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

Pull networking fixes from David Miller:
 "A couple interesting SKB fragment handling fixes, plus the usual small
  bits here and there:

   1) Fix 64-bit divide build failure on 32-bit platforms in mlx5, from
      Tim Gardner.

   2) Get rid of a stupid reimplementation on "%*phC" in our sysfs MAC
      address printing helper.

   3) Fix NETIF_F_SG capability advertisement in hyperv driver, if the
      device can't do checksumming offloads then it shouldn't say it can
      do SG either.  From Haiyang Zhang.

   4) bgmac needs to depend on PHYLIB, from Hauke Mehrtens.

   5) Don't leak DMA mappings on mapping failures, from Neil Horman.

   6) We need to reset the transport header of SKBs in ipv4 before we
      attempt to perform early socket demux, just like ipv6 does.  From
      Eric Dumazet.

   7) Add missing locking on vxlan device removal, from Stephen
      Hemminger.

   8) xen-netfront has to make two passes over an SKB to prepare it for
      transfer.  One pass calculates the number of slots needed, the
      second massages the SKB and fills the slots.  Unfortunately, the
      first pass doesn't calculate the number of slots properly so we
      can end up trying to build a MAX_SKB_FRAGS + 1 SKB which doesn't
      work out so well.  Fix from Jan Beulich with help and discussion
      with several others.

   9) Fix a similar problem in tun and macvtap, which have to split up
      scatter-gather elements at PAGE_SIZE boundaries.  Don't do
      zerocopy if it would result in a > MAX_SKB_FRAGS skb.  Fixes from
      Jason Wang.

  10) On receive, once we've decoded the VLAN state completely, clear
      skb->vlan_tci.  Otherwise demuxed tunnels underneath can trigger
      the VLAN code again, corrupting the packet.  Fix from Eric
      Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  vlan: fix a race in egress prio management
  vlan: mask vlan prio bits
  macvtap: do not zerocopy if iov needs more pages than MAX_SKB_FRAGS
  tuntap: do not zerocopy if iov needs more pages than MAX_SKB_FRAGS
  pkt_sched: sch_qfq: remove a source of high packet delay/jitter
  xen-netfront: pull on receive skb may need to happen earlier
  vxlan: add necessary locking on device removal
  hyperv: Fix the NETIF_F_SG flag setting in netvsc
  net: Fix sysfs_format_mac() code duplication.
  be2net: Fix to avoid hardware workaround when not needed
  macvtap: do not assume 802.1Q when send vlan packets
  macvtap: fix the missing ret value of TUNSETQUEUE
  ipv4: set transport header earlier
  mlx5 core: Fix __udivdi3 when compiling for 32 bit arches
  bgmac: add dependency to phylib
  net/irda: fixed style issues in irlan_eth
  ethtool: fixed trailing statements in ethtool
  ndisc: bool initializations should use true and false
  atl1e: unmap partially mapped skb on dma error and free skb

19 files changed, 248 insertions, 164 deletions

diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 6d1a62a84c9d..1966444590f6 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1678,6 +1678,7 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter,
 	u16 f;
 	int segment;
 	int ring_start = adapter->tx_ring.next_to_use;
+	int ring_end;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	segment = (tpd->word3 >> TPD_SEGMENT_EN_SHIFT) & TPD_SEGMENT_EN_MASK;
@@ -1721,6 +1722,15 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter,
 					map_len, PCI_DMA_TODEVICE);
 
 		if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) {
+			/* We need to unwind the mappings we've done */
+			ring_end = adapter->tx_ring.next_to_use;
+			adapter->tx_ring.next_to_use = ring_start;
+			while (adapter->tx_ring.next_to_use != ring_end) {
+				tpd = atl1e_get_tpd(adapter);
+				tx_buffer = atl1e_get_tx_buffer(adapter, tpd);
+				pci_unmap_single(adapter->pdev, tx_buffer->dma,
+						 tx_buffer->length, PCI_DMA_TODEVICE);
+			}
 			/* Reset the tx rings next pointer */
 			adapter->tx_ring.next_to_use = ring_start;
 			return -ENOSPC;
@@ -1763,6 +1773,16 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter,
 							  DMA_TO_DEVICE);
 
