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

Pull networking changes from David Miller:
 "1) icmp6_dst_alloc() returns NULL instead of ERR_PTR() leading to
     crashes, particularly during shutdown.  Reported by Dave Jones and
     fixed by Eric Dumazet.

  2) hyperv and wimax/i2400m return NETDEV_TX_BUSY when they have
     already freed the SKB, which causes crashes as to the caller this
     means requeue the packet.  Fixes from Eric Dumazet.

  3) usbnet driver doesn't allocate the right amount of headroom on
     fresh RX SKBs, fix from Eric Dumazet.

  4) Fix regression in ip6_mc_find_dev_rcu(), as an RCU lookup it
     abolutely should not take a reference to 'dev', this leads to
     leaks.  Fix from RonQing Li.

  5) Fix netfilter ctnetlink race between delete and timeout expiration.
     From Pablo Neira Ayuso.

  6) Revert SFQ change which causes regressions, specifically queueing
     to tail can lead to unavoidable flow starvation.  From Eric
     Dumazet.

  7) Fix a memory leak and a crash on corrupt firmware files in bnx2x,
     from Michal Schmidt."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  netfilter: ctnetlink: fix race between delete and timeout expiration
  ipv6: Don't dev_hold(dev) in ip6_mc_find_dev_rcu.
  wimax/i2400m: fix erroneous NETDEV_TX_BUSY use
  net/hyperv: fix erroneous NETDEV_TX_BUSY use
  net/usbnet: reserve headroom on rx skbs
  bnx2x: fix memory leak in bnx2x_init_firmware()
  bnx2x: fix a crash on corrupt firmware file
  sch_sfq: revert dont put new flow at the end of flows
  ipv6: fix icmp6_dst_alloc()

8 files changed, 57 insertions, 64 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 254521319150e5..b69f8762b33958 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10824,38 +10824,36 @@ do {									\
 
 int bnx2x_init_firmware(struct bnx2x *bp)
 {
+	const char *fw_file_name;
 	struct bnx2x_fw_file_hdr *fw_hdr;
 	int rc;
 
+	if (bp->firmware)
+		return 0;
 
-	if (!bp->firmware) {
-		const char *fw_file_name;
-
-		if (CHIP_IS_E1(bp))
-			fw_file_name = FW_FILE_NAME_E1;
-		else if (CHIP_IS_E1H(bp))
-			fw_file_name = FW_FILE_NAME_E1H;
-		else if (!CHIP_IS_E1x(bp))
-			fw_file_name = FW_FILE_NAME_E2;
-		else {
-			BNX2X_ERR("Unsupported chip revision\n");
-			return -EINVAL;
-		}
-		BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
+	if (CHIP_IS_E1(bp))
+		fw_file_name = FW_FILE_NAME_E1;
+	else if (CHIP_IS_E1H(bp))
+		fw_file_name = FW_FILE_NAME_E1H;
+	else if (!CHIP_IS_E1x(bp))
+		fw_file_name = FW_FILE_NAME_E2;
+	else {
+		BNX2X_ERR("Unsupported chip revision\n");
+		return -EINVAL;
+	}
+	BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
 
-		rc = request_firmware(&bp->firmware, fw_file_name,
-				      &bp->pdev->dev);
-		if (rc) {
-			BNX2X_ERR("Can't load firmware file %s\n",
-				  fw_file_name);
-			goto request_firmware_exit;
-		}
+	rc = request_firmware(&bp->firmware, fw_file_name, &bp->pdev->dev);
+	if (rc) {
+		BNX2X_ERR("Can't load firmware file %s\n",
+			  fw_file_name);
+		goto request_firmware_exit;
+	}
 
-		rc = bnx2x_check_firmware(bp);
-		if (rc) {
-			BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
-			goto request_firmware_exit;
-		}
+	rc = bnx2x_check_firmware(bp);
+	if (rc) {
+		BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
+		goto request_firmware_exit;
 	}
 
 	fw_hdr = (struct bnx2x_fw_file_hdr *)bp->firmware->data;
@@ -10901,6 +10899,7 @@ init_ops_alloc_err:
 	kfree(bp->init_data);
 request_firmware_exit:
 	release_firmware(bp->firmware);
+	bp->firmware = NULL;
 
 	return rc;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index bf01841bda5bb7..610860f28968a4 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -166,7 +166,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 		dev_kfree_skb(skb);
 		net->stats.tx_dropped++;
-		return NETDEV_TX_BUSY;
+		return NETDEV_TX_OK;
 	}
 
 	packet->extension = (void *)(unsigned long)packet +
@@ -226,7 +226,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 		dev_kfree_skb_any(skb);
 	}
 
