				goto e_inval;
 
-			if (__dev_get_by_index(net, val) == NULL) {
+			dev = dev_get_by_index(net, val);
+			if (!dev) {
 				retv = -ENODEV;
 				break;
 			}
+			dev_put(dev);
 		}
 		np->mcast_oif = val;
 		retv = 0;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 51ab497..fc820cd 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1074,6 +1074,8 @@ restart:
 	err = -ECONNREFUSED;
 	if (other->sk_state != TCP_LISTEN)
 		goto out_unlock;
+	if (other->sk_shutdown & RCV_SHUTDOWN)
+		goto out_unlock;
 
 	if (unix_recvq_full(other)) {
 		err = -EAGAIN;