 			if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) {
+				/* We need to unwind the mappings we've done */
+				ring_end = adapter->tx_ring.next_to_use;
+				adapter->tx_ring.next_to_use = ring_start;
+				while (adapter->tx_ring.next_to_use != ring_end) {
+					tpd = atl1e_get_tpd(adapter);
+					tx_buffer = atl1e_get_tx_buffer(adapter, tpd);
+					dma_unmap_page(&adapter->pdev->dev, tx_buffer->dma,
+						       tx_buffer->length, DMA_TO_DEVICE);
+				}
+
 				/* Reset the ring next to use pointer */
 				adapter->tx_ring.next_to_use = ring_start;
 				return -ENOSPC;
@@ -1853,8 +1873,10 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	if (atl1e_tx_map(adapter, skb, tpd))
+	if (atl1e_tx_map(adapter, skb, tpd)) {
+		dev_kfree_skb_any(skb);
 		goto out;
+	}
 
 	atl1e_tx_queue(adapter, tpd_req, tpd);
 
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 1d680baf43d6..52c96036dcc4 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -131,6 +131,7 @@ config BNX2X_SRIOV
 config BGMAC
 	tristate "BCMA bus GBit core support"
 	depends on BCMA_HOST_SOC && HAS_DMA
+	select PHYLIB
 	---help---
 	  This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus.
 	  They can be found on BCM47xx SoCs and provide gigabit ethernet.
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 2df48bb0f1ca..181edb522450 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -782,16 +782,22 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 
 	if (vlan_tx_tag_present(skb))
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
-	else if (qnq_async_evt_rcvd(adapter) && adapter->pvid)
-		vlan_tag = adapter->pvid;
+
+	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
+		if (!vlan_tag)
+			vlan_tag = adapter->pvid;
+		/* f/w workaround to set skip_hw_vlan = 1, informs the F/W to
+		 * skip VLAN insertion
+		 */
+		if (skip_hw_vlan)
+			*skip_hw_vlan = true;
+	}
 
 	if (vlan_tag) {
 		skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
 		if (unlikely(!skb))
 			return skb;
 		skb->vlan_tci = 0;
-		if (skip_hw_vlan)
-			*skip_hw_vlan = true;
 	}
 
 	/* Insert the outer VLAN, if any */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 4273c06e2e96..9c7194b26ee2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -156,7 +156,7 @@ static ssize_t average_read(struct file *filp, char __user *buf, size_t count,
 	stats = filp->private_data;
 	spin_lock(&stats->lock);
 	if (stats->n)
-		field = stats->sum / stats->n;
+		field = div64_u64(stats->sum, stats->n);
 	spin_unlock(&stats->lock);
 	ret = snprintf(tbuf, sizeof(tbuf), "%llu\n", field);
 	if (ret > 0) {
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4dccead586be..23a0fff0df52 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -431,8 +431,8 @@ static int netvsc_probe(struct hv_device *dev,
 	net->netdev_ops = &device_ops;
 
 	/* TODO: Add GSO and Checksum offload */
-	net->hw_features = NETIF_F_SG;
-	net->features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_TX;
+	net->hw_features = 0;
+	net->features = NETIF_F_HW_VLAN_CTAG_TX;
 
 	SET_ETHTOOL_OPS(net, &ethtool_ops);
 	SET_NETDEV_DEV(net, &dev->device);
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 876c72246ae9..a98fb0ed6aef 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -698,6 +698,28 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 	return 0;
 }
 