-	return ret ? NETDEV_TX_BUSY : NETDEV_TX_OK;
+	return NETDEV_TX_OK;
 }
 
 /*
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 81b96e303757a5..59681f01a54eb9 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -328,13 +328,13 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 	unsigned long		lockflags;
 	size_t			size = dev->rx_urb_size;
 
-	if ((skb = alloc_skb (size + NET_IP_ALIGN, flags)) == NULL) {
+	skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
+	if (!skb) {
 		netif_dbg(dev, rx_err, dev->net, "no rx skb\n");
 		usbnet_defer_kevent (dev, EVENT_RX_MEMORY);
 		usb_free_urb (urb);
 		return -ENOMEM;
 	}
-	skb_reserve (skb, NET_IP_ALIGN);
 
 	entry = (struct skb_data *) skb->cb;
 	entry->urb = urb;
diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c
index 64a110604ad3d1..63e4b709efa956 100644
--- a/drivers/net/wimax/i2400m/netdev.c
+++ b/drivers/net/wimax/i2400m/netdev.c
@@ -367,38 +367,28 @@ netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb,
 {
 	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
 	struct device *dev = i2400m_dev(i2400m);
-	int result;
+	int result = -1;
 
 	d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
-	if (skb_header_cloned(skb)) {
-		/*
-		 * Make tcpdump/wireshark happy -- if they are
-		 * running, the skb is cloned and we will overwrite
-		 * the mac fields in i2400m_tx_prep_header. Expand
-		 * seems to fix this...
-		 */
-		result = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
-		if (result) {
-			result = NETDEV_TX_BUSY;
-			goto error_expand;
-		}
-	}
+
+	if (skb_header_cloned(skb) && 
+	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		goto drop;
 
 	if (i2400m->state == I2400M_SS_IDLE)
 		result = i2400m_net_wake_tx(i2400m, net_dev, skb);
 	else
 		result = i2400m_net_tx(i2400m, net_dev, skb);
-	if (result <  0)
+	if (result <  0) {
+drop:
 		net_dev->stats.tx_dropped++;
-	else {
+	} else {
 		net_dev->stats.tx_packets++;
 		net_dev->stats.tx_bytes += skb->len;
 	}
-	result = NETDEV_TX_OK;
-error_expand:
-	kfree_skb(skb);
+	dev_kfree_skb(skb);
 	d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
-	return result;
+	return NETDEV_TX_OK;
 }
 
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index b853f06cc14874..16c33e308121da 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -257,7 +257,6 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
 
 		if (rt) {
 			dev = rt->dst.dev;
-			dev_hold(dev);
 			dst_release(&rt->dst);
 		}
 	} else
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8c2e3ab58f2af2..22b766407de15f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1077,7 +1077,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	struct net *net = dev_net(dev);
 
 	if (unlikely(!idev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
 	if (unlikely(!rt)) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 10687692831eb5..b49da6c925b3a2 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -943,20 +943,21 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		}
 	}
 
-	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
-				      NETLINK_CB(skb).pid,
-				      nlmsg_report(nlh)) < 0) {
+	if (del_timer(&ct->timeout)) {
+		if (nf_conntrack_event_report(IPCT_DESTROY, ct,
+					      NETLINK_CB(skb).pid,
+					      nlmsg_report(nlh)) < 0) {
+			nf_ct_delete_from_lists(ct);
+			/* we failed to report the event, try later */
+			nf_ct_insert_dying_list(ct);
+			nf_ct_put(ct);
+			return 0;
+		}
+		/* death_by_timeout would report the event again */
+		set_bit(IPS_DYING_BIT, &ct->status);
 		nf_ct_delete_from_lists(ct);
-		/* we failed to report the event, try later */
-		nf_ct_insert_dying_list(ct);
 		nf_ct_put(ct);
-		return 0;
 	}
-
-	/* death_by_timeout would report the event again */
-	set_bit(IPS_DYING_BIT, &ct->status);
-
-	nf_ct_kill(ct);
 	nf_ct_put(ct);
 
 	return 0;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 60d47180f0432e..02a21abea65e20 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -469,11 +469,15 @@ enqueue:
 	if (slot->qlen == 1) {		/* The flow is new */
 		if (q->tail == NULL) {	/* It is the first flow */
 			slot->next = x;
-			q->tail = slot;
 		} else {
 			slot->next = q->tail->next;
 			q->tail->next = x;
 		}
+		/* We put this flow at the end of our flow list.
+		 * This might sound unfair for a new flow to wait after old ones,
+		 * but we could endup servicing new flows only, and freeze old ones.
+		 */
+		q->tail = slot;
 		/* We could use a bigger initial quantum for new flows */
 		slot->allot = q->scaled_quantum;
 	}