+static unsigned long iov_pages(const struct iovec *iv, int offset,
+			       unsigned long nr_segs)
+{
+	unsigned long seg, base;
+	int pages = 0, len, size;
+
+	while (nr_segs && (offset >= iv->iov_len)) {
+		offset -= iv->iov_len;
+		++iv;
+		--nr_segs;
+	}
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		base = (unsigned long)iv[seg].iov_base + offset;
+		len = iv[seg].iov_len - offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		pages += size;
+		offset = 0;
+	}
+
+	return pages;
+}
 
 /* Get packet from user space buffer */
 static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
@@ -744,31 +766,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	if (unlikely(count > UIO_MAXIOV))
 		goto err;
 
-	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
-		zerocopy = true;
-
-	if (zerocopy) {
-		/* Userspace may produce vectors with count greater than
-		 * MAX_SKB_FRAGS, so we need to linearize parts of the skb
-		 * to let the rest of data to be fit in the frags.
-		 */
-		if (count > MAX_SKB_FRAGS) {
-			copylen = iov_length(iv, count - MAX_SKB_FRAGS);
-			if (copylen < vnet_hdr_len)
-				copylen = 0;
-			else
-				copylen -= vnet_hdr_len;
-		}
-		/* There are 256 bytes to be copied in skb, so there is enough
-		 * room for skb expand head in case it is used.
-		 * The rest buffer is mapped from userspace.
-		 */
-		if (copylen < vnet_hdr.hdr_len)
-			copylen = vnet_hdr.hdr_len;
-		if (!copylen)
-			copylen = GOODCOPY_LEN;
+	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
+		copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
 		linear = copylen;
-	} else {
+		if (iov_pages(iv, vnet_hdr_len + copylen, count)
+		    <= MAX_SKB_FRAGS)
+			zerocopy = true;
+	}
+
+	if (!zerocopy) {
 		copylen = len;
 		linear = vnet_hdr.hdr_len;
 	}
@@ -780,9 +786,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (zerocopy)
 		err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
-	else
+	else {
 		err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
 						   len);
+		if (!err && m && m->msg_control) {
+			struct ubuf_info *uarg = m->msg_control;
+			uarg->callback(uarg, false);
+		}
+	}
+
 	if (err)
 		goto err_kfree;
 
@@ -873,7 +885,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 			__be16 h_vlan_proto;
 			__be16 h_vlan_TCI;
 		} veth;
-		veth.h_vlan_proto = htons(ETH_P_8021Q);
+		veth.h_vlan_proto = skb->vlan_proto;
 		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
@@ -1107,6 +1119,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		rtnl_lock();
 		ret = macvtap_ioctl_set_queue(file, u);
 		rtnl_unlock();
+		return ret;
 
 	case TUNGETFEATURES:
 		if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR |
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5cdcf92eb310..db690a372260 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1035,6 +1035,29 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
 	return 0;
 }
 
+static unsigned long iov_pages(const struct iovec *iv, int offset,
+			       unsigned long nr_segs)
+{
+	unsigned long seg, base;
+	int pages = 0, len, size;
+
+	while (nr_segs && (offset >= iv->iov_len)) {
+		offset -= iv->iov_len;
+		++iv;
+		--nr_segs;
+	}
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		base = (unsigned long)iv[seg].iov_base + offset;
+		len = iv[seg].iov_len - offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		pages += size;
+		offset = 0;
+	}
+
+	return pages;
+}
+
 /* Get packet from user space buffer */
 static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			    void *msg_control, const struct iovec *iv,
@@ -1082,32 +1105,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			return -EINVAL;
 	}
 
-	if (msg_control)
-		zerocopy = true;
-
-	if (zerocopy) {
-		/* Userspace may produce vectors with count greater than
-		 * MAX_SKB_FRAGS, so we need to linearize parts of the skb
-		 * to let the rest of data to be fit in the frags.
-		 */
-		if (count > MAX_SKB_FRAGS) {
-			copylen = iov_length(iv, count - MAX_SKB_FRAGS);
-			if (copylen < offset)
-				copylen = 0;
-			else
-				copylen -= offset;
-		} else
-				copylen = 0;
-		/* There are 256 bytes to be copied in skb, so there is enough
-		 * room for skb expand head in case it is used.
+	if (msg_control) {
+		/* There are 256 bytes to be copied in skb, so there is
+		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
-		if (copylen < gso.hdr_len)
-			copylen = gso.hdr_len;
-		if (!copylen)
-			copylen = GOODCOPY_LEN;
+		copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
 		linear = copylen;
-	} else {
+		if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
+			zerocopy = true;
+	}
+
+	if (!zerocopy) {
 		copylen = len;
 		linear = gso.hdr_len;
 	}
@@ -1121,8 +1130,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (zerocopy)
 		err = zerocopy_sg_from_iovec(skb, iv, offset, count);
-	else
+	else {
 		err = skb_copy_datagram_from_iovec(skb, 0, iv, offset, len);
+		if (!err && msg_control) {
+			struct ubuf_info *uarg = msg_control;
+			uarg->callback(uarg, false);
+		}
+	}
 
 	if (err) {
 		tun->dev->stats.rx_dropped++;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0ba1e7edbb1b..a5ba8dd7e6be 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1767,9 +1767,15 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
+	flush_workqueue(vxlan_wq);
+
+	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vxlan->hlist);
+	spin_unlock(&vn->sock_lock);
+
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
 }
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ff7f111fffee..36808bf25677 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -286,8 +286,7 @@ no_skb:
 			break;
 		}
 
-		__skb_fill_page_desc(skb, 0, page, 0, 0);
-		skb_shinfo(skb)->nr_frags = 1;
+		skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
 		__skb_queue_tail(&np->rx_batch, skb);
 	}
 
@@ -831,7 +830,6 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np,
 				  struct sk_buff_head *list)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	int nr_frags = shinfo->nr_frags;
 	RING_IDX cons = np->rx.rsp_cons;
 	struct sk_buff *nskb;
 
@@ -840,19 +838,21 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np,
 			RING_GET_RESPONSE(&np->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
-		__skb_fill_page_desc(skb, nr_frags,
-				     skb_frag_page(nfrag),
-				     rx->offset, rx->status);
+		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
-		skb->data_len += rx->status;
+			BUG_ON(pull_to <= skb_headlen(skb));
+			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
+		}
+		BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+
+		skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+				rx->offset, rx->status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
 		kfree_skb(nskb);
-
-		nr_frags++;
 	}
 
-	shinfo->nr_frags = nr_frags;
 	return cons;
 }
 
@@ -933,7 +933,8 @@ static int handle_incoming_queue(struct net_device *dev,
 	while ((skb = __skb_dequeue(rxq)) != NULL) {
 		int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
-		__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
+		if (pull_to > skb_headlen(skb))
+			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
 		skb->protocol = eth_type_trans(skb, dev);
@@ -1019,16 +1020,10 @@ err:
 		skb_shinfo(skb)->frags[0].page_offset = rx->offset;
 		skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
 		skb->data_len = rx->status;
+		skb->len += rx->status;
 
 		i = xennet_fill_frags(np, skb, &tmpq);
 
-		/*
-                 * Truesize is the actual allocation size, even if the
-                 * allocation is only partially used.
-                 */
-		skb->truesize += PAGE_SIZE * skb_shinfo(skb)->nr_frags;
-		skb->len += skb->data_len;
-
 		if (rx->flags & XEN_NETRXF_csum_blank)
 			skb->ip_summed = CHECKSUM_PARTIAL;
 		else if (rx->flags & XEN_NETRXF_data_validated)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index cdcbafa9b39a..715c343f7c00 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -79,9 +79,8 @@ static inline int is_vlan_dev(struct net_device *dev)
 }
 
 #define vlan_tx_tag_present(__skb)	((__skb)->vlan_tci & VLAN_TAG_PRESENT)
-#define vlan_tx_nonzero_tag_present(__skb) \
-	(vlan_tx_tag_present(__skb) && ((__skb)->vlan_tci & VLAN_VID_MASK))
 #define vlan_tx_tag_get(__skb)		((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
+#define vlan_tx_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
 
 #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
 
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 8a15eaadc4bd..4a78c4de9f20 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 {
 	struct sk_buff *skb = *skbp;
 	__be16 vlan_proto = skb->vlan_proto;
-	u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
+	u16 vlan_id = vlan_tx_tag_get_id(skb);
 	struct net_device *vlan_dev;
 	struct vlan_pcpu_stats *rx_stats;
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 3a8c8fd63c88..1cd3d2a406f5 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -73,6 +73,8 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb)
 {
 	struct vlan_priority_tci_mapping *mp;
 
+	smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
+
 	mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)];
 	while (mp) {
 		if (mp->priority == skb->priority) {
@@ -249,6 +251,11 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
 	np->next = mp;
 	np->priority = skb_prio;
 	np->vlan_qos = vlan_qos;
+	/* Before inserting this element in hash table, make sure all its fields
+	 * are committed to memory.
+	 * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
+	 */
+	smp_wmb();
 	vlan->egress_priority_map[skb_prio & 0xF] = np;
 	if (vlan_qos)
 		vlan->nr_egress_mappings++;
diff --git a/net/core/dev.c b/net/core/dev.c
index a3d8d44cb7f4..26755dd40daa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3580,8 +3580,15 @@ ncls:
 		}
 	}
 
-	if (vlan_tx_nonzero_tag_present(skb))
-		skb->pkt_type = PACKET_OTHERHOST;
+	if (unlikely(vlan_tx_tag_present(skb))) {
+		if (vlan_tx_tag_get_id(skb))
+			skb->pkt_type = PACKET_OTHERHOST;
+		/* Note: we might in the future use prio bits
+		 * and set skb->priority like in vlan_do_receive()
+		 * For the time being, just ignore Priority Code Point
+		 */
+		skb->vlan_tci = 0;
+	}
 
 	/* deliver only exact match when indicated */
 	null_or_dev = deliver_exact ? skb->dev : NULL;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index ab5fa6336c84..78e9d9223e40 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -279,11 +279,16 @@ static u32 __ethtool_get_flags(struct net_device *dev)
 {
 	u32 flags = 0;
 
-	if (dev->features & NETIF_F_LRO)	     flags |= ETH_FLAG_LRO;
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN;
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN;
-	if (dev->features & NETIF_F_NTUPLE)	     flags |= ETH_FLAG_NTUPLE;
-	if (dev->features & NETIF_F_RXHASH)	     flags |= ETH_FLAG_RXHASH;
+	if (dev->features & NETIF_F_LRO)
+		flags |= ETH_FLAG_LRO;
+	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		flags |= ETH_FLAG_RXVLAN;
+	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+		flags |= ETH_FLAG_TXVLAN;
+	if (dev->features & NETIF_F_NTUPLE)
+		flags |= ETH_FLAG_NTUPLE;
+	if (dev->features & NETIF_F_RXHASH)
+		flags |= ETH_FLAG_RXHASH;
 
 	return flags;
 }
@@ -295,11 +300,16 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
 	if (data & ~ETH_ALL_FLAGS)
 		return -EINVAL;
 
-	if (data & ETH_FLAG_LRO)	features |= NETIF_F_LRO;
-	if (data & ETH_FLAG_RXVLAN)	features |= NETIF_F_HW_VLAN_CTAG_RX;
-	if (data & ETH_FLAG_TXVLAN)	features |= NETIF_F_HW_VLAN_CTAG_TX;
-	if (data & ETH_FLAG_NTUPLE)	features |= NETIF_F_NTUPLE;
-	if (data & ETH_FLAG_RXHASH)	features |= NETIF_F_RXHASH;
+	if (data & ETH_FLAG_LRO)
+		features |= NETIF_F_LRO;
+	if (data & ETH_FLAG_RXVLAN)
+		features |= NETIF_F_HW_VLAN_CTAG_RX;
+	if (data & ETH_FLAG_TXVLAN)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	if (data & ETH_FLAG_NTUPLE)
+		features |= NETIF_F_NTUPLE;
+	if (data & ETH_FLAG_RXHASH)
+		features |= NETIF_F_RXHASH;
 
 	/* allow changing only bits set in hw_features */
 	changed = (features ^ dev->features) & ETH_ALL_FEATURES;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 5359560926bc..be1f64d35358 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -401,27 +401,8 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 }
 EXPORT_SYMBOL(alloc_etherdev_mqs);
 
-static size_t _format_mac_addr(char *buf, int buflen,
-			       const unsigned char *addr, int len)
-{
-	int i;
-	char *cp = buf;
-
-	for (i = 0; i < len; i++) {
-		cp += scnprintf(cp, buflen - (cp - buf), "%02x", addr[i]);
-		if (i == len - 1)
-			break;
-		cp += scnprintf(cp, buflen - (cp - buf), ":");
-	}
-	return cp - buf;
-}
-
 ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
 {
-	size_t l;
-
-	l = _format_mac_addr(buf, PAGE_SIZE, addr, len);
-	l += scnprintf(buf + l, PAGE_SIZE - l, "\n");
-	return (ssize_t)l;
+	return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr);
 }
 EXPORT_SYMBOL(sysfs_format_mac);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3da817b89e9b..15e3e683adec 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -190,10 +190,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 
-	__skb_pull(skb, ip_hdrlen(skb));
-
-	/* Point into the IP datagram, just past the header. */
-	skb_reset_transport_header(skb);
+	__skb_pull(skb, skb_network_header_len(skb));
 
 	rcu_read_lock();
 	{
@@ -437,6 +434,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 		goto drop;
 	}
 
+	skb->transport_header = skb->network_header + iph->ihl*4;
+
 	/* Remove any debris in the socket control block */
 	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index b3b5730b48c5..24c03396e008 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -479,7 +479,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
 	if (ifp) {
 		src_addr = solicited_addr;
 		if (ifp->flags & IFA_F_OPTIMISTIC)
-			override = 0;
+			override = false;
 		inc_opt |= ifp->idev->cnf.force_tllao;
 		in6_ifa_put(ifp);
 	} else {
@@ -557,7 +557,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 	}
 
 	if (ipv6_addr_any(saddr))
-		inc_opt = 0;
+		inc_opt = false;
 	if (inc_opt)
 		optlen += ndisc_opt_addr_space(dev);
 
@@ -790,7 +790,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 		     (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
 			if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
 			    skb->pkt_type != PACKET_HOST &&
-			    inc != 0 &&
+			    inc &&
 			    idev->nd_parms->proxy_delay != 0) {
 				/*
 				 * for anycast or proxy,
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index d14152e866d9..ffcec225b5d9 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -44,12 +44,12 @@ static int  irlan_eth_open(struct net_device *dev);
 static int  irlan_eth_close(struct net_device *dev);
 static netdev_tx_t  irlan_eth_xmit(struct sk_buff *skb,
 					 struct net_device *dev);
-static void irlan_eth_set_multicast_list( struct net_device *dev);
+static void irlan_eth_set_multicast_list(struct net_device *dev);
 
 static const struct net_device_ops irlan_eth_netdev_ops = {
-	.ndo_open               = irlan_eth_open,
-	.ndo_stop               = irlan_eth_close,
-	.ndo_start_xmit    	= irlan_eth_xmit,
+	.ndo_open		= irlan_eth_open,
+	.ndo_stop		= irlan_eth_close,
+	.ndo_start_xmit		= irlan_eth_xmit,
 	.ndo_set_rx_mode	= irlan_eth_set_multicast_list,
 	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -110,7 +110,7 @@ static int irlan_eth_open(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
+	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	/* Ready to play! */
 	netif_stop_queue(dev); /* Wait until data link is ready */
@@ -137,7 +137,7 @@ static int irlan_eth_close(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
+	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	/* Stop device */
 	netif_stop_queue(dev);
@@ -310,35 +310,32 @@ static void irlan_eth_set_multicast_list(struct net_device *dev)
 {
 	struct irlan_cb *self = netdev_priv(dev);
 
-	IRDA_DEBUG(2, "%s()\n", __func__ );
+	IRDA_DEBUG(2, "%s()\n", __func__);
 
 	/* Check if data channel has been connected yet */
 	if (self->client.state != IRLAN_DATA) {
-		IRDA_DEBUG(1, "%s(), delaying!\n", __func__ );
+		IRDA_DEBUG(1, "%s(), delaying!\n", __func__);
 		return;
 	}
 
 	if (dev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
 		IRDA_WARNING("Promiscuous mode not implemented by IrLAN!\n");
-	}
-	else if ((dev->flags & IFF_ALLMULTI) ||
+	} else if ((dev->flags & IFF_ALLMULTI) ||
 		 netdev_mc_count(dev) > HW_MAX_ADDRS) {
 		/* Disable promiscuous mode, use normal mode. */
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ );
+		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
 		/* hardware_set_filter(NULL); */
 
 		irlan_set_multicast_filter(self, TRUE);
-	}
-	else if (!netdev_mc_empty(dev)) {
-		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ );
+	} else if (!netdev_mc_empty(dev)) {
+		IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__);
 		/* Walk the address list, and load the filter */
 		/* hardware_set_filter(dev->mc_list); */
 
 		irlan_set_multicast_filter(self, TRUE);
-	}
-	else {
-		IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__ );
+	} else {
+		IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__);
 		irlan_set_multicast_filter(self, FALSE);
 	}
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index a7ab323849b6..8056fb4e618a 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -113,7 +113,6 @@
 
 #define FRAC_BITS		30	/* fixed point arithmetic */
 #define ONE_FP			(1UL << FRAC_BITS)
-#define IWSUM			(ONE_FP/QFQ_MAX_WSUM)
 
 #define QFQ_MTU_SHIFT		16	/* to support TSO/GSO */
 #define QFQ_MIN_LMAX		512	/* see qfq_slot_insert */
@@ -189,6 +188,7 @@ struct qfq_sched {
 	struct qfq_aggregate	*in_serv_agg;   /* Aggregate being served. */
 	u32			num_active_agg; /* Num. of active aggregates */
 	u32			wsum;		/* weight sum */
+	u32			iwsum;		/* inverse weight sum */
 
 	unsigned long bitmaps[QFQ_MAX_STATE];	    /* Group bitmaps. */
 	struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
@@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
 
 	q->wsum +=
 		(int) agg->class_weight * (new_num_classes - agg->num_classes);
+	q->iwsum = ONE_FP / q->wsum;
 
 	agg->num_classes = new_num_classes;
 }
@@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
 {
 	if (!hlist_unhashed(&agg->nonfull_next))
 		hlist_del_init(&agg->nonfull_next);
+	q->wsum -= agg->class_weight;
+	if (q->wsum != 0)
+		q->iwsum = ONE_FP / q->wsum;
+
 	if (q->in_serv_agg == agg)
 		q->in_serv_agg = qfq_choose_next_agg(q);
 	kfree(agg);
@@ -834,38 +839,60 @@ static void qfq_make_eligible(struct qfq_sched *q)
 	}
 }
 
-
 /*
- * The index of the slot in which the aggregate is to be inserted must
- * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1'
- * because the start time of the group may be moved backward by one
- * slot after the aggregate has been inserted, and this would cause
- * non-empty slots to be right-shifted by one position.
+ * The index of the slot in which the input aggregate agg is to be
+ * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2'
+ * and not a '-1' because the start time of the group may be moved
+ * backward by one slot after the aggregate has been inserted, and
+ * this would cause non-empty slots to be right-shifted by one
+ * position.
+ *
+ * QFQ+ fully satisfies this bound to the slot index if the parameters
+ * of the classes are not changed dynamically, and if QFQ+ never
+ * happens to postpone the service of agg unjustly, i.e., it never
+ * happens that the aggregate becomes backlogged and eligible, or just
+ * eligible, while an aggregate with a higher approximated finish time
+ * is being served. In particular, in this case QFQ+ guarantees that
+ * the timestamps of agg are low enough that the slot index is never
+ * higher than 2. Unfortunately, QFQ+ cannot provide the same
+ * guarantee if it happens to unjustly postpone the service of agg, or
+ * if the parameters of some class are changed.
+ *
+ * As for the first event, i.e., an out-of-order service, the
+ * upper bound to the slot index guaranteed by QFQ+ grows to
+ * 2 +
+ * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
+ * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1.
  *
- * If the weight and lmax (max_pkt_size) of the classes do not change,
- * then QFQ+ does meet the above contraint according to the current
- * values of its parameters. In fact, if the weight and lmax of the
- * classes do not change, then, from the theory, QFQ+ guarantees that
- * the slot index is never higher than
- * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
- * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18
+ * The following function deals with this problem by backward-shifting
+ * the timestamps of agg, if needed, so as to guarantee that the slot
+ * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may
+ * cause the service of other aggregates to be postponed, yet the
+ * worst-case guarantees of these aggregates are not violated.  In
+ * fact, in case of no out-of-order service, the timestamps of agg
+ * would have been even lower than they are after the backward shift,
+ * because QFQ+ would have guaranteed a maximum value equal to 2 for
+ * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose
+ * service is postponed because of the backward-shift would have
+ * however waited for the service of agg before being served.
  *
- * When the weight of a class is increased or the lmax of the class is
- * decreased, a new aggregate with smaller slot size than the original
- * parent aggregate of the class may happen to be activated. The
- * activation of this aggregate should be properly delayed to when the
- * service of the class has finished in the ideal system tracked by
- * QFQ+. If the activation of the aggregate is not delayed to this
- * reference time instant, then this aggregate may be unjustly served
- * before other aggregates waiting for service. This may cause the
- * above bound to the slot index to be violated for some of these
- * unlucky aggregates.
+ * The other event that may cause the slot index to be higher than 2
+ * for agg is a recent change of the parameters of some class. If the
+ * weight of a class is increased or the lmax (max_pkt_size) of the
+ * class is decreased, then a new aggregate with smaller slot size
+ * than the original parent aggregate of the class may happen to be
+ * activated. The activation of this aggregate should be properly
+ * delayed to when the service of the class has finished in the ideal
+ * system tracked by QFQ+. If the activation of the aggregate is not
+ * delayed to this reference time instant, then this aggregate may be
+ * unjustly served before other aggregates waiting for service. This
+ * may cause the above bound to the slot index to be violated for some
+ * of these unlucky aggregates.
  *
  * Instead of delaying the activation of the new aggregate, which is
- * quite complex, the following inaccurate but simple solution is used:
- * if the slot index is higher than QFQ_MAX_SLOTS-2, then the
- * timestamps of the aggregate are shifted backward so as to let the
- * slot index become equal to QFQ_MAX_SLOTS-2.
+ * quite complex, the above-discussed capping of the slot index is
+ * used to handle also the consequences of a change of the parameters
+ * of a class.
  */
 static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg,
 			    u64 roundedS)
@@ -1136,7 +1163,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	else
 		in_serv_agg->budget -= len;
 
-	q->V += (u64)len * IWSUM;
+	q->V += (u64)len * q->iwsum;
 	pr_debug("qfq dequeue: len %u F %lld now %lld\n",
 		 len, (unsigned long long) in_serv_agg->F,
 		 (unsigned long long) q->V);